Harden release publication plumbing

.woodpecker/release.yml

@@ -2,8 +2,50 @@ when:
   - event: tag
 
 steps:
+  - name: validate-release
+    image: golang:1.26.5
+    commands:
+      - |
+        set -eu
+
+        version="$CI_COMMIT_TAG"
+        release_note="docs/releases/$version.md"
+
+        if ! printf '%s\n' "$version" |
+          grep -Eq '^v(0|[1-9][0-9]*)\.(0|[1-9][0-9]*)\.(0|[1-9][0-9]*)$'
+        then
+          printf '%s\n' "invalid release tag: $version" >&2
+          exit 1
+        fi
+        test -s "$release_note"
+        test -z "$(git ls-files go.work go.work.sum)"
+        test ! -e vendor
+        if grep -Eq '^[[:space:]]*replace([[:space:]]|\()' go.mod
+        then
+          printf '%s\n' 'go.mod contains a replacement' >&2
+          exit 1
+        fi
+
+        GOWORK=off go test -count=1 ./...
+        GOWORK=off go test -race -count=1 ./...
+        GOWORK=off go vet ./...
+        GOWORK=off go build ./...
+        GOWORK=off go mod tidy -diff
+
+        unformatted=$(
+          git ls-files '*.go' |
+            while IFS= read -r go_file
+            do
+              gofmt -l "$go_file"
+            done
+        )
+        test -z "$unformatted"
+        git diff --check
+
   - name: build-release-assets
-    image: golang:1.25
+    image: golang:1.26.5
+    depends_on:
+      - validate-release
     commands:
       - |
         set -eu
@@ -33,8 +75,11 @@ steps:
         build_binary windows amd64 ".exe"
         build_binary windows arm64 ".exe"
 
+        host_binary="$dist/weatherreporter-$version-$(go env GOOS)-$(go env GOARCH)"
+        test "$("$host_binary" --version)" = "weatherreporter $version"
+
   - name: publish-release
-    image: woodpeckerci/plugin-release
+    image: woodpeckerci/plugin-release:0.3.1
     depends_on:
       - build-release-assets
     settings:
@@ -42,6 +87,8 @@ steps:
         from_secret: GITEA_RELEASE_TOKEN
       files:
         - dist/weatherreporter-*
+      title: Weatherreporter ${CI_COMMIT_TAG}
+      note: docs/releases/${CI_COMMIT_TAG}.md
       checksum: sha256
       checksum-file: SHA256SUMS
       checksum-flatten: true

docs/cli.md

@@ -17,15 +17,13 @@ required Weather API endpoint.
 
 ```text
 weatherreporter --help
-weatherreporter generate daily --date YYYY-MM-DD [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--quiet]
+weatherreporter --version
-weatherreporter generate today [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--date YYYY-MM-DD] [--quiet]
+weatherreporter generate daily --date YYYY-MM-DD [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--llm-debug-dir PATH] [--quiet]
-weatherreporter generate tomorrow [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--quiet]
+weatherreporter generate today [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--date YYYY-MM-DD] [--llm-debug-dir PATH] [--quiet]
-weatherreporter generate hourly [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--quiet]
+weatherreporter generate tomorrow [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--llm-debug-dir PATH] [--quiet]
-weatherreporter generate three-day [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--quiet]
+weatherreporter generate hourly [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--llm-debug-dir PATH] [--quiet]
-weatherreporter generate weekend [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--quiet]
+weatherreporter run morning [--config PATH] [--units VALUE] [--tz NAME] [--out-dir PATH] [--llm-debug-dir PATH] [--quiet]
-weatherreporter generate storm [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--quiet] --start TIME --end TIME
+weatherreporter run evening [--config PATH] [--units VALUE] [--tz NAME] [--out-dir PATH] [--llm-debug-dir PATH] [--quiet]
-weatherreporter run morning [--config PATH] [--units VALUE] [--tz NAME] [--out-dir PATH] [--quiet]
-weatherreporter run evening [--config PATH] [--units VALUE] [--tz NAME] [--out-dir PATH] [--quiet]
 weatherreporter inspect reports [--config PATH] [--limit N]
 weatherreporter inspect metadata [--config PATH] RUN_ID
 weatherreporter inspect modules [--config PATH] RUN_ID
@@ -34,16 +32,19 @@ weatherreporter inspect prior [--config PATH] RUN_ID
 weatherreporter inspect sources [--config PATH] RUN_ID
 ```
 
+`weatherreporter --version` prints the version embedded in the executable.
+Tagged release binaries report their semantic version tag; ordinary local
+builds report `development`.
+
 | Command | Contract |
 | --- | --- |
 | `generate daily` | Requires `--date YYYY-MM-DD`; the date is interpreted in the effective report timezone. |
 | `generate today` | Accepts an optional `--date YYYY-MM-DD`; without it, the current local date in the effective report timezone is used. |
-| `generate tomorrow`, `three-day`, `weekend` | Use their report-defined valid period and accept the common generate flags. |
+| `generate tomorrow` | Uses the next local civil day and accepts the common generate flags. |
-| `generate hourly` | Covers the next six hours in the effective report timezone. It does not accept `--date`, `--start`, `--end`, `--hours`, or `--duration`. |
+| `generate hourly` | Covers the next six hours in the effective report timezone. It does not accept `--date`, `--hours`, or `--duration`. |
-| `generate storm` | Requires both `--start TIME` and `--end TIME`. Each time may be `YYYY-MM-DDTHH:MM` in the effective timezone or an RFC3339 timestamp with an explicit offset. |
 | `run morning` and `run evening` | Run their defined report batches. `--out-dir` writes extra Markdown copies; `--out` is not accepted. |
 
-`generate` accepts all seven report command names shown above. `run` accepts
+`generate` accepts the four report command names shown above. `run` accepts
 only `morning` and `evening`. Batch membership, workspace artifacts, and
 notification sequencing are described in the [operations guide](operations.md).
 
@@ -84,9 +85,8 @@ time, valid period, and status:
 ```
 
 When available, the summary also includes `reportPath`, `metadataPath`,
-`dataPackagePath`, and `preflightPath`. Generated-text reports additionally
+`dataPackagePath`, `preparationPath`, `executionPath`, `generatedTextRawPath`,
-include `generatedTextRawPath`, `generatedTextResultPath`,
+`generatedTextPath`, `renderContextPath`, and `llmDebugPath`. `outputPath` is included only
-`generatedTextPath`, and `renderContextPath`. `outputPath` is included only
 when `--out` wrote an extra copy. Distributor notification, when attempted,
 adds `notificationPath` and may add a compact `notification` object.
 
@@ -113,10 +113,10 @@ batch=morning total=2 succeeded=2 failed=0
 | `--units VALUE` | `generate`, `run` | Override `weather_api.units` for this command. |
 | `--tz NAME` | `generate`, `run` | Override `weather_api.timezone` for this command. |
 | `--out PATH` | every `generate` command | Write an extra Markdown report copy. |
+| `--llm-debug-dir PATH` | every `generate` and `run` command | Write requested sensitive prompt diagnostics outside the managed workspace. The path must be absolute. |
 | `--out-dir PATH` | `run morning`, `run evening` | Write extra Markdown report copies in `PATH`. |
 | `--quiet` | `generate`, `run` | Suppress action summaries and routine batch status output. |
 | `--date YYYY-MM-DD` | `generate daily`, `generate today` | Required for Daily; optional for Today. |
-| `--start TIME`, `--end TIME` | `generate storm` | Required storm-event bounds. |
 | `--limit N` | `inspect reports` | Maximum runs to list. Defaults to `20`; `0` means no limit. |
 
 Distributor notification is configured through `notify.distributor`; there are
@@ -128,8 +128,8 @@ no Distributor-specific CLI flags. See the [configuration reference](config.md).
 weatherreporter generate daily --date 2026-05-29 --out ./daily.md
 weatherreporter generate today --date 2026-05-29 --out ./today.md
 weatherreporter generate hourly --out ./hourly.md
-weatherreporter generate storm --start 2026-05-29T18:00 --end 2026-05-30T06:00 --out ./storm.md
+weatherreporter generate today --llm-debug-dir /var/tmp/weatherreporter-debug
-weatherreporter run morning --out-dir ./reports
+weatherreporter run morning --out-dir ./reports --llm-debug-dir /var/tmp/weatherreporter-debug
 ```
 
 ## Inspection Commands
@@ -152,6 +152,6 @@ weatherreporter inspect sources 20260529T100000.000000000Z_today
 | `inspect prior RUN_ID` | Prior comparable snapshot metadata, or `null` when none exists. |
 | `inspect sources RUN_ID` | Source provenance and source warnings without full weather payloads. |
 
-Inspection is read-only: it does not collect weather data or invoke
+Inspection is read-only: it does not collect weather data or invoke Promptkit.
-`scriptorium`. See the [operations guide](operations.md) for artifact lifecycle
+See the [operations guide](operations.md) for artifact lifecycle
 and recovery.

docs/config.md

@@ -102,10 +102,9 @@ Use `secrets.directory` when a file-backed secret is appropriate.
 Single-report bundle templates accept `location_id`, `report_id`, `run_id`,
 `artifact_group`, `batch_output_name`, `valid_start_date`, `valid_end_date`,
 `valid_start_time`, `valid_end_time`, `valid_start_stamp`, `valid_end_stamp`,
-and `storm_id`. Pipeline and idempotency-key templates may also use
+Pipeline and idempotency-key templates may also use `bundle_id`. Dates use
-`bundle_id`. Dates use `YYYY-MM-DD`; times use `HHMM`; and stamps use
+`YYYY-MM-DD`; times use `HHMM`; and stamps use `YYYY-MM-DDTHHMM` in the
-`YYYY-MM-DDTHHMM` in the effective report timezone. `storm_id` is
+effective report timezone.
-`{valid_start_stamp}-{valid_end_stamp}` for Storm Report and empty otherwise.
 
 Batch bundle and pipeline templates accept `location_id`, `batch`,
 `batch_run_id`, and `batch_started_date`; batch idempotency-key templates may
@@ -124,9 +123,6 @@ The default paths are:
 | `daily` | `daily/{valid_start_date}/{run_id}.md`, `daily/{valid_start_date}/index.md` |
 | `today` | `daily/{valid_start_date}/{run_id}.md`, `daily/{valid_start_date}/index.md`, `today/index.md` |
 | `tomorrow` | `daily/{valid_start_date}/{run_id}.md`, `daily/{valid_start_date}/index.md`, `tomorrow/index.md` |
-| `three_day` | `three-day/{valid_start_date}/{run_id}.md`, `three-day/{valid_start_date}/index.md` |
-| `weekend` | `weekend/{valid_start_date}/{run_id}.md`, `weekend/{valid_start_date}/index.md` |
-| `storm` | `storm/{storm_id}/{run_id}.md`, `storm/{storm_id}/index.md` |
 
 See the [operations guide](operations.md) for notification timing, uploaded
 artifact selection, and failure handling.
@@ -139,15 +135,23 @@ Hourly forecast data is required for generated reports. Supported optional
 source keys are `observations`, `current`, `narrative`, `alerts`, `discussion`,
 `weather_story`, and `spc_convective_outlooks`.
 
-### `scriptorium`
+### `promptkit`
+
+Promptkit configuration selects the executor and prompt/profile checks for
+every `generate` and `run` command. A top-level `scriptorium:` configuration
+key is rejected with a migration error; it is not translated or ignored.
+
+Prompt debug capture has no YAML setting. Use `--llm-debug-dir PATH` on an
+individual `generate` or `run` command when explicitly needed.
 
 | Field | Default | Rules |
 | --- | --- | --- |
-| `binary` | `scriptorium` | Required executable name or path. |
+| `profile` | empty | Optional explicit execution profile. Otherwise the prompt's declared default is used. |
-| `config_path` | empty | Optional Scriptorium configuration path. |
+| `profile_file` | empty | Optional external profile file. Cannot be combined with `profile_dir`. |
-| `profile` | empty | Optional Scriptorium profile. |
+| `profile_dir` | empty | Optional external profile directory. Cannot be combined with `profile_file`. |
 | `timeout` | `2m` | Must be greater than zero. |
-| `extra_args` | empty | Optional extra arguments passed to Scriptorium commands. |
+| `local.endpoint` | empty | Optional absolute URL for the conventional local backend. A blank endpoint leaves it unregistered. |
+| `local.concurrency_limit` | `1` | Maximum local backend concurrency. `0` is unlimited; negative values are invalid. |
 
 ### `workspace`
 
@@ -189,9 +193,8 @@ prior comparable module snapshot.
 `reports` optionally overrides a report's ordered deterministic modules and
 Distributor path templates. Omit a report entry to retain its defaults.
 
-Supported report keys are `daily`, `today`, `tomorrow`, `hourly`, `three_day`,
+Supported report keys are `daily`, `today`, `tomorrow`, and `hourly`; hyphens
-`weekend`, and `storm`. Configuration also accepts `three_day_outlook`,
+and underscores are equivalent.
-`weekend_outlook`, and `storm_report`; hyphens and underscores are equivalent.
 
 Each report entry can contain:
 

docs/development.md

@@ -5,8 +5,8 @@ Weatherreporter. It provides a concise repository orientation and routes each
 kind of change to its canonical documentation.
 
 Weatherreporter is a Go CLI that collects normalized weather data, derives
-deterministic report facts and module snapshots, invokes Scriptorium for
+deterministic report facts and module snapshots, executes Promptkit for
-generated text, renders managed Markdown reports, and can upload completed
+single-report generated text, renders managed Markdown reports, and can upload completed
 reports through Distributor. Start with the [README](../README.md) for product
 context and the [architecture policy](policy/architecture.md) for system
 boundaries and invariants.
@@ -27,7 +27,7 @@ boundaries and invariants.
 | Report definitions, valid periods, report IDs, output naming, or batch composition | [Report registry internals](internal/report-registry.md) and [app orchestration internals](internal/app-orchestration.md) | Report definitions own selection and period rules; orchestration owns execution. |
 | Module IDs, module composition, briefing values, or prompt-facing exports | [Module contract internals](internal/module.md), [module builder internals](internal/briefing.md), and [prompt-input internals](internal/prompt-input.md) | These own module contracts, value construction, and the curated prompt-package boundary. |
 | Recent Changes comparison | [Changes internals](internal/changes.md) and [operations guide](operations.md) | The internal guide owns structured comparison; operations owns user-visible artifact behavior. |
-| Scriptorium commands, subprocess execution, prompt inputs, or result handling | [Scriptorium integration](integrations/scriptorium.md), [Scriptorium adapter internals](internal/scriptorium-adapter.md), and [prompt-input internals](internal/prompt-input.md) | These separate the external CLI contract, subprocess boundary, and input construction. |
+| Prompt execution, profiles, prompt inputs, or result handling | `internal/promptexec`, the Promptkit adapter, and [prompt-input internals](internal/prompt-input.md) | These separate the executor contract and input construction. |
 | Generated-text schemas, validation, render contexts, templates, or Markdown rendering | [Generated-text internals](internal/generatedtext.md), [report-template internals](internal/reporttemplate.md), and [report template guide](templates.md) | These own structured text, renderer implementation, and the maintainer-facing template surface. |
 | Workspace paths, metadata, atomic persistence, lookup, inspection, or recovery | [State internals](internal/state.md), [operations guide](operations.md), and [troubleshooting guide](troubleshooting.md) | These separate implementation, operator workflows, and symptom-based recovery. |
 | Distributor bundles, uploads, notification artifacts, or failures | [Distributor adapter internals](internal/distributor-adapter.md), [Distributor integration contracts](integrations/distributor/), and [operations guide](operations.md) | These separate adapter behavior, external contracts, and operational lifecycle. |
@@ -46,7 +46,7 @@ present before introducing a new package or abstraction.
 | `internal/cli` | Command parsing, flags, help, output, and command wiring. |
 | `internal/app` | Generation, batches, collection coordination, notification, and inspection orchestration. |
 | `internal/config` | Configuration defaults, loading, precedence, secrets, and validation. |
-| `internal/adapters` | Weather API, Scriptorium, and Distributor boundaries. |
+| `internal/adapters` | Weather API, Promptkit, and Distributor boundaries. |
 | `internal/weatherdata`, `internal/forecast`, `internal/facts` | Normalized source facts and deterministic derivation. |
 | `internal/report`, `internal/module`, `internal/briefing`, `internal/changes` | Report registry, module contracts and values, and structured comparison. |
 | `internal/promptinput`, `internal/generatedtext`, `internal/reporttemplate` | Prompt packages, generated-text validation, render contexts, and Markdown templates. |
@@ -68,7 +68,7 @@ implemented subsystem behavior.
 5. Run repository-wide validation before considering the work complete.
 
 Preserve actionable error context, keep secrets out of logs and fixtures, and
-avoid validation that requires live Weather API, Scriptorium, or Distributor
+avoid validation that requires live Weather API, Promptkit providers, or Distributor
 services. The architecture and testing policies own the detailed rules.
 
 ## Baseline Validation

docs/integrations/promptkit.md

@@ -0,0 +1,22 @@
+# Promptkit Integration
+
+Weatherreporter uses Promptkit for all generated-text reports. The four logical prompts are
+`weather.daily_generated_text`, `weather.today_generated_text`,
+`weather.tomorrow_generated_text`, and `weather.hourly_generated_text`, each at version
+`1.0.0`. Their prompt assets and generated-text JSON Schemas are embedded by
+`internal/promptassets`.
+
+Before collection, Weatherreporter inspects the exact prompt version, requires one required
+`data_package` input with content type `application/yaml`, and requires the report's JSON
+Schema output contract. It selects `promptkit.profile` when configured, otherwise the
+prompt's declared default profile. Profiles that require a direct API key are unsupported; a
+profile that reports `APIKeyEnv` requires a nonblank value in that environment variable.
+
+Execution receives the already-persisted YAML package, prepares it once, and returns structured
+JSON that Weatherreporter validates before rendering its own Markdown template. Preparation and
+execution receipts are project-owned, safe provenance records. Content-rich diagnostics are
+opt-in through `--llm-debug-dir`; see [operations](../operations.md) for retention and permissions.
+
+Prompt/profile configuration is owned by the [configuration reference](../config.md). Adapter
+construction and mapping are documented in the [Promptkit adapter internals](../internal/promptkit-adapter.md).
+Durable metadata compatibility is described in [state internals](../internal/state.md).

docs/integrations/scriptorium.md

@@ -1,91 +0,0 @@
-# Scriptorium Integration
-
-`weatherreporter` invokes the Scriptorium executable as a subprocess to
-preflight prompt input and produce report artifacts. This is the limited CLI
-contract Weatherreporter uses, not general Scriptorium documentation.
-
-## Invocation
-
-The configured `scriptorium.binary` is the executable name or path. When it is
-empty, the adapter invokes `scriptorium`. Arguments are passed directly to the
-process, without a shell.
-
-For every command, arguments occur in this order:
-
-1. The subcommand.
-2. `--config <path>` when `scriptorium.config_path` is set.
-3. `--profile <profile>` when `scriptorium.profile` is set.
-4. The command-specific arguments below.
-5. Each configured `scriptorium.extra_args` item.
-
-The adapter uses these exact command shapes:
-
-```text
-scriptorium render [--config <path>] [--profile <profile>] \
-  --prompt <prompt_id> --input data_package=<data_package_path> --format json \
-  [<extra_arg> ...]
-
-scriptorium run [--config <path>] [--profile <profile>] \
-  --prompt <prompt_id> --input data_package=<data_package_path> --out <output_path> \
-  [<extra_arg> ...]
-```
-
-`render` is the preflight command. `run` writes either a Markdown report or a
-raw generated-text artifact to the supplied `--out` path. The structured
-generated-text use of `run` has the same argv as Markdown generation; it does
-not add `--format`, `--schema`, `--schema-path`, or `--json-schema` flags.
-Prompt configuration selected by `<prompt_id>` controls that output.
-
-## Inputs and Outputs
-
-Weatherreporter always supplies exactly one prompt input:
-`--input data_package=<data_package_path>`. The path identifies the YAML data
-package produced by the [prompt-input builder](../internal/prompt-input.md).
-Its schema and the separate JSON module snapshots are internal artifacts, not
-part of this CLI contract.
-
-The application supplies an already-managed output path to every `run` call.
-For direct reports it is the Markdown artifact path. For generated-text
-reports it is the raw JSON artifact path; subsequent validation and Markdown
-rendering are owned by [generated-text processing](../internal/generatedtext.md).
-
-`render` has no output-path argument. Its JSON-formatted stdout remains
-captured output: the adapter records it and does not parse it into a separate
-CLI result type. Likewise, the adapter records `run` output metadata without
-decoding the artifact written at `--out`.
-
-## Execution and Results
-
-`scriptorium.timeout`, when greater than zero, creates a timeout for each
-subprocess invocation. Parent-context cancellation and that timeout stop the
-command through the process context.
-
-Stdout and stderr are captured independently, each up to 1 MiB. Every returned
-result records the complete argv as `command`, the captured `stdout` and
-`stderr`, `exitCode`, and `stdoutTruncated` and `stderrTruncated` when a stream
-was capped. Results from both forms of `run` also record `outputPath`, the
-requested `--out` value.
-
-The [Scriptorium adapter](../internal/scriptorium-adapter.md) owns process
-execution and result capture. [Application orchestration](../internal/app-orchestration.md)
-owns when preflight output, report artifacts, and generated-text artifacts are
-persisted.
-
-## Failure Behavior
-
-Before starting Scriptorium, the adapter requires a prompt ID and data-package
-path for every command, plus an output path for `run`. Missing fields fail
-without executing a subprocess.
-
-A nonzero process exit returns the captured result and an error that includes
-the exit code and stderr. An output file written before such an exit does not
-make the request successful. Failures to start the command, context
-cancellation, and timeout return an error rather than a successful result.
-
-## Operational Notes
-
-- Extra arguments are argv items; they are not shell-interpreted.
-- Prompt input, generated artifacts, stdout, and stderr can contain
-  operationally sensitive weather data.
-- Provide API keys through the Scriptorium environment or its configuration,
-  not through Weatherreporter CLI arguments.

docs/internal/app-orchestration.md

@@ -1,110 +1,48 @@
 # Application Orchestration Internals
 
-`internal/app` composes top-level generation, batch, collection-save, and
+`internal/app` owns top-level generation, batch, collection, inspection, and
-inspection workflows after CLI parsing and configuration loading. It owns
+notification ordering after the CLI has parsed arguments and loaded configuration.
-workflow ordering, request composition, partial-result handling, and the
-application-facing interfaces used for tests.
 
-## Inputs And Outputs
+## Generation
 
-The package accepts generate, resolved-report, batch, explicit-collection, and
+`GenerateDetailed` resolves one of the four report definitions, initializes an
-inspection requests. Generation and batch requests may supply collector,
+optional debug root, and inspects the exact Promptkit prompt/profile before it
-renderer, store, and notifier implementations for tests; production defaults
+collects weather or writes managed state. It then builds facts and modules,
-use the focused packages.
+saves the YAML data package, persists preparation metadata from the executor
+callback, executes the prepared prompt, saves execution provenance and raw
+output, validates generated text, renders Markdown, and optionally copies or
+notifies from the managed report.
 
-A report result contains the module snapshot, prompt package, available
+After a completed prompt run, each successfully written downstream artifact is
-Scriptorium results, generated-text artifacts when used, report and metadata
+atomically added to the execution record before the corresponding metadata
-paths, prior snapshot, Recent Changes, and notification information. A batch
+rewrite. Later failures therefore leave the original Promptkit outcome and its
-result contains aggregate counts, per-report outcomes, and an optional batch
+last durable set of reached paths inspectable.
-notification. Inspection returns persisted values only.
 
-Exact public command syntax, configuration fields, workspace layout, external
+Failure results retain all safe paths reached so far. Validation rejection
-protocols, and report definitions belong in [the CLI reference](../cli.md),
+persists raw output and execution provenance but does not render a report.
-[the configuration reference](../config.md), [operations](../operations.md),
-and their focused integration and internal documents.
 
-## Single-Report Workflow
+## Batches
 
-`GenerateDetailed` first collects weather data, then resolves the requested
+`RunBatchDetailed` constructs a single debug writer and uses the request's
-report using the configured registry and current time, and finally calls
+single executor. Before collection it inspects Today, Tomorrow, and Daily for
-`GenerateReport` with that explicit collection. It returns no result when
+morning, or Tomorrow and Daily for evening, deduplicating effective profile
-collection or resolution fails.
+inspection. It then collects once, plans eligible Daily dates, and calls the
+same prompt-generation core sequentially for each planned report. Per-report
+notification is suppressed; a failed report does not stop later reports.
 
-`GenerateReport` requires a non-nil normalized bundle and then performs this
+Batch notification is skipped when disabled or when any report failed.
-ordered work:
+Successful notification uses the completed managed report paths only. Batch
+items retain preparation, execution, and optional debug paths when reached.
 
-1. Select a state store, determine artifact destinations, and locate a prior
+## Inspection And Boundaries
-   compatible snapshot.
-2. Build report facts and deterministic module snapshots, then save the module
-   snapshot and calculate Recent Changes.
-3. Build and save the prompt data package, run Scriptorium render preflight,
-   save any preflight result, and save initial metadata.
-4. Produce managed Markdown according to the report generation mode.
-5. Optionally make an output copy, save final metadata, optionally notify
-   Distributor from the managed report path, and save metadata again when a
-   notification path is produced.
 
-Direct-Markdown reports prepare the managed report and invoke the Scriptorium
+Inspection loads persisted state only. It does not collect weather, invoke
-run boundary. Generated-text-template reports look up their catalog definition,
+Promptkit, or upload reports. The app coordinates project-owned contracts but
-run structured Scriptorium output to the raw artifact, preserve any structured
+does not parse flags, load YAML, implement transport, construct provider SDKs,
-run result, validate and save generated text, build and save a render context,
+or define report-period policy.
-then render the embedded Markdown template. Schema, template, and subprocess
-details remain in their [generated-text](generatedtext.md),
-[report-template](reporttemplate.md), and [Scriptorium adapter](scriptorium-adapter.md)
-owners.
 
-If preflight returns a result with an error, the result and initial metadata are
+Focused checks:
-saved before the error returns. If report generation fails after a managed path
-is prepared, metadata still records that path; output copies and notification
-are skipped. Generated-text failures preserve the latest artifact reached
-before failure when it was saved.
 
-## Batch And Inspection Workflows
+```sh
-
+go test ./internal/app ./internal/collect
-`RunBatchDetailed` collects once, asks the report registry to plan the batch
+```
-from that collection, and invokes `GenerateReport` independently for every
-planned report using the same collection and state store. Per-report
-notification is suppressed. A failed report is recorded and does not prevent
-later planned reports from running.
-
-After report generation, the batch notifier is considered once. It is omitted
-when Distributor or batch notification is disabled, skipped when any report
-failed, and otherwise receives one multi-file request. A batch notification
-failure increments the aggregate failure count but does not rewrite successful
-report items. Notification identities, path mappings, polling, and redaction
-are owned by the [Distributor adapter](distributor-adapter.md).
-
-Inspection methods create a state store and load existing report records,
-metadata, module snapshots, prompt packages, prior snapshots, or source
-provenance. They neither collect data nor invoke Scriptorium or Distributor.
-
-## Boundaries And Failure Propagation
-
-The app layer does not parse flags, load configuration files, implement Weather
-API transport, construct Scriptorium argv, or define report registry policy. It
-coordinates the relevant collaborators and preserves their error context.
-
-- Collection failure stops a single report or batch before resolution or
-  planning completes.
-- State, fact, module, prompt-input, or preflight failures stop that report
-  before report generation.
-- A terminal Distributor failure is returned with the saved notification
-  information when available.
-- Batch failures are represented per report and through aggregate batch status.
-- Persisted artifact paths are carried in results so callers can inspect work
-  completed before a later failure.
-
-## Tests And Invariants
-
-Focused tests are in `internal/app/app_test.go` and
-`internal/app/batch_plan_test.go`, with collection coverage in
-`internal/collect/collect_test.go`.
-
-- Production workflows collect through `internal/collect`.
-- A report uses one explicit normalized collection throughout its generation.
-- Render preflight precedes report generation.
-- Recent Changes compare structured module snapshots.
-- Generated-text reports render from a validated typed context, never directly
-  from a raw prompt package.
-- Only managed Markdown reports are notification sources; output copies are
-  never uploaded.

docs/internal/briefing.md

@@ -4,7 +4,7 @@
 collected facts, and derived facts. It owns the module registry, including
 module support, fact requirements, option types, missing-data policy, builders,
 and prompt-export hooks. It does not collect data, derive periods, write a
-snapshot, construct YAML, invoke Scriptorium, or render a report.
+snapshot, construct YAML, invoke Promptkit, or render a report.
 
 ## Registry and construction
 

docs/internal/changes.md

@@ -25,19 +25,14 @@ requires a change between its low, possible, likely, and high categories.
 | Comparator | Required snapshot data | Compared values |
 | --- | --- | --- |
 | `CompareDaily` | `derived_daily_summary`, `derived_daypart_summaries` | Low and high temperature, daily precipitation probability and timing, peak gust, alerts, and aggregate indicators |
-| `CompareThreeDay` | `derived_daypart_summaries` | Per-day temperatures, precipitation probability and timing, peak gust, indicators, and added or removed outlook days |
-| `CompareWeekend` | `derived_daypart_summaries` | The three-day values with weekend-prefixed change types |
 
 For daily comparison, `alert_digest` and `precip_timing` are optional: alerts
 are compared when present, and timing is compared only when both snapshots
-contain it. The multi-day comparators build their day map from daypart
+contain it.
-summaries. A missing or added day becomes a dedicated change rather than a
-comparison against invented data.
 
 The application selects a comparator only after state lookup establishes a
-compatible prior snapshot. Daily, Today, and Tomorrow use the daily comparator;
+compatible prior snapshot. Daily, Today, and Tomorrow use the daily comparator.
-Three-day and Weekend use their named comparators. Other report types, such as
+Hourly reports do not produce a Recent Changes list.
-Storm, produce no Recent Changes list.
 
 ## Missing data and failures
 
@@ -51,8 +46,8 @@ behavior. It does not decide report compatibility or retain snapshots.
 
 ## Verification and invariants
 
-Focused tests cover the daily, three-day, and weekend strategies, threshold
+Focused tests cover the daily strategy, threshold boundaries, indicator and
-boundaries, indicator and alert changes, and missing required stanzas:
+alert changes, and missing required stanzas:
 
 ```sh
 go test ./internal/changes

docs/internal/cli.md

@@ -1,65 +1,27 @@
 # CLI Internals
 
-`internal/cli` turns process arguments into application requests and translates
+`internal/cli` parses terminal arguments, loads configuration, constructs app
-application results into terminal output. The user-facing command, flag, and
+requests, and translates app results to bounded JSON summaries. The user
-output contract belongs in the [CLI reference](../cli.md).
+contract belongs in the [CLI reference](../cli.md).
 
-## Responsibilities
+The root `--version` flag reports the build version supplied by
+`internal/buildinfo`. Tagged release builds replace its development default at
+link time.
 
-`Runner.Run` dispatches the top-level action or inspection request. For actions,
+For each `generate` or `run` action, `Runner` constructs one project-owned
-the package parses command-specific and common flags, loads configuration with
+Promptkit executor after configuration loads. It passes the executor and any
-CLI overrides, obtains the current time, and constructs either an
+`--llm-debug-dir` request into the app. `run` accepts the debug flag as well
-`app.GenerateRequest` or an `app.BatchRequest`. It delegates generation and
+as `generate`; the app, not the CLI, secures and initializes the debug root.
-batch execution to `internal/app`.
 
-For inspection, it loads configuration, builds the appropriate app inspection
+Summaries include identity, status, safe artifact paths, and notification
-request, and writes the returned value. Inspection is read-only; the inspected
+provenance. They intentionally exclude module values, YAML package bodies, raw
-artifact types and user invocation remain owned by the [CLI reference](../cli.md)
+generated text, rendered prompts, schemas, endpoints, credentials, and full
-and [operations guide](../operations.md).
+Distributor payloads. A failed action with a partial result still emits its
+safe summary before its error is returned.
 
-## Result Translation
+CLI code owns no report policy, weather collection, persistence, provider
+execution, or notification policy. Focused checks:
 
-Action results become CLI-safe JSON summaries in `result.go`. Generate summaries
+```sh
-carry report identity, status, relevant artifact paths, and notification
+go test ./internal/cli
-summary data. Batch summaries carry aggregate counts, per-report outcomes, and
+```
-the optional batch notification result. The translation deliberately excludes
-full module snapshots, prompt packages, raw generated text, Scriptorium output,
-and complete Distributor payloads.
-
-When an action returns both a result and an error, the CLI writes the failed
-summary before returning that error. Parse, configuration-load, and other
-failures that produce no application result return without a summary.
-
-`writeActionResult` writes action status information to stderr first, then JSON
-to stdout. Batch execution supplies the status writer; single-report generation
-does not emit routine stderr output. Quiet action requests suppress both normal
-streams but still return errors. Inspection writes its JSON value to stdout and
-does not accept quiet mode because stdout is the inspection result.
-
-## Boundaries
-
-The package owns argument parsing, request adaptation, help text, and terminal
-presentation. It does not implement report selection, collection, state
-persistence, external transport, subprocess execution, or notification policy.
-Those concerns remain in [application orchestration](app-orchestration.md) and
-their focused owners.
-
-## Failure Behavior
-
-- Invalid command names, flags, dates, and configuration fail before an app
-  request is executed.
-- Application errors retain their application context; output helpers do not
-  hide or replace them.
-- JSON-encoding errors are returned directly.
-- A failed batch summary causes the CLI to return an aggregate batch error even
-  when the detailed batch call has already returned its result.
-
-## Tests And Invariants
-
-Focused tests are in `internal/cli/root_test.go`, `internal/cli/output_test.go`,
-and `internal/cli/result_test.go`.
-
-- CLI summaries are stable, bounded views of app results.
-- Routine batch status lines precede the batch JSON summary.
-- A quiet action produces no successful or failure summary output.
-- Inspection never invokes action-output helpers.

docs/internal/collect.md

@@ -13,7 +13,7 @@ calls `FetchBundle`, and returns `Result{Bundle: *weatherdata.Bundle}`.
 
 The package wraps adapter construction failures as weather-collection setup
 errors and fetch failures as bundle-collection errors. It does not retry,
-persist, select reports, derive facts, build modules, invoke Scriptorium, or
+persist, select reports, derive facts, build modules, invoke Promptkit, or
 notify Distributor.
 
 ## Application Composition

docs/internal/facts.md

@@ -33,10 +33,8 @@ Report identity controls the summary shape:
 | --- | --- |
 | Hourly | Rolling-period selections and precipitation timing; no daily or daypart summary |
 | Daily, Today, Tomorrow | One local civil-day summary and its dayparts |
-| Three-day, Weekend | One clipped daily summary for each overlapping local day |
-| Storm | One summary for the explicit report window |
 
-`DaypartSummaries` is collected from the resulting daily or storm summaries.
+`DaypartSummaries` is collected from the resulting daily summaries.
 The detailed grouping, daypart-window, and alert rules are owned by
 [forecast derivation](forecast-derivation.md).
 
@@ -55,8 +53,7 @@ not access the CLI, filesystem, subprocesses, or network.
 ## Verification and invariants
 
 Focused tests cover collected-fact separation, report-period selection,
-hourly and storm behavior, daily and partial-day summaries, and convective
+hourly behavior, daily summaries, and convective outlook selection:
-outlook selection:
 
 ```sh
 go test ./internal/facts

docs/internal/generatedtext.md

@@ -8,12 +8,12 @@ maintainer-facing context fields belong to [report templates](../templates.md).
 
 ## Catalog and validation
 
-Only the Daily, Today, Tomorrow, and Hourly report definitions use the
+The Daily, Today, Tomorrow, and Hourly report definitions each use structured
-generated-text-template mode. `LookupDefinition` rejects a direct-Markdown
+generated text. `LookupDefinition` rejects unknown schema or template IDs and
-definition, unknown schema or template IDs, and unsupported schema/template
+unsupported schema/template pairs before the run begins. A handler validates raw JSON, returns a typed
-pairs before the run begins. A handler validates raw JSON, returns a typed
+value and canonical normalized JSON, loads its canonical schema through
-value and canonical normalized JSON, loads its schema, builds a render context,
+`internal/promptassets`, builds a render context, and renders through
-and renders through `internal/reporttemplate`.
+`internal/reporttemplate`.
 
 Daily, Today, and Tomorrow use a day-style value with required trimmed summary
 and one or more nonblank discussion paragraphs. Hourly requires trimmed summary
@@ -33,7 +33,7 @@ template iteration rather than maps.
 Optional source stanzas become nil or fallback context fields. Missing required
 stanzas, type-decoding failures, invalid metadata, or a generated-text type
 that does not match the chosen handler fail before template execution. Prompt
-packages, raw Scriptorium output, state persistence, and template asset lookup
+packages, raw Promptkit output, state persistence, and template asset lookup
 remain outside this package.
 
 ## Verification and invariants
@@ -47,5 +47,5 @@ go test ./internal/generatedtext
 ```
 
 Generated text supplies prose slots only; deterministic weather facts remain in
-module and fact values. Every generated-text definition must resolve to exactly
+module and fact values. Every report definition must resolve to exactly one
-one supported catalog pair.
+supported catalog pair.

docs/internal/module.md

@@ -39,8 +39,6 @@ The registry declares these ordered default compositions:
 | Today | metadata, current conditions, narrative forecast, daily summary, daypart summaries, precipitation timing, alert digest, SPC outlooks, AFD, SPC discussion, weather story, outdoor windows, hourly forecast, today planning |
 | Tomorrow | metadata, current conditions, narrative forecast, daily summary, daypart summaries, precipitation timing, alert digest, SPC outlooks, AFD, SPC discussion, weather story, outdoor windows, tomorrow planning, hourly forecast |
 | Hourly | metadata, current conditions, hourly forecast, precipitation timing, alert digest, SPC outlooks, AFD (key messages and short term), SPC discussion, weather story |
-| Three-day and Weekend | metadata, current conditions, daypart summaries, precipitation timing, alert digest, SPC outlooks, AFD, SPC discussion, weather story, outdoor windows |
-| Storm | metadata, current conditions, precipitation timing, alert digest, SPC outlooks, AFD, SPC discussion, weather story |
 
 The only non-empty default option is the AFD section selection. It accepts a
 `sections` list; omitted or empty selects all available sections. Report

docs/internal/prompt-input.md

@@ -2,9 +2,9 @@
 
 `internal/promptinput` converts report metadata, an ordered module snapshot,
 Recent Changes, and source warnings into the YAML `data_package` consumed by
-Scriptorium. It owns this package's schema, grouping, serialization, loading,
+Promptkit. It owns this package's schema, grouping, serialization, loading,
 and validation—not weather collection, module construction, path choice, or
-subprocess execution.
+provider execution.
 
 ## Package construction
 

docs/internal/promptkit-adapter.md

@@ -0,0 +1,24 @@
+# Promptkit Adapter Internals
+
+`internal/adapters/promptkit` maps Weatherreporter's project-owned executor contract to Promptkit.
+The CLI maps `promptkit` configuration to a `PromptExecutorConfig` and constructs one executor
+per action. Promptkit dependency types do not escape the adapter.
+
+The adapter exposes exact prompt and profile inspection plus prepared execution. It maps Promptkit
+inspection values to project-owned prompt input, output-contract, profile, preparation, execution,
+validation, and optional debug values. It classifies adapter failures without copying provider secrets
+or unbounded response bodies into application errors or normal state.
+
+The app calls the executor's preparation callback before provider execution to persist safe preparation
+provenance. Completed executions are then persisted as safe execution provenance and raw generated text
+is validated by `internal/generatedtext`. The adapter does not write workspace state, render Markdown,
+choose report definitions, or send Distributor notifications.
+
+Focused tests:
+
+```sh
+go test ./internal/adapters/promptkit ./internal/cli ./internal/app
+```
+
+The public logical prompt/profile/schema contract is owned by the
+[Promptkit integration guide](../integrations/promptkit.md).

docs/internal/report-registry.md

@@ -1,7 +1,7 @@
 # Report Registry Internals
 
 `internal/report` owns the registry of report identities and the data declared
-for each one: resolution, generation mode, prompt identity, comparison policy,
+for each one: resolution, prompt identity and version, comparison policy,
 artifact group, output-copy name, default module composition, and Distributor
 path declarations. The public command syntax is owned by the
 [CLI reference](../cli.md); configuration aliases and overrides are owned by
@@ -10,34 +10,28 @@ the [configuration reference](../config.md).
 ## Definitions and resolution
 
 Each `Definition` declares a stable ID and display name, prompt ID, generation
-mode, optional template and generated-text schema IDs, valid-period resolver,
+version, template and generated-text schema IDs, valid-period resolver,
 comparison strategy, artifact group, batch-copy filename, Distributor path
 templates, generation eligibility, compatible prior IDs, default modules, and
 batch eligibility flags. `Resolved` combines that definition with the valid
 period and run metadata for one invocation.
 
-| Report ID | Mode | Period policy | Comparison | Registry batch flag | Output copy |
+| Report ID | Prompt version | Period policy | Comparison | Registry batch flag | Output copy |
 | --- | --- | --- | --- | --- | --- |
-| `daily` | Generated text + template | Explicit local civil day | Same valid date | Dynamic Daily inclusion is app-owned | `daily.md` |
+| `daily` | `1.0.0` | Explicit local civil day | Same valid date | Dynamic Daily inclusion is app-owned | `daily.md` |
-| `today` | Generated text + template | Selected or current local civil day | Same valid date | Morning | `today.md` |
+| `today` | `1.0.0` | Selected or current local civil day | Same valid date | Morning | `today.md` |
-| `tomorrow` | Generated text + template | Next local civil day | Same valid date | Evening | `tomorrow.md` |
+| `tomorrow` | `1.0.0` | Next local civil day | Same valid date | Evening | `tomorrow.md` |
-| `hourly` | Generated text + template | Rolling six-hour interval | Rolling window | — | `hourly.md` |
+| `hourly` | `1.0.0` | Rolling six-hour interval | Rolling window | — | `hourly.md` |
-| `three_day` | Scriptorium Markdown | Generation time through the third following local midnight | Same valid date | Morning | `three-day.md` |
-| `weekend` | Scriptorium Markdown | Upcoming weekend window | Weekend window | Morning | `weekend.md` |
-| `storm` | Scriptorium Markdown | Caller-supplied event window | Explicit window | — | `storm.md` |
 
-The four generated-text reports pair their report ID with matching template and
+Each report pairs its ID and prompt version with matching template and schema
-schema IDs. The three direct-Markdown reports leave both IDs empty. Exact
+IDs. Exact template fields and schema assets belong to [report templates](../templates.md)
-template fields and schema assets belong to [report templates](../templates.md)
 and [generated-text internals](generatedtext.md).
 
-All valid periods are half-open. Storm accepts local `YYYY-MM-DDTHH:MM` values
+All valid periods are half-open.
-in the effective report timezone or offset-bearing RFC3339 values; its end
-must follow its start. Resolving Weekend directly on Sunday is rejected.
 
 ## Registry collaborators
 
-`DefaultRegistry` is the only source of the seven report definitions.
+`DefaultRegistry` is the only source of the four report definitions.
 `Lookup`, `Resolve`, and report-name helpers prevent callers from duplicating
 report identity rules. Registry overrides clone a definition and replace its
 module list only after the report ID is recognized.
@@ -54,13 +48,12 @@ membership and produces the actual batch plan.
 
 Each definition supplies an ordered `[]module.ConfigItem`; the complete
 report-to-module mapping is maintained in [module internals](module.md).
-`ArtifactGroup`, `BatchOutputName`, `Generated`, and comparison compatibility
+`ArtifactGroup`, `BatchOutputName`, and comparison compatibility
 are likewise consumed by state and orchestration rather than recomputed there.
 
-Unknown report IDs or batch names, an invalid weekend resolution, and invalid
+Unknown report IDs or batch names return errors. The registry never collects
-storm windows return errors. The registry never collects weather data, builds
+weather data, builds modules, parses CLI flags, writes state, executes
-modules, parses CLI flags, writes state, executes Scriptorium, or delivers a
+Promptkit, or delivers a report.
-report.
 
 ## Verification and invariants
 

docs/internal/reporttemplate.md

@@ -1,22 +1,21 @@
 # Report Template Internals
 
 `internal/reporttemplate` embeds and renders the repository's native Markdown
-templates and exposes their companion generated-text schemas. The current asset
+templates. The current template IDs are `daily`, `today`, `tomorrow`, and
-IDs are `daily`, `today`, `tomorrow`, and `hourly`. The template files, partials,
+`hourly`. The template files, partials, and complete render-context field
-and complete render-context field reference are maintained in
+reference are maintained in
 [report templates](../templates.md).
 
 ## Assets and lookup
 
-The package embeds top-level templates, shared partials, and JSON schemas from
+The package embeds top-level templates and shared partials. `Template` returns
-its asset directories. `Template` and `Schema` return the requested embedded
+the requested embedded template and fails with the requested ID when it is
-asset and fail with the requested ID when it is unknown or unreadable.
+unknown or unreadable.
 
-Generated-text catalog handlers obtain schema bytes and template source through
+Generated-text schemas and Promptkit definitions are owned by
-these APIs. Prompt source files are repository assets for prompt registration;
+`internal/promptassets`; report-template owns Markdown source only. Report
-they are not reporttemplate lookup assets. Report definitions select IDs, while
+definitions select IDs, while [generated-text internals](generatedtext.md)
-[generated-text internals](generatedtext.md) verifies the supported
+verifies the supported schema/template pairing.
-schema/template pairing.
 
 ## Rendering
 
@@ -36,16 +35,17 @@ validation.
 
 This package does not collect weather data, build modules, validate generated
 text, construct contexts, resolve report definitions, write state, execute
-Scriptorium, or upload reports. It produces Markdown bytes for application
+Promptkit, or upload reports. It produces Markdown bytes for application
 orchestration to persist.
 
-Focused tests cover asset lookup, schema availability, rendering, partial
+Focused tests cover template lookup, rendering, partial
 behavior, missing keys, and malformed context:
 
 ```sh
 go test ./internal/reporttemplate
 ```
 
-Embedded assets stay as separate files, shared fragments stay under the partial
+Embedded templates stay as separate files and shared fragments stay under the
-directory, and generated-text schemas describe prose slots rather than
+partial directory. Generated-text schemas are embedded separately by
-deterministic weather facts.
+`internal/promptassets` and describe prose slots rather than deterministic
+weather facts.

docs/internal/scriptorium-adapter.md

@@ -1,51 +0,0 @@
-# Scriptorium Adapter Internals
-
-`internal/adapters/scriptorium` translates Weatherreporter render requests to
-Scriptorium process arguments and translates process results back to local
-types. The external CLI and output contract belongs to the
-[Scriptorium integration guide](../integrations/scriptorium.md); prompts,
-template inputs, and report ownership remain outside this adapter.
-
-## Request-to-command translation
-
-`Runner` accepts a binary, config path, profile, timeout, extra arguments, and
-an injectable command executor. Its defaults are the `scriptorium` binary and
-the real `ExecRunner`. Optional configuration flags are placed before the
-operation-specific arguments, and extra arguments are appended last.
-
-| Local operation | Required values | Translated arguments |
-| --- | --- | --- |
-| `Render` | prompt ID, data-package path | `render [--config …] [--profile …] --prompt <id> --input data_package=<path> --format json [extra …]` |
-| `Run` | prompt ID, data-package path, output path | `run [--config …] [--profile …] --prompt <id> --input data_package=<path> --out <path> [extra …]` |
-| `StructuredRun` | prompt ID, data-package path, output path | Same translation as `Run` |
-
-Blank required values fail before a command starts. The adapter does not add
-schema flags or interpret a prompt's payload; it only gives Scriptorium the
-named `data_package` input.
-
-## Command execution and result translation
-
-`ExecRunner` uses `exec.CommandContext`, never a shell. A positive configured
-timeout creates a child context. Standard output and standard error are
-captured independently, each with a 1 MiB limit, and the executed command is
-retained for diagnostics.
-
-`RenderResult`, `RunResult`, and `StructuredRunResult` expose the command,
-captured output, truncation markers, and exit code. Run results also retain the
-requested output path. Exit status zero is successful. A nonzero process exit
-returns its result and an error, while a start failure, cancellation, or
-deadline failure returns no result and the execution error.
-
-The adapter does not parse rendered JSON, validate a generated report, write
-state, or upload a report. Those responsibilities sit with
-[application orchestration](app-orchestration.md), [state internals](state.md), and the
-relevant delivery adapter.
-
-## Verification
-
-Focused tests cover argument order, validation, bounded capture, timeout and
-cancellation handling, and exit-status translation:
-
-```sh
-go test ./internal/adapters/scriptorium
-```

docs/internal/state.md

@@ -1,91 +1,56 @@
 # State Internals
 
-The `internal/state` package owns filesystem-backed run state: safe path
+`internal/state` owns safe workspace paths, atomic artifact writes, metadata,
-derivation, metadata persistence, prior-report lookup, and read-only report
+prior-snapshot lookup, and read-only inspection. Operators should use the
-inspection. It does not decide which reports to generate or deliver. For the
+[operations guide](../operations.md) for lifecycle and retention.
-operator-facing layout and retention procedures, see the
-[operations guide](../operations.md).
 
-## Store construction and artifact paths
+## Artifact Paths
 
-`NewFilesystemStore` requires a workspace root and rejects absolute or
+For each run, paths are grouped by artifact group and valid start date:
-escaping values for every configured state directory. `Paths` then validates a
-run ID and artifact group before deriving all paths from the report's valid
-start date (`YYYY-MM-DD`). This keeps a run's artifacts together while making
-the paths safe to use below the configured workspace.
 
-| Artifact | Derived location |
+| Artifact | Location |
 | --- | --- |
 | Module snapshot | `snapshots/<group>/<date>/modules.<run-id>.json` |
 | Metadata | `snapshots/<group>/<date>/metadata.<run-id>.json` |
 | Data package | `data-packages/<group>/<date>/data_package.<run-id>.yaml` |
-| Render preflight | `preflight/<group>/<date>/render.<run-id>.json` |
+| Prompt preparation | `preflight/<group>/<date>/prompt_preparation.<run-id>.json` |
-| Notification record | `notifications/<group>/<date>/distributor.<run-id>.json` |
+| Prompt execution | `snapshots/<group>/<date>/prompt_execution.<run-id>.json` |
+| Raw generated text | `snapshots/<group>/<date>/generated_text_raw.<run-id>.json` |
+| Validated generated text | `snapshots/<group>/<date>/generated_text.<run-id>.json` |
+| Render context | `snapshots/<group>/<date>/render_context.<run-id>.json` |
 | Managed report | `reports/<group>/<date>/report.<run-id>.md` |
-| Generated text | `snapshots/<group>/<date>/generated_text.<run-id>.json` |
+| Notification | `notifications/<group>/<date>/distributor.<run-id>.json` |
-| Generated-text source and result | `snapshots/<group>/<date>/generated_text_raw.<run-id>.json` and `generated_text_result.<run-id>.json` |
-| Generated-text render context | `snapshots/<group>/<date>/render_context.<run-id>.json` |
 
-The configured notification root separates notification artifacts from report
+Batch notification records are `notifications/batches/<batch>/<local-date>/distributor.<batch-run-id>.json`.
-artifacts; single-report notification paths use the report's valid date. Report
-producers create parent directories as needed and write the report body; state
-is responsible for the surrounding paths and saved run artifacts.
 
-Batch Distributor notifications are derived separately as
+## Metadata And Debug Storage
-`notifications/batches/<batch>/<local-date>/distributor.<batch-run-id>.json`.
-Their date is calculated from the batch start in its configured location, and
-the batch identity and run ID receive the same path-segment validation as
-single-report artifact identifiers.
 
-## Metadata and durable writes
+New metadata is `weatherreporter.metadata.v2` and gains preparation and
+execution paths only after those artifacts are saved. Legacy V1 records remain
+readable; their historic preflight and generated-text-result fields are mapped
+to the corresponding preparation and execution views during inspection. New
+runs never write V1 records.
 
-`Metadata` is the durable inventory for a run. It records its schema version,
+Prompt preparation and execution records are validated on both save and load.
-run identity, generated and valid timestamps, artifact group and mode, source
+They require exact report/prompt identity, complete timing, internally
-content and provenance, and the module snapshot, data-package, preflight,
+consistent provenance, and status-appropriate validation or bounded classified
-report, generated-artifact, and notification locations when present.
+errors. Completed execution provenance keeps Promptkit's run identity distinct
+from the Weatherreporter run identity.
 
-`BuildMetadataFromBriefingMetadata` establishes the common fields; the
+For a completed prompt run, the execution record is atomically replaced after
-application adds locations as artifacts are produced. `SaveMetadata` requires
+each downstream artifact is saved. Its path set therefore records the raw and
-the run ID and the module snapshot, data-package, preflight, and metadata
+normalized generated text, render context, managed report, requested output
-paths. The package also saves module snapshots, data packages, preflight
+copy, and notification artifact actually reached without changing the original
-records, generated-text artifacts, render contexts, and notifications. JSON
+Promptkit outcome.
-writes use `fileutil.WriteJSONAtomic`, so readers do not observe a partially
-written state file.
 
-The data package itself follows the shared
+`PromptDebugWriter` is separate from workspace state. An empty root disables
-[prompt-input contract](prompt-input.md). Report text, templates, and external
+it. An enabled absolute root is checked for safe directories and symlinks, then
-delivery payloads remain owned by their respective packages and integration
+stores `preparation.json` and `execution.json` beneath
-references.
+`<root>/<report-id>/<valid-date>/<run-id>/`. Directories are `0700`; files are
+atomic `0600`. Normal state discovery does not read this root.
 
-## Prior reports and inspection
+Focused checks:
-
-`FindPriorSnapshot` searches metadata rather than guessing from filenames. It
-only considers an earlier compatible report in the same artifact group and
-supports the comparison strategies defined by the report request:
-
-- `same_valid_date` finds an earlier generated report for the same valid day.
-- `weekend_window` finds a prior comparable weekend window.
-
-The newest eligible metadata record wins; the current run is excluded.
-Unreadable or malformed candidate metadata is ignored so a damaged historical
-record does not block a new run.
-
-`ListReports` walks saved metadata, returns results ordered newest-first by
-generation time, and treats a missing snapshots directory as an empty history.
-`LoadMetadataByRunID` builds on that inspection path. These APIs are read-only;
-repairing or pruning stored state is an operational concern.
-
-## Boundaries and verification
-
-The package rejects unsafe path components and incomplete metadata before
-writing. Callers must provide a valid report request, artifact group, and
-store configuration. Its focused tests cover path derivation, atomic
-persistence, metadata validation, comparison eligibility, and report listing:
 
 ```sh
 go test ./internal/state
 ```
-
-See [application orchestration](app-orchestration.md) for the order in which
-these artifacts are created and [report templates](../templates.md) for the
-user-facing report contract.

docs/operations.md

@@ -15,24 +15,39 @@ weatherreporter generate today --out ./today.md
 ```
 
 A generation collects weather data, resolves the report period, builds and
-persists the module snapshot and prompt data package, runs Scriptorium
+persists the module snapshot and prompt data package, records Promptkit
-preflight, then produces the managed Markdown report. Daily, Today, Tomorrow,
+preparation provenance before provider execution, then persists raw output and
-and Hourly reports additionally persist generated-text artifacts, validate the
+execution provenance, validates the structured generated text, and renders the
-structured generated text, and render Markdown from the validated text and
+managed Markdown report from the validated text and deterministic values.
-deterministic values.
 
 The managed report and its final metadata are saved before single-report
 Distributor notification is attempted. `--out` writes an extra operator copy;
 it never changes the managed report or upload source. A successful generate
 command prints its summary to stdout unless `--quiet` is used.
 
+## Optional Prompt Debug Capture
+
+Use `--llm-debug-dir` only when content-rich prompt diagnostics are required:
+
+```sh
+weatherreporter generate today --llm-debug-dir /var/tmp/weatherreporter-debug
+```
+
+The directory must be absolute and is initialized before prompt inspection or
+weather collection. Capture files are stored outside the managed workspace,
+with restrictive permissions, under the report ID, valid date, and RunID.
+They can contain rendered prompts and generated output, so the normal metadata,
+CLI summary, and routine logs contain only the optional directory path—not
+their content. A capture-write failure stops that run before later work can
+continue.
+
 Run a scheduled batch with the same configured collection:
 
 ```sh
-weatherreporter run morning --out-dir ./reports
+weatherreporter run morning --out-dir ./reports --llm-debug-dir /var/tmp/weatherreporter-debug
 ```
 
-Each batch collects once before it plans reports. Morning runs Today, Tomorrow,
+Each batch validates its configured prompt/profile candidates, then collects once before it plans reports. Morning runs Today, Tomorrow,
 and every eligible dated Daily Report; evening runs Tomorrow and the same
 eligible Daily Reports. Eligible Daily dates begin after tomorrow and require
 complete hourly coverage for their entire local civil day. A batch continues
@@ -57,22 +72,23 @@ workspace/
   snapshots/<artifact_group>/<YYYY-MM-DD>/modules.<run_id>.json
   snapshots/<artifact_group>/<YYYY-MM-DD>/metadata.<run_id>.json
   snapshots/<artifact_group>/<YYYY-MM-DD>/generated_text_raw.<run_id>.json
-  snapshots/<artifact_group>/<YYYY-MM-DD>/generated_text_result.<run_id>.json
+  snapshots/<artifact_group>/<YYYY-MM-DD>/prompt_execution.<run_id>.json
   snapshots/<artifact_group>/<YYYY-MM-DD>/generated_text.<run_id>.json
   snapshots/<artifact_group>/<YYYY-MM-DD>/render_context.<run_id>.json
 
   data-packages/<artifact_group>/<YYYY-MM-DD>/data_package.<run_id>.yaml
-  preflight/<artifact_group>/<YYYY-MM-DD>/render.<run_id>.json
+  preflight/<artifact_group>/<YYYY-MM-DD>/prompt_preparation.<run_id>.json
 
   notifications/<artifact_group>/<YYYY-MM-DD>/distributor.<run_id>.json
   notifications/batches/<batch>/<YYYY-MM-DD>/distributor.<batch_run_id>.json
 ```
 
-The generated-text and render-context artifacts are written only by Daily,
+The generated-text and render-context artifacts are written for every completed
-Today, Tomorrow, and Hourly reports. A report's metadata links the module
+single-report generation.
-snapshot, data package, preflight artifact, managed report, and any available
+A report's metadata links the module snapshot, data package, preparation and
-generated-text or single-report notification artifact. Batch notification
+execution receipts, managed report, generated-text artifacts, and any available single-report
-artifacts are separate batch-level records under `notifications/batches`.
+notification artifact. Batch notification artifacts are separate batch-level
+records under `notifications/batches`.
 
 RunIDs begin with the UTC generation timestamp and report ID. A Daily RunID
 also contains its local valid date so multiple Daily reports in one batch have
@@ -105,7 +121,7 @@ redacted errors; they do not contain tokens.
 ## Inspecting Stored Runs
 
 Inspection is read-only: it neither collects weather data nor invokes
-Scriptorium or Distributor. Start by finding a RunID:
+Promptkit or Distributor. Start by finding a RunID:
 
 ```sh
 weatherreporter inspect reports --limit 10
@@ -124,17 +140,23 @@ weatherreporter inspect metadata RUN_ID
 A missing snapshots directory produces no listed reports. An unknown or empty
 RunID is an error; use `inspect reports` to obtain a valid value.
 
+New runs write `weatherreporter.metadata.v2`, including preparation and
+execution references once those receipts exist. `inspect metadata` also reads
+historic V1 records; their legacy preflight and generated-text-result fields
+remain visible for compatibility, but Weatherreporter does not write them for
+new runs.
+
 ## Recovery
 
 Keep the workspace when a run fails: artifacts reached before the failure
 remain available where they can be safely persisted.
 
-- A preflight failure can leave the preflight artifact and metadata.
+- A preparation failure can leave its classified receipt and metadata.
 - A report-generation failure can leave the managed report, module snapshot,
   data package, and metadata.
-- A generated-text failure can leave raw text, the structured run result, or a
+- A completed prompt validation rejection leaves raw text, an execution receipt,
-  validated generated-text and render-context artifact, depending on where it
+  and metadata. Later generated-text failures can also leave validated text and
-  stopped.
+  a render-context artifact, depending on where they stopped.
 - A single-report notification failure preserves the report and final metadata,
   including its notification artifact when it was written.
 - A batch notification failure preserves each report's artifacts and adds the
@@ -147,7 +169,7 @@ first response; retain it until the failure is understood.
 
 ## Operational Caveats
 
-- Workspace files, generated reports, and Scriptorium stderr can contain
+- Workspace files and generated reports can contain
   sensitive operational context. Set appropriate filesystem permissions and do
   not publish them unintentionally.
 - Weatherreporter uses one configured Weather API endpoint and local workspace

docs/policy/architecture.md

@@ -2,217 +2,72 @@
 
 ## Purpose
 
-This policy defines Weatherreporter's system shape, normative ownership,
+This policy defines Weatherreporter's system shape, ownership, dependency direction,
-dependency direction, architectural invariants, safety properties, and
+and safety invariants. The [development guide](../development.md) owns the
-non-goals. Developers and coding agents should use it to preserve the
+package inventory; focused documents in `docs/internal/` own implementation detail.
-application's boundaries as the implementation evolves.
-
-The [development guide](../development.md) owns the current package inventory
-and contributor workflow. Focused documents under `docs/internal/` own
-implemented subsystem mechanics. This policy owns the rules those packages and
-mechanics must preserve.
 
 ## System Shape
 
-Weatherreporter is a deterministic weather briefing and report-preparation CLI.
+Weatherreporter is a deterministic weather-report CLI. It collects normalized
-It consumes normalized weather data, derives report facts and module snapshots,
+weather data, derives facts and modules, builds a curated YAML data package,
-builds curated prompt packages, compares structured snapshots with prior runs,
+compares prior snapshots, executes exact-version Promptkit prompts, validates
-and invokes Scriptorium either to produce managed Markdown directly or to
+structured generated prose, and renders repository-owned Markdown. Completed
-produce bounded generated-text prose for repository-owned templates. It
+managed Markdown may be uploaded through Distributor.
-persists inspectable artifacts and can upload completed reports through
-Distributor.
 
-The application is intentionally a small, explicit, dependency-light Go
+The supported report products are Daily, Today, Tomorrow, and Hourly. A batch
-program. Add abstraction only when it protects a real boundary, makes an
+collects once, validates its complete candidate prompt/profile set before
-important invariant testable, or supports an implemented extension point.
+collection, then executes planned reports sequentially with one executor. It
+continues after independent report failures and sends a batch notification only
+after every planned report succeeds.
 
-The primary flow is:
+## Ownership And Boundaries
 
-1. CLI parsing and configuration resolution;
+- `internal/cli` owns command parsing, help, summaries, and one executor
-2. report or batch resolution;
+  construction per action.
-3. normalized weather collection;
+- `internal/config` owns defaults, loading, validation, and secret loading.
-4. deterministic fact derivation and module construction;
+- `internal/app` owns workflow order, partial results, and notification
-5. structured prior-snapshot comparison;
+  coordination through project-owned contracts.
-6. curated prompt input and report-mode-specific Scriptorium processing;
+- Deterministic domain packages own weather derivation, report periods, modules,
-7. generated-text validation when applicable, managed Markdown production,
+  generated-text validation, and template contexts.
-   and metadata persistence; and
+- `internal/adapters/weatherapi`, `internal/adapters/promptkit`, and
-8. optional notification using managed report artifacts.
+  `internal/adapters/distributor` own their external dependency mechanics.
+- `internal/state` owns workspace paths, V2 metadata, atomic persistence, and
+  read-only inspection.
 
-Inspection is a separate read-only flow over persisted state. It must not
+Dependency-specific Promptkit types remain inside its adapter. The application
-collect weather data, invoke Scriptorium, or upload reports.
+does not parse flags, construct provider clients, or render provider output
+directly.
 
-## Ownership And Dependency Direction
+## Prompt Execution Invariants
 
-### Entry Point And CLI
+- Prompts receive curated module packages, never unbounded raw weather payloads.
+- Every execution inspects the exact prompt version and output contract before
+  collection. The selected profile is configured explicitly or declared by the
+  prompt; unsupported direct-key profiles and missing reported credentials fail
+  before collection.
+- Prepared execution persists safe preparation provenance before provider work.
+  Completed execution persists safe execution provenance; raw output is
+  validated before template rendering.
+- Generated text fills defined prose slots only. Deterministic facts remain
+  authoritative and repository-owned templates produce all managed Markdown.
+- Sensitive rendered prompts, schemas, input bodies, provider endpoints, and
+  credentials never enter normal metadata, summaries, logs, or workspace
+  artifacts. They are written only to an explicit secure debug root when
+  requested.
 
-The binary entry point should do no business work beyond constructing and
+## State, Notification, And Testing Invariants
-running the CLI. CLI code owns commands, arguments, flags, help, output
-formatting, and conversion into application requests.
 
-CLI packages must not own meteorological decisions, report composition,
+- Managed writes are atomic where practical and stay beneath the configured
-artifact layout, Recent Changes comparison, external transport, or subprocess
+  workspace root. Reached artifacts remain inspectable after later failures.
-construction.
+- New records use `weatherreporter.metadata.v2`; V1 records remain readable for
-
+  inspection compatibility.
-### Configuration
+- Distributor uploads use only the managed Markdown report, never output copies
-
+  or workspace scans. Notification follows report and final metadata success.
-Configuration loading, built-in defaults, overrides, secret loading, and
+- Default tests are deterministic, offline, and use Promptkit/provider fakes
-validation belong to `internal/config`. Operational values shared across
+  rather than live provider calls. See the [testing policy](testing.md).
-packages must be explicit configuration or constants owned by the responsible
-package, not hidden in CLI or adapter code.
-
-The exact configuration contract belongs in the
-[configuration reference](../config.md). Other architecture documents should
-state ownership and safety rules rather than repeat fields, defaults, or
-precedence.
-
-### Application Orchestration
-
-`internal/app` owns top-level use cases and workflow order. It composes report
-resolution, collection, domain transformations, state, rendering, and optional
-notification through narrow project-owned contracts.
-
-The application layer may coordinate components and convert between their
-contracts. It must not absorb CLI parsing, HTTP transport, subprocess argument
-construction, filesystem layout, weather derivation algorithms, template
-execution, or adapter-specific dependency types.
-
-### Domain And Report Logic
-
-Meteorological selection, forecast-period resolution, daypart grouping,
-threshold detection, fact derivation, report composition, module construction,
-generated-text validation, and Recent Changes comparison belong in deterministic
-Go domain packages.
-
-Domain packages must not depend on CLI parsing, process execution, remote
-transport, or concrete external-library types. Given the same normalized
-inputs, configuration, valid period, prior snapshot, and clock, domain behavior
-should be reproducible.
-
-Report selection must go through the report registry or an equivalent
-centralized mechanism. A report definition owns its identity, prompt and
-rendering mode, valid-period resolver, module composition, comparison strategy,
-artifact grouping, and output naming. Do not scatter report-ID conditionals
-through CLI, orchestration, or adapters.
-
-### External Adapters
-
-External integrations use adapter boundaries under `internal/adapters`.
-Adapters own transport and protocol mechanics; application and domain packages
-own decisions.
-
-- The Weather API adapter owns HTTP request construction, timeouts, retries,
-  response-envelope handling, decoding, and endpoint compatibility.
-- The Scriptorium adapter owns argument construction, context-aware subprocess
-  execution, stdout and stderr capture, exit interpretation, and result
-  decoding. It must avoid shell interpolation.
-- The Distributor adapter owns dependency-specific bundle and upload types,
-  client construction, request execution, status handling, and redaction.
-
-External dependency types must not leak beyond the adapter that integrates
-them. Adapters should expose narrow project-owned inputs and outputs so an
-integration can be tested or replaced without changing domain logic.
-
-### State And Embedded Assets
-
-`internal/state` owns managed workspace paths, durable metadata, atomic
-artifact persistence, prior lookup, and inspection reads. Other packages should
-request state operations rather than reconstruct managed paths independently.
-
-Schemas, prompts, Markdown templates, and partials should live as separate
-repository assets and be embedded by the package that owns their execution or
-lookup. Keep weather derivation and path construction out of templates.
-
-## Architectural Invariants
-
-### Weather Truth And Generated Text
-
-- Normalized source data and deterministic Go derivation are authoritative for
-  weather facts.
-- LLM prompts receive curated module-based packages rather than raw,
-  unbounded source payloads.
-- For generated-text-template reports, generated text is limited to defined
-  prose slots, validated before use, and rendered through typed or otherwise
-  explicit contexts.
-- Direct-Markdown reports receive the same curated prompt-package boundary but
-  produce managed Markdown directly through Scriptorium rather than the
-  generated-text schema and repository-template workflow.
-- Repository-owned templates arrange validated prose and deterministic facts;
-  they do not perform meteorological derivation.
-
-### Reports And Comparison
-
-- Report behavior is resolved through centralized definitions.
-- Recent Changes is computed from structured module snapshots, never by
-  comparing rendered Markdown.
-- Batch workflows collect normalized weather data once and reuse that
-  collection for planning and report generation.
-- Report metadata links identity, generation time, valid period, source
-  provenance, and the managed artifacts produced for the run.
-
-### Managed State And Notification
-
-- Durable structured writes are atomic where practical.
-- Managed paths remain beneath the configured workspace root.
-- Operations that delete, move, overwrite, or copy files use narrow, explicit
-  paths; destructive cleanup is opt-in.
-- Intermediate artifacts reached before a later failure remain inspectable
-  where practical.
-- Distributor uploads use managed Markdown reports, never optional output
-  copies or broad workspace scans.
-- Notification occurs only after the managed report and required metadata have
-  been successfully produced.
-
-### Security, Errors, And Cancellation
-
-- Secrets must not appear in logs, errors, persisted artifacts, examples, or
-  user-facing output.
-- Errors preserve actionable operation, report, RunID, path, endpoint, or
-  subprocess context without exposing secrets or unnecessarily large payloads.
-- External calls, subprocesses, storage operations, and multi-step workflows
-  accept or propagate `context.Context` where cancellation or timeout is
-  meaningful.
-- Adapter failures preserve useful status, stderr, or response context at the
-  boundary and are translated into project-owned errors before crossing into
-  unrelated packages.
-
-## Dependency Policy
-
-Prefer the Go standard library. Add an external dependency only when it
-materially improves correctness, security, interoperability, or
-maintainability. A dependency used for a small convenience does not justify its
-lifetime upgrade and compatibility cost.
-
-Keep dependency-specific types inside the package that intentionally adopts
-the dependency. The application should remain understandable and testable
-without requiring framework-wide abstractions or live external services.
-
-## Verification And Documentation
-
-Core behavior must be testable without live Weather API, Scriptorium, or
-Distributor services. The [testing policy](testing.md) owns test philosophy,
-sufficiency, boundaries, and test-double guidance.
-
-Documentation must follow the
-[documentation policy](documentation.md). Update the canonical user,
-operator, integration, internal, and example documentation in the same change
-as the behavior it describes. Future or proposed behavior belongs under
-`docs/roadmap/`; significant durable decisions may be recorded as ADRs.
 
 ## Non-Goals
 
-Weatherreporter is not:
+Weatherreporter is not a weather-data ingestion service, general LLM
-
+orchestration framework, plugin platform, HTTP service, multi-user job system,
-- a source weather-data ingestion or normalization service;
+or a replacement for Promptkit or Distributor.
-- a general-purpose LLM orchestration framework;
-- an application in which an LLM selects authoritative weather facts or report
-  policy;
-- a plugin framework with dynamically discovered report or module behavior;
-- an HTTP service or multi-user distributed job system;
-- a replacement for Scriptorium or Distributor protocol ownership; or
-- a system that hides operational state exclusively inside opaque logs or
-  remote services.
-
-New requirements may justify revisiting a non-goal. A change that alters system
-shape, dependency direction, a safety property, or another architectural
-invariant should be recorded deliberately in this policy or an ADR rather than
-introduced implicitly.

docs/policy/documentation.md

@@ -87,7 +87,7 @@ mechanisms, not secret values.
 | Operations | `docs/operations.md` | Normal workflows, physical workspace layout, artifacts and metadata, inspection, notification behavior, recovery, cleanup, permissions, and operational caveats. | Complete CLI syntax, configuration field definitions, logical external contracts, and implementation mechanics. |
 | Troubleshooting | `docs/troubleshooting.md` | Recurring symptoms, likely causes, diagnostic steps, safe fixes, and links to normal-operation references. | Complete command and configuration references, routine operating procedures, and implementation detail. |
 | Report template surface | `docs/templates.md` | Implemented template files and partials, render-context fields, editing rules, and maintainer-facing template examples. | Weather derivation, module implementation, generated-text validation internals, and operator procedures. |
-| External and durable integration contracts | `docs/integrations/` | Weather API, Scriptorium, Distributor, external formats and protocols, durable logical paths and schemas, compatibility behavior, and upstream or downstream responsibilities. | Physical runtime placement and lifecycle, internal transformations, CLI syntax, and configuration defaults. |
+| External and durable integration contracts | `docs/integrations/` | Weather API, Promptkit, Distributor, external formats and protocols, durable logical paths and schemas, compatibility behavior, and upstream or downstream responsibilities. | Physical runtime placement and lifecycle, internal transformations, CLI syntax, and configuration defaults. |
 | Internal subsystem behavior | `docs/internal/` | Implementation flow, internal collaborators and state transitions, package-local guarantees and failures, and relevant tests. | Global architecture invariants, user-facing contracts, external schemas, operator procedures, and future package plans. |
 | Architectural decision history | `docs/adr/`, when repository-local decisions require records | Significant decisions, context, alternatives, rationale, consequences, and supersession history. | Current behavior reference, implementation status, and task sequencing. |
 | Temporary feature roadmaps | `docs/roadmap/`, while planned work needs coordination | Proposed, accepted, deferred, or rejected work; sequencing; gates; implementation status; and task breakdowns. | Implemented behavior reference and durable decision rationale. |

docs/policy/testing.md

@@ -54,8 +54,8 @@ Use a classical or Detroit-style approach:
 - Test exact collaborator interactions only when the interaction itself is a
   requirement.
 
-Weatherreporter's important seams include clocks, subprocesses, HTTP services,
+Weatherreporter's important seams include clocks, Promptkit executors, HTTP
-Distributor uploads, filesystem roots, environment-backed secrets, and any
+services, Distributor uploads, filesystem roots, environment-backed secrets, and any
 future source of randomness or nondeterminism.
 
 ## Execution Requirements
@@ -73,7 +73,7 @@ package command while iterating and `go test -race ./...` when the risk crosses
 package boundaries.
 
 Tests in the default suite must be deterministic, offline, and independent of
-real credentials. They must not invoke live Weather API, Scriptorium, or
+real credentials. They must not invoke live Weather API, Promptkit providers, or
 Distributor services or depend on other mutable external infrastructure.
 Tests that require live infrastructure must be explicitly opt-in and clearly
 separated from the default suite.
@@ -198,7 +198,7 @@ Each behavior should have a clear test owner:
 - CLI parser tests own arguments, flags, and command construction.
 - Config tests own loading, precedence, defaults, secrets, and validation.
 - Domain tests own weather transformations and invariants.
-- Adapter tests own HTTP, subprocess, and upload boundaries.
+- Adapter tests own HTTP, Promptkit/provider, and upload boundaries.
 - Orchestrator tests own workflow ordering, persistence, partial success, and
   failure propagation.
 - State tests own path derivation, atomic artifacts, lookup, and round trips.
@@ -220,7 +220,7 @@ observation:
 4. Use mocks when the interaction itself is contractual.
 
 Mocks are appropriate for requirements such as uploading exactly once, saving
-metadata before notification, propagating cancellation to Scriptorium, or
+metadata before notification, propagating cancellation to Promptkit, or
 avoiding an external call after an earlier workflow failure. Do not use mocks
 merely to isolate every object or reproduce the implementation's call graph.
 
@@ -232,7 +232,7 @@ Use:
 - `t.TempDir()` for real filesystem behavior;
 - `httptest.Server` for realistic Weather API interactions;
 - test-controlled clocks for periods and RunIDs;
-- fake command runners for Scriptorium behavior;
+- fake Promptkit executors or provider clients for Promptkit behavior;
 - fake upload clients for Distributor behavior;
 - fuzz tests when parsers, normalization, or path handling have a broad and
   consequential input space;

docs/roadmap/future.md

@@ -7,8 +7,7 @@ status; current behavior is documented outside `docs/roadmap/`.
 
 Status: Proposed and unimplemented.
 
-Manual Storm Report generation is implemented; see the [CLI reference](../cli.md).
+Storm reporting, whether manual or automatic, is unimplemented.
-Automatic storm-event evaluation remains unimplemented.
 
 Possible direction:
 
@@ -16,7 +15,7 @@ Possible direction:
    story context, hourly thresholds, and material forecast changes.
 2. Evaluate candidates through Scriptorium or another narrow evaluator adapter.
 3. Persist storm lifecycle state.
-4. Generate or update Storm Reports only when a meaningful event is present.
+4. Generate or update a storm report only when a meaningful event is present.
 5. Suppress ordinary low-impact thunder or rain chances.
 
 Possible lifecycle states:
@@ -29,8 +28,8 @@ Possible lifecycle states:
 - `resolved`
 
 Before implementation, the design must preserve scheduled report behavior,
-manual Storm Report generation, inspectable evaluator failures, and fixture
+inspectable evaluator failures, and fixture coverage for deterministic
-coverage for deterministic candidate detection.
+candidate detection.
 
 ## Future Report Types
 
@@ -59,7 +58,7 @@ Possible future modules:
   Changes
 - `weekend_planning` if weekend-specific planning guidance needs a dedicated
   deterministic stanza
-- `storm_window_summary` if manual or automatic Storm Reports need a dedicated
+- `storm_window_summary` if manual or automatic storm reports need a dedicated
   prompt-facing storm-window module
 - separate AFD section aliases, such as `afd_key_messages`,
   `afd_short_term_text`, and `afd_long_term_text`, if separate stanzas prove

docs/roadmap/implementation.md

@@ -0,0 +1,555 @@
+# Promptkit Migration Implementation Plan
+
+Status: Completed; Stages 1–19 passed their exit gates.
+
+## Purpose And Authority
+
+This document records the completed implementation of the
+[Promptkit migration roadmap](promptkit.md) and its post-implementation audit
+remediation. The feature roadmap records scope, user intent, policy choices,
+and the implemented end state. This plan records implementation sequence,
+tests, and completion gates.
+
+Stages 12–19 were completed in order. They fixed additional defects exposed by
+their required tests only when those defects were within the same stated
+contract; they did not add new product behavior or reinterpret roadmap
+decisions.
+
+This plan follows the repository's
+[architecture](../policy/architecture.md),
+[documentation](../policy/documentation.md), and
+[testing](../policy/testing.md) policies.
+
+## Continuing Invariants
+
+- Keep `gitea.maximumdirect.net/eric/promptkit` pinned at exactly `v0.4.0`.
+- Keep Promptkit types inside `internal/adapters/promptkit`, its tests, and the
+  external prompt-asset contract test.
+- Preserve one Promptkit engine per `generate` or `run` invocation and one
+  shared engine for every sequential report in a batch.
+- Preserve exact prompt version `1.0.0`, the exact persisted YAML data-package
+  bytes, prepared execution, and preparation persistence before provider work.
+- Do not add retries, repair attempts, concurrent batch generation, direct
+  Markdown generation, arbitrary backend registration, or live-provider
+  tests.
+- Keep ordinary artifacts, errors, logs, and summaries free of credentials,
+  rendered messages, schemas, input bodies, generated bodies, endpoints, and
+  full effective parameter maps.
+- Keep sensitive debug artifacts opt-in, outside normal state, owner-only,
+  atomic, and free of credentials.
+- Treat an artifact path as reached only after the corresponding write or copy
+  succeeds. Never persist or summarize a merely derivable future path.
+- Preserve every safe reached path in partial app and CLI results even when a
+  later persistence, validation, rendering, copy, or notification step fails.
+- Keep v1 metadata read compatibility and write only v2 metadata for new runs.
+- Keep the default test suite deterministic, offline, and credential-free.
+- Run `git diff --check` before completing every stage. Run the full repository
+  gate in Stage 19.
+
+## Completed Migration Summary
+
+Stages 1–11 are implemented and committed. They remain summarized here to
+preserve the history and dependencies of the follow-up work.
+
+| Stage | Completed outcome |
+| --- | --- |
+| 1 | Removed the unfinished three-day, weekend, and storm product surfaces and retained Daily, Today, Tomorrow, and Hourly with exact prompt version `1.0.0`. |
+| 2 | Promoted the four operational prompts and canonical schemas into the embedded `internal/promptassets` source used by Promptkit and generated-text validation. |
+| 3 | Added the project-owned `internal/promptexec` inspection, preparation, execution, validation, debug, and error contract. |
+| 4 | Added the Promptkit v0.4.0 adapter with prepared execution, explicit value mapping, safe error classification, and offline model-client tests. |
+| 5 | Added Promptkit-era preparation and execution artifacts, metadata v2, new paths, and v1 decoding support. |
+| 6 | Added explicitly rooted, permission-restricted, atomic LLM debug persistence. |
+| 7 | Added Promptkit configuration, executor composition, and pre-collection prompt/profile/credential inspection. |
+| 8 | Cut single-report generation over to prepared Promptkit execution and v2 persistence. |
+| 9 | Added `--llm-debug-dir` and Promptkit-era single-report summary fields. |
+| 10 | Cut morning and evening batches over to one shared Promptkit executor and removed Scriptorium code, configuration, and dependency metadata. |
+| 11 | Updated canonical Promptkit documentation, removed the temporary Scriptorium corpus, and ran the available repository checks. |
+
+The post-implementation audit confirmed the principal dependency and package
+boundaries, but found incorrect reached-path bookkeeping, incomplete execution
+artifact updates, insufficient artifact validation, extensive loss of
+behavioral tests during the final cutover, and roadmap lifecycle text that was
+not finalized. The completed remediation addressed those findings without
+changing the intended feature scope.
+
+| Stage | Completed outcome |
+| --- | --- |
+| 12 | Corrected reached-path bookkeeping across metadata, app results, batch items, and CLI summaries. |
+| 13 | Hardened Promptkit-era durable state validation and restored v1/v2 state coverage. |
+| 14 | Recorded every downstream path reached after completed prompt execution. |
+| 15 | Restored assembled single-report behavioral and failure coverage. |
+| 16 | Simplified prompt-generation orchestration while preserving behavior. |
+| 17 | Restored assembled batch, planning, artifact, and notification coverage. |
+| 18 | Restored supported CLI, summary, safety, and historical inspection coverage. |
+| 19 | Reconciled canonical documentation and passed the complete repository verification gate. |
+
+## Stage 12: Correct Reached-Artifact Bookkeeping
+
+Status: Completed.
+
+### Goal
+
+Make metadata, app results, batch items, and CLI summaries truthful at every
+failure boundary: a nonblank path means that artifact was successfully
+created.
+
+### Work
+
+1. Change `state.BuildPromptMetadataFromBriefingMetadata` so it initializes
+   identity, schema, metadata destination, and only artifacts already saved at
+   the call site. It must not prepopulate raw-output, normalized-text,
+   render-context, managed-report, preparation, execution, notification, or
+   output-copy paths.
+2. In `generatePromptReport`, assign each metadata and `ReportResult` path
+   immediately after that artifact write succeeds and before attempting the
+   next write. In particular:
+
+   - do not initialize `ReportResult.ReportPath` from `Store.Paths`;
+   - record a saved failed-preparation receipt in the result before saving
+     metadata;
+   - record a saved failed or completed execution receipt before saving
+     metadata;
+   - retain raw, normalized, context, report, copy, and notification paths
+     when a later step fails; and
+   - keep `MetadataPath` unchanged when a metadata rewrite fails, because the
+     prior successfully written metadata record remains the reached version.
+
+3. Remove batch-item prepopulation from derived `Store.Paths` values.
+   `BatchReportResult` receives paths only from the returned `ReportResult` or
+   from a write that the batch itself successfully completed.
+4. Preserve current CLI field names and omission behavior. Human and JSON
+   summaries must omit every unreached path.
+5. Do not change artifact locations, filenames, schemas, report output, or
+   notification policy in this stage.
+
+### Tests
+
+- Add focused app tests for one representative report using real temporary
+  state plus a narrow failure-injecting store wrapper.
+- Fail the next persistence step immediately after a successful preparation
+  receipt, execution receipt, raw output, normalized output, render context,
+  managed report, output copy, and notification artifact; assert that the
+  returned result contains every reached path and no future path.
+- Include one preparation failure, one operational execution failure, and one
+  completed validation rejection to cover the three execution outcome shapes.
+- Add batch and CLI summary assertions proving unreached paths are omitted.
+- Run:
+
+  ```sh
+  go test ./internal/state ./internal/app ./internal/cli
+  git diff --check
+  ```
+
+### Exit Gate
+
+Every nonblank path in newly written metadata, app results, batch items, and
+CLI summaries names an artifact that exists. Every safe artifact successfully
+written before a later failure remains discoverable from the returned partial
+result.
+
+## Stage 13: Harden Durable State Contracts And Restore State Coverage
+
+Status: Completed.
+
+### Goal
+
+Make the v1/v2 wire boundary and Promptkit-era artifact validation explicit,
+strict, and durably tested.
+
+### Work
+
+1. Strengthen `PromptPreparationArtifact.Validate`:
+
+   - require report ID, Weatherreporter RunID, prompt ID, exact prompt version,
+     data-package path, nonzero start/end times, nonnegative duration, and an
+     end not earlier than the start;
+   - for success, require preparation provenance, prohibit an error, and
+     require its prompt ID/version and data-package path to match the top-level
+     artifact;
+   - for failure, require a classified bounded error and prohibit fabricated
+     preparation provenance.
+
+2. Strengthen `PromptExecutionArtifact.Validate`:
+
+   - require report ID, Weatherreporter RunID, prompt ID, exact prompt version,
+     nonzero start/end times, nonnegative duration, and an end not earlier than
+     the start;
+   - for success and validation rejection, require provenance and completed
+     validation, prohibit an operational error, and require the provenance
+     prompt ID/version to match the artifact;
+   - do not compare the provenance RunID with the Weatherreporter RunID because
+     the provenance value is Promptkit's run identity;
+   - for operational failure, require a classified bounded error and prohibit
+     invented provenance or completed validation.
+
+3. Validate required provenance fields for completed executions, including
+   Promptkit RunID, prompt and rendered hashes, selected profile/backend/model,
+   and data-package path. Permit usage counters and generated hash to be zero
+   when the provider legitimately reports no value.
+4. Restore focused filesystem and metadata tests for:
+
+   - exact v2 paths and filenames;
+   - preparation/execution round trips and required fields;
+   - metadata v2 round trips without legacy aliases;
+   - v1 decoding, normalized internal aliases, and v1-preserving re-marshaling;
+   - unknown schema rejection;
+   - report listing, RunID lookup, source/module/data-package inspection, and
+     retained v1 behavior for historical report IDs;
+   - atomic writes and unsafe workspace/path rejection; and
+   - prior-snapshot behavior for the four supported report IDs.
+
+5. Adapt useful tests from the deleted filesystem suite rather than recreating
+   redundant low-value cases. Do not restore Scriptorium writes or retired
+   report behavior.
+
+### Tests
+
+Run:
+
+```sh
+go test ./internal/state ./internal/app
+git diff --check
+```
+
+### Exit Gate
+
+The state package rejects incomplete or contradictory Promptkit-era artifacts,
+reads historical v1 records, writes only valid v2 records, and has focused
+offline coverage for its durable compatibility and filesystem contracts.
+
+## Stage 14: Complete Execution-Artifact Path Tracking
+
+Status: Completed.
+
+### Goal
+
+Make `PromptExecutionArtifact.Paths` accurately record every downstream
+artifact reached after a completed Promptkit run.
+
+### Work
+
+1. Treat the execution artifact as an atomically updated durable record of the
+   completed Promptkit execution and subsequent artifact destinations. Its
+   status, provenance, validation, usage, and timing remain the provider-run
+   outcome; later application failures do not change a successful Promptkit
+   status into an execution failure.
+2. Save the initial execution artifact after raw output is persisted, with
+   `RawOutputPath` populated.
+3. After each later successful write, update and atomically resave the same
+   execution artifact with the corresponding reached path:
+
+   - normalized generated text;
+   - render context;
+   - managed Markdown report;
+   - an explicitly requested extra output copy, only after the copy succeeds;
+     and
+   - a Distributor notification artifact, including a persisted failure or
+     status artifact when notification produced one.
+
+4. Keep metadata and execution-artifact path values consistent after every
+   successful checkpoint. Save the execution artifact before metadata so a
+   metadata failure does not erase knowledge of a reached downstream artifact.
+   Failure to update the execution artifact is terminal and returns a partial
+   result containing the downstream artifact that was already written.
+5. Refactor finalization return values only as needed to tell the orchestration
+   layer which copy and notification paths were actually written. Distributor
+   must continue uploading only the managed Markdown report.
+6. A validation-rejected execution ends after raw output and therefore records
+   only the raw-output path. An operational execution failure has no completed
+   provenance and records only safe paths reached before that failure.
+
+### Tests
+
+- Add table-driven execution-artifact lifecycle tests for success and every
+  downstream failure point.
+- Load the persisted execution artifact after normalized-text, context,
+  template, copy, metadata, and notification failures and assert its status and
+  exact reached paths.
+- Assert that execution artifacts never contain generated bodies, rendered
+  prompts, schemas, endpoints, parameters, or credentials.
+- Run:
+
+  ```sh
+  go test ./internal/state ./internal/app
+  git diff --check
+  ```
+
+### Exit Gate
+
+For every completed Promptkit run, its execution artifact contains exactly the
+safe downstream paths reached by the workflow and remains semantically correct
+when a later application stage fails.
+
+## Stage 15: Restore Single-Report Behavioral Coverage
+
+Status: Completed.
+
+### Goal
+
+Restore the risk-based application coverage removed during final cutover and
+prove the complete single-report Promptkit workflow through project-owned
+boundaries.
+
+### Work
+
+1. Reintroduce a focused app test harness using real state, prompt-input,
+   generated-text validation, render contexts, and templates with deterministic
+   collector, executor, notifier, clock, and filesystem boundaries.
+2. Add representative successful workflows for Daily, Today, Tomorrow, and
+   Hourly. Verify report identity, exact prompt version, one collection, exact
+   persisted YAML bytes passed to the executor, expected template output,
+   optional copy behavior, and managed-report notification source.
+3. Cover the required failure matrix:
+
+   - inspection and missing credentials before collection;
+   - preparation failure and callback persistence failure before provider work;
+   - execution-time credential disappearance;
+   - capacity rejection without retry;
+   - cancellation and deadline;
+   - generation and operational-validation failure;
+   - completed Promptkit schema rejection with retained raw output;
+   - generated-text decode/domain rejection;
+   - render-context and template failure;
+   - output-copy failure; and
+   - notification failure.
+
+4. Verify preparation persistence precedes provider execution, debug-write
+   failure prevents provider execution, and execution-debug failure preserves
+   previously reached normal and debug artifacts.
+5. Verify Recent Changes, prior-snapshot selection, output naming, and
+   Distributor template values for all four retained reports.
+6. Adapt useful tests from the deleted app suite. Omit Scriptorium mechanics,
+   subprocess interaction assertions, and retired report products.
+7. Fix defects exposed by these tests only when the expected behavior is
+   already decided by the roadmap or canonical policy. Record any new product
+   question instead of silently choosing it.
+
+### Tests
+
+Run:
+
+```sh
+go test ./internal/app
+go test -race ./internal/app ./internal/adapters/promptkit
+git diff --check
+```
+
+### Exit Gate
+
+The single-report workflow has deterministic behavioral coverage for all four
+reports, all consequential failure stages, artifact ordering, partial results,
+debug isolation, output copying, and notification behavior.
+
+## Stage 16: Refactor Prompt Generation Orchestration
+
+Status: Completed.
+
+### Goal
+
+Reduce the complexity and duplicated persistence logic in
+`generatePromptReport` without changing observable behavior.
+
+### Work
+
+1. Use the Stage 12–15 tests as the refactoring safety boundary. Do not weaken
+   assertions to accommodate structural changes.
+2. Split the current orchestration into small app-owned operations with clear
+   inputs and outcomes for:
+
+   - deterministic input and initial state construction;
+   - preparation callback persistence;
+   - preparation-failure persistence;
+   - operational-execution-failure persistence;
+   - completed execution and raw-output persistence;
+   - normalized text and render-context persistence;
+   - managed report, optional copy, metadata, and notification finalization;
+     and
+   - reached-path updates shared by success and failure paths.
+
+3. Keep workflow order visible in one coordinator. Do not introduce a generic
+   workflow engine, hidden retry loop, provider-specific app type, or mutable
+   global state.
+4. Centralize the repeated rule that a successful artifact write updates the
+   result before any following write can fail.
+5. Preserve error identities, safe text, atomic writes, exact bytes, debug
+   ordering, partial results, and notification behavior.
+
+### Tests
+
+Run:
+
+```sh
+gofmt -w internal/app/*.go
+go test ./internal/app ./internal/state ./internal/cli
+go test -race ./internal/app
+git diff --check
+```
+
+### Exit Gate
+
+The top-level coordinator communicates the workflow order without containing
+the full persistence implementation, duplicate failure branches are reduced,
+and every Stage 12–15 behavioral test passes unchanged.
+
+## Stage 17: Restore Batch Behavioral Coverage
+
+Status: Completed.
+
+### Goal
+
+Re-establish confidence that morning and evening batches preserve their
+pre-migration behavior while sharing one Promptkit executor.
+
+### Work
+
+1. Add assembled batch tests proving:
+
+   - one executor factory call and one executor per CLI invocation;
+   - inspection of the full candidate set before collection;
+   - one weather collection;
+   - existing morning/evening planning and ordering;
+   - sequential execution through the shared executor;
+   - continuation after an independent report failure;
+   - no retry after capacity rejection;
+   - distinct identities and debug directories for multiple Daily dates; and
+   - exact reached paths on successful and failed batch items.
+
+2. Restore notification coverage for disabled notification, suppressed
+   per-report notification, all-success batch notification, skipped
+   notification after report failure, and persisted notification failure/status
+   artifacts.
+3. Restore output-directory, Today/Tomorrow naming, dynamic Daily planning,
+   prior-snapshot, and managed-Markdown upload-source coverage.
+4. Adapt useful tests from the deleted batch portions of the app and CLI suites.
+   Do not restore retired report cases or Scriptorium fakes.
+5. Fix only roadmap-defined batch regressions exposed by the restored tests.
+
+### Tests
+
+Run:
+
+```sh
+go test ./internal/app ./internal/cli
+go test -race ./internal/app
+git diff --check
+```
+
+### Exit Gate
+
+Morning and evening batches are covered as assembled sequential workflows and
+demonstrably preserve collection, planning, continuation, output, debug,
+artifact, and notification contracts with one Promptkit executor.
+
+## Stage 18: Restore CLI And Inspection Coverage
+
+Status: Completed.
+
+### Goal
+
+Restore the user-facing command, summary, and historical inspection contracts
+removed with the old root test suite.
+
+### Work
+
+1. Add parser and resolver tests for all four generate commands, both batch
+   commands, shared flags, report-specific date rules, malformed input,
+   `--llm-debug-dir`, `--quiet`, output paths, and rejection of retired report
+   names.
+2. Add assembled CLI tests for representative successful single and batch
+   invocations using injected offline boundaries. Verify exactly one executor
+   construction per action.
+3. Cover pre-run errors with no invented run summary, successful and failed
+   JSON summaries, quiet-mode behavior, safe human status output, partial paths,
+   and omission of absent notification/debug fields.
+4. Restore inspection tests for report listing and v1/v2 metadata, modules,
+   data packages, prior snapshots, and sources. Include failed v2 runs and v1
+   fixtures using historical report IDs.
+5. Assert that routine output never contains rendered prompts, schema bodies,
+   data packages, generated bodies, endpoints, full parameters, credentials, or
+   secret-like dependency errors.
+6. Keep tests at stable CLI/app boundaries; do not restore assertions about
+   private parser formatting or Scriptorium subprocess mechanics.
+
+### Tests
+
+Run:
+
+```sh
+go test ./internal/cli ./internal/app ./internal/state
+go run ./cmd/weatherreporter --help
+git diff --check
+```
+
+### Exit Gate
+
+The supported CLI surface, summaries, quiet mode, partial failures, executor
+composition, and v1/v2 inspection behavior have deterministic offline coverage.
+
+## Stage 19: Finalize Documentation And Repository Verification
+
+Status: Completed.
+
+### Goal
+
+Close the audit remediation, make roadmap lifecycle state truthful, and verify
+the repository against the complete target contract.
+
+### Work
+
+1. Update `docs/roadmap/promptkit.md` from future tense and “unimplemented”
+   statuses to a completed roadmap record. Describe its old seven-report and
+   Scriptorium material explicitly as the pre-migration baseline rather than
+   current behavior.
+2. Mark Stages 12–19 and this implementation plan complete only after their
+   exit gates pass. Retain the concise completed-stage history unless the
+   documentation policy calls for archival in the same change.
+3. Review canonical architecture, app, state, CLI, Promptkit integration,
+   operations, troubleshooting, configuration, and testing documentation
+   against the corrected implementation. Update only actual current-state
+   discrepancies; do not duplicate the roadmap.
+4. Search current-state code, tests, examples, help, and non-roadmap
+   documentation for stale Scriptorium terms, retired reports, old artifact
+   fields, speculative-path descriptions, or claims of missing Promptkit
+   implementation.
+5. Confirm examples contain no credentials or private infrastructure values
+   and load through config tests.
+
+### Final Verification
+
+Run:
+
+```sh
+gofmt -w <all changed Go files>
+go mod tidy
+go vet ./...
+go test -count=1 ./...
+go test -race ./...
+go run ./cmd/weatherreporter --help
+git diff --check
+```
+
+Then verify explicitly:
+
+- `go list -m gitea.maximumdirect.net/eric/promptkit` reports `v0.4.0`;
+- no committed `go.work`, `replace`, secret fixture, or live-provider test
+  exists;
+- all four prompts inspect at exact version `1.0.0`;
+- no runtime prompt requests repair attempts;
+- v1 fixtures remain inspectable and new runs write only v2;
+- normal artifacts and output contain no sensitive prompt/debug content;
+- failed-run metadata, execution artifacts, app results, batch items, and CLI
+  summaries contain exactly the paths actually reached;
+- help exposes only Daily, Today, Tomorrow, Hourly, morning, and evening; and
+- managed Markdown remains the only Distributor upload source.
+
+### Exit Gate
+
+Every migration and audit-remediation criterion is demonstrably satisfied,
+the restored tests protect the consequential contracts, canonical
+documentation describes the corrected implementation, and both roadmap
+documents are marked complete.
+
+## Open Questions
+
+None. The roadmap and this completed plan record the decisions used for the
+audit remediation.

docs/roadmap/promptkit.md

@@ -1,204 +1,353 @@
 # Promptkit Migration Roadmap
 
-Status: Accepted migration policy; the migration itself is unimplemented.
+Status: Completed roadmap record.
 
 ## Purpose
 
-This roadmap defines the scope and desired end state for replacing the
+This roadmap records the scope, decisions, and completed outcome of replacing
-external Scriptorium CLI integration with the Promptkit Go library. The
+the external Scriptorium CLI integration with Promptkit. Canonical
-migration is not yet implemented. Current Scriptorium behavior remains
+documentation outside `docs/roadmap/` owns the implemented behavior.
-documented in the [Scriptorium integration guide](../integrations/scriptorium.md)
-until the replacement is complete.
 
-A separate staged implementation plan will describe how to move from the
+## Pre-Migration Baseline
-current code to this target state. That plan should reference this roadmap
-rather than redefine its architectural decisions or scope.
 
-## Desired End State
+Status: Historical migration input.
 
-Status: Accepted target state; unimplemented.
+Before the migration, Weatherreporter exposed seven report definitions, but
+only four had complete prompt-backed report implementations:
 
-Weatherreporter uses a pinned released version of
+- Daily Report: `weather.daily_generated_text`
-`gitea.maximumdirect.net/eric/promptkit` as its in-process prompt preparation
+- Today Report: `weather.today_generated_text`
-and LLM execution engine. The `scriptorium` executable, subprocess adapter,
+- Tomorrow Report: `weather.tomorrow_generated_text`
-configuration, runtime dependency, and integration documentation have been
+- Hourly Report: `weather.hourly_generated_text`
-removed.
 
-The migration does not change weatherreporter's fundamental product behavior.
+The three-day, weekend, and storm commands and registry definitions had no
-Weather selection, forecast derivation, report periods, module construction,
+corresponding Scriptorium prompt or schema and never formed complete
+operational report products. The `weather.daily_report` Scriptorium prompt was
+legacy source material and was not selected by the registry.
+
+The Scriptorium source corpus was retained temporarily under
+`docs/roadmap/scriptorium/` as migration input. It contained the four
+operational generated-text prompt definitions, their referenced content,
+private response schemas, shared instructions, and the unused legacy Daily
+Markdown prompt. The temporary corpus was removed after the runtime assets
+were reconciled and embedded.
+
+## Implemented End State
+
+Status: Completed.
+
+Weatherreporter pins
+`gitea.maximumdirect.net/eric/promptkit` at `v0.4.0` and uses it as the
+in-process engine for prompt inspection, prepared execution, provider calls,
+and first-pass output validation.
+
+The `scriptorium` executable, subprocess adapter, configuration, runtime
+dependency, direct-Markdown execution path, and integration documentation have
+been removed. The four operational reports continue to use structured
+generated text followed by weatherreporter-owned validation and Markdown
+templates.
+
+The unfinished three-day, weekend, and storm reports are not implemented as
+part of this migration. Their incomplete CLI, registry, documentation, and
+generation declarations are removed from the implemented surface before the
+migration is considered complete. Any future implementation of those products
+requires separate roadmap scope, prompt and schema design, tests, and
+documentation.
+
+Weather selection, forecast derivation, valid periods, module construction,
 Recent Changes, generated-text interpretation, Markdown templates, durable
-state, inspection, output copies, and distributor notification remain owned by
+state, inspection, output copies, and Distributor notification remain owned by
 weatherreporter.
 
-All report prompts and private response schemas are versioned application
+The four report prompts and private response schemas are versioned embedded
-assets. Operators may configure Promptkit execution profiles without replacing
+application assets. Operators configure Promptkit profiles without replacing
-the report-owned prompt and schema corpus. One Promptkit engine is constructed
+the report-owned corpus. One Promptkit engine is constructed per CLI
-per CLI invocation and shared by every report in that invocation, including
+invocation and shared by every report in that invocation, including all
-all reports in a morning or evening batch.
+reports in a morning or evening batch.
 
-Promptkit is isolated behind a weatherreporter-owned prompt execution contract.
+Promptkit is isolated behind a weatherreporter-owned execution contract.
 Promptkit request, result, validation, error, profile, backend, and provider
 types do not leak into application orchestration, report definitions, domain
-packages, CLI summaries, state contracts, or distributor behavior.
+packages, CLI summaries, durable state contracts, or Distributor behavior.
 
 ## Goals
 
-Status: Accepted migration scope; unimplemented.
+Status: Completed migration outcomes.
 
-- Remove the runtime dependency on the `scriptorium` executable.
+- Removed the Scriptorium runtime dependency and subprocess boundary.
-- Replace shell-free subprocess orchestration with typed in-process Promptkit
+- Migrated the four operational report prompts to Promptkit `v0.4.0`.
-  preparation and execution.
+- Used prepared execution to persist preparation provenance before provider work
-- Preserve the seven report definitions and their existing prompt IDs.
+  while executing the exact frozen snapshot.
-- Preserve both direct-Markdown and generated-text-template report workflows.
+- Validated report prompt and profile selections before weather collection when
-- Preserve deterministic module snapshots and structured Recent Changes.
+  the required information is available.
-- Preserve context cancellation, actionable errors, secret redaction, and
+- Preserved deterministic module snapshots and structured Recent Changes.
+- Preserved generated-text domain validation and repository-owned Markdown
+  rendering.
+- Preserved context cancellation, actionable errors, secret redaction, and
   inspectable failures.
-- Improve durable prompt provenance with prompt, input, profile, model,
+- Improved durable prompt provenance with prompt, input, profile, model,
   validation, usage, and timing metadata.
-- Keep content-rich prompt and response diagnostics separate from routine
+- Kept content-rich prompt and response diagnostics separate from routine
   metadata and CLI output.
-- Keep tests offline and deterministic through injected Promptkit model
+- Kept tests offline and deterministic through injected Promptkit model
   clients and fixtures.
+- Removed incomplete report declarations from the implemented product surface
+  rather than creating new report products during an integration migration.
 
 ## Non-Goals
 
-Status: Accepted migration scope; unimplemented.
+Status: Completed migration constraints.
 
-The migration will not:
+The completed migration did not:
 
+- create prompts, schemas, templates, or completed products for three-day,
+  weekend, or storm reports;
+- preserve the unused `weather.daily_report` legacy Markdown prompt as an
+  active runtime asset;
+- preserve a direct-Markdown LLM generation mode;
 - move meteorological selection, derivation, thresholds, or comparison logic
   into prompts or Promptkit;
 - send raw unbounded Weather API responses to the model;
 - replace weatherreporter's generated-text domain validation or Markdown
   template rendering;
 - add a general workflow engine, provider plugin system, or arbitrary backend
-  registry to weatherreporter;
+  registry;
-- add automatic provider, validation, or capacity retries;
+- add automatic provider, validation, repair, or capacity retries;
-- add concurrent report generation to the existing sequential batch workflow;
+- add concurrent report generation to the sequential batch workflow;
-- expose Promptkit types as a weatherreporter component contract;
+- expose Promptkit types as weatherreporter contracts;
-- keep a production-selectable Scriptorium/Promptkit dual-run mode; or
+- keep a production-selectable Scriptorium/Promptkit dual-run mode;
+- require Promptkit eager source validation, structured generation errors, or
+  semantic execution-target fingerprints; or
 - use an unpublished Promptkit commit, committed Go workspace, or committed
   local module replacement.
 
 ## Locked Decisions
 
-Status: Accepted decisions for the unimplemented migration.
+Status: Implemented migration decisions.
 
-### Dependency And Versioning
+### Dependency And Upgrade Boundary
 
-- The initial integration will pin Promptkit `v0.3.0`.
+- The migration pins the tagged Promptkit `v0.4.0` release.
 - Coordinated local development may temporarily use the sibling Promptkit
   checkout, but committed module metadata must reference the tagged release.
-- A future Promptkit upgrade requires an explicit review of the public engine,
+- The adapter relies on the public root Promptkit package only.
-  prompt/profile/schema formats, error identities, validation behavior, and
+- A future Promptkit upgrade requires explicit review of prepared-execution
-  outbound provider contract used by weatherreporter.
+  lifecycle, prompt and profile inspection, prompt/profile/schema formats,
+  error identities, validation behavior, capacity behavior, and the outbound
+  provider contract.
+- Promptkit's deferred eager source validation, structured generation errors,
+  and semantic execution-target fingerprints do not block this migration.
+
+### Operational Report Scope
+
+- The migration preserves these prompt IDs:
+  `weather.daily_generated_text`, `weather.today_generated_text`,
+  `weather.tomorrow_generated_text`, and `weather.hourly_generated_text`.
+- Each operational report definition selects the exact embedded prompt version
+  `1.0.0`; execution does not rely on ambiguous single-version lookup.
+- Morning and evening batch membership remains based on Today, Tomorrow, and
+  eligible future Daily reports.
+- Three-day, weekend, and storm are removed from current CLI help, parsing,
+  report registry membership, tests that claim implemented generation, and
+  non-roadmap documentation.
+- The future product concepts may remain under `docs/roadmap/`, but migration
+  verification does not invent outputs or compare nonexistent prompts.
 
 ### Application Boundary
 
 - Promptkit remains an adapter boundary even though it runs in process.
-- A weatherreporter-owned contract will represent preparation, execution,
+- A weatherreporter-owned contract represents prompt identity, preparation,
-  output formats, validation, usage, provenance, and neutral error categories.
+  execution, output, validation, usage, provenance, and neutral error
-- The Promptkit adapter will map public Promptkit values into that contract at
+  categories.
-  the boundary.
+- The Promptkit adapter maps public Promptkit values into that contract.
-- App orchestration and test fakes will depend on the weatherreporter contract,
+- App orchestration and test fakes depend on the project-owned contract, not
-  not on Promptkit.
+  Promptkit.
-- Existing Scriptorium-specific generation mode names will be replaced with
+- Scriptorium-specific request, result, error, and generation-mode types are
-  provider-neutral names.
+  removed rather than renamed and retained.
 
 ### Prompt And Schema Ownership
 
-- Weatherreporter will embed all report prompt definitions, prompt content,
+- Weatherreporter embeds the four operational prompt definitions, referenced
-  and private response schemas.
+  prompt content, shared prompt content, and private response schemas.
-- Prompt assets will remain separate files rather than inline Go strings.
+- Assets remain separate files rather than inline Go strings.
-- The current Scriptorium prompt corpus will be retrieved before the
+- The temporary corpus under `docs/roadmap/scriptorium/` is migration source
-  implementation stage that establishes the embedded Promptkit assets.
+  material, not the final runtime location.
-- The retrieved corpus will be reviewed and converted to the pinned Promptkit
+- Weatherreporter's existing generated-text domain types, schemas, and
-  format without changing report intent or prompt IDs.
+  templates remain the canonical application contract. Imported Scriptorium
-- The four existing generated-text prompt fragments and schemas under
+  assets are reconciled with that contract rather than copied blindly or kept
-  `internal/reporttemplate` will be reconciled with that corpus rather than
+  as duplicate runtime schemas.
-  duplicated.
+- The imported Daily schema's incorrect Today `$id` and title are corrected.
-- Direct-Markdown prompt assets for the three-day, weekend, and storm reports
+- `confidence` is handled consistently across each prompt, provider-facing
-  will become weatherreporter-owned assets.
+  schema, generated-text domain type, and template. The existing optional
-- Weatherreporter needs one centralized embedded prompt/schema source; it does
+  weatherreporter field remains supported unless a separate domain decision
-  not need Notarius's multi-module asset-flattening registry.
+  removes it.
+- Prompt input metadata identifies the serialized data package as YAML rather
+  than JSON.
+- Imported `pipeline-weather/...` schema paths are replaced with paths valid
+  inside the embedded Promptkit schema source.
+- Imported `repair_attempts: 2` values are removed or set to zero. The
+  migration does not rely on Promptkit's internal-only repair capability.
+- The unused `weather.daily_report` prompt is not promoted into runtime assets.
+- One centralized embedded prompt/schema source is sufficient; Weatherreporter
+  does not need Notarius's multi-module asset-flattening registry.
 
 ### Profiles, Backends, And Credentials
 
 - Execution profiles remain operator-configurable rather than embedded report
   policy.
-- Configuration will support at most one external profile source: a profile
+- Each embedded operational prompt declares Promptkit's built-in
-  directory or a single profile file.
+  `gemini-flash-latest` profile as its default.
-- Prompt definitions may provide their normal default profile, while
+- `gemini-flash-latest` is intentionally a moving model alias. The execution
-  weatherreporter may support an explicit configured profile selection.
+  record captures the effective model identity, but operators who require a
+  pinned model must select an explicit external profile.
+- Configuration supports at most one external profile source:
+  `promptkit.profile_file` or `promptkit.profile_dir`. The two fields are
+  mutually exclusive.
+- A nonblank `promptkit.profile` is the explicit request profile for every
+  report in the invocation and takes precedence over each prompt's
+  `default_profile`. A blank value uses the prompt default.
+- Promptkit's normal profile-source precedence remains intact: an external
+  matching profile takes precedence over an embedded built-in profile, and an
+  invalid matching external profile is an error rather than a reason to fall
+  back.
+- Weatherreporter exposes Promptkit's conventional `local` backend through the
+  narrow `promptkit.local.endpoint` and
+  `promptkit.local.concurrency_limit` configuration fields. It does not expose
+  arbitrary backend registration.
+- A configured local endpoint registers the engine-scoped `local` backend. An
+  operator-supplied external profile selects it with `backend: local` and owns
+  the model-specific settings; Weatherreporter does not invent a local model
+  profile.
+- Local concurrency defaults to one. A value of zero means unlimited, matching
+  Promptkit, and a negative value is invalid. Queue capacity and general
+  backend parameters are not exposed.
 - Credential values remain in environment variables or file-backed
   environment secrets. Configuration contains only credential source names.
-- Provider credentials must not appear in logs, errors, CLI output, durable
+- Provider credentials never appear in logs, errors, CLI output, durable
-  metadata, preparation artifacts, execution artifacts, or debug summaries.
+  metadata, preparation records, execution records, or debug summaries.
-- Weatherreporter will not expose Promptkit's general backend registry as
+- Promptkit `InspectProfile` reports structural target and credential
-  arbitrary application configuration.
+  requirements; Weatherreporter owns policy for checking configured
+  environment availability.
+- Promptkit revalidates environment credentials at `RunPrepared`; a successful
+  preparation does not promise that execution-time credentials remain
+  available.
 
-### Engine Lifetime
+### Configuration Contract
 
-- One Promptkit engine will be constructed per CLI invocation at the
+The replacement configuration surface is:
-  application composition boundary.
+
-- Single-report generation will use that engine for preparation and execution.
+```yaml
-- Morning and evening batches will share the same engine across every planned
+promptkit:
-  report.
+  profile: ""
-- Per-report orchestration will not construct its own default Promptkit engine.
+  profile_file: ""
-- Promptkit backend capacity state and HTTP transport will therefore be shared
+  profile_dir: ""
-  consistently for the invocation.
+  timeout: 2m
+
+  local:
+    endpoint: ""
+    concurrency_limit: 1
+```
+
+- `timeout` remains the transport-wide provider-call safety cap.
+- A blank local endpoint leaves the conventional local backend unregistered.
+- Scriptorium's `binary`, `config_path`, and `extra_args` settings have no
+  Promptkit equivalents and are removed.
+- Configuration validation rejects simultaneous `profile_file` and
+  `profile_dir` values, invalid local endpoints, negative concurrency, and
+  selected profiles that cannot resolve their backend.
+
+### Engine Construction And Inspection
+
+- One Promptkit engine is constructed per CLI invocation at the application
+  composition boundary.
+- Single-report generation and every report in a batch use that same engine.
+- Per-report orchestration does not construct a default engine.
+- Promptkit backend capacity state and HTTP transport are shared consistently
+  for the invocation.
+- Before collection, `InspectPrompt` checks every selected report's exact ID
+  and version, declared `data_package` input, default-profile metadata, prompt
+  hash availability, and declared output contract.
+- `InspectPrompt` is a point-in-time structural check. It does not load a JSON
+  Schema, resolve a profile, or freeze later execution.
+- Explicit profile overrides and relevant prompt defaults are checked with
+  `InspectProfile` before collection when application policy requires them.
+- `InspectProfile` is also point-in-time and does not check credential values.
+- Successful `PrepareExecution`, not inspection, is the per-run authority for
+  loaded schema, rendered content, frozen inputs, effective settings, and
+  durable execution provenance.
 
 ### Prompt Input
 
-- Promptkit will continue to receive the curated `data_package` produced by
+- Promptkit receives only the curated `data_package` produced by
   `internal/promptinput`.
-- Weatherreporter will serialize the data package once, atomically persist
+- Weatherreporter serializes the package once, atomically persists those exact
-  those exact bytes, and supply the same bytes as a Promptkit inline artifact.
+  bytes, and supplies the same bytes with a Promptkit inline artifact.
-- The managed data-package path may be supplied as non-secret artifact
+- The managed data-package path may be supplied as non-secret provenance
-  provenance.
+  through the inline artifact URI.
-- Weatherreporter will not delegate unrestricted path loading to Promptkit's
+- Weatherreporter does not delegate unrestricted path loading to Promptkit's
   default file artifact reader.
-- The same immutable Promptkit request will be used for preparation and
+- Prompt inspection and adapter tests verify that `data_package` is required
-  execution so the preflight and run inputs cannot diverge.
+  and declared with the chosen YAML media type.
 
-### Preparation And Execution
+### Prepared Execution
 
-- Promptkit `Prepare` replaces the current Scriptorium render preflight.
+- `Engine.PrepareExecution` replaces Scriptorium render preflight.
-- Promptkit `Run` performs both Markdown and structured generated-text
+- Weatherreporter obtains `PreparedExecution.Details`, maps a safe subset into
-  execution.
+  its own preparation record, and persists that record before calling
-- Promptkit basic validation will be used where appropriate for direct
+  `Engine.RunPrepared`.
-  Markdown output.
+- `RunPrepared` executes the frozen prompt, profile, schema, inputs, rendered
-- Promptkit JSON Schema validation provides the provider-facing and first
+  messages, target, and validation resources retained by the handle.
-  structured-output check for generated-text reports.
+- Every acquired handle is followed immediately by `defer handle.Discard()`.
+  Discard is safe after execution and releases unused private execution state.
+- Handles remain adapter-local, engine-bound, one-shot, in-process values.
+  They are never serialized, persisted, copied into app contracts, or treated
+  as restartable jobs.
+- Preparation and execution use independent contexts. Execution receives the
+  active report workflow context.
+- Capacity is not reserved during preparation. Capacity rejection can
+  therefore occur after a preparation record has been persisted.
+- `RunPrepared` consumes the handle on success and every operational failure.
+- Preparation details remain available from the adapter after execution or
+  discard, but rendered messages are not copied into routine durable state.
+- Promptkit execution timing excludes preparation and consumer-held delay.
+  Weatherreporter records preparation timing and execution timing separately.
+
+### Execution And Validation
+
+- All four operational reports use Promptkit JSON Schema output validation.
+- A completed Promptkit validation rejection returns a `RunResult`; the
+  adapter retains raw output and bounded validation details before failing the
+  report.
+- An operational generation or validation error returns no partial
+  `RunResult`.
 - Weatherreporter's `internal/generatedtext` validation remains the final
-  report-specific domain boundary.
+  report-specific decode and domain boundary.
-- Weatherreporter's `internal/reporttemplate` remains responsible for
+- Weatherreporter's `internal/reporttemplate` remains responsible for managed
-  generated-text Markdown rendering.
+  Markdown rendering.
-- Weatherreporter will atomically persist Promptkit output rather than asking
+- Weatherreporter atomically persists Promptkit raw output and later artifacts
-  the dependency to write managed report files.
+  rather than asking Promptkit to choose managed filesystem paths.
-- The migration will not rely on Promptkit output repair. Promptkit v0.3.0's
+- No Promptkit output-repair behavior is assumed or requested.
-  public engine validates in a single pass even when a prompt declares repair
-  attempts.
 
 ## Durable Artifacts And Observability
 
-Status: Accepted design constraints; unimplemented.
+Status: Implemented design constraints.
 
-Routine durable artifacts should retain useful non-secret provenance without
+Routine durable state retains useful non-secret provenance without persisting
-persisting full rendered prompts by default.
+full rendered prompts.
 
-The preparation record should contain:
+The preparation record contains:
 
-- prompt ID and version;
+- prompt ID and exact version;
 - prompt definition hash;
 - rendered prompt hash;
 - input hashes;
 - selected profile and backend identity;
 - effective model identity;
-- output contract summary; and
+- output contract summary;
-- preparation timing.
+- preparation start, end, and duration; and
+- the path of the exact persisted data package.
 
-The execution record and run metadata should contain, when available:
+The execution record and run metadata contain, when available:
 
 - Promptkit run ID;
 - prompt ID, version, and hashes;
@@ -206,122 +355,162 @@ The execution record and run metadata should contain, when available:
 - selected profile, backend, and model identity;
 - generated-content hash;
 - token usage;
-- start, end, and duration;
+- execution start, end, and duration;
 - validation status and bounded diagnostics; and
-- the path of any separately persisted raw generated output.
+- paths of separately persisted raw output, normalized generated text, render
+  context, managed Markdown, and other artifacts reached by the workflow.
 
 Provider endpoints, full effective model parameter maps, rendered messages,
 schema bodies, data-package contents, and generated content do not belong in
 routine metadata or CLI summaries.
 
 Rendered messages and other content-rich preparation or response diagnostics
-will be available only through an explicitly enabled debug mechanism. Debug
+are available only when the operator supplies
-artifacts must be documented as potentially sensitive, must not contain
+`--llm-debug-dir <path>` to a single-report or batch command.
-credentials, and must have a clear operator-owned retention policy.
+
+- There is no persistent YAML setting for debug capture.
+- The debug root is validated or created before weather collection or provider
+  work. A requested destination that cannot be secured or written is an error.
+- Artifacts are grouped beneath
+  `<path>/<report-id>/<valid-date>/<run-id>/`.
+- Directories and files use owner-only permissions and atomic writes.
+- Debug artifacts may contain rendered messages and content-rich preparation
+  or response diagnostics, but never credentials.
+- The debug path appears in command output only when debug capture is enabled;
+  it is not added to routine durable metadata.
+- Debug artifacts are not cache or comparison inputs. Their retention is owned
+  by the operator who selected the directory.
+
+### Artifact Identities And Versions
+
+Weatherreporter replaces Scriptorium-specific artifact identities rather than
+reusing names whose meanings have changed:
+
+- `PromptPreparationArtifact` uses schema version
+  `weatherreporter.prompt_preparation.v1`, is written as
+  `prompt_preparation.<runID>.json`, and is referenced by
+  `preparationPath`.
+- `PromptExecutionArtifact` uses schema version
+  `weatherreporter.prompt_execution.v1`, is written as
+  `prompt_execution.<runID>.json`, and is referenced by `executionPath`.
+- Run metadata advances to `weatherreporter.metadata.v2` and uses those new
+  path fields.
+
+Preparation files remain beneath the existing configurable `preflight/`
+directory, and execution files remain beneath the existing `snapshots/` tree.
+The stable physical grouping limits deployment disruption without preserving
+misleading Scriptorium-era filenames or field names. Raw generated output,
+normalized generated text, render context, managed Markdown, and other
+artifacts whose meanings have not changed retain their existing names and
+locations.
+
+Run inspection remains able to read `weatherreporter.metadata.v1` and its
+legacy `preflightPath` and `generatedTextResultPath` references. New runs write
+only the v2 metadata and new artifact names; Weatherreporter does not
+dual-write deprecated aliases. CLI summary fields adopt `preparationPath` and
+`executionPath` as an explicit, documented contract change.
 
 ## Failure Contract
 
-Status: Accepted design constraints; unimplemented.
+Status: Implemented design constraints.
-
-Promptkit returns a completed `RunResult` for output-validation failure but no
-partial result for operational preparation or execution errors. Weatherreporter
-will preserve that distinction.
 
 - A preparation failure produces a redacted weatherreporter-owned failure
   receipt with report, RunID, prompt, stage, timing, and classified error
-  context. It does not fabricate a Promptkit preparation result.
+  context. It does not fabricate Promptkit preparation details.
 - An operational execution failure retains the successful preparation record
   and adds a redacted execution failure receipt. No partial Promptkit result or
   model output is invented.
-- A Promptkit validation failure retains the returned result, raw generated
+- A Promptkit validation rejection retains the returned result, raw generated
   output, validation details, and safe provenance before the report fails.
-- A later weatherreporter generated-text decode, domain-validation, or template
+- A later generated-text decode, domain-validation, or template failure
-  failure retains every raw and validated artifact reached before that stage.
+  retains every raw and validated artifact reached before that stage.
-- Context cancellation takes precedence when the caller context is canceled.
+- Caller cancellation takes precedence when the active workflow context is
-- Promptkit capacity rejection maps to a weatherreporter-owned error category.
+  canceled.
-  It is an operational report failure, not invalid model output.
+- `promptkit.CapacityError` is recognized with `errors.As`; its backend ID is
+  copied into a weatherreporter-owned capacity error while
+  `ErrCapacityExceeded` remains the classification.
+- Capacity rejection is an operational report failure, not invalid model
+  output, and does not trigger an automatic retry.
+- Other Promptkit public error identities are translated into the narrow
+  weatherreporter error categories needed by CLI, metadata, and batch
+  behavior. Diagnostic prose is not parsed as a contract.
 - Single-report commands return the classified failure with available
   inspectable paths.
 - Batch runs continue independent later reports under the existing batch
   failure policy.
-- The migration adds no automatic retries. Any future retry policy belongs to
+- Any future retry policy belongs to app orchestration, not the adapter.
-  app orchestration, not the Promptkit adapter.
 
 ## Compatibility Requirements
 
-Status: Accepted design constraints; unimplemented.
+Status: Implemented design constraints.
 
-- Report IDs, prompt IDs, report selection, valid periods, artifact grouping,
+- Daily, Today, Tomorrow, and Hourly report IDs, prompt IDs, valid periods,
-  output names, and distributor bundle behavior remain stable.
+  artifact grouping, output names, and Distributor bundle behavior remain
+  stable.
+- Morning and evening batch collection, planning, ordering, and continuation
+  behavior remains stable.
 - Module snapshot and Recent Changes behavior remains deterministic.
 - Promptkit receives only the existing curated prompt-input boundary.
-- Generated reports continue to use the managed Markdown path as the
+- Managed Markdown remains the Distributor upload source.
-  distributor upload source.
 - RunID lookup and inspection remain available for successful and failed runs.
-- Existing managed state paths remain stable where their meaning is unchanged.
+- Existing managed paths remain stable where their meaning is unchanged.
-  Scriptorium-specific artifact names or schemas may change when retaining
+  Scriptorium-specific artifact names or schemas change when retaining them
-  them would misrepresent the new contract.
+  would misrepresent the Promptkit contract.
-- Any artifact or metadata schema change is explicit, documented, and covered
+- Existing v1 run metadata and referenced artifacts remain inspectable after
-  by state and inspection tests.
+  the migration. New runs use the v2 metadata and Promptkit-era artifact
+  identities without dual-writing deprecated aliases.
+- Artifact or metadata schema changes are explicit, documented, and covered by
+  state and inspection tests.
 - Prompt or generated content is not added to routine logs or CLI summaries.
-- Tests do not require live Promptkit providers or credentials.
+- Tests do not require live providers or credentials.
+- Removing incomplete three-day, weekend, and storm surfaces is documented as
+  correction of an unfinished product boundary, not as successful Promptkit
+  migration of those reports.
 
 ## Verification And Completion Criteria
 
-Status: Proposed completion criteria for the unimplemented migration.
+Status: Completed and verified.
 
-The migration is complete when:
+Completion was verified by the following outcomes:
 
-- all seven reports prepare and execute through Promptkit using embedded
+- the four operational reports inspect, prepare, and execute through Promptkit
-  report-owned assets;
+  `v0.4.0` using embedded report-owned assets;
-- direct-Markdown and generated-text-template paths have deterministic offline
+- every report uses exact prompt version `1.0.0`, requires the YAML
-  adapter and app-level coverage;
+  `data_package`, and declares the expected JSON Schema output contract;
-- preparation, provider failure, capacity rejection, cancellation, timeout,
+- prepared execution persists a safe preparation record before provider work
-  Promptkit validation failure, generated-text validation failure, template
+  and executes the same frozen snapshot;
-  failure, and successful generation preserve their specified artifacts;
+- deterministic offline adapter and app tests cover success, preparation
-- morning and evening batches construct one shared engine and preserve current
+  failure, credential revalidation, capacity rejection, cancellation, timeout,
+  generation failure, Promptkit validation rejection, generated-text domain
+  failure, template failure, and handle discard;
+- morning and evening batches construct one engine and preserve current
   collection, planning, ordering, continuation, output, and notification
   behavior;
+- the temporary corpus has been reconciled into one runtime prompt/schema
+  source without duplicate provider-facing schemas;
 - configuration examples load and contain no Scriptorium fields;
-- CLI summaries and inspection commands expose the new artifact contract
+- CLI summaries and inspection commands expose the new project-owned artifact
-  without Promptkit dependency types;
+  contract without Promptkit types;
 - Scriptorium code, configuration, tests, and runtime documentation have been
   removed;
+- incomplete three-day, weekend, and storm commands, registry entries, tests,
+  and current-behavior documentation have been removed or moved to roadmap
+  scope;
 - non-roadmap documentation describes only the implemented Promptkit
   integration;
-- `go test ./...`, CLI help validation, and `git diff --check` pass; and
+- `go test ./...`, required focused or race-enabled checks, CLI help
-- no committed `go.work`, local `replace`, live-provider test, or secret-bearing
+  validation, and `git diff --check` pass; and
-  fixture remains.
+- no committed `go.work`, local `replace`, live-provider test, or
+  secret-bearing fixture remains.
 
-Fixture-based comparison with the current Scriptorium behavior is sufficient
+Fixture-based comparison with prior Scriptorium behavior is sufficient.
-for migration verification. A production-selectable dual-run period is not
+Production dual-run is not required because model calls are nondeterministic,
-required because model calls are nondeterministic, costly, and difficult to
+costly, and difficult to compare meaningfully.
-compare meaningfully.
 
-## External Prerequisite
+## Decision Status
 
-Status: Required and unimplemented.
+Status: Completed.
 
-Before implementing the embedded asset stage, the current Scriptorium prompt
+The roadmap has no remaining open product or architecture questions. Later
-corpus must be made available in this repository. It should include the seven
+changes to this completed scope require new roadmap or decision-record scope
-prompt definitions, referenced content files, private response schemas,
+rather than implicit changes to this historical record.
-relevant default-profile declarations, and any shared prompt fragments needed
-to reproduce current report behavior.
-
-## Open Questions
-
-Status: Open; these require decisions before implementation.
-
-- What exact `promptkit.*` configuration fields should replace the current
-  Scriptorium fields, including the name and precedence of an optional explicit
-  profile override?
-- Should weatherreporter expose Promptkit's conventional `local` backend
-  registration as a narrow configuration feature, or rely initially on
-  built-in and endpoint-only profiles?
-- Should report definitions store an explicit Promptkit prompt version, or
-  should each embedded prompt ID be required to have exactly one version?
-- What CLI or configuration control enables sensitive prompt/response debug
-  artifacts, and where should those artifacts live?
-- What final names and schema versions should replace the
-  Scriptorium-specific preflight and run-result artifacts while balancing
-  semantic clarity with existing state-path compatibility?

docs/roadmap/scriptorium/prompts/daily/daily_generated_text.user.md

@@ -1,63 +0,0 @@
-TASK: You are writing structured prose slots for a daily weather report.
-
-The calling application will render the final Markdown report. Your job is not to write the full report. Return only a JSON object matching the configured schema.
-
-Use only the supplied `data_package`. Do not invent weather details, times, hazards, probabilities, or impacts that are not supported by the data.
-
-The report focuses on the valid period in `report.valid_period`, which corresponds to an upcoming civil day for the configured location.
-
-Return these fields:
-
-- `summary`: required. 1-2 sentences summarizing the main weather story for the valid period.
-- `forecast_discussion`: required. 3 paragraphs explaining the broader setup, trend, and/or forecast reasoning most relevant to the valid period.
-- `precipitation_timing`: optional. Include only when the deterministic `precip_timing` module contains precipitation windows. 
-
-Return JSON only.
-
-# summary
-
-The summary should typically consist of two sentences.
-
-If an active warning is relevant during the report period, lead with the hazard. Otherwise, the first sentence should state the most likely local weather outcome for the valid period, including the overall character of the weather and expected temperature/temperature range. 
-
-The second sentence should state the most important active hazard, caveat, uncertainty, or alternate outcome, if one exists. If there is no meaningful caveat, the second sentence may be omitted.
-
-In the lead, distinguish the main weather outcome from the caveat. If showers and thunderstorms have different timing, state that difference rather than combining them as a single risk throughout the valid period. If the main caveat is a regional severe-weather or precipitation risk displaced from the report location, state that limitation clearly.
-
-Example style:
-
-- “Today is expected to be warm and dry, with mostly clear skies. There is a slight chance of isolated showers and thunderstorms developing from late afternoon into early evening.”
-
-# forecast_discussion
-
-Use narrative products to explain the “why” behind the local forecast when useful. Useful context may include:
-
-- synoptic pattern
-- fronts or boundaries
-- shortwaves, troughs, or ridges
-- instability, moisture, shear, forcing, or capping
-- regional placement of precipitation or severe-weather chances
-- hazard types and timing windows
-- confidence or uncertainty
-- conditional outcomes
-- relevant notes about the following day or days
-
-In most cases, the `forecast_discussion` should include three paragraphs:
-
-1. 2–4 sentences summarizing the relevant local/regional setup.
-2. 2-4 sentences describing the main forecast uncertainty or conditional factor, if present.
-3. 2-4 sentences about the next day or broader pattern if supported.
-
-# precipitation_timing
-
-Optional. Return only if precipitation is forecast. If present, provide 1 to 4 sentences to add practical context, including:
-
-  - Whether the precipitation is associated with a moving frontal boundary, convective initiation, or wide stratiform rain (if this can be determined from the data package);
-  - The expected type, intensity, and duration of the precipitation; and
-  - Any caveats or uncertainty with respect to the onset, duration, or occurrance of the precipitation.
-
-# Narrative Source Selection
-
-As previously noted, use `briefing.derived_daily_summary`, `briefing.derived_daypart_summaries`, `briefing.narrative_products.narrative_forecast.periods`, and `briefing.raw_data.hourly_forecast.periods` as your primary reference sources for forecast.
-
-As previously noted, narrative sources can provide significant added value, but you must think carefully about whether information from the available narrative sources is relevant to the valid period. If the valid period relates to a civil day that is several days in the future, then products such as `briefing.narrative_products.weather_story`, `briefing.narrative_products.area_forecast_discussion.key_messages`, and `briefing.narrative_products.area_forecast_discussion.short_term` may have limited relevance. On the other hand, `briefing.narrative_products.area_forecast_discussion.long_term` may have relatively more relevance.

docs/roadmap/scriptorium/prompts/daily_report/daily_report.system.md

@@ -1,13 +0,0 @@
-You are WeatherReporter, a concise personal weather briefing writer.
-
-You generate local daily weather briefings from structured data packages prepared by the weatherreporter application.
-
-The reader is weather-literate and interested in meteorology. Do not write a generic public weather report. Do not include routine lifestyle advice such as bringing an umbrella, wearing a jacket, driving carefully, or checking the radar unless the forecast contains a specific hazard or meaningful uncertainty that makes such a note unusually important.
-
-Your job is to identify the most likely weather outcome, state meaningful caveats or uncertainty, summarize the daypart forecast, and explain the meteorological setup when useful.
-
-Use only the provided data package as your source of truth. Do not invent forecast details, alerts, hazards, timing, locations, rainfall amounts, severe weather risks, synoptic features, confidence levels, or recent changes that are not supported by the package.
-
-Write in plain, precise, meteorologically informed language. Avoid hype, filler, generic safety advice, and TV-weather style. Do not mention that you are an AI model. Do not expose internal implementation details,  field names, source hashes, endpoint names, or missing internal data sources unless the missing data materially limits the report.
-
-The report should be compact, but it may include meteorological context when the forecast discussion supports it.

docs/roadmap/scriptorium/prompts/daily_report/daily_report.user.md

@@ -1,234 +0,0 @@
-Generate a Daily Weather Report from the following weatherreporter YAML data package.
-
-The report may be for today, tomorrow, or a future date. Determine the correct framing from report, briefing.metadata, the report valid period, and the derived daily date when present.
-
-Use Markdown.
-
-# CORE EDITORIAL GOAL
-
-This is a personal weather-nerd briefing, not a generic public forecast. The report should answer:
-
-1. What is the most likely local weather outcome for the day?
-2. What active hazard, caveat, uncertainty, or alternate outcome matters relative to that most likely outcome?
-3. If precipitation is likely, impactful, or meteorologically meaningful, when is it favored, how significant is it, and is severe weather possible?
-4. What should each daypart generally look and feel like?
-5. What broader meteorological setup or forecast dependency is worth watching?
-
-# SOURCE ROLES AND WEIGHTING
-
-Use report and briefing.metadata for framing: location, timezone, units, valid period, generation time, and today/tomorrow/future wording. Do not treat metadata as forecast evidence except where it identifies source relevance, such as alert counts or location matching.
-
-For weather interpretation, think in four source layers, in this order:
-
-## 1. Active hazard and risk products
-
-Give substantial weight to official hazard or risk products that the package identifies as relevant to the forecast location and valid period. This includes current or future package sections for alerts, watches, warnings, advisories, SPC outlook polygon hits, WPC excessive rainfall outlook polygon hits, mesoscale discussions, precipitation discussions, or similar location-matched products.
-
-These products have already been filtered or matched to the forecast location. Treat them as locally relevant, but distinguish product strength:
-
-- Active warnings are urgent and should dominate the lead and relevant sections.
-- Watches and advisories should be mentioned prominently when they affect the report period.
-- Outlook/risk polygon hits are important local risk signals, but they can vary significantly with respect to both impact and certainty. Higher risk levels deserve greater and more detailed attention than lower risk levels. Outlook/risk polygons should elevate the caveat, uncertainty, and ## What to Watch discussion without necessarily implying that severe weather is certain at the exact point.
-- Mesoscale discussions and precipitation discussions are strong short-term situational-awareness signals when they cover the location and valid period.
-
-For the current schema, use `briefing.applicable_risk_products.alert_digest` and `briefing.metadata.alerts` to determine whether relevant local alerts exist. If `relevant_count` is zero, do not imply that the report location is under an active alert merely because `active_count` is nonzero.
-
-## 2. Derived summaries
-
-Use derived summaries as the baseline interpretation of the local forecast when no active hazard product requires stronger framing.
-
-For the current schema:
-
-- Use briefing.derived_daily_summary for the overall daily theme, high/low temperature, dominant conditions, daily precipitation probability, most likely precipitation hour, and thunder flag.
-- Use briefing.derived_daypart_summaries for daypart timing, dominant conditions, temperature ranges, maximum precipitation chances, and notable conditions.
-- Use briefing.precip_timing as the deterministic summary of maximum precipitation probability and whether thunder is mentioned in the structured local forecast.
-- Use briefing.outdoor_windows only if it adds meaningful signal to the daypart discussion. Do not turn the report into outdoor-planning advice.
-
-## 3. Narrative products
-
-Use `briefing.narrative_products` for meteorological context, prose framing, uncertainty, and conditional outcomes. This includes the AFD, Weather Story, NWS narrative forecast text, SPC narrative text, WPC discussions, CPC discussions, and similar products.
-
-For the current schema:
-
-- Use `briefing.narrative_products.narrative_forecast.periods` to confirm and reconcile official day/night wording, high/low temperatures, winds, and broad precipitation wording.
-- Use `briefing.narrative_products.weather_story` to understand what the NWS considers the most relevant, public-facing headlines for the short-term forecast. Because the covered forecast area for this product is relatively large, be wary of discussion that relates to geographical areas outside the forecast location, and preserve spatial limits such as “north of I-70.”
-- Use `briefing.narrative_products.area_forecast_discussion.key_messages` and `briefing.narrative_products.area_forecast_discussion.short_term` for setup, local/regional nuance, confidence, uncertainty, and forecast dependencies affecting the report period.
-- Use `briefing.narrative_products.area_forecast_discussion.long_term` only if it affects the valid day, the overnight period immediately following it, or a brief note about the following day/days.
-- If `briefing.narrative_products.spc_convective_discussion.discussions` is present, use it to understand  and to provide context to the severe weather forecast. Because the covered forecast area for this product is relatively large, be wary of discussion that relates to geographical areas far from the forecast location, except as a discussion of the broader synoptic pattern.
-
-Do not let broad regional narrative language override point-specific local forecast data unless an applicable hazard/risk product, local forecast data, or the narrative itself clearly supports that local implication.
-
-## 4. Raw underlying data
-
-Use `briefing.raw_data` as the source of truth for exact timing, temperatures, precipitation probabilities, wind, humidity/dew point, and condition changes when more detail is needed.
-
-For the current schema, `briefing.raw_data.hourly_forecast.periods` is the most granular local forecast source. Use it to verify daypart summaries, refine timing, identify trends, and resolve ambiguity.
-
-Use `briefing.raw_data.current_conditions` only as generation-time context. For tomorrow or future reports, do not describe current conditions as if they are forecast conditions.
-
-If raw data and derived summaries appear to disagree, prefer the raw data for exact values and timing, but treat the disagreement as a reason to be cautious rather than as permission to invent an explanation.
-
-# CONFLICT RESOLUTION
-
-When sources differ, ask:
-
-1. Which source is most local to the forecast point?
-2. Which source is valid for the report period or near-term window?
-3. Which source is most authoritative for the type of claim being made?
-4. Is the source describing the most likely outcome, or a conditional/low-probability hazard?
-
-Do not turn regional severe-weather discussion into a deterministic local severe-weather forecast unless point-specific data supports that conclusion. Conversely, do not bury a location-specific warning, watch, advisory, outlook polygon hit, or valid mesoscale discussion merely because the baseline derived summary is otherwise quiet.
-
-# LEAD REQUIREMENT
-
-Begin the report with a two-sentence lead before any section headings.
-
-If an active warning is relevant during the report period, lead with the hazard. Otherwise, the first sentence should state the most likely local weather outcome for the day, including the overall character of the weather and expected high temperature.
-
-The second sentence should state the most important active hazard, caveat, uncertainty, or alternate outcome, if one exists. If there is no meaningful caveat, the second sentence may briefly say that no major complications are apparent.
-
-In the lead, distinguish the main weather outcome from the caveat. If showers and thunderstorms have different timing, state that difference rather than combining them as a single all-day risk. If the main caveat is a regional severe-weather or precipitation risk displaced from the report location, state that limitation clearly.
-
-Example style:
-
-- “Tomorrow is expected to be warm, mostly cloudy, and mostly dry, with a high near 72. There is a slight chance of isolated showers and thunderstorms from late afternoon into early evening.”
-
-Do not open with generic planning advice.
-
-# HAZARD AND SEVERE-WEATHER RULES
-
-Mention a hazard only to the extent supported by location-specific products, local structured forecast data, or clearly applicable narrative text.
-
-Preserve product strength and uncertainty. An SPC Slight Risk, WPC Excessive Rainfall Outlook, or similar polygon hit is a locally relevant risk signal, not a warning and not a guarantee of local impact.
-
-Preserve geography. If the package says the main severe risk is north of the metro, north of I-70, along a front, or over a specific part of the CWA, carry that limitation into the report.
-
-Preserve timing. Do not say storms “arrive,” “clear,” “develop,” or “move in” at a specific time unless the hourly data, narrative forecast, Weather Story, AFD, or hazard product supports that timing.
-
-# PRECIPITATION RULES
-
-Do not overstate low precipitation probabilities.
-
-Use precipitation wording consistently:
-
-- 0–14%: usually omit unless relevant to a trend, caveat, hazard product, regional risk, or timing uncertainty.
-- 15–24%: “slight chance,” “isolated,” “spotty,” or “brief passing shower/storm possible.”
-- 25–39%: “chance,” “scattered,” or “some showers/storms possible.”
-- 40–59%: “good chance” or “showers/storms likely enough to plan around.”
-- 60%+: “likely,” “wet,” or “unsettled,” if consistent with the narrative forecast.
-
-Include ## Precipitation Details only when precipitation is likely, potentially impactful, or meteorologically interesting. In that section, address as many of the following as the data supports:
-
-- likely or favored start/end timing
-- most likely precipitation window
-- expected intensity
-- expected rainfall amount
-- thunderstorm potential
-- severe-weather potential
-- uncertainty in timing, coverage, or placement
-
-If the package does not provide rainfall amounts, say nothing about totals unless a narrative product provides a supported qualitative signal. Do not invent QPF.
-
-If local precipitation chances are low and no meaningful local impacts are expected, do not create a full precipitation section solely because regional precipitation or severe weather appears in a narrative product. Mention the regional caveat in the lead or ## What to Watch instead, preserving geographic limits.
-
-# DAYPART RULES
-
-Use dayparts from briefing.derived_daypart_summaries. If a daypart is present but incomplete, use raw hourly data and narrative forecast periods to fill in only what is supported. Only include dayparts present in the package.
-
-In ## Daypart Forecast, each bullet should usually follow this pattern:
-
-- **Daypart:** [Sky/general condition] with [temperature trend or approximate temperature]. [Precipitation/storm/hazard sentence only if relevant.] [Wind sentence only if meaningful.]
-
-Always include the expected sky or general condition when supported, such as mostly cloudy, partly cloudy, sunny, overcast, rainy, snowy, foggy, or stormy.
-
-Prefer natural temperature phrasing:
-
-- “temperatures around 82”
-- “temperatures rising from the upper 60s into the low 70s”
-- “temperatures near 80”
-- “cooling from the low 80s into the low 70s”
-- “holding in the upper 60s”
-- “peaking near 83 late in the day”
-
-For quiet or mostly dry dayparts, keep the bullet to one sentence. For dayparts with meaningful precipitation, thunder, snow, ice, fog, high wind, heat, or other weather impacts, add a second sentence with timing and caveat details.
-
-Keep sky/general condition separate from precipitation probability. Do not write only “slight chance of showers” when the broader condition is “mostly cloudy with a slight chance of showers.”
-
-When precipitation or hazards are likely during only part of a daypart, describe that timing first, then describe the sky/temperature trend. Do not lead with a benign sky condition if showers, storms, snow, ice, fog, or other impacts are likely during that same daypart.
-
-Avoid “throughout the day” unless the same weather risk is meaningfully present across most dayparts.
-
-# METEOROLOGICAL CONTEXT RULES
-
-Use narrative products to explain the “why” behind the local forecast when useful.
-
-Useful context may include:
-
-- synoptic pattern
-- fronts or boundaries
-- shortwaves, troughs, or ridges
-- instability, moisture, shear, forcing, or capping
-- regional placement of precipitation or severe-weather chances
-- hazard types and timing windows
-- confidence or uncertainty
-- conditional outcomes
-- relevant notes about the following day or days
-
-Do not simply quote or summarize narrative products at length. Translate them into concise, plainspoken, weather-literate context.
-
-# OUTPUT FORMAT
-
-Use this structure:
-
-# [Today’s/Tomorrow’s/DOW's] Weather — [Location Name]
-
-[Valid date]
-
-[Two-sentence lead.]
-
-## Daypart Forecast
-
-- Morning: ...
-- Midday: ...
-- Afternoon: ...
-- Evening: ...
-- Overnight: ...
-
-Only include dayparts present in the package. Use natural language timing where helpful.
-
-## Precipitation Details
-
-Include this section only if:
-
-- local precipitation probability reaches at least 30% during the valid period;
-- thunder is mentioned in the structured local forecast and the timing/coverage is meteorologically interesting;
-- a relevant hazard/risk product discusses flooding, severe weather, winter weather, high wind, or another meaningful precipitation-related hazard;
-- narrative products discuss intensity, rainfall rates, flooding, severe potential, or meaningful uncertainty that plausibly affects the report location or is important regional context;
-- recent changes materially affect precipitation timing, coverage, or intensity.
-
-## Recent Changes
-
-Include this section only if recent_changes.items contains meaningful changes. Summarize changes in plain English. Do not fabricate changes.
-
-## What to Watch
-
-Include meteorological context, uncertainty, conditional forecast factors, and any relevant non-warning hazard/risk signals.
-
-In most cases:
-
-- Provide 2–3 sentences summarizing the relevant local/regional setup.
-- Provide 1–2 sentences describing the main forecast uncertainty or conditional factor, if present.
-- Optionally include 1–2 sentences about the next day or broader pattern if supported.
-
-# STYLE RULES
-
-- Plainspoken, precise, and weather-literate.
-- Compact, but not shallow.
-- No generic public-safety filler.
-- No umbrella/rain-jacket/snow-boots advice unless unusually warranted by a specific hazard.
-- No commute or outdoor-plan boilerplate.
-- No unsupported precision.
-- No raw YAML, raw JSON, internal field names, source hashes, endpoint names, URLs, implementation details, or debugging notes.
-- No apologies for missing data.
-- Avoid phrases like “developing,” “moving in,” “clearing,” “threatening,” or “impacting” unless the timing and trend are clearly supported by the package.
-- Prefer “most likely,” “possible,” “favored,” “conditional,” “limited coverage,” and “worth watching” when those phrases accurately reflect the data.

docs/roadmap/scriptorium/prompts/daily_report/daily_report.yml

@@ -1,24 +0,0 @@
-id: weather.daily_report
-version: "1.0.0"
-#default_profile: local-heavy
-default_profile: gemini-3-flash-lite
-description: Daily weather report prompt.
-inputs:
-  - name: data_package
-    required: true
-    content_type: application/json
-    description: Structured weather data package
-messages:
-  - role: system
-    content_file: ./daily_report.system.md
-  - role: user
-    content_file: ./daily_report.user.md
-  - role: user
-    content: |
-      <<<CURRENT_SESSION_TRANSCRIPT
-      {{input "data_package"}}
-      CURRENT_SESSION_TRANSCRIPT>>>
-output:
-  format: markdown
-  validation_mode: basic
-  repair_attempts: 0

docs/roadmap/scriptorium/prompts/hourly/hourly_generated_text.user.md

@@ -1,55 +0,0 @@
-TASK: You are writing structured prose slots for a short-term hourly weather report.
-
-The calling application will render the final Markdown report. Your job is not to write the full report. Return only a JSON object matching the configured schema.
-
-Use only the supplied `data_package`. Do not invent weather details, times, hazards, probabilities, or impacts that are not supported by the data.
-
-The report focuses on the valid period in `report.valid_period`, typically the next several hours for the configured location.
-
-Return these fields:
-
-- `summary`: required. 1-2 sentences summarizing the main weather story for the valid period.
-- `forecast_discussion`: required. 2-3 sentences explaining the broader setup, trend, or forecast reasoning most relevant to the valid period.
-- `precipitation_timing`: optional. Include only when the deterministic `precip_timing` module contains precipitation windows. 
-
-Return JSON only.
-
-# summary
-
-The summary should typically consist of two sentences.
-
-If an active warning is relevant during the report period, lead with the hazard. Otherwise, the first sentence should state the most likely local weather outcome for the valid period, including the overall character of the weather and expected temperature/temperature range. 
-
-If the forecast indicates a significant shift in conditions over time (e.g., from sunny to overcast), then identify the hour when the shift is most likely to occur. If the conditions are generally similar or stable across the forecast period, then pick a single descriptor (e.g., mostly clear) that best captures the character of the weather.
-
-The second sentence should state the most important active hazard, caveat, uncertainty, or alternate outcome, if one exists. If there is no meaningful caveat, the second sentence may be omitted, or may briefly say that no major complications are apparent.
-
-In the lead, distinguish the main weather outcome from the caveat. If showers and thunderstorms have different timing, state that difference rather than combining them as a single risk throughout the valid period. If the main caveat is a regional severe-weather or precipitation risk displaced from the report location, state that limitation clearly.
-
-Example style:
-
-- “The rest of the afternoon is expected to be warm and dry, with mostly clear skies. There is a slight chance of isolated showers and thunderstorms developing from late afternoon into early evening.”
-
-# forecast_discussion
-
-Use narrative products to explain the “why” behind the local forecast when useful.
-
-Useful context may include:
-
-- synoptic pattern
-- fronts or boundaries
-- shortwaves, troughs, or ridges
-- instability, moisture, shear, forcing, or capping
-- regional placement of precipitation or severe-weather chances
-- hazard types and timing windows
-- confidence or uncertainty
-- conditional outcomes
-- relevant notes about the following day or days
-
-# precipitation_timing
-
-Optional. Return only if precipitation is forecast. If present, provide 1 to 4 sentences to add practical context, including:
-
-  - Whether the precipitation is associated with a moving frontal boundary, convective initiation, or wide stratiform rain (if this can be determined from the data package);
-  - The expected type, intensity, and duration of the precipitation; and
-  - Any caveats or uncertainty with respect to the onset, duration, or occurrance of the precipitation.

docs/roadmap/scriptorium/prompts/today/today_generated_text.user.md

@@ -1,57 +0,0 @@
-TASK: You are writing structured prose slots for a daily weather report.
-
-The calling application will render the final Markdown report. Your job is not to write the full report. Return only a JSON object matching the configured schema.
-
-Use only the supplied `data_package`. Do not invent weather details, times, hazards, probabilities, or impacts that are not supported by the data.
-
-The report focuses on the valid period in `report.valid_period`, which corresponds to the current civil day (today) for the configured location.
-
-Return these fields:
-
-- `summary`: required. 1-2 sentences summarizing the main weather story for the valid period.
-- `forecast_discussion`: required. 3 paragraphs explaining the broader setup, trend, and/or forecast reasoning most relevant to the valid period.
-- `precipitation_timing`: optional. Include only when the deterministic `precip_timing` module contains precipitation windows. 
-
-Return JSON only.
-
-# summary
-
-The summary should typically consist of two sentences.
-
-If an active warning is relevant during the report period, lead with the hazard. Otherwise, the first sentence should state the most likely local weather outcome for the valid period, including the overall character of the weather and expected temperature/temperature range. 
-
-The second sentence should state the most important active hazard, caveat, uncertainty, or alternate outcome, if one exists. If there is no meaningful caveat, the second sentence may be omitted.
-
-In the lead, distinguish the main weather outcome from the caveat. If showers and thunderstorms have different timing, state that difference rather than combining them as a single risk throughout the valid period. If the main caveat is a regional severe-weather or precipitation risk displaced from the report location, state that limitation clearly.
-
-Example style:
-
-- “Today is expected to be warm and dry, with mostly clear skies. There is a slight chance of isolated showers and thunderstorms developing from late afternoon into early evening.”
-
-# forecast_discussion
-
-Use narrative products to explain the “why” behind the local forecast when useful. Useful context may include:
-
-- synoptic pattern
-- fronts or boundaries
-- shortwaves, troughs, or ridges
-- instability, moisture, shear, forcing, or capping
-- regional placement of precipitation or severe-weather chances
-- hazard types and timing windows
-- confidence or uncertainty
-- conditional outcomes
-- relevant notes about the following day or days
-
-In most cases, the `forecast_discussion` should include three paragraphs:
-
-1. 2–4 sentences summarizing the relevant local/regional setup.
-2. 2-4 sentences describing the main forecast uncertainty or conditional factor, if present.
-3. 2-4 sentences about the next day or broader pattern if supported.
-
-# precipitation_timing
-
-Optional. Return only if precipitation is forecast. If present, provide 1 to 4 sentences to add practical context, including:
-
-  - Whether the precipitation is associated with a moving frontal boundary, convective initiation, or wide stratiform rain (if this can be determined from the data package);
-  - The expected type, intensity, and duration of the precipitation; and
-  - Any caveats or uncertainty with respect to the onset, duration, or occurrance of the precipitation.

docs/roadmap/scriptorium/prompts/tomorrow/tomorrow_generated_text.user.md

@@ -1,58 +0,0 @@
-TASK: You are writing structured prose slots for a daily weather report.
-
-The calling application will render the final Markdown report. Your job is not to write the full report. Return only a JSON object matching the configured schema.
-
-Use only the supplied `data_package`. Do not invent weather details, times, hazards, probabilities, or impacts that are not supported by the data.
-
-The report focuses on the valid period in `report.valid_period`, which corresponds to the next civil day (tomorrow) for the configured location.
-
-Return these fields:
-
-- `summary`: required. 1-2 sentences summarizing the main weather story for the valid period.
-- `forecast_discussion`: required. 3 paragraphs explaining the broader setup, trend, and/or forecast reasoning most relevant to the valid period.
-- `precipitation_timing`: optional. Include only when the deterministic `precip_timing` module contains precipitation windows. 
-- `confidence`: optional. Include only if uncertainty, timing spread, or conflicting signals materially affect how the reader should interpret the forecast.
-
-Return JSON only.
-
-# summary
-
-The summary should typically consist of two sentences.
-
-If an active warning is relevant during the report period, lead with the hazard. Otherwise, the first sentence should state the most likely local weather outcome for the valid period, including the overall character of the weather and expected temperature/temperature range. 
-
-The second sentence should state the most important active hazard, caveat, uncertainty, or alternate outcome, if one exists. If there is no meaningful caveat, the second sentence may be omitted.
-
-In the lead, distinguish the main weather outcome from the caveat. If showers and thunderstorms have different timing, state that difference rather than combining them as a single risk throughout the valid period. If the main caveat is a regional severe-weather or precipitation risk displaced from the report location, state that limitation clearly.
-
-Example style:
-
-- “Sunday is expected to be warm and dry, with mostly clear skies. There is a slight chance of isolated showers and thunderstorms developing from late afternoon into early evening.”
-
-# forecast_discussion
-
-Use narrative products to explain the “why” behind the local forecast when useful. Useful context may include:
-
-- synoptic pattern
-- fronts or boundaries
-- shortwaves, troughs, or ridges
-- instability, moisture, shear, forcing, or capping
-- regional placement of precipitation or severe-weather chances
-- hazard types and timing windows
-- confidence or uncertainty
-- conditional outcomes
-- relevant notes about the following day or days
-
-In most cases, the `forecast_discussion` should include three paragraphs:
-
-1. 2–4 sentences summarizing the relevant local/regional setup.
-2. 2-4 sentences describing the main forecast uncertainty or conditional factor, if present.
-3. 2-4 sentences about the next day or broader pattern if supported.
-
-# precipitation_timing
-
-Use 1-2 sentences to add practical context, including:
-
-  - Whether the precipitation is associated with a moving frontal boundary, convective initiation, or wide stratiform rain (if this can be determined from the data package);
-  - The expected type, intensity, and duration of the precipitation; and
-  - Any caveats or uncertainty with respect to the onset, duration, or occurrance of the precipitation.

docs/roadmap/scriptorium/schemas/daily/daily.generated_text.schema.json

@@ -1,26 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "weatherreporter.today.generated_text.schema.json",
-  "title": "Today GeneratedText",
-  "type": "object",
-  "additionalProperties": false,
-  "required": [
-    "summary",
-    "forecast_discussion"
-  ],
-  "properties": {
-    "summary": {
-      "type": "string"
-    },
-    "forecast_discussion": {
-      "type": "array",
-      "items": {
-        "type": "string"
-      },
-      "minItems": 1
-    },
-    "precipitation_timing": {
-      "type": "string"
-    }
-  }
-}

docs/roadmap/scriptorium/schemas/today/today.generated_text.schema.json

@@ -1,26 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "weatherreporter.today.generated_text.schema.json",
-  "title": "Today GeneratedText",
-  "type": "object",
-  "additionalProperties": false,
-  "required": [
-    "summary",
-    "forecast_discussion"
-  ],
-  "properties": {
-    "summary": {
-      "type": "string"
-    },
-    "forecast_discussion": {
-      "type": "array",
-      "items": {
-        "type": "string"
-      },
-      "minItems": 1
-    },
-    "precipitation_timing": {
-      "type": "string"
-    }
-  }
-}

docs/roadmap/scriptorium/schemas/tomorrow/tomorrow.generated_text.schema.json

@@ -1,26 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "weatherreporter.tomorrow.generated_text.schema.json",
-  "title": "Tomorrow GeneratedText",
-  "type": "object",
-  "additionalProperties": false,
-  "required": [
-    "summary",
-    "forecast_discussion"
-  ],
-  "properties": {
-    "summary": {
-      "type": "string"
-    },
-    "forecast_discussion": {
-      "type": "array",
-      "items": {
-        "type": "string"
-      },
-      "minItems": 1
-    },
-    "precipitation_timing": {
-      "type": "string"
-    }
-  }
-}

docs/templates.md

@@ -14,14 +14,14 @@ source:
 
 | Report | Template | Schema | Prompt ID and source |
 | --- | --- | --- | --- |
-| Daily | `templates/daily.md.tmpl` (`daily`) | `daily` | `weather.daily_generated_text`; `prompts/daily.generated_text.md` |
+| Daily | `templates/daily.md.tmpl` (`daily`) | `daily` | `weather.daily_generated_text`; `internal/promptassets/assets/prompts/daily/` |
-| Today | `templates/today.md.tmpl` (`today`) | `today` | `weather.today_generated_text`; `prompts/today.generated_text.md` |
+| Today | `templates/today.md.tmpl` (`today`) | `today` | `weather.today_generated_text`; `internal/promptassets/assets/prompts/today/` |
-| Tomorrow | `templates/tomorrow.md.tmpl` (`tomorrow`) | `tomorrow` | `weather.tomorrow_generated_text`; `prompts/tomorrow.generated_text.md` |
+| Tomorrow | `templates/tomorrow.md.tmpl` (`tomorrow`) | `tomorrow` | `weather.tomorrow_generated_text`; `internal/promptassets/assets/prompts/tomorrow/` |
-| Hourly | `templates/hourly.md.tmpl` (`hourly`) | `hourly` | `weather.hourly_generated_text`; `prompts/hourly.generated_text.md` |
+| Hourly | `templates/hourly.md.tmpl` (`hourly`) | `hourly` | `weather.hourly_generated_text`; `internal/promptassets/assets/prompts/hourly/` |
 
-The matching schema files are under `internal/reporttemplate/schemas/`. The
+The matching schemas and Promptkit definitions are embedded by
-generated-text catalog pairs each schema ID with its template ID; keep the
+`internal/promptassets`. The generated-text catalog pairs each schema ID with
-matching report prompt source aligned with that pair.
+its template ID; keep the matching prompt definition aligned with that pair.
 
 Shared partials are under `internal/reporttemplate/templates/partials/`:
 
@@ -97,7 +97,7 @@ fields:
 | Field | Purpose |
 | --- | --- |
 | `.Report` | Display labels and canonical report timing metadata. |
-| `.GeneratedText` | Validated prose supplied by Scriptorium. |
+| `.GeneratedText` | Validated prose supplied by Promptkit. |
 | `.Modules` | Deterministic, typed values prepared for Markdown rendering. |
 | `.Collected` | Normalized upstream facts for advanced use. |
 | `.Derived` | Shared calculated facts for advanced use. |
@@ -121,7 +121,7 @@ of formatting timestamps in a template.
 
 ### Validated GeneratedText Prose
 
-GeneratedText is prose returned by Scriptorium and validated before rendering.
+GeneratedText is prose returned by Promptkit and validated before rendering.
 It is not a source for deterministic weather facts.
 
 | Field | Hourly type | Daily, Today, and Tomorrow type | Notes |

docs/troubleshooting.md

@@ -1,271 +1,48 @@
 # Troubleshooting
 
-Use the error from the command together with the run artifacts when a run ID is
+Keep failed workspace artifacts in place. When a RunID is available, start
-available. Start with [`inspect metadata`](cli.md#inspection-commands) to identify the
+with `weatherreporter inspect metadata RUN_ID` and use the paths in its result.
-report and artifact paths, then use the narrower inspection command named
-below. Do not remove a workspace to diagnose a failure: it contains the
-evidence needed to correct it safely.
 
-## A command or configuration is rejected before work starts
+## Prompt inspection or credentials fail before collection
 
-Symptom: The command exits before it creates a run, with an unknown-flag,
+A prompt/version, contract, selected profile, unsupported direct-key profile,
-missing-argument, invalid date or time bound, invalid timezone, or
+or required environment credential can fail before weather collection. Correct
-`weather_api.base_url` message.
+the configured `promptkit` profile or profile source, confirm the exact
+Promptkit asset is available, and supply any reported environment credential.
+Do not add provider keys to YAML. See [configuration](config.md).
 
-Likely cause: The command does not accept that option for the requested report,
+## Preparation, capacity, or execution fails
-or required command and configuration values are absent or malformed.
 
-Diagnostic: Compare the command with [`generate` and `run`](cli.md#commands-and-usage)
+A preparation failure occurs before provider work; an execution failure occurs
-and review the configured value named in the error. `generate daily` requires
+after preparation. Both leave safe provenance and metadata when reached. A
-`--date`; `generate storm` requires both `--start` and `--end`.
+capacity error for one batch report does not retry that report or prevent later
-
+independent reports. Inspect the preparation or execution path, correct the
-Safe fix: Correct only the reported option or configuration value. Use an
+profile/backend condition, and create a new run. See [operations](operations.md).
-absolute Weather API URL and a valid IANA timezone; do not change unrelated
-workspace data.
-
-See also: [Configuration](config.md) and [Weather API integration](integrations/weatherapi.md).
-
-## Weather data cannot be collected
-
-Symptom: A generation command fails while fetching weather data, or reports
-`hourly forecast data is missing` or `contains no periods`.
-
-Likely cause: The Weather API is unavailable, its configured endpoint or
-credentials are unsuitable, or the response lacks the hourly forecast required
-by the selected report.
-
-Diagnostic: Check the service status and the configured base URL, then retry
-the same report. If a run ID was produced, run `weatherreporter inspect sources
-RUN_ID` to see the recorded source result.
-
-Safe fix: Restore access to the configured Weather API or choose a reporting
-period supported by the returned forecast. Do not invent missing hourly values
-in local artifacts.
-
-See also: [Configuration](config.md) and [Weather API integration](integrations/weatherapi.md).
-
-## Optional source warnings appear
-
-Symptom: The report succeeds but its output says that a source supplied a
-warning or degraded result.
-
-Likely cause: An optional source did not return usable data; mandatory weather
-collection still completed.
-
-Diagnostic: Run `weatherreporter inspect sources RUN_ID` and identify the
-source and warning recorded for that run.
-
-Safe fix: Correct the affected source configuration or service issue, then
-generate a new report if the missing optional information is needed. Keep the
-existing run for comparison.
-
-See also: [Inspecting a run](cli.md#inspection-commands) and [Operations](operations.md).
-
-## Scriptorium cannot be prepared
-
-Symptom: The report fails with a fragment such as `run scriptorium render`, or
-the Scriptorium executable cannot be started.
-
-Likely cause: The configured executable, profile, prompt, or its local runtime
-environment is unavailable to Weatherreporter.
-
-Diagnostic: Confirm that the configured executable can be run by the same user
-and inspect `weatherreporter inspect metadata RUN_ID` when a run ID is shown.
-
-Safe fix: Repair the executable path or the Scriptorium configuration and retry
-the report. Do not edit generated artifacts to bypass preparation.
-
-See also: [Configuration](config.md) and [Operations](operations.md).
-
-## Scriptorium preflight fails
-
-Symptom: A Scriptorium-backed report stops before text generation, often with
-a `scriptorium render exited with code` fragment.
-
-Likely cause: Scriptorium rejected the render request, prompt, profile, or data
-package before it could run the report.
-
-Diagnostic: Inspect the run metadata and the saved preflight artifact path it
-references. Compare the reported Scriptorium diagnostic with its configuration.
-
-Safe fix: Correct the reported Scriptorium input or configuration, then create
-a new run. Preserve the failed preflight artifact for support or comparison.
-
-See also: [Inspecting a run](cli.md#inspection-commands) and [Operations](operations.md).
-
-## Scriptorium report execution fails
-
-Symptom: Preparation succeeded, but generation stops with a
-`scriptorium run exited with code` fragment.
-
-Likely cause: The Scriptorium run failed after preflight, for example because
-its prompt execution or runtime dependency failed.
-
-Diagnostic: Inspect the run metadata and preflight artifact, then review the
-exit diagnostic from the command. This distinguishes a run failure from a
-preflight failure.
-
-Safe fix: Correct the Scriptorium issue identified by that diagnostic and run
-the report again; leave the failed run artifacts in place.
-
-See also: [Operations](operations.md).
 
 ## Generated text fails validation
 
-Symptom: A generated-text report fails after Scriptorium returns text, with a
+Raw generated output may be saved but Markdown is not rendered when the JSON
-message about generated text or required report content.
+does not match the report schema. Correct the Promptkit prompt/profile behavior
+or the matching schema and validator in source control; do not edit raw output
+to treat it as validated. See [templates](templates.md).
 
-Likely cause: Returned text does not meet the report's validation rules.
+## Debug capture fails
 
-Diagnostic: Use `weatherreporter inspect metadata RUN_ID` to find the saved raw
+`--llm-debug-dir` must be an absolute secure directory outside workspace state.
-generated-text artifact, and inspect it alongside the reported validation
+A debug-write failure stops the affected report to avoid continuing without the
-message.
+requested diagnostic. Repair the named path's ownership or permissions, then
+rerun. Treat capture files as sensitive. See [operations](operations.md).
 
-Safe fix: Correct the upstream prompt or generation configuration that caused
+## Weather, state, output, or notification fails
-the invalid output, then create a new run. Do not hand-edit saved raw text and
-present it as a validated report.
 
-See also: [Operations](operations.md).
+Collection errors precede planning. Later filesystem, output-copy, template,
-
+or Distributor errors retain the reached safe paths in the summary. Repair only
-## Report template rendering fails
+the reported endpoint or path, leave successful managed reports intact, and
-
+rerun the affected report or batch. A batch notification is intentionally
-Symptom: Scriptorium output is available, but the report fails while building
+skipped when any report item fails.
-the final Markdown document.
-
-Likely cause: The selected report template or the render context is
-incompatible with the generated or collected data.
-
-Diagnostic: Inspect the metadata, generated-text result, and render-context
-artifacts for the run. Note the template or missing-field fragment in the
-error rather than relying on a complete error string.
-
-Safe fix: Correct the template or its supported inputs in source control, test
-the change, and create a new report. Do not alter the saved context merely to
-make one historical run render.
-
-See also: [Operations](operations.md).
-
-## A report fails after artifacts are saved
-
-Symptom: A generation command reports an error after showing a run ID, such as
-an error writing the managed report, copying `--out`, saving metadata, or
-notifying Distributor.
-
-Likely cause: A local filesystem permission or path problem, an unavailable
-destination for `--out`, or a later report-delivery failure occurred after
-earlier steps succeeded.
-
-Diagnostic: Run `weatherreporter inspect metadata RUN_ID` and check the exact
-path and operation named in the error. For an `--out` failure, verify only the
-specified destination directory and filename.
-
-Safe fix: Repair access to that exact path or disable the optional delivery
-step only when appropriate, then generate a new report. Keep the existing
-managed artifacts untouched.
-
-See also: [Operations](operations.md) and [Distributor integration](integrations/distributor/pkg-upload.md).
-
-## A batch has partial report failures
-
-Symptom: `run morning` or `run evening` returns nonzero and reports both
-succeeded and failed report items.
-
-Likely cause: A report-level collection, generation, rendering, or local
-output failure affected one or more planned reports; the remaining reports
-continue independently.
-
-Diagnostic: Read the per-report status lines, then inspect the run ID for each
-failed item with `weatherreporter inspect metadata RUN_ID`.
-
-Safe fix: Correct the specific failure and rerun the batch or affected report.
-Do not delete successful reports simply because another item failed.
-
-See also: [Batch commands](cli.md#commands-and-usage) and [Operations](operations.md).
-
-## A batch upload is skipped
-
-Symptom: The batch result says Distributor notification was skipped because
-one or more reports failed.
-
-Likely cause: Batch notification intentionally runs only after every planned
-report succeeds.
-
-Diagnostic: Review the failed report items and their metadata; a skipped batch
-notification is expected while any item is failed.
-
-Safe fix: Resolve the report failures and rerun the batch. Do not upload a
-partial bundle by manually reusing batch artifacts.
-
-See also: [Batch commands](cli.md#commands-and-usage) and [Operations](operations.md).
-
-## Distributor notification fails
-
-Symptom: A completed report or otherwise successful batch reports a Distributor
-error, including a rejected upload, source or idempotency conflict, or service
-unavailability.
-
-Likely cause: Distributor rejected the request identity or bundle, required
-credentials are unavailable, or the remote service cannot be reached.
-
-Diagnostic: Inspect the report metadata or batch result for the notification
-artifact and the error fragment. Verify the configured Distributor endpoint and
-request identity without exposing credentials.
-
-Safe fix: Resolve the reported remote conflict, configuration, or availability
-issue and create a new report or rerun the batch. Do not modify recorded bundle
-or idempotency artifacts to force an upload.
-
-See also: [Configuration](config.md), [Distributor integration](integrations/distributor/pkg-upload.md), and [Operations](operations.md).
 
 ## Secrets cannot be loaded
 
-Symptom: Startup reports `read secrets directory`, `secret file`, or a token
+Secret files must be regular non-symlink files directly beneath
-environment-variable error before the affected service can be used.
+`secrets.directory` with valid environment-variable basenames. Correct the
-
+reported file or directory without placing secret values in YAML.
-Likely cause: The configured secrets directory cannot be read, contains a
-non-regular file, or does not supply the environment variable required by an
-enabled integration.
-
-Diagnostic: Check the configured secrets directory path, ownership, and that
-each intended secret is a regular file. Confirm the variable name from
-configuration only; never print or paste its value.
-
-Safe fix: Correct permissions, file type, or the missing secret file, then
-retry. Keep secret values out of commands, logs, tickets, and artifacts.
-
-See also: [Configuration](config.md) and [Operations](operations.md).
-
-## A run ID or saved state cannot be found
-
-Symptom: An inspection command reports that metadata for a run ID was not
-found, or a report cannot use a prior snapshot.
-
-Likely cause: The run ID is wrong, the configured workspace is different from
-the one that created the run, or no compatible prior snapshot exists.
-
-Diagnostic: Use `weatherreporter inspect reports` to list available reports in
-the current workspace, then copy the run ID from that output. Confirm the
-workspace configuration before retrying a prior-snapshot operation.
-
-Safe fix: Use an existing run ID and its original workspace, or generate a new
-compatible report when no prior snapshot is available. Do not fabricate state
-files or run IDs.
-
-See also: [Inspecting a run](cli.md#inspection-commands) and [Operations](operations.md).
-
-## Workspace paths cannot be read or written
-
-Symptom: Startup or report persistence reports a workspace-path, permission,
-or "must be relative to workspace root" error.
-
-Likely cause: A configured artifact directory escapes the workspace, or the
-current user lacks access to the specific workspace location.
-
-Diagnostic: Check the named configuration path against the configured workspace
-root and inspect ownership and permissions of that exact directory.
-
-Safe fix: Set the path to a location within the workspace or repair access to
-the named directory, then rerun. Do not remove the workspace or broadly relax
-permissions.
-
-See also: [Configuration](config.md) and [Operations](operations.md).

examples/config.yml

@@ -35,9 +35,10 @@ missing_source:
   sources:
     alerts: none
 
-scriptorium:
+promptkit:
-  binary: scriptorium
   timeout: 2m
+  local:
+    concurrency_limit: 1
 
 workspace:
   root: workspace

go.mod

@@ -4,4 +4,12 @@ go 1.26
 
 require gopkg.in/yaml.v3 v3.0.1
 
-require gitea.maximumdirect.net/eric/distributor v0.5.0
+require (
+	gitea.maximumdirect.net/eric/distributor v0.5.0
+	gitea.maximumdirect.net/eric/promptkit v0.4.0
+)
+
+require (
+	github.com/santhosh-tekuri/jsonschema/v6 v6.0.2 // indirect
+	golang.org/x/text v0.14.0 // indirect
+)

go.sum

@@ -1,5 +1,7 @@
 gitea.maximumdirect.net/eric/distributor v0.5.0 h1:+al7Bw+kMv6V35a3Sm5rUtCTQhwOn5b9x3RsclPMKJk=
 gitea.maximumdirect.net/eric/distributor v0.5.0/go.mod h1:G03FCFZPHpsUKC6SeMgTdbfNRpPQBdyTtDUj04e1Tu8=
+gitea.maximumdirect.net/eric/promptkit v0.4.0 h1:WHRQEt3BVBAR7hQePBaGtNXpzrs59mlr/42nQzwgOz4=
+gitea.maximumdirect.net/eric/promptkit v0.4.0/go.mod h1:R95NM6fbMDGDC0/UomgnSBP6ui2ns+8SZb8bESNvrDQ=
 github.com/aws/aws-sdk-go-v2 v1.41.9 h1:/rYeyO2+HrMztAmxAq9++XJtFMqSIpSsNA0yDGALYq4=
 github.com/aws/aws-sdk-go-v2 v1.41.9/go.mod h1:+HsoOEX80qAVUitj1A2DhCNTjmb3edVyuDypb6LNEeo=
 github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.11 h1:h5+3VT69KUBK24grGuuA5saDJTj2IIjLb9au668Fo5I=
@@ -36,16 +38,22 @@ github.com/aws/aws-sdk-go-v2/service/sts v1.42.3 h1:ErklX/7uhSbkAAeyQD/Y1OoQ9hO3
 github.com/aws/aws-sdk-go-v2/service/sts v1.42.3/go.mod h1:ULe4HCzfKPiR6R3HEurE3b1upEkuk8AkMrOKtaOxKO8=
 github.com/aws/smithy-go v1.26.0 h1:9ouqbi+NyKP7fV3Te7UElCwdAb6Y8uk7LGwPE5tVe/s=
 github.com/aws/smithy-go v1.26.0/go.mod h1:YE2RhdIuDbA5E5bTdciG9KrW3+TiEONeUWCqxX9i1Fc=
+github.com/dlclark/regexp2 v1.11.0 h1:G/nrcoOa7ZXlpoa/91N3X7mM3r8eIlMBBJZvsz/mxKI=
+github.com/dlclark/regexp2 v1.11.0/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
 github.com/kr/fs v0.1.0 h1:Jskdu9ieNAYnjxsi0LbQp1ulIKZV1LAFgK1tWhpZgl8=
 github.com/kr/fs v0.1.0/go.mod h1:FFnZGqtBN9Gxj7eW1uZ42v5BccTP0vu6NEaFoC2HwRg=
 github.com/pkg/sftp v1.13.10 h1:+5FbKNTe5Z9aspU88DPIKJ9z2KZoaGCu6Sr6kKR/5mU=
 github.com/pkg/sftp v1.13.10/go.mod h1:bJ1a7uDhrX/4OII+agvy28lzRvQrmIQuaHrcI1HbeGA=
+github.com/santhosh-tekuri/jsonschema/v6 v6.0.2 h1:KRzFb2m7YtdldCEkzs6KqmJw4nqEVZGK7IN2kJkjTuQ=
+github.com/santhosh-tekuri/jsonschema/v6 v6.0.2/go.mod h1:JXeL+ps8p7/KNMjDQk3TCwPpBy0wYklyWTfbkIzdIFU=
 github.com/yuin/goldmark v1.8.2 h1:kEGpgqJXdgbkhcOgBxkC0X0PmoPG1ZyoZ117rDVp4zE=
 github.com/yuin/goldmark v1.8.2/go.mod h1:ip/1k0VRfGynBgxOz0yCqHrbZXhcjxyuS66Brc7iBKg=
 golang.org/x/crypto v0.52.0 h1:RMs7fP2rXdep0CftQlK8Uf+kibLm7qkCcradZWYz988=
 golang.org/x/crypto v0.52.0/go.mod h1:1QgfPxDqh0T2M/elOJtp9RvuR95kVjir0e6/BvEmGbc=
 golang.org/x/sys v0.45.0 h1:dO4czNzziLiiXplLQgBCEpCvXQ3dnkn0SdaZSYdQ+FY=
 golang.org/x/sys v0.45.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
+golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
+golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=

internal/adapters/promptkit/adapter.go

@@ -0,0 +1,322 @@
+// Package promptkitadapter implements promptexec with Promptkit.
+package promptkitadapter
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"time"
+
+	promptkit "gitea.maximumdirect.net/eric/promptkit"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptassets"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptexec"
+)
+
+// Config selects the Promptkit sources and optional local backend for one engine.
+type Config struct {
+	ProfileDirectory      string
+	ProfileFile           string
+	LocalEndpoint         string
+	LocalConcurrencyLimit int
+	Timeout               time.Duration
+}
+
+// Adapter owns one Promptkit engine and its opaque prepared execution handles.
+type Adapter struct {
+	engine *promptkit.Engine
+}
+
+var _ promptexec.Executor = (*Adapter)(nil)
+
+// New constructs a Promptkit-backed executor from Weatherreporter-owned settings.
+func New(config Config) (*Adapter, error) {
+	return newAdapter(config)
+}
+
+func newAdapter(config Config, additionalOptions ...promptkit.Option) (*Adapter, error) {
+	if config.ProfileDirectory != "" && config.ProfileFile != "" {
+		return nil, promptexec.NewError(promptexec.InvalidConfiguration, "profile directory and profile file cannot both be configured", nil)
+	}
+	if config.LocalEndpoint == "" && config.LocalConcurrencyLimit != 0 {
+		return nil, promptexec.NewError(promptexec.InvalidConfiguration, "local concurrency requires a local endpoint", nil)
+	}
+
+	options := []promptkit.Option{
+		promptkit.WithPromptFS(promptassets.PromptFS(), "."),
+		promptkit.WithSchemaFS(promptassets.SchemaFS(), "."),
+	}
+	if config.ProfileFile != "" {
+		options = append(options, promptkit.WithProfileFile(config.ProfileFile))
+	}
+	if config.LocalEndpoint != "" {
+		options = append(options, promptkit.WithBackend(promptkit.LocalBackend(config.LocalEndpoint, config.LocalConcurrencyLimit)))
+	}
+	options = append(options, additionalOptions...)
+	engine, err := promptkit.NewEngine(promptkit.Config{
+		ProfileDir: config.ProfileDirectory,
+		Timeout:    config.Timeout,
+	}, options...)
+	if err != nil {
+		return nil, classifyConfigurationError(err)
+	}
+	return &Adapter{engine: engine}, nil
+}
+
+func newAdapterForTest(config Config, client promptkit.LLMClient) (*Adapter, error) {
+	return newAdapter(config, promptkit.WithLLMClient(client))
+}
+
+// InspectPrompt maps an exact Promptkit prompt inspection into project-owned values.
+func (adapter *Adapter) InspectPrompt(ctx context.Context, promptID string, promptVersion string) (promptexec.PromptInspection, error) {
+	if adapter == nil || adapter.engine == nil {
+		return promptexec.PromptInspection{}, promptexec.NewError(promptexec.InvalidConfiguration, "prompt executor is not configured", nil)
+	}
+	inspection, err := adapter.engine.InspectPrompt(ctx, promptID, promptVersion)
+	if err != nil {
+		return promptexec.PromptInspection{}, classifyError(err)
+	}
+	inputs := make([]promptexec.InputDefinition, len(inspection.Inputs))
+	for index, input := range inspection.Inputs {
+		inputs[index] = promptexec.InputDefinition{
+			Name:        input.Name,
+			Required:    input.Required,
+			ContentType: input.ContentType,
+			Description: input.Description,
+		}
+	}
+	return promptexec.PromptInspection{
+		PromptID:         inspection.PromptID,
+		PromptVersion:    inspection.PromptVersion,
+		PromptHash:       inspection.PromptHash,
+		DefaultProfileID: inspection.DefaultProfileID,
+		Inputs:           inputs,
+		Output:           outputContract(inspection.OutputContract),
+	}, nil
+}
+
+// InspectProfile maps one explicit Promptkit profile inspection into safe values.
+func (adapter *Adapter) InspectProfile(ctx context.Context, profileID string) (promptexec.ProfileInspection, error) {
+	if adapter == nil || adapter.engine == nil {
+		return promptexec.ProfileInspection{}, promptexec.NewError(promptexec.InvalidConfiguration, "prompt executor is not configured", nil)
+	}
+	inspection, err := adapter.engine.InspectProfile(ctx, profileID)
+	if err != nil {
+		return promptexec.ProfileInspection{}, classifyError(err)
+	}
+	return promptexec.ProfileInspection{
+		ProfileID:          inspection.ProfileID,
+		BackendID:          inspection.EffectiveModelParams.BackendID,
+		ModelName:          inspection.EffectiveModelParams.Model,
+		CredentialRequired: inspection.APIKeyRequired,
+		APIKeyEnv:          inspection.EffectiveModelParams.APIKeyEnv,
+	}, nil
+}
+
+// Execute prepares one exact inline data package, invokes prepared after a
+// successful preparation, and then runs the same opaque prepared handle.
+func (adapter *Adapter) Execute(ctx context.Context, request promptexec.ExecuteRequest, preparedCallback promptexec.PreparationCallback) (*promptexec.Execution, error) {
+	if adapter == nil || adapter.engine == nil {
+		return nil, promptexec.NewError(promptexec.InvalidConfiguration, "prompt executor is not configured", nil)
+	}
+	prepared, err := adapter.engine.PrepareExecution(ctx, promptkit.RunRequest{
+		PromptID:      request.PromptID,
+		PromptVersion: request.PromptVersion,
+		ProfileID:     request.ProfileID,
+		Inputs: map[string]promptkit.ArtifactRef{
+			"data_package": promptkit.InlineWithURI(request.DataPackagePath, string(append([]byte(nil), request.DataPackage...))),
+		},
+	})
+	if err != nil {
+		return nil, classifyError(err)
+	}
+	defer prepared.Discard()
+
+	details := prepared.Details()
+	preparation, debug := preparationValues(details, request.DataPackagePath, request.CaptureDebug)
+	if preparedCallback != nil {
+		if err := preparedCallback(preparation, debug); err != nil {
+			return nil, err
+		}
+	}
+
+	result, err := adapter.engine.RunPrepared(ctx, prepared)
+	if err != nil {
+		return nil, classifyError(err)
+	}
+	return executionValue(result, request.DataPackagePath, request.CaptureDebug), nil
+}
+
+func outputContract(value promptkit.OutputContract) promptexec.OutputContract {
+	return promptexec.OutputContract{
+		Format:         string(value.Format),
+		ValidationMode: string(value.ValidationMode),
+		SchemaPath:     value.SchemaPath,
+	}
+}
+
+func preparationValues(value promptkit.PreparedRun, dataPackagePath string, captureDebug bool) (promptexec.Preparation, *promptexec.PreparationDebug) {
+	preparation := promptexec.Preparation{
+		PromptID:           value.PromptID,
+		PromptVersion:      value.PromptVersion,
+		PromptHash:         value.PromptHash,
+		RenderedPromptHash: value.RenderedPromptHash,
+		InputHashes:        copyInputHashes(value.InputHashes),
+		ProfileID:          value.SelectedProfileID,
+		BackendID:          value.SelectedBackendID,
+		ModelName:          value.EffectiveModelParams.Model,
+		Output:             outputContract(value.OutputContract),
+		StartedAt:          value.StartTime,
+		EndedAt:            value.EndTime,
+		Duration:           time.Duration(value.DurationMS) * time.Millisecond,
+		DataPackagePath:    dataPackagePath,
+	}
+	if !captureDebug {
+		return preparation, nil
+	}
+	debug := &promptexec.PreparationDebug{
+		RenderedMessages: renderedMessages(value.Messages),
+		Endpoint:         value.EffectiveModelParams.Endpoint,
+		ParametersJSON:   marshalDebugParameters(value.EffectiveModelParams),
+	}
+	if value.StructuredOutput != nil && value.StructuredOutput.JSONSchema != nil {
+		debug.StructuredSchema, _ = json.Marshal(value.StructuredOutput.JSONSchema.Schema)
+	}
+	return preparation, debug
+}
+
+func executionValue(value *promptkit.RunResult, dataPackagePath string, captureDebug bool) *promptexec.Execution {
+	if value == nil {
+		return nil
+	}
+	validation := promptexec.NewValidation(
+		promptexec.ValidationStatus(value.Validation.Status),
+		string(value.Validation.Mode),
+		value.Validation.SchemaPath,
+		value.Validation.Errors,
+	)
+	execution := &promptexec.Execution{
+		RunID:              value.RunID,
+		PromptID:           value.PromptID,
+		PromptVersion:      value.PromptVersion,
+		PromptHash:         value.PromptHash,
+		RenderedPromptHash: value.RenderedPromptHash,
+		InputHashes:        copyInputHashes(value.InputHashes),
+		ProfileID:          value.SelectedProfileID,
+		BackendID:          value.SelectedBackendID,
+		ModelName:          value.ModelName,
+		GeneratedHash:      value.Artifact.Hash,
+		Usage: promptexec.TokenUsage{
+			PromptTokens:     value.Usage.PromptTokens,
+			CompletionTokens: value.Usage.CompletionTokens,
+			TotalTokens:      value.Usage.TotalTokens,
+			CachedTokens:     value.Usage.CachedTokens,
+			CacheWriteTokens: value.Usage.CacheWriteTokens,
+		},
+		StartedAt:       value.StartTime,
+		EndedAt:         value.EndTime,
+		Duration:        value.Duration,
+		Validation:      validation,
+		DataPackagePath: dataPackagePath,
+		RawOutput:       []byte(value.RawOutput),
+	}
+	if captureDebug {
+		execution.Debug = &promptexec.ExecutionDebug{
+			RawOutput:             append([]byte(nil), value.RawOutput...),
+			ValidationDiagnostics: append([]string(nil), validation.Diagnostics...),
+		}
+	}
+	return execution
+}
+
+func renderedMessages(values []promptkit.RenderedMessage) []promptexec.RenderedMessage {
+	messages := make([]promptexec.RenderedMessage, len(values))
+	for index, value := range values {
+		messages[index] = promptexec.RenderedMessage{Role: value.Role, Content: value.Content}
+	}
+	return messages
+}
+
+func copyInputHashes(values map[string]string) map[string]string {
+	if values == nil {
+		return nil
+	}
+	copy := make(map[string]string, len(values))
+	for key, value := range values {
+		copy[key] = value
+	}
+	return copy
+}
+
+func marshalDebugParameters(value promptkit.ExecutionTarget) []byte {
+	parameters := struct {
+		Temperature     float64        `json:"temperature"`
+		MaxTokens       int            `json:"max_tokens"`
+		TopP            float64        `json:"top_p"`
+		TimeoutSeconds  int            `json:"timeout_seconds"`
+		ServiceTier     string         `json:"service_tier"`
+		ReasoningEffort string         `json:"reasoning_effort"`
+		ExtraParams     map[string]any `json:"extra_params"`
+	}{
+		Temperature:     value.Temperature,
+		MaxTokens:       value.MaxTokens,
+		TopP:            value.TopP,
+		TimeoutSeconds:  value.TimeoutSeconds,
+		ServiceTier:     value.ServiceTier,
+		ReasoningEffort: value.ReasoningEffort,
+		ExtraParams:     value.ExtraParams,
+	}
+	data, _ := json.Marshal(parameters)
+	return data
+}
+
+func classifyConfigurationError(err error) error {
+	if err == nil {
+		return nil
+	}
+	return promptexec.NewError(promptexec.InvalidConfiguration, "prompt executor configuration is invalid", err)
+}
+
+func classifyError(err error) error {
+	if err == nil {
+		return nil
+	}
+	if errors.Is(err, context.Canceled) {
+		return promptexec.NewError(promptexec.Canceled, "prompt operation was canceled", err)
+	}
+	if errors.Is(err, context.DeadlineExceeded) {
+		return promptexec.NewError(promptexec.DeadlineExceeded, "prompt operation exceeded its deadline", err)
+	}
+	var capacityError *promptkit.CapacityError
+	if errors.As(err, &capacityError) {
+		return promptexec.NewCapacityError(capacityError.BackendID, "prompt backend capacity is unavailable", err)
+	}
+	switch {
+	case errors.Is(err, promptkit.ErrInvalidConfig):
+		return promptexec.NewError(promptexec.InvalidConfiguration, "prompt executor configuration is invalid", err)
+	case errors.Is(err, promptkit.ErrPromptNotFound):
+		return promptexec.NewError(promptexec.PromptNotFound, "prompt definition was not found", err)
+	case errors.Is(err, promptkit.ErrPromptLoad):
+		return promptexec.NewError(promptexec.PromptLoad, "prompt definition could not be loaded", err)
+	case errors.Is(err, promptkit.ErrProfileNotFound):
+		return promptexec.NewError(promptexec.ProfileNotFound, "execution profile was not found", err)
+	case errors.Is(err, promptkit.ErrProfileLoad):
+		return promptexec.NewError(promptexec.ProfileLoad, "execution profile could not be loaded", err)
+	case errors.Is(err, promptkit.ErrAPIKeyEnvMissing):
+		return promptexec.NewError(promptexec.MissingCredential, "execution credential is unavailable", err)
+	case errors.Is(err, promptkit.ErrArtifactLoad):
+		return promptexec.NewError(promptexec.ArtifactLoad, "prompt input could not be loaded", err)
+	case errors.Is(err, promptkit.ErrPromptRender):
+		return promptexec.NewError(promptexec.PromptRender, "prompt could not be rendered", err)
+	case errors.Is(err, promptkit.ErrCapacityExceeded):
+		return promptexec.NewCapacityError("", "prompt backend capacity is unavailable", err)
+	case errors.Is(err, promptkit.ErrLLMGenerate):
+		return promptexec.NewError(promptexec.Generation, "prompt generation failed", err)
+	case errors.Is(err, promptkit.ErrValidation):
+		return promptexec.NewError(promptexec.OperationalValidation, "prompt output validation could not be completed", err)
+	case errors.Is(err, promptkit.ErrInvalidRequest), errors.Is(err, promptkit.ErrProfileRequired):
+		return promptexec.NewError(promptexec.InvalidRequest, "prompt execution request is invalid", err)
+	default:
+		return promptexec.NewError(promptexec.Generation, "prompt operation failed", fmt.Errorf("%w", err))
+	}
+}

internal/adapters/promptkit/adapter_test.go

@@ -0,0 +1,384 @@
+package promptkitadapter
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"sync"
+	"testing"
+	"time"
+
+	promptkit "gitea.maximumdirect.net/eric/promptkit"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptexec"
+)
+
+type fakeClient struct {
+	mu       sync.Mutex
+	response *promptkit.GenerateResponse
+	err      error
+	calls    int
+	requests []promptkit.GenerateRequest
+	block    bool
+}
+
+type recordingReader struct {
+	ref promptkit.ArtifactRef
+}
+
+func (reader *recordingReader) Read(_ context.Context, ref promptkit.ArtifactRef) (*promptkit.Artifact, error) {
+	reader.ref = ref
+	return &promptkit.Artifact{
+		Name:        "data_package",
+		ContentType: "application/yaml",
+		Body:        []byte(ref.Body),
+		URI:         ref.URI,
+		Hash:        "input-hash",
+	}, nil
+}
+
+func (client *fakeClient) Generate(ctx context.Context, request promptkit.GenerateRequest) (*promptkit.GenerateResponse, error) {
+	client.mu.Lock()
+	client.calls++
+	client.requests = append(client.requests, request)
+	block := client.block
+	response := client.response
+	err := client.err
+	client.mu.Unlock()
+	if block {
+		<-ctx.Done()
+		return nil, ctx.Err()
+	}
+	return response, err
+}
+
+func (client *fakeClient) callCount() int {
+	client.mu.Lock()
+	defer client.mu.Unlock()
+	return client.calls
+}
+
+func (client *fakeClient) request() promptkit.GenerateRequest {
+	client.mu.Lock()
+	defer client.mu.Unlock()
+	return client.requests[0]
+}
+
+func TestInspectPromptAndProfile(t *testing.T) {
+	adapter := newTestAdapter(t, &fakeClient{})
+	inspection, err := adapter.InspectPrompt(context.Background(), "weather.daily_generated_text", "1.0.0")
+	if err != nil {
+		t.Fatalf("InspectPrompt() error = %v", err)
+	}
+	if inspection.PromptID != "weather.daily_generated_text" || inspection.PromptVersion != "1.0.0" || inspection.DefaultProfileID != "gemini-flash-latest" {
+		t.Fatalf("inspection = %#v", inspection)
+	}
+	if len(inspection.Inputs) != 1 || inspection.Inputs[0].Name != "data_package" || !inspection.Inputs[0].Required || inspection.Inputs[0].ContentType != "application/yaml" {
+		t.Fatalf("inputs = %#v", inspection.Inputs)
+	}
+	if inspection.Output.Format != "json" || inspection.Output.ValidationMode != "json_schema" || inspection.Output.SchemaPath != "daily.generated_text.schema.json" {
+		t.Fatalf("output = %#v", inspection.Output)
+	}
+
+	profile, err := adapter.InspectProfile(context.Background(), "test-profile")
+	if err != nil {
+		t.Fatalf("InspectProfile() error = %v", err)
+	}
+	if profile.ProfileID != "test-profile" || profile.BackendID != "" || profile.ModelName != "test-model" || profile.CredentialRequired {
+		t.Fatalf("profile = %#v", profile)
+	}
+	if strings.Contains(fmt.Sprintf("%#v", profile), "https://profile.example") {
+		t.Fatalf("profile leaks endpoint: %#v", profile)
+	}
+
+	builtin, err := adapter.InspectProfile(context.Background(), "gemini-flash-latest")
+	if err != nil {
+		t.Fatalf("InspectProfile(builtin) error = %v", err)
+	}
+	if builtin.ProfileID != "gemini-flash-latest" || builtin.ModelName == "" {
+		t.Fatalf("builtin profile = %#v", builtin)
+	}
+}
+
+func TestExecuteUsesPreparedInlineDataPackage(t *testing.T) {
+	client := &fakeClient{response: validResponse()}
+	adapter := newTestAdapter(t, client)
+	request := testExecuteRequest()
+	callbackCalls := 0
+	result, err := adapter.Execute(context.Background(), request, func(preparation promptexec.Preparation, debug *promptexec.PreparationDebug) error {
+		callbackCalls++
+		if preparation.PromptID != request.PromptID || preparation.PromptVersion != request.PromptVersion || preparation.DataPackagePath != request.DataPackagePath || preparation.ModelName != "test-model" {
+			t.Fatalf("preparation = %#v", preparation)
+		}
+		if debug != nil {
+			t.Fatalf("debug = %#v, want nil", debug)
+		}
+		if client.callCount() != 0 {
+			t.Fatal("provider called before preparation callback")
+		}
+		return nil
+	})
+	if err != nil {
+		t.Fatalf("Execute() error = %v", err)
+	}
+	if callbackCalls != 1 || client.callCount() != 1 {
+		t.Fatalf("callback/provider calls = %d/%d, want 1/1", callbackCalls, client.callCount())
+	}
+	if result == nil || result.Validation.Status != promptexec.ValidationPassed || string(result.RawOutput) != client.response.Content || result.DataPackagePath != request.DataPackagePath {
+		t.Fatalf("result = %#v", result)
+	}
+	if result.Debug != nil {
+		t.Fatalf("debug = %#v, want nil", result.Debug)
+	}
+	providerRequest := client.request()
+	if providerRequest.Target.Model != "test-model" || providerRequest.Target.Endpoint != "https://profile.example/v1" {
+		t.Fatalf("provider target = %#v", providerRequest.Target)
+	}
+	if len(providerRequest.Prompt.Messages) == 0 || !strings.Contains(providerRequest.Prompt.Messages[2].Content, string(request.DataPackage)) {
+		t.Fatalf("rendered messages do not contain exact data package: %#v", providerRequest.Prompt.Messages)
+	}
+}
+
+func TestExecuteUsesExactInlineDataPackageProvenance(t *testing.T) {
+	client := &fakeClient{response: validResponse()}
+	reader := &recordingReader{}
+	adapter := newTestAdapterWithOptions(t, client, promptkit.WithArtifactReader(reader))
+	request := testExecuteRequest()
+	if _, err := adapter.Execute(context.Background(), request, nil); err != nil {
+		t.Fatalf("Execute() error = %v", err)
+	}
+	if reader.ref.Type != promptkit.ArtifactRefInline || reader.ref.URI != request.DataPackagePath || reader.ref.Body != string(request.DataPackage) {
+		t.Fatalf("artifact ref = %#v, want exact inline data package provenance", reader.ref)
+	}
+}
+
+func TestExecuteCapturesSensitiveDebugOnlyWhenRequested(t *testing.T) {
+	client := &fakeClient{response: validResponse()}
+	adapter := newTestAdapter(t, client)
+	request := testExecuteRequest()
+	request.CaptureDebug = true
+	var preparationDebug *promptexec.PreparationDebug
+	result, err := adapter.Execute(context.Background(), request, func(preparation promptexec.Preparation, debug *promptexec.PreparationDebug) error {
+		preparationDebug = debug
+		if strings.Contains(fmt.Sprintf("%#v", preparation), "https://profile.example") || strings.Contains(fmt.Sprintf("%#v", preparation), string(request.DataPackage)) {
+			t.Fatalf("safe preparation leaks sensitive content: %#v", preparation)
+		}
+		return nil
+	})
+	if err != nil {
+		t.Fatalf("Execute() error = %v", err)
+	}
+	if preparationDebug == nil || preparationDebug.Endpoint != "https://profile.example/v1" || len(preparationDebug.RenderedMessages) == 0 || len(preparationDebug.StructuredSchema) == 0 || len(preparationDebug.ParametersJSON) == 0 {
+		t.Fatalf("preparation debug = %#v", preparationDebug)
+	}
+	if result.Debug == nil || string(result.Debug.RawOutput) != client.response.Content {
+		t.Fatalf("execution debug = %#v", result.Debug)
+	}
+}
+
+func TestExecuteCallbackFailurePreventsGeneration(t *testing.T) {
+	client := &fakeClient{response: validResponse()}
+	adapter := newTestAdapter(t, client)
+	callbackError := errors.New("save preparation")
+	result, err := adapter.Execute(context.Background(), testExecuteRequest(), func(promptexec.Preparation, *promptexec.PreparationDebug) error {
+		return callbackError
+	})
+	if result != nil || !errors.Is(err, callbackError) || client.callCount() != 0 {
+		t.Fatalf("result/error/provider calls = %#v/%v/%d", result, err, client.callCount())
+	}
+}
+
+func TestExecuteReturnsCompletedValidationRejection(t *testing.T) {
+	client := &fakeClient{response: &promptkit.GenerateResponse{Content: `{"summary":42}`, Usage: promptkit.TokenUsage{TotalTokens: 5}}}
+	adapter := newTestAdapter(t, client)
+	result, err := adapter.Execute(context.Background(), testExecuteRequest(), nil)
+	if err != nil {
+		t.Fatalf("Execute() error = %v", err)
+	}
+	if result == nil || result.Validation.Status != promptexec.ValidationFailed || len(result.Validation.Diagnostics) == 0 || string(result.RawOutput) != client.response.Content {
+		t.Fatalf("result = %#v", result)
+	}
+}
+
+func TestExecuteClassifiesOperationalFailures(t *testing.T) {
+	tests := []struct {
+		name     string
+		client   *fakeClient
+		context  func() (context.Context, context.CancelFunc)
+		category promptexec.ErrorCategory
+	}{
+		{
+			name:   "generation",
+			client: &fakeClient{err: errors.New("provider response body")},
+			context: func() (context.Context, context.CancelFunc) {
+				return context.WithCancel(context.Background())
+			},
+			category: promptexec.Generation,
+		},
+		{
+			name:   "canceled",
+			client: &fakeClient{block: true},
+			context: func() (context.Context, context.CancelFunc) {
+				ctx, cancel := context.WithCancel(context.Background())
+				cancel()
+				return ctx, func() {}
+			},
+			category: promptexec.Canceled,
+		},
+		{
+			name:   "deadline",
+			client: &fakeClient{block: true},
+			context: func() (context.Context, context.CancelFunc) {
+				return context.WithTimeout(context.Background(), time.Nanosecond)
+			},
+			category: promptexec.DeadlineExceeded,
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			adapter := newTestAdapter(t, test.client)
+			ctx, cancel := test.context()
+			defer cancel()
+			result, err := adapter.Execute(ctx, testExecuteRequest(), nil)
+			if result != nil || err == nil || promptexec.CategoryOf(err) != test.category {
+				t.Fatalf("result/error/category = %#v/%v/%q, want %q", result, err, promptexec.CategoryOf(err), test.category)
+			}
+			if strings.Contains(err.Error(), "provider response body") {
+				t.Fatalf("error leaks provider detail: %v", err)
+			}
+		})
+	}
+}
+
+func TestClassifyPromptkitErrors(t *testing.T) {
+	tests := []struct {
+		err      error
+		category promptexec.ErrorCategory
+	}{
+		{promptkit.ErrInvalidConfig, promptexec.InvalidConfiguration},
+		{promptkit.ErrInvalidRequest, promptexec.InvalidRequest},
+		{promptkit.ErrPromptNotFound, promptexec.PromptNotFound},
+		{promptkit.ErrPromptLoad, promptexec.PromptLoad},
+		{promptkit.ErrProfileNotFound, promptexec.ProfileNotFound},
+		{promptkit.ErrProfileLoad, promptexec.ProfileLoad},
+		{promptkit.ErrAPIKeyEnvMissing, promptexec.MissingCredential},
+		{promptkit.ErrArtifactLoad, promptexec.ArtifactLoad},
+		{promptkit.ErrPromptRender, promptexec.PromptRender},
+		{promptkit.ErrLLMGenerate, promptexec.Generation},
+		{promptkit.ErrValidation, promptexec.OperationalValidation},
+		{&promptkit.CapacityError{BackendID: "local"}, promptexec.Capacity},
+	}
+	for _, test := range tests {
+		t.Run(string(test.category), func(t *testing.T) {
+			got := classifyError(test.err)
+			if promptexec.CategoryOf(got) != test.category {
+				t.Fatalf("category = %q, want %q", promptexec.CategoryOf(got), test.category)
+			}
+		})
+	}
+}
+
+func TestNewValidatesConfiguration(t *testing.T) {
+	if _, err := New(Config{ProfileDirectory: "profiles", ProfileFile: "profile.yml"}); promptexec.CategoryOf(err) != promptexec.InvalidConfiguration {
+		t.Fatalf("profile source error = %v", err)
+	}
+	if _, err := New(Config{LocalConcurrencyLimit: 1}); promptexec.CategoryOf(err) != promptexec.InvalidConfiguration {
+		t.Fatalf("local concurrency error = %v", err)
+	}
+	if _, err := New(Config{LocalEndpoint: "not a URL"}); promptexec.CategoryOf(err) != promptexec.InvalidConfiguration {
+		t.Fatalf("local endpoint error = %v", err)
+	}
+}
+
+func TestLocalBackendAndMissingCredentialBehavior(t *testing.T) {
+	profiles := testProfileDirectory(t, `id: local-profile
+backend: local
+model: local-model
+`)
+	adapter, err := newAdapterForTest(Config{
+		ProfileDirectory:      profiles,
+		LocalEndpoint:         "https://local.example/v1",
+		LocalConcurrencyLimit: 1,
+	}, &fakeClient{})
+	if err != nil {
+		t.Fatalf("newAdapterForTest(local) error = %v", err)
+	}
+	profile, err := adapter.InspectProfile(context.Background(), "local-profile")
+	if err != nil || profile.BackendID != promptkit.BackendLocal || profile.ModelName != "local-model" {
+		t.Fatalf("local profile/error = %#v/%v", profile, err)
+	}
+	if got := classifyError(&promptkit.CapacityError{BackendID: promptkit.BackendLocal}); promptexec.CategoryOf(got) != promptexec.Capacity {
+		t.Fatalf("capacity classification = %v", got)
+	}
+
+	credentialProfiles := testProfileDirectory(t, `id: credential-profile
+endpoint: https://profile.example/v1
+model: test-model
+api_key_env: WEATHERREPORTER_TEST_MISSING_KEY
+`)
+	client := &fakeClient{response: validResponse()}
+	credentialAdapter, err := newAdapterForTest(Config{ProfileDirectory: credentialProfiles}, client)
+	if err != nil {
+		t.Fatalf("newAdapterForTest(credential) error = %v", err)
+	}
+	credentialProfile, err := credentialAdapter.InspectProfile(context.Background(), "credential-profile")
+	if err != nil || credentialProfile.CredentialRequired || credentialProfile.APIKeyEnv != "WEATHERREPORTER_TEST_MISSING_KEY" {
+		t.Fatalf("credential profile/error = %#v/%v", credentialProfile, err)
+	}
+	request := testExecuteRequest()
+	request.ProfileID = "credential-profile"
+	result, err := credentialAdapter.Execute(context.Background(), request, nil)
+	if result != nil || promptexec.CategoryOf(err) != promptexec.MissingCredential || client.callCount() != 0 {
+		t.Fatalf("credential result/category/calls = %#v/%q/%d", result, promptexec.CategoryOf(err), client.callCount())
+	}
+}
+
+func newTestAdapter(t *testing.T, client promptkit.LLMClient) *Adapter {
+	return newTestAdapterWithOptions(t, client)
+}
+
+func newTestAdapterWithOptions(t *testing.T, client promptkit.LLMClient, options ...promptkit.Option) *Adapter {
+	t.Helper()
+	profiles := testProfileDirectory(t, `id: test-profile
+endpoint: https://profile.example/v1
+model: test-model
+temperature: 0.2
+max_tokens: 300
+top_p: 1
+timeout_seconds: 30
+`)
+	options = append(options, promptkit.WithLLMClient(client))
+	adapter, err := newAdapter(Config{ProfileDirectory: profiles, Timeout: time.Second}, options...)
+	if err != nil {
+		t.Fatalf("newAdapter() error = %v", err)
+	}
+	return adapter
+}
+
+func testProfileDirectory(t *testing.T, profile string) string {
+	t.Helper()
+	profiles := t.TempDir()
+	if err := os.WriteFile(filepath.Join(profiles, "profile.yml"), []byte(profile), 0o600); err != nil {
+		t.Fatalf("write profile: %v", err)
+	}
+	return profiles
+}
+
+func testExecuteRequest() promptexec.ExecuteRequest {
+	return promptexec.ExecuteRequest{
+		PromptID:        "weather.daily_generated_text",
+		PromptVersion:   "1.0.0",
+		ProfileID:       "test-profile",
+		DataPackage:     []byte("report:\n  id: daily\nbriefing: {}\n"),
+		DataPackagePath: "data-packages/daily/data_package.yaml",
+	}
+}
+
+func validResponse() *promptkit.GenerateResponse {
+	return &promptkit.GenerateResponse{
+		Content: `{"summary":"A quiet day is expected.","forecast_discussion":["High pressure keeps conditions settled."],"confidence":"High."}`,
+		Usage:   promptkit.TokenUsage{PromptTokens: 12, CompletionTokens: 8, TotalTokens: 20},
+	}
+}

internal/adapters/scriptorium/runner.go

@@ -1,338 +0,0 @@
-// Package scriptorium adapts the external scriptorium CLI.
-package scriptorium
-
-import (
-	"context"
-	"fmt"
-	"io"
-	"os/exec"
-	"time"
-)
-
-const maxCapturedOutputBytes = 1024 * 1024
-
-type CommandRunner interface {
-	Run(ctx context.Context, name string, args []string, timeout time.Duration) (CommandResult, error)
-}
-
-type CommandResult struct {
-	Stdout          []byte
-	Stderr          []byte
-	StdoutTruncated bool
-	StderrTruncated bool
-	ExitCode        int
-}
-
-type ExecRunner struct{}
-
-func (ExecRunner) Run(ctx context.Context, name string, args []string, timeout time.Duration) (CommandResult, error) {
-	runCtx := ctx
-	cancel := func() {}
-	if timeout > 0 {
-		runCtx, cancel = context.WithTimeout(ctx, timeout)
-	}
-	defer cancel()
-
-	cmd := exec.CommandContext(runCtx, name, args...)
-	stdout := &limitedBuffer{limit: maxCapturedOutputBytes}
-	stderr := &limitedBuffer{limit: maxCapturedOutputBytes}
-	cmd.Stdout = stdout
-	cmd.Stderr = stderr
-	err := cmd.Run()
-	result := CommandResult{
-		Stdout:          stdout.Bytes(),
-		Stderr:          stderr.Bytes(),
-		StdoutTruncated: stdout.Truncated(),
-		StderrTruncated: stderr.Truncated(),
-		ExitCode:        0,
-	}
-	if err == nil {
-		return result, nil
-	}
-	if runCtx.Err() != nil {
-		return result, runCtx.Err()
-	}
-	if exitErr, ok := err.(*exec.ExitError); ok {
-		result.ExitCode = exitErr.ExitCode()
-		return result, nil
-	}
-	return result, err
-}
-
-type Runner struct {
-	Binary     string
-	ConfigPath string
-	Profile    string
-	Timeout    time.Duration
-	ExtraArgs  []string
-	Commands   CommandRunner
-}
-
-type RenderRequest struct {
-	PromptID        string
-	DataPackagePath string
-}
-
-type RunRequest struct {
-	PromptID        string
-	DataPackagePath string
-	OutputPath      string
-}
-
-type StructuredRunRequest struct {
-	PromptID        string
-	DataPackagePath string
-	OutputPath      string
-}
-
-type RenderResult struct {
-	Command         []string `json:"command"`
-	Stdout          string   `json:"stdout"`
-	Stderr          string   `json:"stderr"`
-	StdoutTruncated bool     `json:"stdoutTruncated,omitempty"`
-	StderrTruncated bool     `json:"stderrTruncated,omitempty"`
-	ExitCode        int      `json:"exitCode"`
-}
-
-type RunResult struct {
-	Command         []string `json:"command"`
-	Stdout          string   `json:"stdout"`
-	Stderr          string   `json:"stderr"`
-	StdoutTruncated bool     `json:"stdoutTruncated,omitempty"`
-	StderrTruncated bool     `json:"stderrTruncated,omitempty"`
-	ExitCode        int      `json:"exitCode"`
-	OutputPath      string   `json:"outputPath"`
-}
-
-type StructuredRunResult struct {
-	Command         []string `json:"command"`
-	Stdout          string   `json:"stdout"`
-	Stderr          string   `json:"stderr"`
-	StdoutTruncated bool     `json:"stdoutTruncated,omitempty"`
-	StderrTruncated bool     `json:"stderrTruncated,omitempty"`
-	ExitCode        int      `json:"exitCode"`
-	OutputPath      string   `json:"outputPath"`
-}
-
-func (r Runner) Render(ctx context.Context, req RenderRequest) (*RenderResult, error) {
-	if req.PromptID == "" {
-		return nil, fmt.Errorf("prompt id is required")
-	}
-	if req.DataPackagePath == "" {
-		return nil, fmt.Errorf("data package path is required")
-	}
-	execution, err := r.execute(ctx, r.renderArgs(req))
-	if err != nil {
-		return nil, fmt.Errorf("run scriptorium render: %w", err)
-	}
-	result := &RenderResult{
-		Command:         execution.argv(),
-		Stdout:          string(execution.result.Stdout),
-		Stderr:          string(execution.result.Stderr),
-		StdoutTruncated: execution.result.StdoutTruncated,
-		StderrTruncated: execution.result.StderrTruncated,
-		ExitCode:        execution.result.ExitCode,
-	}
-	if execution.result.ExitCode != 0 {
-		return result, fmt.Errorf("scriptorium render exited with code %d: %s", execution.result.ExitCode, result.Stderr)
-	}
-	return result, nil
-}
-
-func (r Runner) Run(ctx context.Context, req RunRequest) (*RunResult, error) {
-	result, err := r.executeRun(ctx, outputRunRequest{
-		PromptID:        req.PromptID,
-		DataPackagePath: req.DataPackagePath,
-		OutputPath:      req.OutputPath,
-	}, "run scriptorium", "scriptorium run")
-	if err != nil {
-		if result == nil {
-			return nil, err
-		}
-		return result.runResult(), err
-	}
-	return result.runResult(), nil
-}
-
-func (r Runner) StructuredRun(ctx context.Context, req StructuredRunRequest) (*StructuredRunResult, error) {
-	result, err := r.executeRun(ctx, outputRunRequest{
-		PromptID:        req.PromptID,
-		DataPackagePath: req.DataPackagePath,
-		OutputPath:      req.OutputPath,
-	}, "run scriptorium structured output", "scriptorium structured run")
-	if err != nil {
-		if result == nil {
-			return nil, err
-		}
-		return result.structuredRunResult(), err
-	}
-	return result.structuredRunResult(), nil
-}
-
-func (result outputRunResult) runResult() *RunResult {
-	return &RunResult{
-		Command:         result.Command,
-		Stdout:          result.Stdout,
-		Stderr:          result.Stderr,
-		StdoutTruncated: result.StdoutTruncated,
-		StderrTruncated: result.StderrTruncated,
-		ExitCode:        result.ExitCode,
-		OutputPath:      result.OutputPath,
-	}
-}
-
-func (result outputRunResult) structuredRunResult() *StructuredRunResult {
-	return &StructuredRunResult{
-		Command:         result.Command,
-		Stdout:          result.Stdout,
-		Stderr:          result.Stderr,
-		StdoutTruncated: result.StdoutTruncated,
-		StderrTruncated: result.StderrTruncated,
-		ExitCode:        result.ExitCode,
-		OutputPath:      result.OutputPath,
-	}
-}
-
-type execution struct {
-	binary string
-	args   []string
-	result CommandResult
-}
-
-type outputRunRequest struct {
-	PromptID        string
-	DataPackagePath string
-	OutputPath      string
-}
-
-type outputRunResult struct {
-	Command         []string
-	Stdout          string
-	Stderr          string
-	StdoutTruncated bool
-	StderrTruncated bool
-	ExitCode        int
-	OutputPath      string
-}
-
-func (r Runner) executeRun(ctx context.Context, req outputRunRequest, executeContext string, exitContext string) (*outputRunResult, error) {
-	if req.PromptID == "" {
-		return nil, fmt.Errorf("prompt id is required")
-	}
-	if req.DataPackagePath == "" {
-		return nil, fmt.Errorf("data package path is required")
-	}
-	if req.OutputPath == "" {
-		return nil, fmt.Errorf("output path is required")
-	}
-	execution, err := r.execute(ctx, r.runArgs(RunRequest{
-		PromptID:        req.PromptID,
-		DataPackagePath: req.DataPackagePath,
-		OutputPath:      req.OutputPath,
-	}))
-	if err != nil {
-		return nil, fmt.Errorf("%s: %w", executeContext, err)
-	}
-	result := &outputRunResult{
-		Command:         execution.argv(),
-		Stdout:          string(execution.result.Stdout),
-		Stderr:          string(execution.result.Stderr),
-		StdoutTruncated: execution.result.StdoutTruncated,
-		StderrTruncated: execution.result.StderrTruncated,
-		ExitCode:        execution.result.ExitCode,
-		OutputPath:      req.OutputPath,
-	}
-	if execution.result.ExitCode != 0 {
-		return result, fmt.Errorf("%s exited with code %d: %s", exitContext, execution.result.ExitCode, result.Stderr)
-	}
-	return result, nil
-}
-
-func (r Runner) execute(ctx context.Context, args []string) (execution, error) {
-	binary := r.Binary
-	if binary == "" {
-		binary = "scriptorium"
-	}
-	commands := r.Commands
-	if commands == nil {
-		commands = ExecRunner{}
-	}
-	result, err := commands.Run(ctx, binary, args, r.Timeout)
-	if err != nil {
-		return execution{}, err
-	}
-	return execution{binary: binary, args: args, result: result}, nil
-}
-
-func (e execution) argv() []string {
-	return append([]string{e.binary}, e.args...)
-}
-
-func (r Runner) renderArgs(req RenderRequest) []string {
-	args := []string{"render"}
-	if r.ConfigPath != "" {
-		args = append(args, "--config", r.ConfigPath)
-	}
-	if r.Profile != "" {
-		args = append(args, "--profile", r.Profile)
-	}
-	args = append(args,
-		"--prompt", req.PromptID,
-		"--input", "data_package="+req.DataPackagePath,
-		"--format", "json",
-	)
-	args = append(args, r.ExtraArgs...)
-	return args
-}
-
-func (r Runner) runArgs(req RunRequest) []string {
-	args := []string{"run"}
-	if r.ConfigPath != "" {
-		args = append(args, "--config", r.ConfigPath)
-	}
-	if r.Profile != "" {
-		args = append(args, "--profile", r.Profile)
-	}
-	args = append(args,
-		"--prompt", req.PromptID,
-		"--input", "data_package="+req.DataPackagePath,
-		"--out", req.OutputPath,
-	)
-	args = append(args, r.ExtraArgs...)
-	return args
-}
-
-type limitedBuffer struct {
-	data      []byte
-	limit     int
-	truncated bool
-}
-
-func (b *limitedBuffer) Write(p []byte) (int, error) {
-	if b.limit <= 0 {
-		b.truncated = true
-		return len(p), nil
-	}
-	remaining := b.limit - len(b.data)
-	if remaining <= 0 {
-		b.truncated = true
-		return len(p), nil
-	}
-	if len(p) > remaining {
-		b.data = append(b.data, p[:remaining]...)
-		b.truncated = true
-		return len(p), nil
-	}
-	b.data = append(b.data, p...)
-	return len(p), nil
-}
-
-func (b *limitedBuffer) Bytes() []byte {
-	return append([]byte{}, b.data...)
-}
-
-func (b *limitedBuffer) Truncated() bool {
-	return b.truncated
-}
-
-var _ io.Writer = (*limitedBuffer)(nil)

internal/adapters/scriptorium/runner_test.go

@@ -1,544 +0,0 @@
-package scriptorium
-
-import (
-	"context"
-	"fmt"
-	"reflect"
-	"strings"
-	"testing"
-	"time"
-)
-
-func TestRenderConstructsCommand(t *testing.T) {
-	commands := &fakeCommands{result: CommandResult{Stdout: []byte(`{"ok":true}`)}}
-	runner := Runner{
-		Binary:     "/usr/local/bin/scriptorium",
-		ConfigPath: "/etc/scriptorium.yml",
-		Profile:    "weather",
-		Timeout:    time.Minute,
-		Commands:   commands,
-	}
-
-	result, err := runner.Render(context.Background(), RenderRequest{
-		PromptID:        "weather.markdown_report",
-		DataPackagePath: "/tmp/data_package.yaml",
-	})
-	if err != nil {
-		t.Fatalf("Render() error = %v", err)
-	}
-
-	wantArgs := []string{
-		"render",
-		"--config", "/etc/scriptorium.yml",
-		"--profile", "weather",
-		"--prompt", "weather.markdown_report",
-		"--input", "data_package=/tmp/data_package.yaml",
-		"--format", "json",
-	}
-	if commands.name != "/usr/local/bin/scriptorium" {
-		t.Fatalf("command name = %q, want custom binary", commands.name)
-	}
-	if !reflect.DeepEqual(commands.args, wantArgs) {
-		t.Fatalf("args = %#v, want %#v", commands.args, wantArgs)
-	}
-	if !reflect.DeepEqual(result.Command, append([]string{"/usr/local/bin/scriptorium"}, wantArgs...)) {
-		t.Fatalf("result command = %#v, want full argv", result.Command)
-	}
-}
-
-func TestRenderReturnsResultForNonzeroExit(t *testing.T) {
-	runner := Runner{
-		Commands: &fakeCommands{
-			result: CommandResult{
-				Stderr:   []byte("missing input"),
-				ExitCode: 1,
-			},
-		},
-	}
-
-	result, err := runner.Render(context.Background(), RenderRequest{
-		PromptID:        "weather.markdown_report",
-		DataPackagePath: "/tmp/data_package.yaml",
-	})
-	if err == nil {
-		t.Fatal("Render() error = nil, want nonzero exit error")
-	}
-	if result == nil {
-		t.Fatal("Render() result = nil, want captured result")
-	}
-	if result.ExitCode != 1 {
-		t.Fatalf("ExitCode = %d, want 1", result.ExitCode)
-	}
-	if !strings.Contains(err.Error(), "missing input") {
-		t.Fatalf("error = %q, want stderr context", err.Error())
-	}
-}
-
-func TestRunConstructsCommand(t *testing.T) {
-	commands := &fakeCommands{result: CommandResult{Stderr: []byte("wrote report")}}
-	runner := Runner{
-		Binary:     "/usr/local/bin/scriptorium",
-		ConfigPath: "/etc/scriptorium.yml",
-		Profile:    "weather",
-		Timeout:    45 * time.Second,
-		Commands:   commands,
-	}
-
-	result, err := runner.Run(context.Background(), RunRequest{
-		PromptID:        "weather.markdown_report",
-		DataPackagePath: "/tmp/data_package.yaml",
-		OutputPath:      "/tmp/daily.md",
-	})
-	if err != nil {
-		t.Fatalf("Run() error = %v", err)
-	}
-
-	wantArgs := []string{
-		"run",
-		"--config", "/etc/scriptorium.yml",
-		"--profile", "weather",
-		"--prompt", "weather.markdown_report",
-		"--input", "data_package=/tmp/data_package.yaml",
-		"--out", "/tmp/daily.md",
-	}
-	if commands.name != "/usr/local/bin/scriptorium" {
-		t.Fatalf("command name = %q, want custom binary", commands.name)
-	}
-	if !reflect.DeepEqual(commands.args, wantArgs) {
-		t.Fatalf("args = %#v, want %#v", commands.args, wantArgs)
-	}
-	if commands.timeout != 45*time.Second {
-		t.Fatalf("timeout = %s, want 45s", commands.timeout)
-	}
-	if !reflect.DeepEqual(result.Command, append([]string{"/usr/local/bin/scriptorium"}, wantArgs...)) {
-		t.Fatalf("result command = %#v, want full argv", result.Command)
-	}
-	if result.OutputPath != "/tmp/daily.md" {
-		t.Fatalf("OutputPath = %q, want /tmp/daily.md", result.OutputPath)
-	}
-}
-
-func TestRunReturnsResultForValidationExit(t *testing.T) {
-	runner := Runner{
-		Commands: &fakeCommands{
-			result: CommandResult{
-				Stdout:   []byte("# Daily Report\n"),
-				Stderr:   []byte("validation failed"),
-				ExitCode: 2,
-			},
-		},
-	}
-
-	result, err := runner.Run(context.Background(), RunRequest{
-		PromptID:        "weather.markdown_report",
-		DataPackagePath: "/tmp/data_package.yaml",
-		OutputPath:      "/tmp/daily.md",
-	})
-	if err == nil {
-		t.Fatal("Run() error = nil, want nonzero exit error")
-	}
-	if result == nil {
-		t.Fatal("Run() result = nil, want captured result")
-	}
-	if result.ExitCode != 2 {
-		t.Fatalf("ExitCode = %d, want 2", result.ExitCode)
-	}
-	if !strings.Contains(err.Error(), "validation failed") {
-		t.Fatalf("error = %q, want stderr context", err.Error())
-	}
-}
-
-func TestStructuredRunConstructsCommandWithoutSchemaFlags(t *testing.T) {
-	commands := &fakeCommands{result: CommandResult{
-		Stdout:          []byte(`{"summary":"ok"}`),
-		Stderr:          []byte("wrote generated text"),
-		StdoutTruncated: true,
-	}}
-	runner := Runner{
-		Binary:     "/usr/local/bin/scriptorium",
-		ConfigPath: "/etc/scriptorium.yml",
-		Profile:    "weather",
-		Timeout:    30 * time.Second,
-		Commands:   commands,
-	}
-
-	result, err := runner.StructuredRun(context.Background(), StructuredRunRequest{
-		PromptID:        "weather.hourly_generated_text",
-		DataPackagePath: "/tmp/data_package.hourly.yaml",
-		OutputPath:      "/tmp/generated_text_raw.hourly.json",
-	})
-	if err != nil {
-		t.Fatalf("StructuredRun() error = %v", err)
-	}
-
-	wantArgs := []string{
-		"run",
-		"--config", "/etc/scriptorium.yml",
-		"--profile", "weather",
-		"--prompt", "weather.hourly_generated_text",
-		"--input", "data_package=/tmp/data_package.hourly.yaml",
-		"--out", "/tmp/generated_text_raw.hourly.json",
-	}
-	if commands.name != "/usr/local/bin/scriptorium" {
-		t.Fatalf("command name = %q, want custom binary", commands.name)
-	}
-	if !reflect.DeepEqual(commands.args, wantArgs) {
-		t.Fatalf("args = %#v, want %#v", commands.args, wantArgs)
-	}
-	for _, disallowed := range []string{"--format", "--schema", "--schema-path", "--json-schema"} {
-		if containsArg(commands.args, disallowed) {
-			t.Fatalf("args = %#v, should not include %q", commands.args, disallowed)
-		}
-	}
-	if commands.timeout != 30*time.Second {
-		t.Fatalf("timeout = %s, want 30s", commands.timeout)
-	}
-	if !reflect.DeepEqual(result.Command, append([]string{"/usr/local/bin/scriptorium"}, wantArgs...)) {
-		t.Fatalf("result command = %#v, want full argv", result.Command)
-	}
-	if result.Stdout != `{"summary":"ok"}` || result.Stderr != "wrote generated text" || !result.StdoutTruncated {
-		t.Fatalf("result = %#v, want captured output and truncation flags", result)
-	}
-	if result.OutputPath != "/tmp/generated_text_raw.hourly.json" {
-		t.Fatalf("OutputPath = %q, want generated text raw path", result.OutputPath)
-	}
-}
-
-func TestStructuredRunReturnsResultForNonzeroExit(t *testing.T) {
-	runner := Runner{
-		Commands: &fakeCommands{
-			result: CommandResult{
-				Stdout:   []byte(`{"summary":"partial"}`),
-				Stderr:   []byte("structured output failed"),
-				ExitCode: 3,
-			},
-		},
-	}
-
-	result, err := runner.StructuredRun(context.Background(), StructuredRunRequest{
-		PromptID:        "weather.hourly_generated_text",
-		DataPackagePath: "/tmp/data_package.hourly.yaml",
-		OutputPath:      "/tmp/generated_text_raw.hourly.json",
-	})
-	if err == nil {
-		t.Fatal("StructuredRun() error = nil, want nonzero exit error")
-	}
-	if result == nil {
-		t.Fatal("StructuredRun() result = nil, want captured result")
-	}
-	if result.ExitCode != 3 {
-		t.Fatalf("ExitCode = %d, want 3", result.ExitCode)
-	}
-	if result.Stdout != `{"summary":"partial"}` || result.OutputPath != "/tmp/generated_text_raw.hourly.json" {
-		t.Fatalf("result = %#v, want captured result fields", result)
-	}
-	if !strings.Contains(err.Error(), "structured output failed") {
-		t.Fatalf("error = %q, want stderr context", err.Error())
-	}
-}
-
-func TestOutputRunsPreserveCapturedResultFields(t *testing.T) {
-	type commonResult struct {
-		Command         []string
-		Stdout          string
-		Stderr          string
-		StdoutTruncated bool
-		StderrTruncated bool
-		ExitCode        int
-		OutputPath      string
-	}
-	tests := []struct {
-		name string
-		run  func(Runner) (*commonResult, error)
-	}{
-		{
-			name: "Run",
-			run: func(runner Runner) (*commonResult, error) {
-				result, err := runner.Run(context.Background(), RunRequest{
-					PromptID:        "weather.markdown_report",
-					DataPackagePath: "/tmp/data_package.yaml",
-					OutputPath:      "/tmp/report.md",
-				})
-				if result == nil {
-					return nil, err
-				}
-				return &commonResult{
-					Command:         result.Command,
-					Stdout:          result.Stdout,
-					Stderr:          result.Stderr,
-					StdoutTruncated: result.StdoutTruncated,
-					StderrTruncated: result.StderrTruncated,
-					ExitCode:        result.ExitCode,
-					OutputPath:      result.OutputPath,
-				}, err
-			},
-		},
-		{
-			name: "StructuredRun",
-			run: func(runner Runner) (*commonResult, error) {
-				result, err := runner.StructuredRun(context.Background(), StructuredRunRequest{
-					PromptID:        "weather.markdown_report",
-					DataPackagePath: "/tmp/data_package.yaml",
-					OutputPath:      "/tmp/report.md",
-				})
-				if result == nil {
-					return nil, err
-				}
-				return &commonResult{
-					Command:         result.Command,
-					Stdout:          result.Stdout,
-					Stderr:          result.Stderr,
-					StdoutTruncated: result.StdoutTruncated,
-					StderrTruncated: result.StderrTruncated,
-					ExitCode:        result.ExitCode,
-					OutputPath:      result.OutputPath,
-				}, err
-			},
-		},
-	}
-
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-			commands := &fakeCommands{result: CommandResult{
-				Stdout:          []byte("captured stdout"),
-				Stderr:          []byte("captured stderr"),
-				StdoutTruncated: true,
-				StderrTruncated: true,
-			}}
-			runner := Runner{
-				Binary:     "/usr/local/bin/scriptorium",
-				ConfigPath: "/etc/scriptorium.yml",
-				Profile:    "weather",
-				Timeout:    15 * time.Second,
-				Commands:   commands,
-			}
-
-			result, err := test.run(runner)
-			if err != nil {
-				t.Fatalf("%s error = %v", test.name, err)
-			}
-			wantArgs := []string{
-				"run",
-				"--config", "/etc/scriptorium.yml",
-				"--profile", "weather",
-				"--prompt", "weather.markdown_report",
-				"--input", "data_package=/tmp/data_package.yaml",
-				"--out", "/tmp/report.md",
-			}
-			if !reflect.DeepEqual(commands.args, wantArgs) {
-				t.Fatalf("args = %#v, want %#v", commands.args, wantArgs)
-			}
-			if commands.timeout != 15*time.Second {
-				t.Fatalf("timeout = %s, want 15s", commands.timeout)
-			}
-			if !reflect.DeepEqual(result.Command, append([]string{"/usr/local/bin/scriptorium"}, wantArgs...)) {
-				t.Fatalf("Command = %#v, want full argv", result.Command)
-			}
-			if result.Stdout != "captured stdout" || result.Stderr != "captured stderr" {
-				t.Fatalf("captured output = %q/%q, want stdout/stderr", result.Stdout, result.Stderr)
-			}
-			if !result.StdoutTruncated || !result.StderrTruncated {
-				t.Fatalf("truncation flags = %t/%t, want both true", result.StdoutTruncated, result.StderrTruncated)
-			}
-			if result.ExitCode != 0 || result.OutputPath != "/tmp/report.md" {
-				t.Fatalf("result = %#v, want exit 0 and output path", result)
-			}
-		})
-	}
-}
-
-func TestOutputRunsReturnCapturedResultForNonzeroExit(t *testing.T) {
-	type commonResult struct {
-		Stdout          string
-		Stderr          string
-		StderrTruncated bool
-		ExitCode        int
-		OutputPath      string
-	}
-	tests := []struct {
-		name    string
-		run     func(Runner) (*commonResult, error)
-		wantErr string
-	}{
-		{
-			name: "Run",
-			run: func(runner Runner) (*commonResult, error) {
-				result, err := runner.Run(context.Background(), RunRequest{
-					PromptID:        "weather.markdown_report",
-					DataPackagePath: "/tmp/data_package.yaml",
-					OutputPath:      "/tmp/report.md",
-				})
-				if result == nil {
-					return nil, err
-				}
-				return &commonResult{
-					Stdout:          result.Stdout,
-					Stderr:          result.Stderr,
-					StderrTruncated: result.StderrTruncated,
-					ExitCode:        result.ExitCode,
-					OutputPath:      result.OutputPath,
-				}, err
-			},
-			wantErr: "scriptorium run exited with code 7: captured stderr",
-		},
-		{
-			name: "StructuredRun",
-			run: func(runner Runner) (*commonResult, error) {
-				result, err := runner.StructuredRun(context.Background(), StructuredRunRequest{
-					PromptID:        "weather.markdown_report",
-					DataPackagePath: "/tmp/data_package.yaml",
-					OutputPath:      "/tmp/report.md",
-				})
-				if result == nil {
-					return nil, err
-				}
-				return &commonResult{
-					Stdout:          result.Stdout,
-					Stderr:          result.Stderr,
-					StderrTruncated: result.StderrTruncated,
-					ExitCode:        result.ExitCode,
-					OutputPath:      result.OutputPath,
-				}, err
-			},
-			wantErr: "scriptorium structured run exited with code 7: captured stderr",
-		},
-	}
-
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-			runner := Runner{
-				Commands: &fakeCommands{result: CommandResult{
-					Stdout:          []byte("captured stdout"),
-					Stderr:          []byte("captured stderr"),
-					StderrTruncated: true,
-					ExitCode:        7,
-				}},
-			}
-
-			result, err := test.run(runner)
-			if err == nil {
-				t.Fatalf("%s error = nil, want nonzero exit error", test.name)
-			}
-			if result == nil {
-				t.Fatalf("%s result = nil, want captured result", test.name)
-			}
-			if err.Error() != test.wantErr {
-				t.Fatalf("%s error = %q, want %q", test.name, err.Error(), test.wantErr)
-			}
-			if result.Stdout != "captured stdout" || result.Stderr != "captured stderr" || !result.StderrTruncated {
-				t.Fatalf("captured result = %#v, want stdout/stderr/truncation", result)
-			}
-			if result.ExitCode != 7 || result.OutputPath != "/tmp/report.md" {
-				t.Fatalf("result = %#v, want exit 7 and output path", result)
-			}
-		})
-	}
-}
-
-func TestOutputRunsValidateRequiredFieldsBeforeExecution(t *testing.T) {
-	tests := []struct {
-		name string
-		run  func(Runner, string, string, string) error
-	}{
-		{
-			name: "Run",
-			run: func(runner Runner, promptID string, dataPackagePath string, outputPath string) error {
-				result, err := runner.Run(context.Background(), RunRequest{
-					PromptID:        promptID,
-					DataPackagePath: dataPackagePath,
-					OutputPath:      outputPath,
-				})
-				if result != nil {
-					return fmt.Errorf("result = %#v, want nil", result)
-				}
-				return err
-			},
-		},
-		{
-			name: "StructuredRun",
-			run: func(runner Runner, promptID string, dataPackagePath string, outputPath string) error {
-				result, err := runner.StructuredRun(context.Background(), StructuredRunRequest{
-					PromptID:        promptID,
-					DataPackagePath: dataPackagePath,
-					OutputPath:      outputPath,
-				})
-				if result != nil {
-					return fmt.Errorf("result = %#v, want nil", result)
-				}
-				return err
-			},
-		},
-	}
-	cases := []struct {
-		name            string
-		promptID        string
-		dataPackagePath string
-		outputPath      string
-		want            string
-	}{
-		{
-			name:            "prompt id",
-			dataPackagePath: "/tmp/data_package.yaml",
-			outputPath:      "/tmp/report.md",
-			want:            "prompt id is required",
-		},
-		{
-			name:       "data package path",
-			promptID:   "weather.markdown_report",
-			outputPath: "/tmp/report.md",
-			want:       "data package path is required",
-		},
-		{
-			name:            "output path",
-			promptID:        "weather.markdown_report",
-			dataPackagePath: "/tmp/data_package.yaml",
-			want:            "output path is required",
-		},
-	}
-
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-			for _, tc := range cases {
-				t.Run(tc.name, func(t *testing.T) {
-					commands := &fakeCommands{}
-					err := test.run(Runner{Commands: commands}, tc.promptID, tc.dataPackagePath, tc.outputPath)
-					if err == nil {
-						t.Fatalf("%s error = nil, want validation error", test.name)
-					}
-					if !strings.Contains(err.Error(), tc.want) {
-						t.Fatalf("%s error = %v, want %q", test.name, err, tc.want)
-					}
-					if commands.calls != 0 {
-						t.Fatalf("commands calls = %d, want no subprocess execution", commands.calls)
-					}
-				})
-			}
-		})
-	}
-}
-
-type fakeCommands struct {
-	name    string
-	args    []string
-	timeout time.Duration
-	result  CommandResult
-	err     error
-	calls   int
-}
-
-func (f *fakeCommands) Run(_ context.Context, name string, args []string, timeout time.Duration) (CommandResult, error) {
-	f.calls++
-	f.name = name
-	f.args = append([]string{}, args...)
-	f.timeout = timeout
-	return f.result, f.err
-}
-
-func containsArg(args []string, want string) bool {
-	for _, arg := range args {
-		if arg == want {
-			return true
-		}
-	}
-	return false
-}

internal/app/app.go

@@ -3,13 +3,11 @@ package app
 
 import (
 	"context"
-	"errors"
 	"fmt"
 	"path/filepath"
 	"time"
 
 	distributoradapter "gitea.maximumdirect.net/eric/weatherreporter/internal/adapters/distributor"
-	"gitea.maximumdirect.net/eric/weatherreporter/internal/adapters/scriptorium"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/briefing"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/changes"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/collect"
@@ -17,8 +15,8 @@ import (
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/facts"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/fileutil"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/forecast"
-	"gitea.maximumdirect.net/eric/weatherreporter/internal/generatedtext"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/module"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptexec"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptinput"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/report"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/state"
@@ -33,9 +31,6 @@ const (
 	ReportToday    ReportKind = ReportKind(report.CommandNameToday)
 	ReportTomorrow ReportKind = ReportKind(report.CommandNameTomorrow)
 	ReportHourly   ReportKind = ReportKind(report.CommandNameHourly)
-	ReportThreeDay ReportKind = ReportKind(report.CommandNameThreeDay)
-	ReportWeekend  ReportKind = ReportKind(report.CommandNameWeekend)
-	ReportStorm    ReportKind = ReportKind(report.CommandNameStorm)
 )
 
 type BatchKind string
@@ -46,26 +41,28 @@ const (
 )
 
 type GenerateRequest struct {
-	Config     config.Config
+	Config      config.Config
-	Report     ReportKind
+	Report      ReportKind
-	OutputPath string
+	OutputPath  string
-	Now        time.Time
+	LLMDebugDir string
-	Date       time.Time
+	Now         time.Time
-	StormStart time.Time
+	Date        time.Time
-	StormEnd   time.Time
+	Collector   Collector
-	Collector  Collector
+	Notifier    Notifier
-	Notifier   Notifier
+	Executor    promptexec.Executor
+	Store       state.Store
 }
 
 type BatchRequest struct {
-	Config    config.Config
+	Config      config.Config
-	Batch     BatchKind
+	Batch       BatchKind
-	Now       time.Time
+	Now         time.Time
-	OutputDir string
+	OutputDir   string
-	Collector Collector
+	LLMDebugDir string
-	Renderer  Renderer
+	Collector   Collector
-	Store     state.Store
+	Executor    promptexec.Executor
-	Notifier  Notifier
+	Store       state.Store
+	Notifier    Notifier
 }
 
 type FetchBundleRequest struct {
@@ -83,38 +80,25 @@ type ReportFacts struct {
 	Derived   facts.DerivedFacts
 }
 
-type ReportRequest struct {
-	Config     config.Config
-	Resolved   report.Resolved
-	OutputPath string
-	Collection collect.Result
-	Renderer   Renderer
-	Store      state.Store
-	Notifier   Notifier
-	noNotify   bool
-}
-
 type ReportResult struct {
-	ModuleSnapshot          module.Snapshot
+	ModuleSnapshot       module.Snapshot
-	ModuleSnapshotPath      string
+	ModuleSnapshotPath   string
-	DataPackage             promptinput.Package
+	DataPackage          promptinput.Package
-	DataPackagePath         string
+	DataPackagePath      string
-	PreflightPath           string
+	PreparationPath      string
-	ReportPath              string
+	ExecutionPath        string
-	OutputPath              string
+	LLMDebugPath         string
-	NotificationPath        string
+	ReportPath           string
-	Metadata                state.Metadata
+	OutputPath           string
-	MetadataPath            string
+	NotificationPath     string
-	PriorSnapshot           *state.PriorSnapshot
+	Metadata             state.Metadata
-	RecentChanges           []changes.Change
+	MetadataPath         string
-	RenderResult            *scriptorium.RenderResult
+	PriorSnapshot        *state.PriorSnapshot
-	RunResult               *scriptorium.RunResult
+	RecentChanges        []changes.Change
-	StructuredRunResult     *scriptorium.StructuredRunResult
+	GeneratedTextRawPath string
-	GeneratedTextRawPath    string
+	GeneratedTextPath    string
-	GeneratedTextResultPath string
+	RenderContextPath    string
-	GeneratedTextPath       string
+	Notification         *NotificationResult
-	RenderContextPath       string
-	Notification            *NotificationResult
 }
 
 type BatchResult struct {
@@ -162,7 +146,9 @@ type BatchReportResult struct {
 	GeneratedAt            time.Time       `json:"generatedAt"`
 	ValidPeriod            timeutil.Period `json:"validPeriod"`
 	DataPackagePath        string          `json:"dataPackagePath,omitempty"`
-	PreflightPath          string          `json:"preflightPath,omitempty"`
+	PreparationPath        string          `json:"preparationPath,omitempty"`
+	ExecutionPath          string          `json:"executionPath,omitempty"`
+	LLMDebugPath           string          `json:"llmDebugPath,omitempty"`
 	ReportPath             string          `json:"reportPath,omitempty"`
 	OutputPath             string          `json:"outputPath,omitempty"`
 	MetadataPath           string          `json:"metadataPath,omitempty"`
@@ -202,12 +188,6 @@ func batchReportFailures(result *BatchResult) int {
 	return failures
 }
 
-type Renderer interface {
-	Render(context.Context, scriptorium.RenderRequest) (*scriptorium.RenderResult, error)
-	Run(context.Context, scriptorium.RunRequest) (*scriptorium.RunResult, error)
-	StructuredRun(context.Context, scriptorium.StructuredRunRequest) (*scriptorium.StructuredRunResult, error)
-}
-
 type Collector interface {
 	Run(context.Context, collect.Request) (*collect.Result, error)
 }
@@ -277,24 +257,33 @@ func GenerateDetailed(ctx context.Context, req GenerateRequest) (*ReportResult,
 	if now.IsZero() {
 		now = time.Now()
 	}
-	collection, err := collectWeather(ctx, req.Config, req.Collector)
-	if err != nil {
-		return nil, err
-	}
 	resolved, err := ResolveGenerate(req, now)
 	if err != nil {
 		return nil, err
 	}
-	if resolved.Definition.Generated {
+	debugWriter, err := state.NewPromptDebugWriter(req.LLMDebugDir)
-		return GenerateReport(ctx, ReportRequest{
+	if err != nil {
-			Config:     req.Config,
+		return nil, promptexec.NewError(promptexec.InvalidConfiguration, "initialize prompt debug", err)
-			Resolved:   resolved,
-			OutputPath: req.OutputPath,
-			Collection: *collection,
-			Notifier:   req.Notifier,
-		})
 	}
-	return nil, fmt.Errorf("generate is not implemented")
+	inspection, err := InspectPromptExecution(ctx, PromptInspectionRequest{
+		Resolved:  resolved,
+		Executor:  req.Executor,
+		Promptkit: req.Config.Promptkit,
+	})
+	if err != nil {
+		return nil, err
+	}
+	collection, err := collectWeather(ctx, req.Config, req.Collector)
+	if err != nil {
+		return nil, err
+	}
+	return generatePromptReport(ctx, promptReportRequest{
+		GenerateRequest: req,
+		Resolved:        resolved,
+		Collection:      *collection,
+		Inspection:      inspection,
+		DebugWriter:     debugWriter,
+	})
 }
 
 func RunBatch(ctx context.Context, req BatchRequest) error {
@@ -316,6 +305,22 @@ func RunBatchDetailed(ctx context.Context, req BatchRequest) (*BatchResult, erro
 	if _, err := report.BatchForCommandName(string(req.Batch)); err != nil {
 		return nil, err
 	}
+	debugWriter, err := state.NewPromptDebugWriter(req.LLMDebugDir)
+	if err != nil {
+		return nil, promptexec.NewError(promptexec.InvalidConfiguration, "initialize prompt debug", err)
+	}
+	candidates, err := batchInspectionCandidates(req, now)
+	if err != nil {
+		return nil, err
+	}
+	inspections, err := InspectPromptExecutions(ctx, PromptExecutionsInspectionRequest{
+		Resolved:  candidates,
+		Executor:  req.Executor,
+		Promptkit: req.Config.Promptkit,
+	})
+	if err != nil {
+		return nil, err
+	}
 	collection, err := collectWeather(ctx, req.Config, req.Collector)
 	if err != nil {
 		return nil, err
@@ -335,58 +340,33 @@ func RunBatchDetailed(ctx context.Context, req BatchRequest) (*BatchResult, erro
 		}
 		startedAt := now
 		result := &BatchResult{Batch: req.Batch, StartedAt: startedAt}
-		for _, planned := range plannedReports {
-			resolved := planned.Resolved
-			if !resolved.Definition.Generated {
-				return nil, fmt.Errorf("run is not implemented")
-			}
-		}
 		for _, planned := range plannedReports {
 			resolved := planned.Resolved
 			item := batchReportResult(planned)
-			if paths, err := store.Paths(resolved); err == nil {
-				item.DataPackagePath = paths.DataPackage
-				item.PreflightPath = paths.Preflight
-				item.ReportPath = paths.RenderedReport
-				item.MetadataPath = paths.Metadata
-			}
 			outputPath := plannedBatchOutputPath(req.OutputDir, planned)
-			reportResult, err := GenerateReport(ctx, ReportRequest{
+			reportResult, err := generatePromptReport(ctx, promptReportRequest{
-				Config:     req.Config,
+				GenerateRequest: GenerateRequest{
-				Resolved:   resolved,
+					Config:     req.Config,
-				OutputPath: outputPath,
+					OutputPath: outputPath,
-				Collection: *collection,
+					Notifier:   req.Notifier,
-				Renderer:   req.Renderer,
+					Executor:   req.Executor,
-				Store:      store,
+					Store:      store,
-				Notifier:   req.Notifier,
+				},
-				noNotify:   true,
+				Resolved:    resolved,
+				Collection:  *collection,
+				Inspection:  inspections[resolved.Definition.ID],
+				DebugWriter: debugWriter,
+				noNotify:    true,
 			})
+			if reportResult != nil {
+				copyBatchReportPaths(&item, reportResult)
+			}
 			if err != nil {
 				item.Status = "failed"
 				item.Error = err.Error()
-				var notificationErr *NotificationError
-				if errors.As(err, &notificationErr) {
-					item.NotificationStatus = "failed"
-					item.NotificationError = notificationErr.Error()
-					item.NotificationPipelineID = notificationErr.Request.PipelineID
-					if paths, pathErr := store.Paths(resolved); pathErr == nil {
-						item.NotificationPath = paths.Notification
-					}
-				}
 				result.Failed++
 			} else {
 				item.Status = "succeeded"
-				item.DataPackagePath = reportResult.DataPackagePath
-				item.PreflightPath = reportResult.PreflightPath
-				item.ReportPath = reportResult.ReportPath
-				item.OutputPath = reportResult.OutputPath
-				item.MetadataPath = reportResult.MetadataPath
-				item.NotificationPath = reportResult.NotificationPath
-				if reportResult.Notification != nil {
-					item.NotificationStatus = reportResult.Notification.Status
-					item.NotificationRunID = reportResult.Notification.RunID
-					item.NotificationPipelineID = reportResult.Notification.PipelineID
-				}
 				result.Succeeded++
 			}
 			result.Reports = append(result.Reports, item)
@@ -405,6 +385,51 @@ func RunBatchDetailed(ctx context.Context, req BatchRequest) (*BatchResult, erro
 	return nil, fmt.Errorf("run is not implemented")
 }
 
+func copyBatchReportPaths(item *BatchReportResult, result *ReportResult) {
+	item.DataPackagePath = result.DataPackagePath
+	item.PreparationPath = result.PreparationPath
+	item.ExecutionPath = result.ExecutionPath
+	item.LLMDebugPath = result.LLMDebugPath
+	item.ReportPath = result.ReportPath
+	item.OutputPath = result.OutputPath
+	item.MetadataPath = result.MetadataPath
+	item.NotificationPath = result.NotificationPath
+	if result.Notification != nil {
+		item.NotificationStatus = result.Notification.Status
+		item.NotificationRunID = result.Notification.RunID
+		item.NotificationPipelineID = result.Notification.PipelineID
+	}
+}
+
+func batchInspectionCandidates(req BatchRequest, now time.Time) ([]report.Resolved, error) {
+	location, err := timeutil.LoadLocation(req.Config.WeatherAPI.Timezone)
+	if err != nil {
+		return nil, err
+	}
+	registry, err := reportRegistry(req.Config)
+	if err != nil {
+		return nil, err
+	}
+	ids := []report.ID{report.Tomorrow, report.Daily}
+	if req.Batch == BatchMorning {
+		ids = []report.ID{report.Today, report.Tomorrow, report.Daily}
+	}
+	date := timeutil.LocalDate(now, location).AddDate(0, 0, 2)
+	candidates := make([]report.Resolved, 0, len(ids))
+	for _, id := range ids {
+		resolveReq := report.ResolveRequest{Now: now, Location: location}
+		if id == report.Daily {
+			resolveReq.Date = date
+		}
+		resolved, err := registry.Resolve(id, resolveReq)
+		if err != nil {
+			return nil, err
+		}
+		candidates = append(candidates, resolved)
+	}
+	return candidates, nil
+}
+
 func batchReportResult(planned plannedBatchReport) BatchReportResult {
 	resolved := planned.Resolved
 	metadata := resolved.Metadata()
@@ -446,11 +471,9 @@ func ResolveGenerate(req GenerateRequest, now time.Time) (report.Resolved, error
 		return report.Resolved{}, err
 	}
 	return registry.Resolve(id, report.ResolveRequest{
-		Now:        now,
+		Now:      now,
-		Location:   location,
+		Location: location,
-		Date:       req.Date,
+		Date:     req.Date,
-		StormStart: req.StormStart,
-		StormEnd:   req.StormEnd,
 	})
 }
 
@@ -505,391 +528,13 @@ func FetchAndSaveBundle(ctx context.Context, req FetchBundleRequest) (*weatherda
 	return bundle, nil
 }
 
-func GenerateReport(ctx context.Context, req ReportRequest) (*ReportResult, error) {
-	bundle := req.Collection.Bundle
-	if bundle == nil {
-		return nil, fmt.Errorf("collected weather bundle is required")
-	}
-
-	store := req.Store
-	if store == nil {
-		defaultStore, err := defaultStore(req.Config)
-		if err != nil {
-			return nil, err
-		}
-		store = defaultStore
-	}
-	paths, err := store.Paths(req.Resolved)
-	if err != nil {
-		return nil, err
-	}
-	priorSnapshot, err := store.FindPriorSnapshot(ctx, req.Resolved)
-	if err != nil {
-		return nil, err
-	}
-
-	reportFacts, err := BuildReportFacts(ModuleSnapshotRequest{
-		Config:   req.Config,
-		Resolved: req.Resolved,
-	}, bundle)
-	if err != nil {
-		return nil, err
-	}
-	moduleSnapshot, err := BuildModuleSnapshotFromFacts(ModuleSnapshotRequest{
-		Config:   req.Config,
-		Resolved: req.Resolved,
-	}, reportFacts)
-	if err != nil {
-		return nil, err
-	}
-
-	moduleSnapshotPath, err := store.SaveModuleSnapshot(ctx, req.Resolved, moduleSnapshot)
-	if err != nil {
-		return nil, err
-	}
-
-	recentChanges, err := recentChanges(ctx, store, priorSnapshot, req.Resolved.Definition.ID, moduleSnapshot, req.Config.RecentChange)
-	if err != nil {
-		return nil, err
-	}
-	briefingMetadata := briefing.BuildMetadata(briefingBuildContext(req.Config, req.Resolved, reportFacts.Collected))
-	metadata := state.BuildMetadataFromBriefingMetadata(req.Resolved, briefingMetadata, state.ArtifactPaths{
-		ModuleSnapshot:      moduleSnapshotPath,
-		Metadata:            paths.Metadata,
-		DataPackage:         paths.DataPackage,
-		Preflight:           paths.Preflight,
-		RenderedReport:      paths.RenderedReport,
-		GeneratedTextRaw:    paths.GeneratedTextRaw,
-		GeneratedTextResult: paths.GeneratedTextResult,
-		GeneratedText:       paths.GeneratedText,
-		RenderContext:       paths.RenderContext,
-	})
-	dataPackage, err := promptinput.Build(promptinput.BuildRequest{
-		Metadata:      promptMetadata(metadata),
-		Modules:       moduleSnapshot,
-		RecentChanges: recentChanges,
-	})
-	if err != nil {
-		return nil, err
-	}
-	dataPackagePath, err := store.SaveDataPackage(ctx, req.Resolved, dataPackage)
-	if err != nil {
-		return nil, err
-	}
-	metadata.DataPackagePath = dataPackagePath
-
-	renderer := req.Renderer
-	if renderer == nil {
-		renderer = scriptorium.Runner{
-			Binary:     req.Config.Scriptorium.Binary,
-			ConfigPath: req.Config.Scriptorium.ConfigPath,
-			Profile:    req.Config.Scriptorium.Profile,
-			Timeout:    req.Config.Scriptorium.Timeout,
-			ExtraArgs:  req.Config.Scriptorium.ExtraArgs,
-		}
-	}
-	renderResult, renderErr := renderer.Render(ctx, scriptorium.RenderRequest{
-		PromptID:        req.Resolved.Definition.PromptID,
-		DataPackagePath: dataPackagePath,
-	})
-
-	preflightPath := paths.Preflight
-	if renderResult != nil {
-		var err error
-		preflightPath, err = store.SavePreflight(ctx, req.Resolved, preflightArtifact(renderResult))
-		if err != nil {
-			return nil, err
-		}
-	}
-	metadata.PreflightPath = preflightPath
-	metadataPath, metadataErr := store.SaveMetadata(ctx, metadata)
-	if metadataErr != nil {
-		return nil, metadataErr
-	}
-	if renderErr != nil {
-		if req.Resolved.Definition.GenerationMode == report.GenerationModeGeneratedTextTemplate {
-			return nil, generatedReportError(req.Resolved, metadata.RunID, "render preflight", renderErr)
-		}
-		return nil, renderErr
-	}
-
-	if req.Resolved.Definition.GenerationMode == report.GenerationModeGeneratedTextTemplate {
-		return generateTextTemplateReport(ctx, generatedReportRequest{
-			ReportRequest:      req,
-			store:              store,
-			paths:              paths,
-			moduleSnapshot:     moduleSnapshot,
-			moduleSnapshotPath: moduleSnapshotPath,
-			reportFacts:        reportFacts,
-			dataPackage:        dataPackage,
-			dataPackagePath:    dataPackagePath,
-			briefingMetadata:   briefingMetadata,
-			metadata:           metadata,
-			metadataPath:       metadataPath,
-			preflightPath:      preflightPath,
-			priorSnapshot:      priorSnapshot,
-			recentChanges:      recentChanges,
-			renderResult:       renderResult,
-			renderer:           renderer,
-		})
-	}
-	if req.Resolved.Definition.GenerationMode != report.GenerationModeScriptoriumMarkdown {
-		return nil, fmt.Errorf("generation mode %q is not supported for report %q", req.Resolved.Definition.GenerationMode, req.Resolved.Definition.ID)
-	}
-
-	reportPath, err := store.PrepareRenderedReport(ctx, req.Resolved)
-	if err != nil {
-		return nil, err
-	}
-	runResult, runErr := renderer.Run(ctx, scriptorium.RunRequest{
-		PromptID:        req.Resolved.Definition.PromptID,
-		DataPackagePath: dataPackagePath,
-		OutputPath:      reportPath,
-	})
-	finalized, err := finalizeRenderedReport(ctx, finalizeRenderedReportRequest{
-		Config:            req.Config,
-		Store:             store,
-		Resolved:          req.Resolved,
-		Metadata:          metadata,
-		ManagedReportPath: reportPath,
-		OutputPath:        req.OutputPath,
-		Notifier:          req.Notifier,
-		GenerationErr:     runErr,
-		noNotify:          req.noNotify,
-	})
-	if err != nil {
-		if finalizeResultEmpty(finalized) {
-			return nil, err
-		}
-		return renderedReportResult(reportResultRequest{
-			moduleSnapshot:     moduleSnapshot,
-			moduleSnapshotPath: moduleSnapshotPath,
-			dataPackage:        dataPackage,
-			dataPackagePath:    dataPackagePath,
-			preflightPath:      preflightPath,
-			reportPath:         reportPath,
-			finalized:          finalized,
-			priorSnapshot:      priorSnapshot,
-			recentChanges:      recentChanges,
-			renderResult:       renderResult,
-			runResult:          runResult,
-		}), err
-	}
-
-	return renderedReportResult(reportResultRequest{
-		moduleSnapshot:     moduleSnapshot,
-		moduleSnapshotPath: moduleSnapshotPath,
-		dataPackage:        dataPackage,
-		dataPackagePath:    dataPackagePath,
-		preflightPath:      preflightPath,
-		reportPath:         reportPath,
-		finalized:          finalized,
-		priorSnapshot:      priorSnapshot,
-		recentChanges:      recentChanges,
-		renderResult:       renderResult,
-		runResult:          runResult,
-	}), nil
-}
-
-type generatedReportRequest struct {
-	ReportRequest
-	store              state.Store
-	paths              state.ArtifactPaths
-	moduleSnapshot     module.Snapshot
-	moduleSnapshotPath string
-	reportFacts        ReportFacts
-	dataPackage        promptinput.Package
-	dataPackagePath    string
-	briefingMetadata   briefing.Metadata
-	metadata           state.Metadata
-	metadataPath       string
-	preflightPath      string
-	priorSnapshot      *state.PriorSnapshot
-	recentChanges      []changes.Change
-	renderResult       *scriptorium.RenderResult
-	renderer           Renderer
-}
-
-func generateTextTemplateReport(ctx context.Context, req generatedReportRequest) (*ReportResult, error) {
-	handler, err := generatedtext.LookupDefinition(req.Resolved.Definition)
-	if err != nil {
-		return nil, generatedReportError(req.Resolved, req.metadata.RunID, "lookup generated text catalog", err)
-	}
-
-	structuredResult, runErr := req.renderer.StructuredRun(ctx, scriptorium.StructuredRunRequest{
-		PromptID:        req.Resolved.Definition.PromptID,
-		DataPackagePath: req.dataPackagePath,
-		OutputPath:      req.paths.GeneratedTextRaw,
-	})
-	generatedTextResultPath := req.paths.GeneratedTextResult
-	if structuredResult != nil {
-		var err error
-		generatedTextResultPath, err = req.store.SaveGeneratedTextResult(ctx, req.Resolved, structuredResult)
-		if err != nil {
-			return nil, err
-		}
-		req.metadata.GeneratedTextResultPath = generatedTextResultPath
-		req.metadataPath, err = req.store.SaveMetadata(ctx, req.metadata)
-		if err != nil {
-			return nil, err
-		}
-	}
-	if runErr != nil {
-		return nil, generatedReportError(req.Resolved, req.metadata.RunID, "structured generated text", runErr)
-	}
-
-	rawGeneratedText, err := req.store.LoadGeneratedText(ctx, req.paths.GeneratedTextRaw)
-	if err != nil {
-		return nil, generatedReportError(req.Resolved, req.metadata.RunID, "load raw generated text", err)
-	}
-	generatedText, normalizedGeneratedText, err := handler.Validate(rawGeneratedText)
-	if err != nil {
-		return nil, generatedReportError(req.Resolved, req.metadata.RunID, "validate generated text", err)
-	}
-	generatedTextPath, err := req.store.SaveGeneratedText(ctx, req.Resolved, normalizedGeneratedText)
-	if err != nil {
-		return nil, err
-	}
-	req.metadata.GeneratedTextPath = generatedTextPath
-	req.metadataPath, err = req.store.SaveMetadata(ctx, req.metadata)
-	if err != nil {
-		return nil, err
-	}
-
-	renderContext, err := handler.BuildRenderContext(req.briefingMetadata, req.moduleSnapshot, req.reportFacts.Collected, req.reportFacts.Derived, generatedText)
-	if err != nil {
-		return nil, generatedReportError(req.Resolved, req.metadata.RunID, "build render context", err)
-	}
-	renderContextPath, err := req.store.SaveRenderContext(ctx, req.Resolved, renderContext)
-	if err != nil {
-		return nil, err
-	}
-	req.metadata.RenderContextPath = renderContextPath
-	req.metadataPath, err = req.store.SaveMetadata(ctx, req.metadata)
-	if err != nil {
-		return nil, err
-	}
-
-	rendered, err := handler.Render(renderContext)
-	if err != nil {
-		return nil, generatedReportError(req.Resolved, req.metadata.RunID, "render template", err)
-	}
-	reportPath, err := req.store.PrepareRenderedReport(ctx, req.Resolved)
-	if err != nil {
-		return nil, err
-	}
-	if err := fileutil.WriteFileAtomic(reportPath, rendered); err != nil {
-		return nil, err
-	}
-	finalized, err := finalizeRenderedReport(ctx, finalizeRenderedReportRequest{
-		Config:            req.Config,
-		Store:             req.store,
-		Resolved:          req.Resolved,
-		Metadata:          req.metadata,
-		ManagedReportPath: reportPath,
-		OutputPath:        req.OutputPath,
-		Notifier:          req.Notifier,
-		noNotify:          req.noNotify,
-	})
-	if err != nil {
-		if finalizeResultEmpty(finalized) {
-			return nil, err
-		}
-		return renderedReportResult(reportResultRequest{
-			moduleSnapshot:          req.moduleSnapshot,
-			moduleSnapshotPath:      req.moduleSnapshotPath,
-			dataPackage:             req.dataPackage,
-			dataPackagePath:         req.dataPackagePath,
-			preflightPath:           req.preflightPath,
-			reportPath:              reportPath,
-			finalized:               finalized,
-			priorSnapshot:           req.priorSnapshot,
-			recentChanges:           req.recentChanges,
-			renderResult:            req.renderResult,
-			structuredRunResult:     structuredResult,
-			generatedTextRawPath:    req.paths.GeneratedTextRaw,
-			generatedTextResultPath: generatedTextResultPath,
-			generatedTextPath:       generatedTextPath,
-			renderContextPath:       renderContextPath,
-		}), err
-	}
-
-	return renderedReportResult(reportResultRequest{
-		moduleSnapshot:          req.moduleSnapshot,
-		moduleSnapshotPath:      req.moduleSnapshotPath,
-		dataPackage:             req.dataPackage,
-		dataPackagePath:         req.dataPackagePath,
-		preflightPath:           req.preflightPath,
-		reportPath:              reportPath,
-		finalized:               finalized,
-		priorSnapshot:           req.priorSnapshot,
-		recentChanges:           req.recentChanges,
-		renderResult:            req.renderResult,
-		structuredRunResult:     structuredResult,
-		generatedTextRawPath:    req.paths.GeneratedTextRaw,
-		generatedTextResultPath: generatedTextResultPath,
-		generatedTextPath:       generatedTextPath,
-		renderContextPath:       renderContextPath,
-	}), nil
-}
-
-func finalizeResultEmpty(result finalizeRenderedReportResult) bool {
-	return result.OutputPath == "" &&
-		result.NotificationPath == "" &&
-		result.MetadataPath == "" &&
-		result.Metadata.RunID == "" &&
-		result.Notification == nil
-}
-
-type reportResultRequest struct {
-	moduleSnapshot          module.Snapshot
-	moduleSnapshotPath      string
-	dataPackage             promptinput.Package
-	dataPackagePath         string
-	preflightPath           string
-	reportPath              string
-	finalized               finalizeRenderedReportResult
-	priorSnapshot           *state.PriorSnapshot
-	recentChanges           []changes.Change
-	renderResult            *scriptorium.RenderResult
-	runResult               *scriptorium.RunResult
-	structuredRunResult     *scriptorium.StructuredRunResult
-	generatedTextRawPath    string
-	generatedTextResultPath string
-	generatedTextPath       string
-	renderContextPath       string
-}
-
-func renderedReportResult(req reportResultRequest) *ReportResult {
-	return &ReportResult{
-		ModuleSnapshot:          req.moduleSnapshot,
-		ModuleSnapshotPath:      req.moduleSnapshotPath,
-		DataPackage:             req.dataPackage,
-		DataPackagePath:         req.dataPackagePath,
-		PreflightPath:           req.preflightPath,
-		ReportPath:              req.reportPath,
-		OutputPath:              req.finalized.OutputPath,
-		NotificationPath:        req.finalized.NotificationPath,
-		Metadata:                req.finalized.Metadata,
-		MetadataPath:            req.finalized.MetadataPath,
-		PriorSnapshot:           req.priorSnapshot,
-		RecentChanges:           req.recentChanges,
-		RenderResult:            req.renderResult,
-		RunResult:               req.runResult,
-		StructuredRunResult:     req.structuredRunResult,
-		GeneratedTextRawPath:    req.generatedTextRawPath,
-		GeneratedTextResultPath: req.generatedTextResultPath,
-		GeneratedTextPath:       req.generatedTextPath,
-		RenderContextPath:       req.renderContextPath,
-		Notification:            req.finalized.Notification,
-	}
-}
-
 type finalizeRenderedReportRequest struct {
 	Config            config.Config
 	Store             state.Store
 	Resolved          report.Resolved
 	Metadata          state.Metadata
+	MetadataPath      string
+	ExecutionArtifact *state.PromptExecutionArtifact
 	ManagedReportPath string
 	OutputPath        string
 	Notifier          Notifier
@@ -912,28 +557,35 @@ func finalizeRenderedReport(ctx context.Context, req finalizeRenderedReportReque
 	if req.ManagedReportPath == "" {
 		return finalizeRenderedReportResult{}, fmt.Errorf("managed report path is required for report %q", req.Resolved.Definition.ID)
 	}
+	if req.ExecutionArtifact == nil {
+		return finalizeRenderedReportResult{}, fmt.Errorf("prompt execution artifact is required for report %q", req.Resolved.Definition.ID)
+	}
 
-	metadata := req.Metadata
+	result := finalizeRenderedReportResult{Metadata: req.Metadata, MetadataPath: req.MetadataPath}
-	metadata.RenderedReportPath = req.ManagedReportPath
+	if req.OutputPath != "" && req.GenerationErr == nil {
-	outputPath := req.ManagedReportPath
+		if req.OutputPath != req.ManagedReportPath {
-	if req.OutputPath != "" {
-		outputPath = req.OutputPath
-		if req.GenerationErr == nil && req.OutputPath != req.ManagedReportPath {
 			if err := fileutil.CopyFileAtomic(req.ManagedReportPath, req.OutputPath); err != nil {
-				return finalizeRenderedReportResult{}, err
+				return result, err
 			}
+			result.OutputPath = req.OutputPath
+			if err := persistReachedPromptPath(ctx, req.Store, req.Resolved, req.ExecutionArtifact, func(paths *state.PromptExecutionPaths) {
+				paths.OutputPath = req.OutputPath
+			}); err != nil {
+				return result, err
+			}
+		} else {
+			result.OutputPath = req.OutputPath
 		}
 	}
 
+	metadata := req.Metadata
+	metadata.RenderedReportPath = req.ManagedReportPath
 	metadataPath, err := req.Store.SaveMetadata(ctx, metadata)
 	if err != nil {
-		return finalizeRenderedReportResult{}, err
+		return result, err
-	}
-	result := finalizeRenderedReportResult{
-		OutputPath:   outputPath,
-		Metadata:     metadata,
-		MetadataPath: metadataPath,
 	}
+	result.Metadata = metadata
+	result.MetadataPath = metadataPath
 	if req.GenerationErr != nil {
 		return result, req.GenerationErr
 	}
@@ -943,14 +595,21 @@ func finalizeRenderedReport(ctx context.Context, req finalizeRenderedReportReque
 
 	notification, notificationPath, err := notifyReport(ctx, req.Config, req.Resolved, req.ManagedReportPath, metadata, req.Notifier, req.Store)
 	if notificationPath != "" {
+		result.NotificationPath = notificationPath
+		result.Notification = notification
 		metadata.NotificationPath = notificationPath
+		result.Metadata = metadata
+		if saveErr := persistReachedPromptPath(ctx, req.Store, req.Resolved, req.ExecutionArtifact, func(paths *state.PromptExecutionPaths) {
+			paths.NotificationPath = notificationPath
+		}); saveErr != nil {
+			return result, saveErr
+		}
 		metadataPath, saveErr := req.Store.SaveMetadata(ctx, metadata)
 		if saveErr != nil {
-			return finalizeRenderedReportResult{}, saveErr
+			return result, saveErr
 		}
 		result.Metadata = metadata
 		result.MetadataPath = metadataPath
-		result.NotificationPath = notificationPath
 	}
 	result.Notification = notification
 	if err != nil {
@@ -1046,9 +705,6 @@ func distributorTemplateValuesForReport(cfg config.Config, resolved report.Resol
 	if err := addDistributorValidPeriodValues(&values, resolved.ValidPeriod, cfg.WeatherAPI.Timezone); err != nil {
 		return config.DistributorTemplateValues{}, err
 	}
-	if resolved.Definition.ID == report.Storm {
-		values.StormID = values.ValidStartStamp + "-" + values.ValidEndStamp
-	}
 	return values, nil
 }
 
@@ -1359,29 +1015,11 @@ func recentChanges(ctx context.Context, store state.Store, priorSnapshot *state.
 	switch reportID {
 	case report.Daily, report.Today, report.Tomorrow:
 		return changes.CompareDaily(previous, current, thresholds)
-	case report.ThreeDay:
-		return changes.CompareThreeDay(previous, current, thresholds)
-	case report.Weekend:
-		return changes.CompareWeekend(previous, current, thresholds)
 	default:
 		return nil, nil
 	}
 }
 
-func preflightArtifact(result *scriptorium.RenderResult) state.PreflightArtifact {
-	if result == nil {
-		return state.PreflightArtifact{}
-	}
-	return state.PreflightArtifact{
-		Command:         append([]string(nil), result.Command...),
-		Stdout:          result.Stdout,
-		Stderr:          result.Stderr,
-		StdoutTruncated: result.StdoutTruncated,
-		StderrTruncated: result.StderrTruncated,
-		ExitCode:        result.ExitCode,
-	}
-}
-
 func generatedReportError(resolved report.Resolved, runID string, operation string, err error) error {
 	if err == nil {
 		return nil

internal/app/batch_execution_test.go

@@ -0,0 +1,85 @@
+package app
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"strings"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/collect"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/config"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptexec"
+)
+
+func TestRunBatchDetailedInspectsEveryCandidateBeforeCollection(t *testing.T) {
+	tests := []struct {
+		name        string
+		batch       BatchKind
+		now         string
+		wantPrompts int
+	}{
+		{name: "morning", batch: BatchMorning, now: "2026-05-29T08:00:00-05:00", wantPrompts: 3},
+		{name: "evening", batch: BatchEvening, now: "2026-05-29T18:00:00-05:00", wantPrompts: 2},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			cfg := config.Defaults()
+			cfg.Workspace.Root = t.TempDir()
+			now := mustParse(test.now)
+			req := BatchRequest{Config: cfg, Batch: test.batch, Now: now}
+			candidates, err := batchInspectionCandidates(req, now)
+			if err != nil {
+				t.Fatalf("batchInspectionCandidates() error = %v", err)
+			}
+			executor := &inspectionExecutor{profiles: map[string]promptexec.ProfileInspection{
+				"default-profile": {ProfileID: "default-profile", BackendID: "local", ModelName: "model"},
+			}, prompts: map[string]promptexec.PromptInspection{}}
+			for _, candidate := range candidates {
+				executor.prompts[candidate.Definition.PromptID] = validPromptInspection(candidate.Definition)
+			}
+			collector := collectorFunc(func(context.Context, collect.Request) (*collect.Result, error) {
+				return nil, errors.New("collection reached")
+			})
+			req.Executor = executor
+			req.Collector = collector
+			_, err = RunBatchDetailed(context.Background(), req)
+			if err == nil || err.Error() != "collection reached" {
+				t.Fatalf("RunBatchDetailed() error = %v, want collection error", err)
+			}
+			if len(executor.promptRequests) != test.wantPrompts || len(executor.profileRequests) != 1 {
+				t.Fatalf("inspection calls = prompts %#v profiles %#v", executor.promptRequests, executor.profileRequests)
+			}
+		})
+	}
+}
+
+func TestCopyBatchReportPathsLeavesUnreachedPathsEmpty(t *testing.T) {
+	item := BatchReportResult{}
+	copyBatchReportPaths(&item, &ReportResult{
+		DataPackagePath: "/runs/daily/data_package.yaml",
+		PreparationPath: "/runs/daily/preparation.json",
+	})
+
+	data, err := json.Marshal(item)
+	if err != nil {
+		t.Fatalf("Marshal() error = %v", err)
+	}
+	text := string(data)
+	for _, omitted := range []string{"executionPath", "reportPath", "outputPath", "metadataPath", "notificationPath"} {
+		if strings.Contains(text, omitted) {
+			t.Fatalf("batch item includes unreached field %q:\n%s", omitted, text)
+		}
+	}
+	if !strings.Contains(text, "dataPackagePath") || !strings.Contains(text, "preparationPath") {
+		t.Fatalf("batch item omits reached paths:\n%s", text)
+	}
+}
+
+type collectorFunc func(context.Context, collect.Request) (*collect.Result, error)
+
+func (f collectorFunc) Run(ctx context.Context, req collect.Request) (*collect.Result, error) {
+	return f(ctx, req)
+}
+
+var _ Collector = collectorFunc(nil)

internal/app/batch_plan_test.go

@@ -55,19 +55,6 @@ func TestPlanBatchRunDynamicDailyDatesStartAfterTomorrow(t *testing.T) {
 	assertPlanningPeriod(t, daily[1].Resolved.ValidPeriod, "2026-06-01T00:00:00-05:00", "2026-06-02T00:00:00-05:00")
 }
 
-func TestPlanBatchRunMorningExcludesLegacyStaticReports(t *testing.T) {
-	planned, err := planBatchRun(BatchRequest{Config: planningConfig(), Batch: BatchMorning}, mustParse("2026-05-29T08:00:00-05:00"), collect.Result{Bundle: &weatherdata.Bundle{}})
-	if err != nil {
-		t.Fatalf("planBatchRun() error = %v", err)
-	}
-
-	for _, item := range planned {
-		if item.Resolved.Definition.ID == report.ThreeDay || item.Resolved.Definition.ID == report.Weekend {
-			t.Fatalf("morning plan includes %s, want no 3-Day or Weekend", item.Resolved.Definition.ID)
-		}
-	}
-}
-
 func TestPlanBatchRunDynamicDailyOutputCopyNames(t *testing.T) {
 	location := mustLoadTestLocation(t, "America/Chicago")
 	hourly := hourlyRun(fullDayPeriods(t, "2026-05-31", location)...)

internal/app/batch_workflow_test.go

@@ -0,0 +1,500 @@
+package app
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"errors"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/collect"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/config"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptexec"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptinput"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/report"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/state"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/weatherdata"
+)
+
+type assembledBatchExecutor struct {
+	definitions     map[string]report.Definition
+	promptRequests  []string
+	profileRequests []string
+	executeRequests []promptexec.ExecuteRequest
+	failures        map[int]error
+	active          int
+	maxActive       int
+}
+
+func newAssembledBatchExecutor() *assembledBatchExecutor {
+	definitions := make(map[string]report.Definition)
+	for _, definition := range report.DefaultRegistry().All() {
+		definitions[definition.PromptID] = definition
+	}
+	return &assembledBatchExecutor{definitions: definitions, failures: make(map[int]error)}
+}
+
+func (e *assembledBatchExecutor) InspectPrompt(_ context.Context, id, version string) (promptexec.PromptInspection, error) {
+	e.promptRequests = append(e.promptRequests, id+"@"+version)
+	definition, ok := e.definitions[id]
+	if !ok || definition.PromptVersion != version {
+		return promptexec.PromptInspection{}, errors.New("unexpected prompt inspection")
+	}
+	return validPromptInspection(definition), nil
+}
+
+func (e *assembledBatchExecutor) InspectProfile(_ context.Context, id string) (promptexec.ProfileInspection, error) {
+	e.profileRequests = append(e.profileRequests, id)
+	return promptexec.ProfileInspection{ProfileID: id, BackendID: "fixture", ModelName: "fixture-model"}, nil
+}
+
+func (e *assembledBatchExecutor) Execute(_ context.Context, req promptexec.ExecuteRequest, callback promptexec.PreparationCallback) (*promptexec.Execution, error) {
+	call := len(e.executeRequests)
+	e.executeRequests = append(e.executeRequests, req)
+	e.active++
+	if e.active > e.maxActive {
+		e.maxActive = e.active
+	}
+	defer func() { e.active-- }()
+	stamp := time.Date(2026, 5, 29, 15, 0, 0, 0, time.UTC)
+	preparation := promptexec.Preparation{
+		PromptID: req.PromptID, PromptVersion: req.PromptVersion, PromptHash: "prompt-hash",
+		RenderedPromptHash: "rendered-hash", ProfileID: req.ProfileID, BackendID: "fixture",
+		ModelName: "fixture-model", DataPackagePath: req.DataPackagePath, StartedAt: stamp, EndedAt: stamp,
+	}
+	if err := callback(preparation, nil); err != nil {
+		return nil, err
+	}
+	if err := e.failures[call]; err != nil {
+		return nil, err
+	}
+	definition := e.definitions[req.PromptID]
+	return &promptexec.Execution{
+		RunID: "provider-run", PromptID: req.PromptID, PromptVersion: req.PromptVersion,
+		PromptHash: "prompt-hash", RenderedPromptHash: "rendered-hash", ProfileID: req.ProfileID,
+		BackendID: "fixture", ModelName: "fixture-model", GeneratedHash: "generated-hash",
+		StartedAt: stamp, EndedAt: stamp, DataPackagePath: req.DataPackagePath,
+		RawOutput:  []byte(generatedTextForPrompt(req.PromptID)),
+		Validation: promptexec.NewValidation(promptexec.ValidationPassed, "json_schema", definition.GeneratedTextSchemaID+".generated_text.schema.json", nil),
+	}, nil
+}
+
+type assembledBatchNotifier struct {
+	reportRequests []NotificationRequest
+	batchRequests  []batchNotificationRequest
+	batchResult    *NotificationResult
+	batchErr       error
+}
+
+func (n *assembledBatchNotifier) Notify(_ context.Context, req NotificationRequest) (*NotificationResult, error) {
+	n.reportRequests = append(n.reportRequests, req)
+	return nil, errors.New("per-report notification must be suppressed")
+}
+
+func (n *assembledBatchNotifier) NotifyBatch(_ context.Context, req batchNotificationRequest) (*NotificationResult, error) {
+	n.batchRequests = append(n.batchRequests, req)
+	if n.batchErr != nil {
+		return nil, n.batchErr
+	}
+	if n.batchResult != nil {
+		result := *n.batchResult
+		if result.PipelineID == "" {
+			result.PipelineID = req.PipelineID
+		}
+		if result.BundleID == "" {
+			result.BundleID = req.BundleID
+		}
+		if result.IdempotencyKey == "" {
+			result.IdempotencyKey = req.IdempotencyKey
+		}
+		return &result, nil
+	}
+	return &NotificationResult{
+		RunID: "batch-notification-run", PipelineID: req.PipelineID, BundleID: req.BundleID,
+		IdempotencyKey: req.IdempotencyKey, Status: "succeeded", UploadStatus: "accepted",
+	}, nil
+}
+
+func TestRunBatchDetailedExecutesRetainedReportsSequentially(t *testing.T) {
+	tests := []struct {
+		name       string
+		batch      BatchKind
+		now        time.Time
+		wantIDs    []report.ID
+		wantCopies []string
+	}{
+		{name: "morning", batch: BatchMorning, now: workflowTime("2026-05-29T08:00:00-05:00"), wantIDs: []report.ID{report.Today, report.Tomorrow, report.Daily}, wantCopies: []string{"today.md", "tomorrow.md", "daily-2026-05-31.md"}},
+		{name: "evening", batch: BatchEvening, now: workflowTime("2026-05-29T18:00:00-05:00"), wantIDs: []report.ID{report.Tomorrow, report.Daily}, wantCopies: []string{"tomorrow.md", "daily-2026-05-31.md"}},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			cfg := assembledBatchConfig(t, false)
+			bundle := assembledBatchBundle(t, "2026-05-31")
+			collector := &workflowCollector{result: &collect.Result{Bundle: &bundle}}
+			executor := newAssembledBatchExecutor()
+			outputDir := filepath.Join(t.TempDir(), "output")
+			debugRoot := filepath.Join(t.TempDir(), "debug")
+			result, err := RunBatchDetailed(context.Background(), BatchRequest{
+				Config: cfg, Batch: test.batch, Now: test.now, OutputDir: outputDir, LLMDebugDir: debugRoot,
+				Collector: collector, Executor: executor,
+			})
+			if err != nil {
+				t.Fatalf("RunBatchDetailed() error = %v", err)
+			}
+			if collector.calls != 1 || result.Total != len(test.wantIDs) || result.Succeeded != len(test.wantIDs) || result.Failed != 0 {
+				t.Fatalf("collection/summary = %d/%d/%d/%d", collector.calls, result.Total, result.Succeeded, result.Failed)
+			}
+			if len(executor.executeRequests) != len(test.wantIDs) || executor.maxActive != 1 {
+				t.Fatalf("executor calls/max active = %d/%d, want %d/1", len(executor.executeRequests), executor.maxActive, len(test.wantIDs))
+			}
+			if len(executor.profileRequests) != 1 {
+				t.Fatalf("profile inspections = %#v, want one shared profile inspection", executor.profileRequests)
+			}
+			for index, item := range result.Reports {
+				if item.ReportID != test.wantIDs[index] || item.Status != "succeeded" {
+					t.Fatalf("report %d = %s/%s, want %s/succeeded", index, item.ReportID, item.Status, test.wantIDs[index])
+				}
+				if executor.executeRequests[index].PromptID != item.PromptID {
+					t.Fatalf("execution %d prompt = %q, want item prompt %q", index, executor.executeRequests[index].PromptID, item.PromptID)
+				}
+				if item.DataPackagePath == "" || item.PreparationPath == "" || item.ExecutionPath == "" || item.LLMDebugPath == "" || item.ReportPath == "" || item.OutputPath == "" || item.MetadataPath == "" {
+					t.Fatalf("successful report paths = %#v", item)
+				}
+				assertBatchItemMatchesMetadata(t, item)
+				if filepath.Base(item.OutputPath) != test.wantCopies[index] {
+					t.Fatalf("output copy = %q, want %q", item.OutputPath, test.wantCopies[index])
+				}
+				assertBatchPathsExist(t, item.DataPackagePath, item.PreparationPath, item.ExecutionPath, item.LLMDebugPath, item.ReportPath, item.OutputPath, item.MetadataPath)
+				managed, readErr := os.ReadFile(item.ReportPath)
+				if readErr != nil {
+					t.Fatalf("read managed report: %v", readErr)
+				}
+				copied, readErr := os.ReadFile(item.OutputPath)
+				if readErr != nil || !bytes.Equal(managed, copied) {
+					t.Fatalf("output copy mismatch/error = %v", readErr)
+				}
+			}
+		})
+	}
+}
+
+func TestRunBatchDetailedContinuesAfterCapacityRejection(t *testing.T) {
+	cfg := assembledBatchConfig(t, true)
+	bundle := assembledBatchBundle(t, "2026-05-31")
+	collector := &workflowCollector{result: &collect.Result{Bundle: &bundle}}
+	executor := newAssembledBatchExecutor()
+	executor.failures[1] = promptexec.NewError(promptexec.Capacity, "capacity rejected", nil)
+	notifier := &assembledBatchNotifier{}
+	result, err := RunBatchDetailed(context.Background(), BatchRequest{
+		Config: cfg, Batch: BatchMorning, Now: workflowTime("2026-05-29T08:00:00-05:00"),
+		OutputDir: filepath.Join(t.TempDir(), "output"), LLMDebugDir: filepath.Join(t.TempDir(), "debug"),
+		Collector: collector, Executor: executor, Notifier: notifier,
+	})
+	if err != nil {
+		t.Fatalf("RunBatchDetailed() error = %v", err)
+	}
+	if collector.calls != 1 || len(executor.executeRequests) != 3 || result.Total != 3 || result.Succeeded != 2 || result.Failed != 1 {
+		t.Fatalf("collection/execution/summary = %d/%d/%d/%d/%d", collector.calls, len(executor.executeRequests), result.Total, result.Succeeded, result.Failed)
+	}
+	if len(notifier.reportRequests) != 0 || len(notifier.batchRequests) != 0 || result.Notification == nil || result.Notification.Status != "skipped" {
+		t.Fatalf("notification state = reports %d batches %d result %#v", len(notifier.reportRequests), len(notifier.batchRequests), result.Notification)
+	}
+	for index, item := range result.Reports {
+		if index == 1 {
+			if item.ReportID != report.Tomorrow || item.Status != "failed" || !strings.Contains(item.Error, string(promptexec.Capacity)) {
+				t.Fatalf("failed item = %#v", item)
+			}
+			if item.DataPackagePath == "" || item.PreparationPath == "" || item.ExecutionPath == "" || item.LLMDebugPath == "" || item.MetadataPath == "" || item.ReportPath != "" || item.OutputPath != "" {
+				t.Fatalf("failed item reached paths = %#v", item)
+			}
+			assertBatchItemMatchesMetadata(t, item)
+			continue
+		}
+		if item.Status != "succeeded" || item.ReportPath == "" || item.OutputPath == "" {
+			t.Fatalf("continued item %d = %#v", index, item)
+		}
+	}
+}
+
+func TestRunBatchDetailedNotificationLifecycle(t *testing.T) {
+	t.Run("disabled", func(t *testing.T) {
+		cfg := assembledBatchConfig(t, false)
+		bundle := assembledBatchBundle(t, "2026-05-31")
+		notifier := &assembledBatchNotifier{}
+		result, err := RunBatchDetailed(context.Background(), BatchRequest{
+			Config: cfg, Batch: BatchEvening, Now: workflowTime("2026-05-29T18:00:00-05:00"),
+			Collector: &workflowCollector{result: &collect.Result{Bundle: &bundle}}, Executor: newAssembledBatchExecutor(), Notifier: notifier,
+		})
+		if err != nil || result.Notification != nil || result.Failed != 0 || len(notifier.reportRequests) != 0 || len(notifier.batchRequests) != 0 {
+			t.Fatalf("result/error/requests = %#v/%v/%d/%d", result, err, len(notifier.reportRequests), len(notifier.batchRequests))
+		}
+	})
+
+	t.Run("batch disabled", func(t *testing.T) {
+		cfg := assembledBatchConfig(t, true)
+		cfg.Notify.Distributor.Batch.Enabled = false
+		bundle := assembledBatchBundle(t, "2026-05-31")
+		notifier := &assembledBatchNotifier{}
+		result, err := RunBatchDetailed(context.Background(), BatchRequest{
+			Config: cfg, Batch: BatchEvening, Now: workflowTime("2026-05-29T18:00:00-05:00"),
+			Collector: &workflowCollector{result: &collect.Result{Bundle: &bundle}}, Executor: newAssembledBatchExecutor(), Notifier: notifier,
+		})
+		if err != nil || result.Notification != nil || len(notifier.reportRequests) != 0 || len(notifier.batchRequests) != 0 {
+			t.Fatalf("result/error/requests = %#v/%v/%d/%d", result, err, len(notifier.reportRequests), len(notifier.batchRequests))
+		}
+	})
+
+	t.Run("all success", func(t *testing.T) {
+		cfg := assembledBatchConfig(t, true)
+		bundle := assembledBatchBundle(t, "2026-05-31")
+		notifier := &assembledBatchNotifier{batchResult: &NotificationResult{
+			RunID: "batch-notification-run", Status: "succeeded", UploadStatus: "accepted",
+			Report: []byte(`{"actions":[{"action":"replace_older"}]}`),
+		}}
+		outputDir := filepath.Join(t.TempDir(), "output")
+		result, err := RunBatchDetailed(context.Background(), BatchRequest{
+			Config: cfg, Batch: BatchMorning, Now: workflowTime("2026-05-29T08:00:00-05:00"), OutputDir: outputDir,
+			Collector: &workflowCollector{result: &collect.Result{Bundle: &bundle}}, Executor: newAssembledBatchExecutor(), Notifier: notifier,
+		})
+		if err != nil {
+			t.Fatalf("RunBatchDetailed() error = %v", err)
+		}
+		if result.Failed != 0 || result.Notification == nil || result.Notification.Status != "succeeded" || result.Notification.Path == "" || len(notifier.reportRequests) != 0 || len(notifier.batchRequests) != 1 {
+			t.Fatalf("notification result/requests = %#v/%d/%d", result.Notification, len(notifier.reportRequests), len(notifier.batchRequests))
+		}
+		managedPaths := make(map[string]struct{}, len(result.Reports))
+		for _, item := range result.Reports {
+			managedPaths[item.ReportPath] = struct{}{}
+			if item.NotificationPath != "" {
+				t.Fatalf("report item contains per-report notification path: %#v", item)
+			}
+		}
+		request := notifier.batchRequests[0]
+		if len(request.IncludedReports) != len(result.Reports) {
+			t.Fatalf("included reports = %d, want %d", len(request.IncludedReports), len(result.Reports))
+		}
+		for _, file := range request.Files {
+			if _, ok := managedPaths[file.SourcePath]; !ok || strings.HasPrefix(file.SourcePath, outputDir+string(filepath.Separator)) || file.BundlePath == "" {
+				t.Fatalf("notification file = %#v, want managed Markdown source", file)
+			}
+		}
+		artifact := readBatchNotificationArtifact(t, result.Notification.Path)
+		if artifact.Status != "succeeded" || artifact.Upload == nil || artifact.Upload.RunID != "batch-notification-run" || artifact.RunStatus == nil || len(artifact.Reports) != len(result.Reports) {
+			t.Fatalf("notification artifact = %#v", artifact)
+		}
+	})
+
+	t.Run("upload failure", func(t *testing.T) {
+		cfg := assembledBatchConfig(t, true)
+		bundle := assembledBatchBundle(t, "2026-05-31")
+		notifier := &assembledBatchNotifier{batchErr: errors.New("batch upload rejected")}
+		result, err := RunBatchDetailed(context.Background(), BatchRequest{
+			Config: cfg, Batch: BatchEvening, Now: workflowTime("2026-05-29T18:00:00-05:00"),
+			Collector: &workflowCollector{result: &collect.Result{Bundle: &bundle}}, Executor: newAssembledBatchExecutor(), Notifier: notifier,
+		})
+		if err != nil {
+			t.Fatalf("RunBatchDetailed() error = %v", err)
+		}
+		if result.Succeeded != 2 || result.Failed != 1 || result.Notification == nil || result.Notification.Status != "failed" || result.Notification.Path == "" {
+			t.Fatalf("result = %#v, want successful reports and failed notification", result)
+		}
+		for _, item := range result.Reports {
+			if item.Status != "succeeded" {
+				t.Fatalf("report item = %#v, want success despite notification failure", item)
+			}
+		}
+		artifact := readBatchNotificationArtifact(t, result.Notification.Path)
+		if artifact.Status != "failed" || !strings.Contains(artifact.Error, "batch upload rejected") {
+			t.Fatalf("notification artifact = %#v", artifact)
+		}
+	})
+
+	t.Run("status report", func(t *testing.T) {
+		cfg := assembledBatchConfig(t, true)
+		bundle := assembledBatchBundle(t, "2026-05-31")
+		notifier := &assembledBatchNotifier{batchResult: &NotificationResult{
+			RunID: "batch-notification-run", Status: "accepted", UploadStatus: "accepted",
+			StatusError: "status lookup unavailable", Report: []byte(`{"actions":[{"action":"replace_older"}]}`),
+		}}
+		result, err := RunBatchDetailed(context.Background(), BatchRequest{
+			Config: cfg, Batch: BatchEvening, Now: workflowTime("2026-05-29T18:00:00-05:00"),
+			Collector: &workflowCollector{result: &collect.Result{Bundle: &bundle}}, Executor: newAssembledBatchExecutor(), Notifier: notifier,
+		})
+		if err != nil || result.Failed != 0 || result.Notification == nil || result.Notification.Path == "" {
+			t.Fatalf("result/error = %#v/%v", result, err)
+		}
+		artifact := readBatchNotificationArtifact(t, result.Notification.Path)
+		if artifact.StatusError != "status lookup unavailable" || artifact.RunStatus == nil || !bytes.Contains(artifact.RunStatus.Report, []byte("replace_older")) {
+			t.Fatalf("notification artifact = %#v", artifact)
+		}
+	})
+}
+
+func TestRunBatchDetailedKeepsDynamicDailyArtifactsDistinct(t *testing.T) {
+	cfg := assembledBatchConfig(t, false)
+	bundle := assembledBatchBundle(t, "2026-05-31", "2026-06-01")
+	outputDir := filepath.Join(t.TempDir(), "output")
+	debugRoot := filepath.Join(t.TempDir(), "debug")
+	result, err := RunBatchDetailed(context.Background(), BatchRequest{
+		Config: cfg, Batch: BatchEvening, Now: workflowTime("2026-05-29T18:00:00-05:00"), OutputDir: outputDir, LLMDebugDir: debugRoot,
+		Collector: &workflowCollector{result: &collect.Result{Bundle: &bundle}}, Executor: newAssembledBatchExecutor(),
+	})
+	if err != nil || result.Failed != 0 || len(result.Reports) != 3 {
+		t.Fatalf("result/error = %#v/%v", result, err)
+	}
+	seenRuns := make(map[string]struct{})
+	seenDebug := make(map[string]struct{})
+	dailyDates := make(map[string]BatchReportResult)
+	for _, item := range result.Reports {
+		if _, exists := seenRuns[item.RunID]; exists {
+			t.Fatalf("duplicate run ID %q", item.RunID)
+		}
+		seenRuns[item.RunID] = struct{}{}
+		if _, exists := seenDebug[item.LLMDebugPath]; exists {
+			t.Fatalf("duplicate debug path %q", item.LLMDebugPath)
+		}
+		seenDebug[item.LLMDebugPath] = struct{}{}
+		if item.ReportID == report.Daily {
+			date := item.ValidPeriod.Start.In(mustLoadTestLocation(t, "America/Chicago")).Format("2006-01-02")
+			dailyDates[date] = item
+		}
+	}
+	for _, date := range []string{"2026-05-31", "2026-06-01"} {
+		item, ok := dailyDates[date]
+		if !ok {
+			t.Fatalf("daily items = %#v, want %s", dailyDates, date)
+		}
+		if !strings.HasSuffix(item.RunID, "_daily_"+date) || item.OutputPath != filepath.Join(outputDir, "daily-"+date+".md") {
+			t.Fatalf("daily identity/output = %q/%q", item.RunID, item.OutputPath)
+		}
+		wantDebugPrefix := filepath.Join(debugRoot, "daily", date, item.RunID)
+		if item.LLMDebugPath != wantDebugPrefix {
+			t.Fatalf("daily debug path = %q, want %q", item.LLMDebugPath, wantDebugPrefix)
+		}
+		assertBatchPathsExist(t, filepath.Join(item.LLMDebugPath, "preparation.json"), filepath.Join(item.LLMDebugPath, "execution.json"))
+	}
+}
+
+func TestRunBatchDetailedUsesPriorSnapshotsForPromptPackages(t *testing.T) {
+	cfg := assembledBatchConfig(t, false)
+	firstBundle := assembledBatchBundle(t, "2026-05-31")
+	setWorkflowTemperatures(&firstBundle, 45)
+	first, err := RunBatchDetailed(context.Background(), BatchRequest{
+		Config: cfg, Batch: BatchMorning, Now: workflowTime("2026-05-29T08:00:00-05:00"),
+		Collector: &workflowCollector{result: &collect.Result{Bundle: &firstBundle}}, Executor: newAssembledBatchExecutor(),
+	})
+	if err != nil || first.Failed != 0 {
+		t.Fatalf("first result/error = %#v/%v", first, err)
+	}
+	secondBundle := assembledBatchBundle(t, "2026-05-31")
+	setWorkflowTemperatures(&secondBundle, 85)
+	second, err := RunBatchDetailed(context.Background(), BatchRequest{
+		Config: cfg, Batch: BatchMorning, Now: workflowTime("2026-05-29T08:30:00-05:00"),
+		Collector: &workflowCollector{result: &collect.Result{Bundle: &secondBundle}}, Executor: newAssembledBatchExecutor(),
+	})
+	if err != nil || second.Failed != 0 || len(second.Reports) != len(first.Reports) {
+		t.Fatalf("second result/error = %#v/%v", second, err)
+	}
+	for _, item := range second.Reports {
+		pkg := loadBatchDataPackage(t, item.DataPackagePath)
+		if len(pkg.RecentChanges.Items) == 0 {
+			t.Fatalf("report %s data package has no changes from prior snapshot", item.ReportID)
+		}
+	}
+}
+
+func assembledBatchConfig(t *testing.T, notify bool) config.Config {
+	t.Helper()
+	cfg := workflowConfig(t)
+	cfg.Notify.Distributor.Enabled = notify
+	cfg.Notify.Distributor.Batch.Enabled = notify
+	return cfg
+}
+
+func assembledBatchBundle(t *testing.T, dates ...string) weatherdata.Bundle {
+	t.Helper()
+	bundle := workflowBundle(t)
+	location := mustLoadTestLocation(t, "America/Chicago")
+	for _, date := range dates {
+		periods := fullDayPeriods(t, date, location)
+		for index := range periods {
+			temperature := float64(60 + index)
+			periods[index].TemperatureF = &temperature
+			periods[index].TextDescription = "Partly cloudy"
+		}
+		bundle.Hourly.Periods = append(bundle.Hourly.Periods, periods...)
+	}
+	return bundle
+}
+
+func generatedTextForPrompt(promptID string) string {
+	switch promptID {
+	case "weather.today_generated_text":
+		return validTodayWorkflowJSON()
+	case "weather.tomorrow_generated_text":
+		return validTomorrowWorkflowJSON()
+	case "weather.daily_generated_text":
+		return validDailyWorkflowJSON()
+	case "weather.hourly_generated_text":
+		return validHourlyWorkflowJSON()
+	default:
+		return ""
+	}
+}
+
+func assertBatchPathsExist(t *testing.T, paths ...string) {
+	t.Helper()
+	for _, path := range paths {
+		if _, err := os.Stat(path); err != nil {
+			t.Fatalf("expected path %q: %v", path, err)
+		}
+	}
+}
+
+func assertBatchItemMatchesMetadata(t *testing.T, item BatchReportResult) {
+	t.Helper()
+	data, err := os.ReadFile(item.MetadataPath)
+	if err != nil {
+		t.Fatalf("read metadata %q: %v", item.MetadataPath, err)
+	}
+	var metadata state.Metadata
+	if err := json.Unmarshal(data, &metadata); err != nil {
+		t.Fatalf("decode metadata %q: %v", item.MetadataPath, err)
+	}
+	if item.ReportID != metadata.ReportID || item.RunID != metadata.RunID ||
+		item.DataPackagePath != metadata.DataPackagePath || item.PreparationPath != metadata.PreparationPath ||
+		item.ExecutionPath != metadata.ExecutionPath || item.ReportPath != metadata.RenderedReportPath ||
+		item.NotificationPath != metadata.NotificationPath {
+		t.Fatalf("batch item paths do not exactly match metadata: item=%#v metadata=%#v", item, metadata)
+	}
+}
+
+func readBatchNotificationArtifact(t *testing.T, path string) state.BatchDistributorNotificationArtifact {
+	t.Helper()
+	data, err := os.ReadFile(path)
+	if err != nil {
+		t.Fatalf("read batch notification artifact: %v", err)
+	}
+	var artifact state.BatchDistributorNotificationArtifact
+	if err := json.Unmarshal(data, &artifact); err != nil {
+		t.Fatalf("decode batch notification artifact: %v", err)
+	}
+	return artifact
+}
+
+func loadBatchDataPackage(t *testing.T, path string) promptinput.Package {
+	t.Helper()
+	data, err := os.ReadFile(path)
+	if err != nil {
+		t.Fatalf("read data package: %v", err)
+	}
+	pkg, err := promptinput.LoadYAML(data)
+	if err != nil {
+		t.Fatalf("LoadYAML() error = %v", err)
+	}
+	return pkg
+}

internal/app/prompt_artifact_paths_test.go

@@ -0,0 +1,552 @@
+package app
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/collect"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/config"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptexec"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/report"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/state"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/weatherdata"
+)
+
+const (
+	failPromptExecution         = "prompt execution"
+	failMetadata                = "metadata"
+	failGeneratedText           = "generated text"
+	failRenderContext           = "render context"
+	failRenderedReportPath      = "rendered report path"
+	failDistributorNotification = "distributor notification"
+)
+
+type failingPersistenceStore struct {
+	state.Store
+	failOperation      string
+	failExecutionCall  int
+	failMetadataCall   int
+	executionCalls     int
+	metadataCalls      int
+	renderedReportPath string
+}
+
+func (s *failingPersistenceStore) SavePromptExecution(ctx context.Context, resolved report.Resolved, artifact state.PromptExecutionArtifact) (string, error) {
+	s.executionCalls++
+	if s.failOperation == failPromptExecution && (s.failExecutionCall == 0 || s.executionCalls == s.failExecutionCall) {
+		return "", errors.New("injected prompt execution persistence failure")
+	}
+	return s.Store.SavePromptExecution(ctx, resolved, artifact)
+}
+
+func (s *failingPersistenceStore) SaveGeneratedText(ctx context.Context, resolved report.Resolved, data []byte) (string, error) {
+	if s.failOperation == failGeneratedText {
+		return "", errors.New("injected generated text persistence failure")
+	}
+	return s.Store.SaveGeneratedText(ctx, resolved, data)
+}
+
+func (s *failingPersistenceStore) SaveRenderContext(ctx context.Context, resolved report.Resolved, value any) (string, error) {
+	if s.failOperation == failRenderContext {
+		return "", errors.New("injected render context persistence failure")
+	}
+	return s.Store.SaveRenderContext(ctx, resolved, value)
+}
+
+func (s *failingPersistenceStore) PrepareRenderedReport(ctx context.Context, resolved report.Resolved) (string, error) {
+	if s.failOperation == failRenderedReportPath {
+		return s.renderedReportPath, nil
+	}
+	return s.Store.PrepareRenderedReport(ctx, resolved)
+}
+
+func (s *failingPersistenceStore) SaveDistributorNotification(ctx context.Context, resolved report.Resolved, artifact state.DistributorNotificationArtifact) (string, error) {
+	if s.failOperation == failDistributorNotification {
+		return "", errors.New("injected notification persistence failure")
+	}
+	return s.Store.SaveDistributorNotification(ctx, resolved, artifact)
+}
+
+func (s *failingPersistenceStore) SaveMetadata(ctx context.Context, metadata state.Metadata) (string, error) {
+	s.metadataCalls++
+	if s.failOperation == failMetadata && s.metadataCalls == s.failMetadataCall {
+		return "", errors.New("injected metadata persistence failure")
+	}
+	return s.Store.SaveMetadata(ctx, metadata)
+}
+
+type artifactPathExecutor struct {
+	beforePreparationErr error
+	afterPreparationErr  error
+	validation           promptexec.ValidationStatus
+}
+
+func (e artifactPathExecutor) InspectPrompt(context.Context, string, string) (promptexec.PromptInspection, error) {
+	return promptexec.PromptInspection{}, errors.New("unexpected inspection")
+}
+
+func (e artifactPathExecutor) InspectProfile(context.Context, string) (promptexec.ProfileInspection, error) {
+	return promptexec.ProfileInspection{}, errors.New("unexpected inspection")
+}
+
+func (e artifactPathExecutor) Execute(_ context.Context, req promptexec.ExecuteRequest, callback promptexec.PreparationCallback) (*promptexec.Execution, error) {
+	if e.beforePreparationErr != nil {
+		return nil, e.beforePreparationErr
+	}
+	now := time.Date(2026, 5, 29, 15, 0, 0, 0, time.UTC)
+	if err := callback(promptexec.Preparation{
+		PromptID: req.PromptID, PromptVersion: req.PromptVersion, PromptHash: "prompt-hash",
+		RenderedPromptHash: "rendered-hash", ProfileID: req.ProfileID, BackendID: "test",
+		ModelName: "test-model", DataPackagePath: req.DataPackagePath, StartedAt: now, EndedAt: now,
+	}, nil); err != nil {
+		return nil, err
+	}
+	if e.afterPreparationErr != nil {
+		return nil, e.afterPreparationErr
+	}
+	validation := e.validation
+	if validation == "" {
+		validation = promptexec.ValidationPassed
+	}
+	return &promptexec.Execution{
+		RunID: "provider-run", PromptID: req.PromptID, PromptVersion: req.PromptVersion,
+		PromptHash: "prompt-hash", RenderedPromptHash: "rendered-hash", ProfileID: req.ProfileID,
+		BackendID: "test", ModelName: "test-model", GeneratedHash: "generated-hash",
+		StartedAt: now, EndedAt: now, DataPackagePath: req.DataPackagePath,
+		RawOutput:  []byte(`{"summary":"Showers are possible during the selected day.","forecast_discussion":["A front will keep rain chances in the forecast."],"precipitation_timing":"Rain is most likely during the afternoon.","confidence":"Medium"}`),
+		Validation: promptexec.NewValidation(validation, "json_schema", "daily.generated_text.schema.json", nil),
+	}, nil
+}
+
+type successfulNotifier struct{}
+
+func (successfulNotifier) Notify(context.Context, NotificationRequest) (*NotificationResult, error) {
+	return &NotificationResult{RunID: "notification-run", Status: "succeeded", UploadStatus: "accepted"}, nil
+}
+
+type failingNotifier struct{}
+
+func (failingNotifier) Notify(context.Context, NotificationRequest) (*NotificationResult, error) {
+	return nil, errors.New("injected notification failure")
+}
+
+func TestGeneratePromptReportReturnsOnlyReachedArtifactPaths(t *testing.T) {
+	tests := []struct {
+		name             string
+		failOperation    string
+		failMetadataCall int
+		outputCopy       bool
+		notify           bool
+		want             reachedPromptArtifacts
+	}{
+		{name: "preparation then metadata", failOperation: failMetadata, failMetadataCall: 1, want: reachedPromptArtifacts{preparation: true}},
+		{name: "raw output then execution", failOperation: failPromptExecution, want: reachedPromptArtifacts{preparation: true, metadata: true, raw: true}},
+		{name: "execution then metadata", failOperation: failMetadata, failMetadataCall: 2, want: reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true}},
+		{name: "normalized output then metadata", failOperation: failMetadata, failMetadataCall: 3, want: reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true}},
+		{name: "render context then metadata", failOperation: failMetadata, failMetadataCall: 4, want: reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true, renderContext: true}},
+		{name: "managed report then metadata", failOperation: failMetadata, failMetadataCall: 5, want: reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true, renderContext: true, report: true}},
+		{name: "output copy then metadata", failOperation: failMetadata, failMetadataCall: 5, outputCopy: true, want: reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true, renderContext: true, report: true, output: true}},
+		{name: "notification then metadata", failOperation: failMetadata, failMetadataCall: 6, notify: true, want: reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true, renderContext: true, report: true, notification: true}},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			req, paths := promptArtifactRequest(t, artifactPathExecutor{})
+			store := &failingPersistenceStore{Store: req.Store, failOperation: test.failOperation, failMetadataCall: test.failMetadataCall}
+			req.Store = store
+			if test.outputCopy {
+				req.OutputPath = filepath.Join(t.TempDir(), "daily.md")
+				paths.output = req.OutputPath
+			}
+			if test.notify {
+				req.Config.Notify.Distributor.Enabled = true
+				req.Config.Notify.Distributor.PipelineIDTemplate = "weatherreporter"
+				req.Notifier = successfulNotifier{}
+				req.noNotify = false
+			}
+
+			result, err := generatePromptReport(context.Background(), req)
+			if err == nil || result == nil {
+				t.Fatalf("generatePromptReport() result/error = %#v/%v, want partial result and failure", result, err)
+			}
+			assertReachedPromptArtifacts(t, result, paths, test.want)
+		})
+	}
+}
+
+func TestGeneratePromptReportFailureReceiptsExposeReachedPaths(t *testing.T) {
+	tests := []struct {
+		name                string
+		executor            artifactPathExecutor
+		want                reachedPromptArtifacts
+		wantExecutionStatus state.PromptExecutionStatus
+		wantExecutionPaths  state.PromptExecutionPaths
+		wantRawExecution    bool
+	}{
+		{
+			name:     "preparation failure",
+			executor: artifactPathExecutor{beforePreparationErr: promptexec.NewError(promptexec.Generation, "prepare failed", nil)},
+			want:     reachedPromptArtifacts{preparation: true, metadata: true},
+		},
+		{
+			name:                "operational execution failure",
+			executor:            artifactPathExecutor{afterPreparationErr: promptexec.NewError(promptexec.Generation, "provider failed", nil)},
+			want:                reachedPromptArtifacts{preparation: true, execution: true, metadata: true},
+			wantExecutionStatus: state.PromptExecutionFailed,
+		},
+		{
+			name:                "completed validation rejection",
+			executor:            artifactPathExecutor{validation: promptexec.ValidationFailed},
+			want:                reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true},
+			wantExecutionStatus: state.PromptExecutionValidationRejected,
+			wantRawExecution:    true,
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			req, paths := promptArtifactRequest(t, test.executor)
+			if test.wantRawExecution {
+				test.wantExecutionPaths.RawOutputPath = paths.GeneratedTextRaw
+			}
+			result, err := generatePromptReport(context.Background(), req)
+			if err == nil || result == nil {
+				t.Fatalf("generatePromptReport() result/error = %#v/%v, want partial result and failure", result, err)
+			}
+			assertReachedPromptArtifacts(t, result, paths, test.want)
+			if test.wantExecutionStatus != "" {
+				artifact, loadErr := req.Store.LoadPromptExecution(context.Background(), result.ExecutionPath)
+				if loadErr != nil {
+					t.Fatalf("LoadPromptExecution() error = %v", loadErr)
+				}
+				if artifact.Status != test.wantExecutionStatus || artifact.Paths != test.wantExecutionPaths {
+					t.Fatalf("execution outcome/paths = %q/%#v, want %q/%#v", artifact.Status, artifact.Paths, test.wantExecutionStatus, test.wantExecutionPaths)
+				}
+			}
+		})
+	}
+}
+
+func TestCompletedExecutionArtifactTracksDownstreamLifecycle(t *testing.T) {
+	req, paths := promptArtifactRequest(t, artifactPathExecutor{})
+	req.OutputPath = filepath.Join(t.TempDir(), "daily.md")
+	paths.output = req.OutputPath
+	req.Config.Notify.Distributor.Enabled = true
+	req.Config.Notify.Distributor.PipelineIDTemplate = "weatherreporter"
+	req.Notifier = successfulNotifier{}
+	req.noNotify = false
+
+	result, err := generatePromptReport(context.Background(), req)
+	if err != nil {
+		t.Fatalf("generatePromptReport() error = %v", err)
+	}
+	want := state.PromptExecutionPaths{
+		RawOutputPath: paths.GeneratedTextRaw, GeneratedTextPath: paths.GeneratedText,
+		RenderContextPath: paths.RenderContext, RenderedReportPath: paths.RenderedReport,
+		OutputPath: paths.output, NotificationPath: paths.Notification,
+	}
+	assertPersistedExecutionPaths(t, req.Store, result.ExecutionPath, want)
+
+	data, err := os.ReadFile(result.ExecutionPath)
+	if err != nil {
+		t.Fatalf("read execution artifact: %v", err)
+	}
+	text := string(data)
+	for _, forbidden := range []string{
+		"Showers are possible during the selected day", `"rawOutput":`, `"debug":`,
+		`"renderedMessages":`, `"structuredSchema":`, `"endpoint":`, `"parametersJSON":`,
+		"credential", "secret-value",
+	} {
+		if strings.Contains(text, forbidden) {
+			t.Fatalf("execution artifact contains unsafe generated or provider detail %q:\n%s", forbidden, text)
+		}
+	}
+}
+
+func TestCompletedExecutionArtifactRetainsLastPersistedCheckpoint(t *testing.T) {
+	tests := []struct {
+		name                string
+		failOperation       string
+		failExecutionCall   int
+		failMetadataCall    int
+		requestOutput       bool
+		failOutputCopy      bool
+		notify              bool
+		notificationFailure bool
+		wantExecution       reachedExecutionArtifacts
+		wantResult          reachedPromptArtifacts
+	}{
+		{
+			name: "normalized text write", failOperation: failGeneratedText,
+			wantExecution: reachedExecutionArtifacts{raw: true},
+			wantResult:    reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true},
+		},
+		{
+			name: "normalized text checkpoint", failOperation: failPromptExecution, failExecutionCall: 2,
+			wantExecution: reachedExecutionArtifacts{raw: true},
+			wantResult:    reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true},
+		},
+		{
+			name: "normalized text metadata", failOperation: failMetadata, failMetadataCall: 3,
+			wantExecution: reachedExecutionArtifacts{raw: true, normalized: true},
+			wantResult:    reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true},
+		},
+		{
+			name: "render context write", failOperation: failRenderContext,
+			wantExecution: reachedExecutionArtifacts{raw: true, normalized: true},
+			wantResult:    reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true},
+		},
+		{
+			name: "render context checkpoint", failOperation: failPromptExecution, failExecutionCall: 3,
+			wantExecution: reachedExecutionArtifacts{raw: true, normalized: true},
+			wantResult:    reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true, renderContext: true},
+		},
+		{
+			name: "render context metadata", failOperation: failMetadata, failMetadataCall: 4,
+			wantExecution: reachedExecutionArtifacts{raw: true, normalized: true, renderContext: true},
+			wantResult:    reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true, renderContext: true},
+		},
+		{
+			name: "managed report write", failOperation: failRenderedReportPath,
+			wantExecution: reachedExecutionArtifacts{raw: true, normalized: true, renderContext: true},
+			wantResult:    reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true, renderContext: true},
+		},
+		{
+			name: "managed report checkpoint", failOperation: failPromptExecution, failExecutionCall: 4,
+			wantExecution: reachedExecutionArtifacts{raw: true, normalized: true, renderContext: true},
+			wantResult:    reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true, renderContext: true, report: true},
+		},
+		{
+			name: "output copy write", requestOutput: true, failOutputCopy: true,
+			wantExecution: reachedExecutionArtifacts{raw: true, normalized: true, renderContext: true, report: true},
+			wantResult:    reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true, renderContext: true, report: true},
+		},
+		{
+			name: "output copy checkpoint", failOperation: failPromptExecution, failExecutionCall: 5, requestOutput: true,
+			wantExecution: reachedExecutionArtifacts{raw: true, normalized: true, renderContext: true, report: true},
+			wantResult:    reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true, renderContext: true, report: true, output: true},
+		},
+		{
+			name: "output copy metadata", failOperation: failMetadata, failMetadataCall: 5, requestOutput: true,
+			wantExecution: reachedExecutionArtifacts{raw: true, normalized: true, renderContext: true, report: true, output: true},
+			wantResult:    reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true, renderContext: true, report: true, output: true},
+		},
+		{
+			name: "notification artifact write", failOperation: failDistributorNotification, requestOutput: true, notify: true,
+			wantExecution: reachedExecutionArtifacts{raw: true, normalized: true, renderContext: true, report: true, output: true},
+			wantResult:    reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true, renderContext: true, report: true, output: true},
+		},
+		{
+			name: "notification checkpoint", failOperation: failPromptExecution, failExecutionCall: 6, requestOutput: true, notify: true,
+			wantExecution: reachedExecutionArtifacts{raw: true, normalized: true, renderContext: true, report: true, output: true},
+			wantResult:    reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true, renderContext: true, report: true, output: true, notification: true},
+		},
+		{
+			name: "notification metadata", failOperation: failMetadata, failMetadataCall: 6, requestOutput: true, notify: true,
+			wantExecution: reachedExecutionArtifacts{raw: true, normalized: true, renderContext: true, report: true, output: true, notification: true},
+			wantResult:    reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true, renderContext: true, report: true, output: true, notification: true},
+		},
+		{
+			name: "notification operation", requestOutput: true, notify: true, notificationFailure: true,
+			wantExecution: reachedExecutionArtifacts{raw: true, normalized: true, renderContext: true, report: true, output: true, notification: true},
+			wantResult:    reachedPromptArtifacts{preparation: true, execution: true, metadata: true, raw: true, normalized: true, renderContext: true, report: true, output: true, notification: true},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			req, paths := promptArtifactRequest(t, artifactPathExecutor{})
+			store := &failingPersistenceStore{
+				Store: req.Store, failOperation: test.failOperation,
+				failExecutionCall: test.failExecutionCall, failMetadataCall: test.failMetadataCall,
+			}
+			if test.failOperation == failRenderedReportPath {
+				store.renderedReportPath = t.TempDir()
+			}
+			req.Store = store
+			if test.requestOutput {
+				req.OutputPath = filepath.Join(t.TempDir(), "daily.md")
+				paths.output = req.OutputPath
+			}
+			if test.failOutputCopy {
+				blocker := filepath.Join(t.TempDir(), "not-a-directory")
+				if err := os.WriteFile(blocker, []byte("block"), 0o600); err != nil {
+					t.Fatalf("write output blocker: %v", err)
+				}
+				req.OutputPath = filepath.Join(blocker, "daily.md")
+				paths.output = req.OutputPath
+			}
+			if test.notify {
+				req.Config.Notify.Distributor.Enabled = true
+				req.Config.Notify.Distributor.PipelineIDTemplate = "weatherreporter"
+				req.Notifier = successfulNotifier{}
+				req.noNotify = false
+			}
+			if test.notificationFailure {
+				req.Notifier = failingNotifier{}
+			}
+
+			result, err := generatePromptReport(context.Background(), req)
+			if err == nil || result == nil {
+				t.Fatalf("generatePromptReport() result/error = %#v/%v, want partial result and failure", result, err)
+			}
+			assertReachedPromptArtifacts(t, result, paths, test.wantResult)
+			assertPersistedExecutionPaths(t, store, result.ExecutionPath, executionPathsFor(paths, test.wantExecution))
+		})
+	}
+}
+
+type reachedExecutionArtifacts struct {
+	raw           bool
+	normalized    bool
+	renderContext bool
+	report        bool
+	output        bool
+	notification  bool
+}
+
+func executionPathsFor(paths promptArtifactPaths, reached reachedExecutionArtifacts) state.PromptExecutionPaths {
+	result := state.PromptExecutionPaths{}
+	if reached.raw {
+		result.RawOutputPath = paths.GeneratedTextRaw
+	}
+	if reached.normalized {
+		result.GeneratedTextPath = paths.GeneratedText
+	}
+	if reached.renderContext {
+		result.RenderContextPath = paths.RenderContext
+	}
+	if reached.report {
+		result.RenderedReportPath = paths.RenderedReport
+	}
+	if reached.output {
+		result.OutputPath = paths.output
+	}
+	if reached.notification {
+		result.NotificationPath = paths.Notification
+	}
+	return result
+}
+
+func assertPersistedExecutionPaths(t *testing.T, store state.Store, path string, want state.PromptExecutionPaths) {
+	t.Helper()
+	artifact, err := store.LoadPromptExecution(context.Background(), path)
+	if err != nil {
+		t.Fatalf("LoadPromptExecution() error = %v", err)
+	}
+	if artifact.Status != state.PromptExecutionSucceeded || artifact.Validation == nil || artifact.Validation.Status != promptexec.ValidationPassed {
+		t.Fatalf("execution outcome changed after downstream write: %#v", artifact)
+	}
+	if artifact.Provenance == nil || artifact.Provenance.RunID != "provider-run" || artifact.Provenance.PromptHash != "prompt-hash" {
+		t.Fatalf("execution provenance changed after downstream write: %#v", artifact.Provenance)
+	}
+	if artifact.Paths != want {
+		t.Fatalf("execution paths = %#v, want %#v", artifact.Paths, want)
+	}
+}
+
+type promptArtifactPaths struct {
+	state.ArtifactPaths
+	output string
+}
+
+type reachedPromptArtifacts struct {
+	preparation   bool
+	execution     bool
+	metadata      bool
+	raw           bool
+	normalized    bool
+	renderContext bool
+	report        bool
+	output        bool
+	notification  bool
+}
+
+func promptArtifactRequest(t *testing.T, executor promptexec.Executor) (promptReportRequest, promptArtifactPaths) {
+	t.Helper()
+	cfg := config.Defaults()
+	cfg.Workspace.Root = t.TempDir()
+	resolved, err := ResolveGenerate(GenerateRequest{
+		Config: cfg, Report: ReportDaily, Date: mustParse("2026-05-29T12:00:00-05:00"),
+	}, mustParse("2026-05-29T05:00:00-05:00"))
+	if err != nil {
+		t.Fatalf("ResolveGenerate() error = %v", err)
+	}
+	bundleData, err := os.ReadFile(filepath.Join("..", "forecast", "testdata", "daily_bundle.json"))
+	if err != nil {
+		t.Fatalf("read daily fixture: %v", err)
+	}
+	var bundle weatherdata.Bundle
+	if err := json.Unmarshal(bundleData, &bundle); err != nil {
+		t.Fatalf("decode daily fixture: %v", err)
+	}
+	filesystemStore, err := state.NewFilesystemStore(cfg.Workspace)
+	if err != nil {
+		t.Fatalf("NewFilesystemStore() error = %v", err)
+	}
+	paths, err := filesystemStore.Paths(resolved)
+	if err != nil {
+		t.Fatalf("Paths() error = %v", err)
+	}
+	debugWriter, err := state.NewPromptDebugWriter("")
+	if err != nil {
+		t.Fatalf("NewPromptDebugWriter() error = %v", err)
+	}
+	return promptReportRequest{
+		GenerateRequest: GenerateRequest{Config: cfg, Report: ReportDaily, Executor: executor, Store: filesystemStore},
+		Resolved:        resolved, Collection: collect.Result{Bundle: &bundle},
+		Inspection: PromptInspectionResult{
+			PromptID: resolved.Definition.PromptID, PromptVersion: resolved.Definition.PromptVersion,
+			PromptHash: "prompt-hash", ProfileID: "test-profile", BackendID: "test", ModelName: "test-model",
+		},
+		DebugWriter: debugWriter, noNotify: true,
+	}, promptArtifactPaths{ArtifactPaths: paths}
+}
+
+func assertReachedPromptArtifacts(t *testing.T, result *ReportResult, paths promptArtifactPaths, want reachedPromptArtifacts) {
+	t.Helper()
+	if result.ModuleSnapshotPath != paths.ModuleSnapshot || result.DataPackagePath != paths.DataPackage {
+		t.Fatalf("base paths = module %q data %q, want %q and %q", result.ModuleSnapshotPath, result.DataPackagePath, paths.ModuleSnapshot, paths.DataPackage)
+	}
+	if result.Metadata.ModuleSnapshotPath != paths.ModuleSnapshot || result.Metadata.DataPackagePath != paths.DataPackage || result.Metadata.MetadataPath != paths.Metadata {
+		t.Fatalf("metadata base paths = %#v, want reached module/data paths and metadata destination", result.Metadata)
+	}
+	checks := []struct {
+		name        string
+		got         string
+		metadataGot string
+		inMetadata  bool
+		path        string
+		want        bool
+	}{
+		{"preparation", result.PreparationPath, result.Metadata.PreparationPath, true, paths.Preparation, want.preparation},
+		{"execution", result.ExecutionPath, result.Metadata.ExecutionPath, true, paths.Execution, want.execution},
+		{"metadata", result.MetadataPath, "", false, paths.Metadata, want.metadata},
+		{"raw", result.GeneratedTextRawPath, result.Metadata.GeneratedTextRawPath, true, paths.GeneratedTextRaw, want.raw},
+		{"normalized", result.GeneratedTextPath, result.Metadata.GeneratedTextPath, true, paths.GeneratedText, want.normalized},
+		{"render context", result.RenderContextPath, result.Metadata.RenderContextPath, true, paths.RenderContext, want.renderContext},
+		{"report", result.ReportPath, result.Metadata.RenderedReportPath, true, paths.RenderedReport, want.report},
+		{"output", result.OutputPath, "", false, paths.output, want.output},
+		{"notification", result.NotificationPath, result.Metadata.NotificationPath, true, paths.Notification, want.notification},
+	}
+	for _, check := range checks {
+		if check.want && check.got != check.path {
+			t.Errorf("%s path = %q, want reached path %q", check.name, check.got, check.path)
+		}
+		if check.want && check.inMetadata && check.metadataGot != check.path {
+			t.Errorf("metadata %s path = %q, want reached path %q", check.name, check.metadataGot, check.path)
+		}
+		if !check.want && check.got != "" {
+			t.Errorf("%s path = %q, want empty because artifact was not reached", check.name, check.got)
+		}
+		if !check.want && check.inMetadata && check.metadataGot != "" {
+			t.Errorf("metadata %s path = %q, want empty because artifact was not reached", check.name, check.metadataGot)
+		}
+	}
+}

internal/app/prompt_generate.go

@@ -0,0 +1,423 @@
+package app
+
+import (
+	"context"
+	"fmt"
+	"time"
+
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/briefing"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/collect"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/fileutil"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/generatedtext"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/module"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptexec"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptinput"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/report"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/state"
+)
+
+type promptReportRequest struct {
+	GenerateRequest
+	Resolved    report.Resolved
+	Collection  collect.Result
+	Inspection  PromptInspectionResult
+	DebugWriter *state.PromptDebugWriter
+	noNotify    bool
+}
+
+func generatePromptReport(ctx context.Context, req promptReportRequest) (*ReportResult, error) {
+	workflow, err := newPromptReportWorkflow(ctx, req)
+	if err != nil {
+		return nil, err
+	}
+	if err := workflow.buildInputs(); err != nil {
+		return workflow.result, err
+	}
+
+	execution, executeErr := workflow.executePrompt()
+	if executeErr != nil {
+		return workflow.result, workflow.handleExecutionFailure(executeErr)
+	}
+	if execution == nil {
+		err := promptexec.NewError(promptexec.Generation, "prompt executor returned no execution", nil)
+		if saveErr := workflow.persistOperationalExecutionFailure(err); saveErr != nil {
+			return workflow.result, saveErr
+		}
+		return workflow.result, workflow.reportError("execute prompt", err)
+	}
+	if err := workflow.persistExecutionDebug(*execution); err != nil {
+		return workflow.result, err
+	}
+
+	if execution.Validation.Status != promptexec.ValidationPassed && execution.Validation.Status != promptexec.ValidationFailed {
+		err := promptexec.NewError(promptexec.OperationalValidation, "prompt execution did not complete validation", nil)
+		if saveErr := workflow.persistOperationalExecutionFailure(err); saveErr != nil {
+			return workflow.result, saveErr
+		}
+		return workflow.result, workflow.reportError("validate prompt execution", err)
+	}
+	if err := workflow.persistCompletedExecution(*execution); err != nil {
+		return workflow.result, err
+	}
+	if execution.Validation.Status == promptexec.ValidationFailed {
+		err := promptexec.NewError(promptexec.ValidationRejected, "prompt output did not satisfy its schema", nil)
+		return workflow.result, workflow.reportError("validate prompt execution", err)
+	}
+
+	rendered, err := workflow.persistGeneratedContent(execution.RawOutput)
+	if err != nil {
+		return workflow.result, err
+	}
+	return workflow.finalizeReport(rendered)
+}
+
+type promptReportWorkflow struct {
+	ctx               context.Context
+	req               promptReportRequest
+	store             state.Store
+	result            *ReportResult
+	metadata          state.Metadata
+	briefingMetadata  briefing.Metadata
+	reportFacts       ReportFacts
+	moduleSnapshot    module.Snapshot
+	dataPackageBytes  []byte
+	handler           generatedtext.Handler
+	executionArtifact state.PromptExecutionArtifact
+	debugRef          state.PromptDebugRef
+	prepared          bool
+	callbackFailed    bool
+}
+
+func newPromptReportWorkflow(ctx context.Context, req promptReportRequest) (*promptReportWorkflow, error) {
+	if req.Collection.Bundle == nil {
+		return nil, fmt.Errorf("collected weather bundle is required")
+	}
+	store := req.Store
+	var err error
+	if store == nil {
+		store, err = defaultStore(req.Config)
+		if err != nil {
+			return nil, err
+		}
+	}
+	return &promptReportWorkflow{ctx: ctx, req: req, store: store}, nil
+}
+
+func (w *promptReportWorkflow) buildInputs() error {
+	paths, err := w.store.Paths(w.req.Resolved)
+	if err != nil {
+		return err
+	}
+	w.result = &ReportResult{}
+	priorSnapshot, err := w.store.FindPriorSnapshot(w.ctx, w.req.Resolved)
+	if err != nil {
+		return err
+	}
+	w.reportFacts, err = BuildReportFacts(ModuleSnapshotRequest{Config: w.req.Config, Resolved: w.req.Resolved}, w.req.Collection.Bundle)
+	if err != nil {
+		return generatedReportError(w.req.Resolved, w.req.Resolved.Metadata().RunID, "build report facts", err)
+	}
+	w.moduleSnapshot, err = BuildModuleSnapshotFromFacts(ModuleSnapshotRequest{Config: w.req.Config, Resolved: w.req.Resolved}, w.reportFacts)
+	if err != nil {
+		return generatedReportError(w.req.Resolved, w.req.Resolved.Metadata().RunID, "build module snapshot", err)
+	}
+	moduleSnapshotPath, err := w.store.SaveModuleSnapshot(w.ctx, w.req.Resolved, w.moduleSnapshot)
+	if err != nil {
+		return err
+	}
+	w.result.ModuleSnapshot = w.moduleSnapshot
+	w.result.ModuleSnapshotPath = moduleSnapshotPath
+	w.result.PriorSnapshot = priorSnapshot
+
+	recent, err := recentChanges(w.ctx, w.store, priorSnapshot, w.req.Resolved.Definition.ID, w.moduleSnapshot, w.req.Config.RecentChange)
+	if err != nil {
+		return err
+	}
+	w.result.RecentChanges = recent
+	w.briefingMetadata = briefing.BuildMetadata(briefingBuildContext(w.req.Config, w.req.Resolved, w.reportFacts.Collected))
+	w.metadata = state.BuildPromptMetadataFromBriefingMetadata(w.req.Resolved, w.briefingMetadata, state.ArtifactPaths{
+		ModuleSnapshot: moduleSnapshotPath,
+		Metadata:       paths.Metadata,
+	})
+	w.result.Metadata = w.metadata
+	dataPackage, err := promptinput.Build(promptinput.BuildRequest{
+		Metadata: promptMetadata(w.metadata), Modules: w.moduleSnapshot, RecentChanges: recent,
+	})
+	if err != nil {
+		return w.reportError("build data package", err)
+	}
+	w.dataPackageBytes, err = promptinput.MarshalYAML(dataPackage)
+	if err != nil {
+		return err
+	}
+	dataPackagePath, err := w.store.SaveDataPackageBytes(w.ctx, w.req.Resolved, w.dataPackageBytes)
+	if err != nil {
+		return err
+	}
+	w.metadata.DataPackagePath = dataPackagePath
+	w.result.DataPackage = dataPackage
+	w.result.DataPackagePath = dataPackagePath
+	w.result.Metadata = w.metadata
+	w.handler, err = generatedtext.LookupDefinition(w.req.Resolved.Definition)
+	if err != nil {
+		return w.reportError("lookup generated text catalog", err)
+	}
+	w.debugRef = state.PromptDebugRef{
+		ReportID: w.req.Resolved.Definition.ID, ValidDate: w.req.Resolved.ValidPeriod.Start.Format("2006-01-02"), RunID: w.metadata.RunID,
+	}
+	return nil
+}
+
+func (w *promptReportWorkflow) executePrompt() (*promptexec.Execution, error) {
+	return w.req.Executor.Execute(w.ctx, promptexec.ExecuteRequest{
+		PromptID: w.req.Inspection.PromptID, PromptVersion: w.req.Inspection.PromptVersion,
+		ProfileID: w.req.Inspection.ProfileID, DataPackage: w.dataPackageBytes,
+		DataPackagePath: w.result.DataPackagePath, CaptureDebug: w.req.DebugWriter.Enabled(),
+	}, w.persistPreparation)
+}
+
+func (w *promptReportWorkflow) persistPreparation(preparation promptexec.Preparation, debug *promptexec.PreparationDebug) error {
+	artifact := state.PromptPreparationArtifact{
+		SchemaVersion: state.PromptPreparationSchemaVersion, Status: state.PromptPreparationSucceeded,
+		ReportID: w.req.Resolved.Definition.ID, RunID: w.metadata.RunID,
+		PromptID: w.req.Inspection.PromptID, PromptVersion: w.req.Inspection.PromptVersion,
+		DataPackagePath: w.result.DataPackagePath, Preparation: &preparation,
+		StartedAt: preparation.StartedAt, EndedAt: preparation.EndedAt, Duration: preparation.Duration,
+	}
+	path, err := w.store.SavePromptPreparation(w.ctx, w.req.Resolved, artifact)
+	if err != nil {
+		w.callbackFailed = true
+		return err
+	}
+	w.prepared = true
+	w.result.PreparationPath = path
+	w.metadata.PreparationPath = path
+	w.result.Metadata = w.metadata
+	debugPath, err := w.req.DebugWriter.WritePreparation(w.debugRef, preparation, debug)
+	if err != nil {
+		w.callbackFailed = true
+		return promptDebugWriteError(err)
+	}
+	if debugPath != "" {
+		w.result.LLMDebugPath = debugPath
+	}
+	if err := w.saveMetadata(); err != nil {
+		w.callbackFailed = true
+		return err
+	}
+	return nil
+}
+
+func (w *promptReportWorkflow) handleExecutionFailure(executeErr error) error {
+	if w.callbackFailed {
+		return executeErr
+	}
+	executeErr = classifiedPromptError("prompt execution failed", executeErr)
+	if !w.prepared {
+		if err := w.persistPreparationFailure(executeErr); err != nil {
+			return err
+		}
+		return w.reportError("prepare prompt", executeErr)
+	}
+	if promptexec.CategoryOf(executeErr) != "" {
+		if err := w.persistOperationalExecutionFailure(executeErr); err != nil {
+			return err
+		}
+	}
+	return w.reportError("execute prompt", executeErr)
+}
+
+func (w *promptReportWorkflow) persistPreparationFailure(executeErr error) error {
+	startedAt, endedAt := time.Now(), time.Now()
+	artifact := state.PromptPreparationArtifact{
+		SchemaVersion: state.PromptPreparationSchemaVersion, Status: state.PromptPreparationFailed,
+		ReportID: w.req.Resolved.Definition.ID, RunID: w.metadata.RunID,
+		PromptID: w.req.Inspection.PromptID, PromptVersion: w.req.Inspection.PromptVersion,
+		DataPackagePath: w.result.DataPackagePath, StartedAt: startedAt, EndedAt: endedAt,
+		Error: state.NewPromptArtifactError(executeErr),
+	}
+	path, err := w.store.SavePromptPreparation(w.ctx, w.req.Resolved, artifact)
+	if err != nil {
+		return err
+	}
+	w.result.PreparationPath = path
+	w.metadata.PreparationPath = path
+	w.result.Metadata = w.metadata
+	return w.saveMetadata()
+}
+
+func (w *promptReportWorkflow) persistOperationalExecutionFailure(executeErr error) error {
+	artifact := failedPromptExecutionArtifact(w.req.Resolved, w.metadata, w.req.Inspection, executeErr)
+	path, err := w.store.SavePromptExecution(w.ctx, w.req.Resolved, artifact)
+	if err != nil {
+		return err
+	}
+	w.result.ExecutionPath = path
+	w.metadata.ExecutionPath = path
+	w.result.Metadata = w.metadata
+	return w.saveMetadata()
+}
+
+func (w *promptReportWorkflow) persistExecutionDebug(execution promptexec.Execution) error {
+	debugPath, err := w.req.DebugWriter.WriteExecution(w.debugRef, execution)
+	if err != nil {
+		return w.reportError("write prompt debug", promptDebugWriteError(err))
+	}
+	if debugPath != "" {
+		w.result.LLMDebugPath = debugPath
+	}
+	return nil
+}
+
+func (w *promptReportWorkflow) persistCompletedExecution(execution promptexec.Execution) error {
+	rawPath, err := w.store.SaveGeneratedTextRaw(w.ctx, w.req.Resolved, execution.RawOutput)
+	if err != nil {
+		return err
+	}
+	w.result.GeneratedTextRawPath = rawPath
+	w.metadata.GeneratedTextRawPath = rawPath
+	w.result.Metadata = w.metadata
+	w.executionArtifact = state.PromptExecutionArtifact{
+		SchemaVersion: state.PromptExecutionSchemaVersion,
+		ReportID:      w.req.Resolved.Definition.ID, RunID: w.metadata.RunID,
+		PromptID: w.req.Inspection.PromptID, PromptVersion: w.req.Inspection.PromptVersion,
+		Provenance: ptr(state.PromptExecutionProvenanceFrom(execution)), Validation: &execution.Validation,
+		Paths:     state.PromptExecutionPaths{RawOutputPath: rawPath},
+		StartedAt: execution.StartedAt, EndedAt: execution.EndedAt, Duration: execution.Duration,
+	}
+	if execution.Validation.Status == promptexec.ValidationPassed {
+		w.executionArtifact.Status = state.PromptExecutionSucceeded
+	} else {
+		w.executionArtifact.Status = state.PromptExecutionValidationRejected
+	}
+	executionPath, err := w.store.SavePromptExecution(w.ctx, w.req.Resolved, w.executionArtifact)
+	if err != nil {
+		return err
+	}
+	w.result.ExecutionPath = executionPath
+	w.metadata.ExecutionPath = executionPath
+	w.result.Metadata = w.metadata
+	return w.saveMetadata()
+}
+
+func (w *promptReportWorkflow) persistGeneratedContent(raw []byte) ([]byte, error) {
+	generatedText, normalized, err := w.handler.Validate(raw)
+	if err != nil {
+		return nil, w.reportError("validate generated text", err)
+	}
+	generatedTextPath, err := w.store.SaveGeneratedText(w.ctx, w.req.Resolved, normalized)
+	if err != nil {
+		return nil, err
+	}
+	w.result.GeneratedTextPath = generatedTextPath
+	w.metadata.GeneratedTextPath = generatedTextPath
+	w.result.Metadata = w.metadata
+	if err := w.persistReachedPathAndMetadata(func(paths *state.PromptExecutionPaths) { paths.GeneratedTextPath = generatedTextPath }); err != nil {
+		return nil, err
+	}
+
+	renderContext, err := w.handler.BuildRenderContext(w.briefingMetadata, w.moduleSnapshot, w.reportFacts.Collected, w.reportFacts.Derived, generatedText)
+	if err != nil {
+		return nil, w.reportError("build render context", err)
+	}
+	renderContextPath, err := w.store.SaveRenderContext(w.ctx, w.req.Resolved, renderContext)
+	if err != nil {
+		return nil, err
+	}
+	w.result.RenderContextPath = renderContextPath
+	w.metadata.RenderContextPath = renderContextPath
+	w.result.Metadata = w.metadata
+	if err := w.persistReachedPathAndMetadata(func(paths *state.PromptExecutionPaths) { paths.RenderContextPath = renderContextPath }); err != nil {
+		return nil, err
+	}
+
+	rendered, err := w.handler.Render(renderContext)
+	if err != nil {
+		return nil, w.reportError("render template", err)
+	}
+	return rendered, nil
+}
+
+func (w *promptReportWorkflow) finalizeReport(rendered []byte) (*ReportResult, error) {
+	reportPath, err := w.store.PrepareRenderedReport(w.ctx, w.req.Resolved)
+	if err != nil {
+		return w.result, err
+	}
+	if err := fileutil.WriteFileAtomic(reportPath, rendered); err != nil {
+		return w.result, err
+	}
+	w.result.ReportPath = reportPath
+	w.metadata.RenderedReportPath = reportPath
+	w.result.Metadata = w.metadata
+	if err := w.persistReachedPath(func(paths *state.PromptExecutionPaths) { paths.RenderedReportPath = reportPath }); err != nil {
+		return w.result, err
+	}
+	finalized, err := finalizeRenderedReport(w.ctx, finalizeRenderedReportRequest{
+		Config: w.req.Config, Store: w.store, Resolved: w.req.Resolved, Metadata: w.metadata, MetadataPath: w.result.MetadataPath,
+		ExecutionArtifact: &w.executionArtifact, ManagedReportPath: reportPath, OutputPath: w.req.OutputPath,
+		Notifier: w.req.Notifier, noNotify: w.req.noNotify,
+	})
+	w.result.OutputPath, w.result.NotificationPath = finalized.OutputPath, finalized.NotificationPath
+	w.result.Metadata, w.result.MetadataPath, w.result.Notification = finalized.Metadata, finalized.MetadataPath, finalized.Notification
+	return w.result, err
+}
+
+func (w *promptReportWorkflow) persistReachedPath(update func(*state.PromptExecutionPaths)) error {
+	return persistReachedPromptPath(w.ctx, w.store, w.req.Resolved, &w.executionArtifact, update)
+}
+
+func (w *promptReportWorkflow) persistReachedPathAndMetadata(update func(*state.PromptExecutionPaths)) error {
+	if err := w.persistReachedPath(update); err != nil {
+		return err
+	}
+	return w.saveMetadata()
+}
+
+func (w *promptReportWorkflow) saveMetadata() error {
+	path, err := w.store.SaveMetadata(w.ctx, w.metadata)
+	if err != nil {
+		return err
+	}
+	w.result.Metadata = w.metadata
+	w.result.MetadataPath = path
+	return nil
+}
+
+func (w *promptReportWorkflow) reportError(operation string, err error) error {
+	return generatedReportError(w.req.Resolved, w.metadata.RunID, operation, err)
+}
+
+func persistReachedPromptPath(
+	ctx context.Context,
+	store state.Store,
+	resolved report.Resolved,
+	artifact *state.PromptExecutionArtifact,
+	update func(*state.PromptExecutionPaths),
+) error {
+	update(&artifact.Paths)
+	_, err := store.SavePromptExecution(ctx, resolved, *artifact)
+	return err
+}
+
+func failedPromptExecutionArtifact(resolved report.Resolved, metadata state.Metadata, inspection PromptInspectionResult, err error) state.PromptExecutionArtifact {
+	now := time.Now()
+	return state.PromptExecutionArtifact{
+		SchemaVersion: state.PromptExecutionSchemaVersion, Status: state.PromptExecutionFailed,
+		ReportID: resolved.Definition.ID, RunID: metadata.RunID, PromptID: inspection.PromptID,
+		PromptVersion: inspection.PromptVersion, StartedAt: now, EndedAt: now,
+		Error: state.NewPromptArtifactError(err),
+	}
+}
+
+func classifiedPromptError(operation string, err error) error {
+	if promptexec.CategoryOf(err) != "" {
+		return err
+	}
+	return promptexec.NewError(promptexec.Generation, operation, err)
+}
+
+func promptDebugWriteError(err error) error {
+	return promptexec.NewError(promptexec.InvalidConfiguration, "write requested prompt debug artifact", err)
+}
+
+func ptr[T any](value T) *T { return &value }

internal/app/prompt_inspection.go

@@ -0,0 +1,142 @@
+package app
+
+import (
+	"context"
+	"os"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/config"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptexec"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/report"
+)
+
+// PromptInspectionRequest contains the non-executing inputs required to
+// validate one report's configured prompt and profile.
+type PromptInspectionRequest struct {
+	Resolved  report.Resolved
+	Executor  promptexec.Executor
+	Promptkit config.PromptkitConfig
+	LookupEnv func(string) (string, bool)
+}
+
+// PromptInspectionResult contains only safe identity and provenance from a
+// prompt/profile inspection.
+type PromptInspectionResult struct {
+	PromptID      string
+	PromptVersion string
+	PromptHash    string
+	ProfileID     string
+	BackendID     string
+	ModelName     string
+}
+
+// PromptExecutionsInspectionRequest validates all prompt/profile combinations
+// needed by a batch before collection begins.
+type PromptExecutionsInspectionRequest struct {
+	Resolved  []report.Resolved
+	Executor  promptexec.Executor
+	Promptkit config.PromptkitConfig
+	LookupEnv func(string) (string, bool)
+}
+
+// InspectPromptExecution validates the exact prompt and profile needed for a
+// report before collection, execution, or durable writes begin.
+func InspectPromptExecution(ctx context.Context, req PromptInspectionRequest) (PromptInspectionResult, error) {
+	results, err := InspectPromptExecutions(ctx, PromptExecutionsInspectionRequest{
+		Resolved:  []report.Resolved{req.Resolved},
+		Executor:  req.Executor,
+		Promptkit: req.Promptkit,
+		LookupEnv: req.LookupEnv,
+	})
+	if err != nil {
+		return PromptInspectionResult{}, err
+	}
+	return results[req.Resolved.Definition.ID], nil
+}
+
+// InspectPromptExecutions validates exact prompt contracts and their unique
+// effective profiles. It performs no collection, execution, or durable write.
+func InspectPromptExecutions(ctx context.Context, req PromptExecutionsInspectionRequest) (map[report.ID]PromptInspectionResult, error) {
+	if req.Executor == nil {
+		return nil, promptexec.NewError(promptexec.InvalidConfiguration, "prompt executor is required", nil)
+	}
+	results := make(map[report.ID]PromptInspectionResult, len(req.Resolved))
+	profiles := map[string]promptexec.ProfileInspection{}
+	for _, resolved := range req.Resolved {
+		definition := resolved.Definition
+		if strings.TrimSpace(definition.PromptID) == "" || strings.TrimSpace(definition.PromptVersion) == "" {
+			return nil, promptexec.NewError(promptexec.InvalidConfiguration, "report prompt identity is incomplete", nil)
+		}
+		inspection, err := req.Executor.InspectPrompt(ctx, definition.PromptID, definition.PromptVersion)
+		if err != nil {
+			return nil, promptInspectionError("prompt inspection failed", err)
+		}
+		if inspection.PromptID != definition.PromptID || inspection.PromptVersion != definition.PromptVersion {
+			return nil, promptexec.NewError(promptexec.InvalidConfiguration, "prompt inspection did not return the requested prompt version", nil)
+		}
+		if !validPromptInput(inspection.Inputs) {
+			return nil, promptexec.NewError(promptexec.InvalidConfiguration, "prompt must declare exactly one required application/yaml data_package input", nil)
+		}
+		if !validPromptOutput(definition, inspection.Output) {
+			return nil, promptexec.NewError(promptexec.InvalidConfiguration, "prompt must declare the report JSON Schema output contract", nil)
+		}
+		profileID := req.Promptkit.Profile
+		if profileID == "" {
+			profileID = inspection.DefaultProfileID
+		}
+		if strings.TrimSpace(profileID) == "" {
+			return nil, promptexec.NewError(promptexec.InvalidConfiguration, "prompt has no execution profile", nil)
+		}
+		profile, ok := profiles[profileID]
+		if !ok {
+			profile, err = inspectPromptProfile(ctx, req.Executor, profileID, req.LookupEnv)
+			if err != nil {
+				return nil, err
+			}
+			profiles[profileID] = profile
+		}
+		results[definition.ID] = PromptInspectionResult{
+			PromptID: inspection.PromptID, PromptVersion: inspection.PromptVersion, PromptHash: inspection.PromptHash,
+			ProfileID: profile.ProfileID, BackendID: profile.BackendID, ModelName: profile.ModelName,
+		}
+	}
+	return results, nil
+}
+
+func inspectPromptProfile(ctx context.Context, executor promptexec.Executor, profileID string, lookupEnv func(string) (string, bool)) (promptexec.ProfileInspection, error) {
+	profile, err := executor.InspectProfile(ctx, profileID)
+	if err != nil {
+		return promptexec.ProfileInspection{}, promptInspectionError("profile inspection failed", err)
+	}
+	if profile.ProfileID != profileID {
+		return promptexec.ProfileInspection{}, promptexec.NewError(promptexec.InvalidConfiguration, "profile inspection did not return the selected profile", nil)
+	}
+	if profile.CredentialRequired {
+		return promptexec.ProfileInspection{}, promptexec.NewError(promptexec.MissingCredential, "selected profile requires an unsupported direct API key", nil)
+	}
+	if strings.TrimSpace(profile.APIKeyEnv) != "" {
+		if lookupEnv == nil {
+			lookupEnv = os.LookupEnv
+		}
+		value, present := lookupEnv(profile.APIKeyEnv)
+		if !present || strings.TrimSpace(value) == "" {
+			return promptexec.ProfileInspection{}, promptexec.NewError(promptexec.MissingCredential, "selected profile credential is unavailable", nil)
+		}
+	}
+	return profile, nil
+}
+
+func validPromptInput(inputs []promptexec.InputDefinition) bool {
+	return len(inputs) == 1 && inputs[0].Name == "data_package" && inputs[0].Required && inputs[0].ContentType == "application/yaml"
+}
+
+func validPromptOutput(definition report.Definition, output promptexec.OutputContract) bool {
+	return output.Format == "json" && output.ValidationMode == "json_schema" && output.SchemaPath == definition.GeneratedTextSchemaID+".generated_text.schema.json"
+}
+
+func promptInspectionError(operation string, err error) error {
+	if promptexec.CategoryOf(err) != "" {
+		return err
+	}
+	return promptexec.NewError(promptexec.InvalidConfiguration, operation, err)
+}

internal/app/prompt_inspection_test.go

@@ -0,0 +1,191 @@
+package app
+
+import (
+	"context"
+	"errors"
+	"strings"
+	"testing"
+	"time"
+
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/config"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptexec"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/report"
+)
+
+func TestInspectPromptExecutionSelectsDefaultAndOverrideProfiles(t *testing.T) {
+	resolved := inspectionResolved(t)
+	executor := &inspectionExecutor{
+		prompt: validPromptInspection(resolved.Definition),
+		profiles: map[string]promptexec.ProfileInspection{
+			"default-profile":  {ProfileID: "default-profile", BackendID: "local", ModelName: "default-model"},
+			"override-profile": {ProfileID: "override-profile", BackendID: "cloud", ModelName: "override-model"},
+		},
+	}
+	defaultResult, err := InspectPromptExecution(context.Background(), PromptInspectionRequest{Resolved: resolved, Executor: executor})
+	if err != nil {
+		t.Fatalf("InspectPromptExecution(default) error = %v", err)
+	}
+	if defaultResult.ProfileID != "default-profile" || defaultResult.ModelName != "default-model" {
+		t.Fatalf("default result = %#v", defaultResult)
+	}
+	overrideResult, err := InspectPromptExecution(context.Background(), PromptInspectionRequest{
+		Resolved: resolved, Executor: executor, Promptkit: config.PromptkitConfig{Profile: "override-profile"},
+	})
+	if err != nil {
+		t.Fatalf("InspectPromptExecution(override) error = %v", err)
+	}
+	if overrideResult.ProfileID != "override-profile" || overrideResult.ModelName != "override-model" {
+		t.Fatalf("override result = %#v", overrideResult)
+	}
+	if len(executor.promptRequests) != 2 || executor.promptRequests[0].version != resolved.Definition.PromptVersion || executor.profileRequests[0] != "default-profile" || executor.profileRequests[1] != "override-profile" {
+		t.Fatalf("inspection requests = prompts %#v profiles %#v", executor.promptRequests, executor.profileRequests)
+	}
+}
+
+func TestInspectPromptExecutionRejectsInvalidContractsAndCredentials(t *testing.T) {
+	resolved := inspectionResolved(t)
+	basePrompt := validPromptInspection(resolved.Definition)
+	tests := []struct {
+		name         string
+		prompt       promptexec.PromptInspection
+		profile      promptexec.ProfileInspection
+		lookupEnv    func(string) (string, bool)
+		wantCategory promptexec.ErrorCategory
+	}{
+		{
+			name: "extra input",
+			prompt: func() promptexec.PromptInspection {
+				value := basePrompt
+				value.Inputs = append(value.Inputs, promptexec.InputDefinition{Name: "unexpected"})
+				return value
+			}(),
+			wantCategory: promptexec.InvalidConfiguration,
+		},
+		{
+			name: "wrong schema",
+			prompt: func() promptexec.PromptInspection {
+				value := basePrompt
+				value.Output.SchemaPath = "unexpected.schema.json"
+				return value
+			}(),
+			wantCategory: promptexec.InvalidConfiguration,
+		},
+		{
+			name:         "direct key",
+			prompt:       basePrompt,
+			profile:      promptexec.ProfileInspection{ProfileID: "default-profile", CredentialRequired: true},
+			wantCategory: promptexec.MissingCredential,
+		},
+		{
+			name:         "missing environment credential",
+			prompt:       basePrompt,
+			profile:      promptexec.ProfileInspection{ProfileID: "default-profile", APIKeyEnv: "PROMPT_API_KEY"},
+			lookupEnv:    func(string) (string, bool) { return "", false },
+			wantCategory: promptexec.MissingCredential,
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			executor := &inspectionExecutor{prompt: test.prompt, profiles: map[string]promptexec.ProfileInspection{"default-profile": test.profile}}
+			_, err := InspectPromptExecution(context.Background(), PromptInspectionRequest{Resolved: resolved, Executor: executor, LookupEnv: test.lookupEnv})
+			if err == nil || promptexec.CategoryOf(err) != test.wantCategory {
+				t.Fatalf("error/category = %v/%q, want %q", err, promptexec.CategoryOf(err), test.wantCategory)
+			}
+		})
+	}
+}
+
+func TestInspectPromptExecutionReturnsSafeInspectionError(t *testing.T) {
+	resolved := inspectionResolved(t)
+	executor := &inspectionExecutor{promptErr: errors.New("provider response contains resolved-secret-value")}
+	_, err := InspectPromptExecution(context.Background(), PromptInspectionRequest{Resolved: resolved, Executor: executor})
+	if err == nil || promptexec.CategoryOf(err) != promptexec.InvalidConfiguration {
+		t.Fatalf("error/category = %v/%q", err, promptexec.CategoryOf(err))
+	}
+	if strings.Contains(err.Error(), "resolved-secret-value") {
+		t.Fatalf("inspection error leaks provider value: %v", err)
+	}
+}
+
+func TestInspectPromptExecutionsReusesEffectiveProfile(t *testing.T) {
+	first := inspectionResolved(t)
+	second := first
+	second.Definition.ID = report.Today
+	second.Definition.PromptID = "weather.today"
+	executor := &inspectionExecutor{
+		prompt: validPromptInspection(first.Definition),
+		profiles: map[string]promptexec.ProfileInspection{
+			"default-profile": {ProfileID: "default-profile", BackendID: "local", ModelName: "model"},
+		},
+	}
+	executor.prompts = map[string]promptexec.PromptInspection{
+		first.Definition.PromptID:  validPromptInspection(first.Definition),
+		second.Definition.PromptID: validPromptInspection(second.Definition),
+	}
+	results, err := InspectPromptExecutions(context.Background(), PromptExecutionsInspectionRequest{Resolved: []report.Resolved{first, second}, Executor: executor})
+	if err != nil {
+		t.Fatalf("InspectPromptExecutions() error = %v", err)
+	}
+	if len(results) != 2 || len(executor.profileRequests) != 1 {
+		t.Fatalf("results/profile requests = %#v/%#v, want two results and one profile inspection", results, executor.profileRequests)
+	}
+}
+
+type inspectionPromptRequest struct {
+	id      string
+	version string
+}
+
+type inspectionExecutor struct {
+	prompt          promptexec.PromptInspection
+	prompts         map[string]promptexec.PromptInspection
+	profiles        map[string]promptexec.ProfileInspection
+	promptErr       error
+	promptRequests  []inspectionPromptRequest
+	profileRequests []string
+}
+
+func (e *inspectionExecutor) InspectPrompt(_ context.Context, id string, version string) (promptexec.PromptInspection, error) {
+	e.promptRequests = append(e.promptRequests, inspectionPromptRequest{id: id, version: version})
+	if e.promptErr != nil {
+		return promptexec.PromptInspection{}, e.promptErr
+	}
+	if prompt, ok := e.prompts[id]; ok {
+		return prompt, nil
+	}
+	return e.prompt, nil
+}
+
+func (e *inspectionExecutor) InspectProfile(_ context.Context, id string) (promptexec.ProfileInspection, error) {
+	e.profileRequests = append(e.profileRequests, id)
+	value, ok := e.profiles[id]
+	if !ok {
+		return promptexec.ProfileInspection{}, errors.New("profile missing")
+	}
+	return value, nil
+}
+
+func (e *inspectionExecutor) Execute(context.Context, promptexec.ExecuteRequest, promptexec.PreparationCallback) (*promptexec.Execution, error) {
+	return nil, errors.New("unexpected execution")
+}
+
+func inspectionResolved(t *testing.T) report.Resolved {
+	t.Helper()
+	resolved, err := report.DefaultRegistry().Resolve(report.Daily, report.ResolveRequest{
+		Now:      time.Date(2026, 5, 29, 12, 0, 0, 0, time.UTC),
+		Date:     time.Date(2026, 5, 29, 0, 0, 0, 0, time.UTC),
+		Location: time.UTC,
+	})
+	if err != nil {
+		t.Fatalf("Resolve() error = %v", err)
+	}
+	return resolved
+}
+
+func validPromptInspection(definition report.Definition) promptexec.PromptInspection {
+	return promptexec.PromptInspection{
+		PromptID: definition.PromptID, PromptVersion: definition.PromptVersion, PromptHash: "prompt-hash", DefaultProfileID: "default-profile",
+		Inputs: []promptexec.InputDefinition{{Name: "data_package", Required: true, ContentType: "application/yaml"}},
+		Output: promptexec.OutputContract{Format: "json", ValidationMode: "json_schema", SchemaPath: definition.GeneratedTextSchemaID + ".generated_text.schema.json"},
+	}
+}

internal/app/single_report_workflow_test.go

@@ -0,0 +1,659 @@
+package app
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"errors"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/collect"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/config"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/module"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptexec"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/report"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/state"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/weatherdata"
+)
+
+type workflowCollector struct {
+	result *collect.Result
+	err    error
+	calls  int
+}
+
+func (c *workflowCollector) Run(context.Context, collect.Request) (*collect.Result, error) {
+	c.calls++
+	if c.err != nil {
+		return nil, c.err
+	}
+	return c.result, nil
+}
+
+type workflowExecutor struct {
+	definition           report.Definition
+	raw                  []byte
+	inspectionErr        error
+	profile              promptexec.ProfileInspection
+	beforePreparationErr error
+	afterCallbackErr     error
+	afterPreparationErr  error
+	validation           promptexec.ValidationStatus
+	executeCalls         int
+	providerCalls        int
+	request              promptexec.ExecuteRequest
+	beforeProvider       func()
+	preparationDebug     *promptexec.PreparationDebug
+	executionDebug       *promptexec.ExecutionDebug
+}
+
+func (e *workflowExecutor) InspectPrompt(_ context.Context, id, version string) (promptexec.PromptInspection, error) {
+	if e.inspectionErr != nil {
+		return promptexec.PromptInspection{}, e.inspectionErr
+	}
+	if id != e.definition.PromptID || version != e.definition.PromptVersion {
+		return promptexec.PromptInspection{}, errors.New("unexpected prompt identity")
+	}
+	return validPromptInspection(e.definition), nil
+}
+
+func (e *workflowExecutor) InspectProfile(_ context.Context, id string) (promptexec.ProfileInspection, error) {
+	profile := e.profile
+	if profile.ProfileID == "" {
+		profile = promptexec.ProfileInspection{ProfileID: id, BackendID: "fixture", ModelName: "fixture-model"}
+	}
+	return profile, nil
+}
+
+func (e *workflowExecutor) Execute(_ context.Context, req promptexec.ExecuteRequest, callback promptexec.PreparationCallback) (*promptexec.Execution, error) {
+	e.executeCalls++
+	e.request = req
+	if e.beforePreparationErr != nil {
+		return nil, e.beforePreparationErr
+	}
+	stamp := time.Date(2026, 5, 29, 15, 0, 0, 0, time.UTC)
+	preparation := promptexec.Preparation{
+		PromptID: req.PromptID, PromptVersion: req.PromptVersion, PromptHash: "prompt-hash",
+		RenderedPromptHash: "rendered-hash", ProfileID: req.ProfileID, BackendID: "fixture",
+		ModelName: "fixture-model", DataPackagePath: req.DataPackagePath, StartedAt: stamp, EndedAt: stamp,
+	}
+	if err := callback(preparation, e.preparationDebug); err != nil {
+		return nil, err
+	}
+	if e.afterCallbackErr != nil {
+		return nil, e.afterCallbackErr
+	}
+	if e.beforeProvider != nil {
+		e.beforeProvider()
+	}
+	e.providerCalls++
+	if e.afterPreparationErr != nil {
+		return nil, e.afterPreparationErr
+	}
+	validation := e.validation
+	if validation == "" {
+		validation = promptexec.ValidationPassed
+	}
+	return &promptexec.Execution{
+		RunID: "provider-run", PromptID: req.PromptID, PromptVersion: req.PromptVersion,
+		PromptHash: "prompt-hash", RenderedPromptHash: "rendered-hash", ProfileID: req.ProfileID,
+		BackendID: "fixture", ModelName: "fixture-model", GeneratedHash: "generated-hash",
+		StartedAt: stamp, EndedAt: stamp, DataPackagePath: req.DataPackagePath, RawOutput: e.raw,
+		Debug:      e.executionDebug,
+		Validation: promptexec.NewValidation(validation, "json_schema", e.definition.GeneratedTextSchemaID+".generated_text.schema.json", nil),
+	}, nil
+}
+
+type workflowNotifier struct {
+	requests []NotificationRequest
+	err      error
+}
+
+func (n *workflowNotifier) Notify(_ context.Context, req NotificationRequest) (*NotificationResult, error) {
+	n.requests = append(n.requests, req)
+	if n.err != nil {
+		return nil, n.err
+	}
+	return &NotificationResult{
+		RunID: "notification-run", PipelineID: req.PipelineID, BundleID: req.BundleID,
+		IdempotencyKey: req.IdempotencyKey, Status: "succeeded", UploadStatus: "accepted",
+	}, nil
+}
+
+func TestGenerateDetailedCompletesRetainedReportWorkflows(t *testing.T) {
+	tests := []struct {
+		name       string
+		kind       ReportKind
+		id         report.ID
+		date       time.Time
+		raw        string
+		wantOutput string
+	}{
+		{name: "daily", kind: ReportDaily, id: report.Daily, date: workflowTime("2026-05-29T12:00:00-05:00"), raw: validDailyWorkflowJSON(), wantOutput: "Showers are possible during the selected day."},
+		{name: "today", kind: ReportToday, id: report.Today, raw: validTodayWorkflowJSON(), wantOutput: "Today starts with showers before improving."},
+		{name: "tomorrow", kind: ReportTomorrow, id: report.Tomorrow, raw: validTomorrowWorkflowJSON(), wantOutput: "Tomorrow starts with showers before improving."},
+		{name: "hourly", kind: ReportHourly, id: report.Hourly, raw: validHourlyWorkflowJSON(), wantOutput: "Storm chances increase through late morning."},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			cfg := workflowConfig(t)
+			definition := report.DefaultRegistry().MustLookup(test.id)
+			bundle := workflowBundle(t)
+			collector := &workflowCollector{result: &collect.Result{Bundle: &bundle}}
+			executor := &workflowExecutor{definition: definition, raw: []byte(test.raw)}
+			notifier := &workflowNotifier{}
+			outputPath := filepath.Join(t.TempDir(), test.name+".md")
+
+			result, err := GenerateDetailed(context.Background(), GenerateRequest{
+				Config: cfg, Report: test.kind, Date: test.date, Now: workflowTime("2026-05-29T08:30:00-05:00"),
+				OutputPath: outputPath, Collector: collector, Executor: executor, Notifier: notifier,
+			})
+			if err != nil {
+				t.Fatalf("GenerateDetailed() error = %v", err)
+			}
+			if result.Metadata.ReportID != test.id || result.Metadata.PromptID != definition.PromptID {
+				t.Fatalf("metadata identity = %q/%q, want %q/%q", result.Metadata.ReportID, result.Metadata.PromptID, test.id, definition.PromptID)
+			}
+			if executor.request.PromptVersion != definition.PromptVersion {
+				t.Fatalf("prompt version = %q, want %q", executor.request.PromptVersion, definition.PromptVersion)
+			}
+			filesystem, storeErr := state.NewFilesystemStore(cfg.Workspace)
+			if storeErr != nil {
+				t.Fatalf("NewFilesystemStore() error = %v", storeErr)
+			}
+			preparation, loadErr := filesystem.LoadPromptPreparation(context.Background(), result.PreparationPath)
+			if loadErr != nil || preparation.PromptVersion != definition.PromptVersion {
+				t.Fatalf("persisted preparation prompt version = %q, error %v, want %q", preparation.PromptVersion, loadErr, definition.PromptVersion)
+			}
+			if collector.calls != 1 || executor.executeCalls != 1 || executor.providerCalls != 1 {
+				t.Fatalf("calls = collect %d execute %d provider %d, want one each", collector.calls, executor.executeCalls, executor.providerCalls)
+			}
+			persisted, readErr := os.ReadFile(result.DataPackagePath)
+			if readErr != nil {
+				t.Fatalf("read data package: %v", readErr)
+			}
+			if !bytes.Equal(executor.request.DataPackage, persisted) {
+				t.Fatal("executor data package differs from exact persisted YAML bytes")
+			}
+			managed, readErr := os.ReadFile(result.ReportPath)
+			if readErr != nil || !strings.Contains(string(managed), test.wantOutput) {
+				t.Fatalf("managed report = %q, error %v, want generated template output %q", managed, readErr, test.wantOutput)
+			}
+			copied, readErr := os.ReadFile(outputPath)
+			if readErr != nil || !bytes.Equal(copied, managed) || result.OutputPath != outputPath {
+				t.Fatalf("output copy mismatch/error/path = %v/%q", readErr, result.OutputPath)
+			}
+			if len(notifier.requests) != 1 || notifier.requests[0].ReportPath != result.ReportPath || notifier.requests[0].ReportPath == outputPath {
+				t.Fatalf("notification requests = %#v, want managed report source", notifier.requests)
+			}
+			wantPipeline := "reports." + string(test.id) + "." + definition.ArtifactGroup
+			if notifier.requests[0].PipelineID != wantPipeline {
+				t.Fatalf("pipeline = %q, want %q", notifier.requests[0].PipelineID, wantPipeline)
+			}
+			validDate := result.Metadata.ValidPeriod.Start.Format("2006-01-02")
+			wantBundlePaths := workflowBundlePaths(test.id, validDate, result.Metadata.RunID)
+			if strings.Join(notifier.requests[0].BundlePaths, "\n") != strings.Join(wantBundlePaths, "\n") {
+				t.Fatalf("bundle paths = %#v, want %#v", notifier.requests[0].BundlePaths, wantBundlePaths)
+			}
+			managedName := filepath.Base(result.ReportPath)
+			if !strings.HasPrefix(managedName, "report.") || !strings.Contains(managedName, "_"+test.name) || !strings.HasSuffix(managedName, ".md") || filepath.Base(result.OutputPath) != test.name+".md" {
+				t.Fatalf("output names = managed %q copy %q", result.ReportPath, result.OutputPath)
+			}
+		})
+	}
+}
+
+type preparationFailingStore struct {
+	state.Store
+}
+
+type renderContextFailingStore struct {
+	state.Store
+}
+
+func (s renderContextFailingStore) SaveModuleSnapshot(ctx context.Context, resolved report.Resolved, snapshot module.Snapshot) (string, error) {
+	path, err := s.Store.SaveModuleSnapshot(ctx, resolved, snapshot)
+	if err != nil {
+		return "", err
+	}
+	for index := range snapshot.Outputs {
+		snapshot.Outputs[index].Value = "invalid module value"
+	}
+	return path, nil
+}
+
+func (s preparationFailingStore) SavePromptPreparation(context.Context, report.Resolved, state.PromptPreparationArtifact) (string, error) {
+	return "", errors.New("injected preparation persistence failure")
+}
+
+func TestGenerateDetailedStopsAtConsequentialPromptFailures(t *testing.T) {
+	tests := []struct {
+		name             string
+		configure        func(*workflowExecutor)
+		wantCategory     promptexec.ErrorCategory
+		wantPreparation  bool
+		wantExecution    bool
+		wantRaw          bool
+		wantProviderCall int
+	}{
+		{name: "preparation", configure: func(e *workflowExecutor) {
+			e.beforePreparationErr = promptexec.NewError(promptexec.Generation, "preparation failed", nil)
+		}, wantCategory: promptexec.Generation, wantPreparation: true},
+		{name: "credential disappears", configure: func(e *workflowExecutor) {
+			e.afterCallbackErr = promptexec.NewError(promptexec.MissingCredential, "credential unavailable", nil)
+		}, wantCategory: promptexec.MissingCredential, wantPreparation: true, wantExecution: true},
+		{name: "capacity is not retried", configure: func(e *workflowExecutor) {
+			e.afterPreparationErr = promptexec.NewError(promptexec.Capacity, "capacity rejected", nil)
+		}, wantCategory: promptexec.Capacity, wantPreparation: true, wantExecution: true, wantProviderCall: 1},
+		{name: "canceled", configure: func(e *workflowExecutor) {
+			e.afterPreparationErr = promptexec.NewError(promptexec.Canceled, "request canceled", context.Canceled)
+		}, wantCategory: promptexec.Canceled, wantPreparation: true, wantExecution: true, wantProviderCall: 1},
+		{name: "deadline", configure: func(e *workflowExecutor) {
+			e.afterPreparationErr = promptexec.NewError(promptexec.DeadlineExceeded, "deadline exceeded", context.DeadlineExceeded)
+		}, wantCategory: promptexec.DeadlineExceeded, wantPreparation: true, wantExecution: true, wantProviderCall: 1},
+		{name: "generation", configure: func(e *workflowExecutor) {
+			e.afterPreparationErr = promptexec.NewError(promptexec.Generation, "generation failed", nil)
+		}, wantCategory: promptexec.Generation, wantPreparation: true, wantExecution: true, wantProviderCall: 1},
+		{name: "operational validation error", configure: func(e *workflowExecutor) {
+			e.afterPreparationErr = promptexec.NewError(promptexec.OperationalValidation, "validator failed", nil)
+		}, wantCategory: promptexec.OperationalValidation, wantPreparation: true, wantExecution: true, wantProviderCall: 1},
+		{name: "operational validation incomplete", configure: func(e *workflowExecutor) { e.validation = promptexec.ValidationSkipped }, wantCategory: promptexec.OperationalValidation, wantPreparation: true, wantExecution: true, wantProviderCall: 1},
+		{name: "schema rejection", configure: func(e *workflowExecutor) { e.validation = promptexec.ValidationFailed }, wantCategory: promptexec.ValidationRejected, wantPreparation: true, wantExecution: true, wantRaw: true, wantProviderCall: 1},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			cfg := workflowConfig(t)
+			cfg.Notify.Distributor.Enabled = false
+			definition := report.DefaultRegistry().MustLookup(report.Daily)
+			executor := &workflowExecutor{definition: definition, raw: []byte(validDailyWorkflowJSON())}
+			test.configure(executor)
+			bundle := workflowBundle(t)
+			collector := &workflowCollector{result: &collect.Result{Bundle: &bundle}}
+			result, err := GenerateDetailed(context.Background(), GenerateRequest{
+				Config: cfg, Report: ReportDaily, Date: workflowTime("2026-05-29T12:00:00-05:00"), Now: workflowTime("2026-05-29T08:30:00-05:00"),
+				Collector: collector, Executor: executor,
+			})
+			if err == nil || result == nil || promptexec.CategoryOf(err) != test.wantCategory {
+				t.Fatalf("result/error/category = %#v/%v/%q, want partial result and %q", result, err, promptexec.CategoryOf(err), test.wantCategory)
+			}
+			if (result.PreparationPath != "") != test.wantPreparation || (result.ExecutionPath != "") != test.wantExecution || (result.GeneratedTextRawPath != "") != test.wantRaw {
+				t.Fatalf("paths = preparation %q execution %q raw %q", result.PreparationPath, result.ExecutionPath, result.GeneratedTextRawPath)
+			}
+			if executor.executeCalls != 1 || executor.providerCalls != test.wantProviderCall {
+				t.Fatalf("calls = execute %d provider %d, want 1/%d", executor.executeCalls, executor.providerCalls, test.wantProviderCall)
+			}
+		})
+	}
+}
+
+func TestGenerateDetailedRejectsInspectionAndCredentialsBeforeCollection(t *testing.T) {
+	tests := []struct {
+		name         string
+		configure    func(*workflowExecutor)
+		wantCategory promptexec.ErrorCategory
+	}{
+		{name: "inspection", configure: func(e *workflowExecutor) { e.inspectionErr = errors.New("inspection unavailable") }, wantCategory: promptexec.InvalidConfiguration},
+		{name: "credential", configure: func(e *workflowExecutor) {
+			e.profile = promptexec.ProfileInspection{ProfileID: "default-profile", CredentialRequired: true}
+		}, wantCategory: promptexec.MissingCredential},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			cfg := workflowConfig(t)
+			definition := report.DefaultRegistry().MustLookup(report.Daily)
+			executor := &workflowExecutor{definition: definition}
+			test.configure(executor)
+			collector := &workflowCollector{err: errors.New("collector must not run")}
+			result, err := GenerateDetailed(context.Background(), GenerateRequest{
+				Config: cfg, Report: ReportDaily, Date: workflowTime("2026-05-29T12:00:00-05:00"), Now: workflowTime("2026-05-29T08:30:00-05:00"),
+				Collector: collector, Executor: executor,
+			})
+			if err == nil || result != nil || promptexec.CategoryOf(err) != test.wantCategory || collector.calls != 0 || executor.executeCalls != 0 {
+				t.Fatalf("result/error/category/collect/execute = %#v/%v/%q/%d/%d", result, err, promptexec.CategoryOf(err), collector.calls, executor.executeCalls)
+			}
+			entries, readErr := os.ReadDir(cfg.Workspace.Root)
+			if readErr != nil || len(entries) != 0 {
+				t.Fatalf("workspace entries/error = %#v/%v, want no writes before collection", entries, readErr)
+			}
+		})
+	}
+}
+
+func TestGenerateDetailedStopsProviderWhenPreparationCannotPersist(t *testing.T) {
+	cfg := workflowConfig(t)
+	cfg.Notify.Distributor.Enabled = false
+	filesystem, err := state.NewFilesystemStore(cfg.Workspace)
+	if err != nil {
+		t.Fatalf("NewFilesystemStore() error = %v", err)
+	}
+	definition := report.DefaultRegistry().MustLookup(report.Daily)
+	executor := &workflowExecutor{definition: definition, raw: []byte(validDailyWorkflowJSON())}
+	bundle := workflowBundle(t)
+	result, err := GenerateDetailed(context.Background(), GenerateRequest{
+		Config: cfg, Report: ReportDaily, Date: workflowTime("2026-05-29T12:00:00-05:00"), Now: workflowTime("2026-05-29T08:30:00-05:00"),
+		Collector: &workflowCollector{result: &collect.Result{Bundle: &bundle}}, Executor: executor, Store: preparationFailingStore{Store: filesystem},
+	})
+	if err == nil || result == nil || result.PreparationPath != "" || executor.providerCalls != 0 {
+		t.Fatalf("result/error/preparation/provider = %#v/%v/%q/%d", result, err, result.PreparationPath, executor.providerCalls)
+	}
+}
+
+func TestGenerateDetailedPersistsPreparationBeforeProviderExecution(t *testing.T) {
+	cfg := workflowConfig(t)
+	cfg.Notify.Distributor.Enabled = false
+	now := workflowTime("2026-05-29T08:30:00-05:00")
+	request := GenerateRequest{Config: cfg, Report: ReportDaily, Date: workflowTime("2026-05-29T12:00:00-05:00"), Now: now}
+	resolved, err := ResolveGenerate(request, now)
+	if err != nil {
+		t.Fatalf("ResolveGenerate() error = %v", err)
+	}
+	filesystem, err := state.NewFilesystemStore(cfg.Workspace)
+	if err != nil {
+		t.Fatalf("NewFilesystemStore() error = %v", err)
+	}
+	paths, err := filesystem.Paths(resolved)
+	if err != nil {
+		t.Fatalf("Paths() error = %v", err)
+	}
+	checked := false
+	executor := &workflowExecutor{definition: resolved.Definition, raw: []byte(validDailyWorkflowJSON())}
+	executor.beforeProvider = func() {
+		checked = true
+		if _, statErr := os.Stat(paths.Preparation); statErr != nil {
+			t.Fatalf("preparation was not durable before provider execution: %v", statErr)
+		}
+	}
+	bundle := workflowBundle(t)
+	request.Collector = &workflowCollector{result: &collect.Result{Bundle: &bundle}}
+	request.Executor = executor
+	request.Store = filesystem
+	result, err := GenerateDetailed(context.Background(), request)
+	if err != nil || result == nil || !checked || result.OutputPath != "" {
+		t.Fatalf("result/error/checked/output = %#v/%v/%t/%q", result, err, checked, result.OutputPath)
+	}
+}
+
+func TestGenerateDetailedRetainsInspectableArtifactsAfterApplicationFailures(t *testing.T) {
+	tests := []struct {
+		name           string
+		raw            string
+		configure      func(*GenerateRequest, *workflowNotifier)
+		wantRaw        bool
+		wantNormalized bool
+		wantContext    bool
+		wantReport     bool
+		wantOutput     bool
+		wantNotify     bool
+	}{
+		{name: "generated text decode", raw: `{`, wantRaw: true},
+		{name: "generated text domain", raw: `{}`, wantRaw: true},
+		{name: "render context build", raw: validDailyWorkflowJSON(), configure: func(req *GenerateRequest, _ *workflowNotifier) {
+			req.Store = renderContextFailingStore{Store: req.Store}
+		}, wantRaw: true, wantNormalized: true},
+		{name: "render context persistence", raw: validDailyWorkflowJSON(), configure: func(req *GenerateRequest, _ *workflowNotifier) {
+			req.Store = &failingPersistenceStore{Store: req.Store, failOperation: failRenderContext}
+		}, wantRaw: true, wantNormalized: true},
+		{name: "template write", raw: validDailyWorkflowJSON(), configure: func(req *GenerateRequest, _ *workflowNotifier) {
+			blocker := filepath.Join(t.TempDir(), "report-blocker")
+			if err := os.Mkdir(blocker, 0o700); err != nil {
+				t.Fatalf("create report blocker: %v", err)
+			}
+			req.Store = &failingPersistenceStore{Store: req.Store, failOperation: failRenderedReportPath, renderedReportPath: blocker}
+		}, wantRaw: true, wantNormalized: true, wantContext: true},
+		{name: "output copy", raw: validDailyWorkflowJSON(), configure: func(req *GenerateRequest, _ *workflowNotifier) {
+			req.OutputPath = t.TempDir()
+		}, wantRaw: true, wantNormalized: true, wantContext: true, wantReport: true},
+		{name: "notification", raw: validDailyWorkflowJSON(), configure: func(_ *GenerateRequest, notifier *workflowNotifier) {
+			notifier.err = errors.New("notification rejected")
+		}, wantRaw: true, wantNormalized: true, wantContext: true, wantReport: true, wantOutput: true, wantNotify: true},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			cfg := workflowConfig(t)
+			definition := report.DefaultRegistry().MustLookup(report.Daily)
+			executor := &workflowExecutor{definition: definition, raw: []byte(test.raw)}
+			notifier := &workflowNotifier{}
+			bundle := workflowBundle(t)
+			filesystem, err := state.NewFilesystemStore(cfg.Workspace)
+			if err != nil {
+				t.Fatalf("NewFilesystemStore() error = %v", err)
+			}
+			req := GenerateRequest{
+				Config: cfg, Report: ReportDaily, Date: workflowTime("2026-05-29T12:00:00-05:00"), Now: workflowTime("2026-05-29T08:30:00-05:00"),
+				OutputPath: filepath.Join(t.TempDir(), "daily.md"), Collector: &workflowCollector{result: &collect.Result{Bundle: &bundle}},
+				Executor: executor, Notifier: notifier, Store: filesystem,
+			}
+			if test.configure != nil {
+				test.configure(&req, notifier)
+			}
+			result, err := GenerateDetailed(context.Background(), req)
+			if err == nil || result == nil {
+				t.Fatalf("result/error = %#v/%v, want partial result and error", result, err)
+			}
+			if (result.GeneratedTextRawPath != "") != test.wantRaw || (result.GeneratedTextPath != "") != test.wantNormalized ||
+				(result.RenderContextPath != "") != test.wantContext || (result.ReportPath != "") != test.wantReport ||
+				(result.OutputPath != "") != test.wantOutput || (result.NotificationPath != "") != test.wantNotify {
+				t.Fatalf("reached paths = raw %q normalized %q context %q report %q output %q notification %q", result.GeneratedTextRawPath, result.GeneratedTextPath, result.RenderContextPath, result.ReportPath, result.OutputPath, result.NotificationPath)
+			}
+			if test.wantRaw {
+				persisted, readErr := os.ReadFile(result.GeneratedTextRawPath)
+				if readErr != nil || !bytes.Equal(persisted, []byte(test.raw)) {
+					t.Fatalf("retained raw output = %q, error %v", persisted, readErr)
+				}
+			}
+			if test.name == "notification" && (len(notifier.requests) != 1 || notifier.requests[0].ReportPath != result.ReportPath) {
+				t.Fatalf("notification requests = %#v", notifier.requests)
+			}
+		})
+	}
+}
+
+func TestGenerateDetailedDebugFailuresRespectProviderBoundary(t *testing.T) {
+	tests := []struct {
+		name                string
+		createCollision     func(string, report.Resolved) error
+		wantProviderCalls   int
+		wantPreparationFile bool
+	}{
+		{
+			name: "preparation debug",
+			createCollision: func(root string, resolved report.Resolved) error {
+				path := workflowDebugRunPath(root, resolved)
+				if err := os.MkdirAll(filepath.Dir(path), 0o700); err != nil {
+					return err
+				}
+				return os.WriteFile(path, []byte("not a directory"), 0o600)
+			},
+		},
+		{
+			name: "execution debug", wantProviderCalls: 1, wantPreparationFile: true,
+			createCollision: func(root string, resolved report.Resolved) error {
+				return os.MkdirAll(filepath.Join(workflowDebugRunPath(root, resolved), "execution.json"), 0o700)
+			},
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			cfg := workflowConfig(t)
+			cfg.Notify.Distributor.Enabled = false
+			now := workflowTime("2026-05-29T08:30:00-05:00")
+			request := GenerateRequest{Config: cfg, Report: ReportDaily, Date: workflowTime("2026-05-29T12:00:00-05:00"), Now: now}
+			resolved, err := ResolveGenerate(request, now)
+			if err != nil {
+				t.Fatalf("ResolveGenerate() error = %v", err)
+			}
+			debugRoot := filepath.Join(t.TempDir(), "prompt-debug")
+			if err := test.createCollision(debugRoot, resolved); err != nil {
+				t.Fatalf("create debug collision: %v", err)
+			}
+			bundle := workflowBundle(t)
+			executor := &workflowExecutor{definition: resolved.Definition, raw: []byte(validDailyWorkflowJSON())}
+			request.Collector = &workflowCollector{result: &collect.Result{Bundle: &bundle}}
+			request.Executor = executor
+			request.LLMDebugDir = debugRoot
+			result, err := GenerateDetailed(context.Background(), request)
+			if err == nil || result == nil || promptexec.CategoryOf(err) != promptexec.InvalidConfiguration {
+				t.Fatalf("result/error/category = %#v/%v/%q", result, err, promptexec.CategoryOf(err))
+			}
+			if executor.providerCalls != test.wantProviderCalls || result.PreparationPath == "" || result.ExecutionPath != "" || result.GeneratedTextRawPath != "" {
+				t.Fatalf("provider/preparation/metadata/execution/raw = %d/%q/%q/%q/%q", executor.providerCalls, result.PreparationPath, result.MetadataPath, result.ExecutionPath, result.GeneratedTextRawPath)
+			}
+			if test.wantPreparationFile && result.MetadataPath == "" {
+				t.Fatal("execution debug failure lost previously persisted metadata")
+			}
+			preparationDebug := filepath.Join(workflowDebugRunPath(debugRoot, resolved), "preparation.json")
+			_, statErr := os.Stat(preparationDebug)
+			if (statErr == nil) != test.wantPreparationFile {
+				t.Fatalf("preparation debug stat error = %v, want file %t", statErr, test.wantPreparationFile)
+			}
+		})
+	}
+}
+
+func workflowDebugRunPath(root string, resolved report.Resolved) string {
+	return filepath.Join(root, string(resolved.Definition.ID), resolved.ValidPeriod.Start.Format("2006-01-02"), resolved.Metadata().RunID)
+}
+
+func workflowBundlePaths(id report.ID, validDate, runID string) []string {
+	switch id {
+	case report.Daily:
+		return []string{"daily/" + validDate + "/" + runID + ".md", "daily/" + validDate + "/index.md"}
+	case report.Today:
+		return []string{"daily/" + validDate + "/" + runID + ".md", "daily/" + validDate + "/index.md", "today/index.md"}
+	case report.Tomorrow:
+		return []string{"daily/" + validDate + "/" + runID + ".md", "daily/" + validDate + "/index.md", "tomorrow/index.md"}
+	case report.Hourly:
+		return []string{"hourly/index.md"}
+	default:
+		return nil
+	}
+}
+
+func TestGenerateDetailedSelectsPriorSnapshotsForRetainedReports(t *testing.T) {
+	tests := []struct {
+		name              string
+		kind              ReportKind
+		id                report.ID
+		date              time.Time
+		raw               string
+		wantPrior         bool
+		wantRecentChanges bool
+	}{
+		{name: "daily", kind: ReportDaily, id: report.Daily, date: workflowTime("2026-05-29T12:00:00-05:00"), raw: validDailyWorkflowJSON(), wantPrior: true, wantRecentChanges: true},
+		{name: "today", kind: ReportToday, id: report.Today, raw: validTodayWorkflowJSON(), wantPrior: true, wantRecentChanges: true},
+		{name: "tomorrow", kind: ReportTomorrow, id: report.Tomorrow, raw: validTomorrowWorkflowJSON(), wantPrior: true, wantRecentChanges: true},
+		{name: "hourly", kind: ReportHourly, id: report.Hourly, raw: validHourlyWorkflowJSON()},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			cfg := workflowConfig(t)
+			cfg.Notify.Distributor.Enabled = false
+			definition := report.DefaultRegistry().MustLookup(test.id)
+			firstBundle := workflowBundle(t)
+			setWorkflowTemperatures(&firstBundle, 45)
+			first, err := GenerateDetailed(context.Background(), GenerateRequest{
+				Config: cfg, Report: test.kind, Date: test.date, Now: workflowTime("2026-05-29T08:00:00-05:00"),
+				Collector: &workflowCollector{result: &collect.Result{Bundle: &firstBundle}},
+				Executor:  &workflowExecutor{definition: definition, raw: []byte(test.raw)},
+			})
+			if err != nil {
+				t.Fatalf("first GenerateDetailed() error = %v", err)
+			}
+			secondBundle := workflowBundle(t)
+			setWorkflowTemperatures(&secondBundle, 85)
+			second, err := GenerateDetailed(context.Background(), GenerateRequest{
+				Config: cfg, Report: test.kind, Date: test.date, Now: workflowTime("2026-05-29T08:30:00-05:00"),
+				Collector: &workflowCollector{result: &collect.Result{Bundle: &secondBundle}},
+				Executor:  &workflowExecutor{definition: definition, raw: []byte(test.raw)},
+			})
+			if err != nil {
+				t.Fatalf("second GenerateDetailed() error = %v", err)
+			}
+			if test.wantPrior && (second.PriorSnapshot == nil || second.PriorSnapshot.Metadata.RunID != first.Metadata.RunID || second.PriorSnapshot.Metadata.ReportID != test.id) {
+				t.Fatalf("prior snapshot = %#v, want first %s run %q", second.PriorSnapshot, test.id, first.Metadata.RunID)
+			}
+			if !test.wantPrior && second.PriorSnapshot != nil {
+				t.Fatalf("prior snapshot = %#v, want none for non-overlapping rolling window", second.PriorSnapshot)
+			}
+			if (len(second.RecentChanges) > 0) != test.wantRecentChanges {
+				t.Fatalf("recent changes = %#v, want present %t", second.RecentChanges, test.wantRecentChanges)
+			}
+			if (len(second.DataPackage.RecentChanges.Items) > 0) != test.wantRecentChanges {
+				t.Fatalf("data package recent changes = %#v, want present %t", second.DataPackage.RecentChanges.Items, test.wantRecentChanges)
+			}
+		})
+	}
+}
+
+func setWorkflowTemperatures(bundle *weatherdata.Bundle, temperature float64) {
+	for index := range bundle.Hourly.Periods {
+		value := temperature
+		bundle.Hourly.Periods[index].TemperatureF = &value
+	}
+}
+
+func workflowConfig(t *testing.T) config.Config {
+	t.Helper()
+	cfg := config.Defaults()
+	cfg.Workspace.Root = t.TempDir()
+	cfg.WeatherAPI.Timezone = "America/Chicago"
+	cfg.Location.ID = "home"
+	cfg.Location.Name = "Testville"
+	cfg.Location.Region = "MO"
+	cfg.Notify.Distributor.Enabled = true
+	cfg.Notify.Distributor.PipelineIDTemplate = "reports.{report_id}.{artifact_group}"
+	return cfg
+}
+
+func workflowBundle(t *testing.T) weatherdata.Bundle {
+	t.Helper()
+	data, err := os.ReadFile(filepath.Join("..", "forecast", "testdata", "daily_bundle.json"))
+	if err != nil {
+		t.Fatalf("read bundle fixture: %v", err)
+	}
+	var bundle weatherdata.Bundle
+	if err := json.Unmarshal(data, &bundle); err != nil {
+		t.Fatalf("decode bundle fixture: %v", err)
+	}
+	future := bundle.Hourly.Periods[0]
+	future.StartTime = workflowTime("2026-05-30T06:00:00-05:00")
+	future.EndTime = workflowTime("2026-05-30T07:00:00-05:00")
+	bundle.Hourly.Periods = append(bundle.Hourly.Periods, future)
+	futureNarrative := bundle.Narrative.Periods[0]
+	futureNarrative.StartTime = workflowTime("2026-05-30T06:00:00-05:00")
+	futureNarrative.EndTime = workflowTime("2026-05-30T18:00:00-05:00")
+	futureNarrative.Name = "Tomorrow"
+	bundle.Narrative.Periods = append(bundle.Narrative.Periods, futureNarrative)
+	return bundle
+}
+
+func workflowTime(value string) time.Time {
+	parsed, err := time.Parse(time.RFC3339, value)
+	if err != nil {
+		panic(err)
+	}
+	return parsed
+}
+
+func validHourlyWorkflowJSON() string {
+	return `{"summary":"Storm chances increase through late morning.","forecast_discussion":"A front will keep the region unsettled.","precipitation_timing":"A cold front is moving into the region.","confidence":"Medium"}`
+}
+
+func validTomorrowWorkflowJSON() string {
+	return `{"summary":"Tomorrow starts with showers before improving.","forecast_discussion":["Morning showers should taper as drier air arrives.","Afternoon conditions trend quieter."],"precipitation_timing":"The best rain chance is during the morning."}`
+}
+
+func validTodayWorkflowJSON() string {
+	return `{"summary":"Today starts with showers before improving.","forecast_discussion":["Morning showers should taper as drier air arrives.","Afternoon conditions trend quieter."],"precipitation_timing":"The best rain chance is during the morning."}`
+}
+
+func validDailyWorkflowJSON() string {
+	return `{"summary":"Showers are possible during the selected day.","forecast_discussion":["A front will keep rain chances in the forecast.","Temperatures stay seasonable by afternoon."],"precipitation_timing":"Rain is most likely during the afternoon.","confidence":"Medium"}`
+}

internal/app/test_helpers_test.go

@@ -0,0 +1,21 @@
+package app
+
+import (
+	"testing"
+	"time"
+)
+
+func mustParse(value string) time.Time {
+	parsed, err := time.Parse(time.RFC3339, value)
+	if err != nil {
+		panic(err)
+	}
+	return parsed
+}
+
+func requireNoError(t *testing.T, err error) {
+	t.Helper()
+	if err != nil {
+		t.Fatal(err)
+	}
+}

internal/briefing/base_modules_test.go

@@ -155,10 +155,10 @@ func TestHourlyForecastPrecipMentionThreshold(t *testing.T) {
 func TestHourlyForecastModuleRejectsUnsupportedReports(t *testing.T) {
 	registry := MustDefaultModuleRegistry()
 	ctx := testModuleContext()
-	ctx.Resolved.Definition = report.DefaultRegistry().MustLookup(report.Weekend)
+	ctx.Resolved.Definition = report.Definition{ID: report.ID("unsupported")}
 
 	_, err := registry.BuildModule(ctx, module.ConfigItem{ID: module.HourlyForecast})
-	if err == nil || !strings.Contains(err.Error(), `module "hourly_forecast" is not compatible with report "weekend"`) {
+	if err == nil || !strings.Contains(err.Error(), `module "hourly_forecast" is not compatible with report "unsupported"`) {
 		t.Fatalf("BuildModule() error = %v, want incompatible report", err)
 	}
 }
@@ -227,10 +227,10 @@ func TestNarrativeForecastModuleUsesValidPeriodNarrativePeriods(t *testing.T) {
 func TestNarrativeForecastModuleRejectsUnsupportedReports(t *testing.T) {
 	registry := MustDefaultModuleRegistry()
 	ctx := testModuleContext()
-	ctx.Resolved.Definition = report.DefaultRegistry().MustLookup(report.Weekend)
+	ctx.Resolved.Definition = report.Definition{ID: report.ID("unsupported")}
 
 	_, err := registry.BuildModule(ctx, module.ConfigItem{ID: module.NarrativeForecast})
-	if err == nil || !strings.Contains(err.Error(), `module "narrative_forecast" is not compatible with report "weekend"`) {
+	if err == nil || !strings.Contains(err.Error(), `module "narrative_forecast" is not compatible with report "unsupported"`) {
 		t.Fatalf("BuildModule() error = %v, want incompatible report", err)
 	}
 }

internal/briefing/derived_modules_test.go

@@ -603,7 +603,7 @@ func TestDailyPlanningModulePackagesPlanningFields(t *testing.T) {
 
 func TestDailyPlanningModuleRejectsUnsupportedReports(t *testing.T) {
 	registry := MustDefaultModuleRegistry()
-	for _, id := range []report.ID{report.Today, report.Tomorrow, report.Hourly, report.ThreeDay, report.Weekend, report.Storm} {
+	for _, id := range []report.ID{report.Today, report.Tomorrow, report.Hourly} {
 		t.Run(string(id), func(t *testing.T) {
 			ctx := derivedModuleContext(id)
 			_, err := registry.BuildModule(ctx, module.ConfigItem{ID: module.DailyPlanning})

internal/briefing/modules.go

@@ -265,8 +265,8 @@ func (d ModuleDefinition) ValidateOptions(options any) error {
 }
 
 func defaultModuleDefinitions() []ModuleDefinition {
-	allReports := []report.ID{report.Daily, report.Today, report.Tomorrow, report.Hourly, report.ThreeDay, report.Weekend, report.Storm}
+	allReports := []report.ID{report.Daily, report.Today, report.Tomorrow, report.Hourly}
-	daypartReports := []report.ID{report.Daily, report.Today, report.Tomorrow, report.ThreeDay, report.Weekend}
+	daypartReports := []report.ID{report.Daily, report.Today, report.Tomorrow}
 	return []ModuleDefinition{
 		{
 			ID:                module.Metadata,

internal/briefing/modules_test.go

@@ -373,7 +373,7 @@ func TestModuleRegistryValidatesDailyPlanningSupport(t *testing.T) {
 	if err := registry.ValidateComposition(report.Daily, []module.ConfigItem{{ID: module.DailyPlanning}}); err != nil {
 		t.Fatalf("ValidateComposition(daily) error = %v", err)
 	}
-	for _, id := range []report.ID{report.Today, report.Tomorrow, report.Hourly, report.ThreeDay, report.Weekend, report.Storm} {
+	for _, id := range []report.ID{report.Today, report.Tomorrow, report.Hourly} {
 		t.Run(string(id), func(t *testing.T) {
 			err := registry.ValidateComposition(id, []module.ConfigItem{{ID: module.DailyPlanning}})
 			if err == nil || !strings.Contains(err.Error(), `module "daily_planning" is not compatible with report`) {

internal/buildinfo/buildinfo.go

@@ -0,0 +1,6 @@
+// Package buildinfo exposes release metadata injected by the build pipeline.
+package buildinfo
+
+// Version identifies this Weatherreporter build. Release builds replace the
+// development value with their semantic version tag through the Go linker.
+var Version = "development"

internal/changes/three_day.go

@@ -1,144 +0,0 @@
-package changes
-
-import (
-	"fmt"
-	"sort"
-
-	"gitea.maximumdirect.net/eric/weatherreporter/internal/module"
-)
-
-func CompareThreeDay(previous module.Snapshot, current module.Snapshot, thresholds Thresholds) ([]Change, error) {
-	previousDayparts, err := requiredStanza[map[string]daypartSummaryStanza](previous, "derived_daypart_summaries")
-	if err != nil {
-		return nil, fmt.Errorf("previous daypart summaries: %w", err)
-	}
-	currentDayparts, err := requiredStanza[map[string]daypartSummaryStanza](current, "derived_daypart_summaries")
-	if err != nil {
-		return nil, fmt.Errorf("current daypart summaries: %w", err)
-	}
-	previousDays := outlookDaysFromDayparts(previousDayparts)
-	currentDays := outlookDaysFromDayparts(currentDayparts)
-	return compareOutlookDays(previousDays, currentDays, thresholds, "")
-}
-
-type outlookDay struct {
-	Date           string
-	LowTempF       *int
-	HighTempF      *int
-	MaxPopPercent  *int
-	MaxPopTime     string
-	MaxWindGustMph *int
-	Indicators     indicators
-}
-
-func compareOutlookDays(previousDays map[string]outlookDay, currentDays map[string]outlookDay, thresholds Thresholds, prefix string) ([]Change, error) {
-	var changes []Change
-	for date, currentDay := range currentDays {
-		previousDay, ok := previousDays[date]
-		if !ok {
-			changes = append(changes, Change{Type: prefix + "outlook_day_added", Message: fmt.Sprintf("Outlook day added: %s.", date), Current: date})
-			continue
-		}
-		changes = append(changes, compareOutlookDay(date, previousDay, currentDay, thresholds, prefix)...)
-	}
-	for date := range previousDays {
-		if _, ok := currentDays[date]; !ok {
-			changes = append(changes, Change{Type: prefix + "outlook_day_removed", Message: fmt.Sprintf("Outlook day removed: %s.", date), Previous: date})
-		}
-	}
-	sortChanges(changes)
-	return changes, nil
-}
-
-func compareOutlookDay(date string, previous outlookDay, current outlookDay, thresholds Thresholds, prefix string) []Change {
-	var changes []Change
-	for _, change := range compareTemperatureValues("Low", previous.LowTempF, current.LowTempF, thresholds.TemperatureDegrees) {
-		change.Message = date + ": " + change.Message
-		change.Type = prefix + "outlook_" + change.Type
-		changes = append(changes, change)
-	}
-	for _, change := range compareTemperatureValues("High", previous.HighTempF, current.HighTempF, thresholds.TemperatureDegrees) {
-		change.Message = date + ": " + change.Message
-		change.Type = prefix + "outlook_" + change.Type
-		changes = append(changes, change)
-	}
-	for _, change := range comparePrecipitationValues(previous.MaxPopPercent, current.MaxPopPercent, thresholds.PrecipProbabilityPoints, prefix+"outlook_") {
-		change.Message = date + ": " + change.Message
-		changes = append(changes, change)
-	}
-	for _, change := range comparePrecipTiming(previous.MaxPopTime, current.MaxPopTime, thresholds.PrecipTimingShiftMinutes, prefix+"outlook_") {
-		change.Message = date + ": " + change.Message
-		changes = append(changes, change)
-	}
-	for _, change := range compareWindValues(previous.MaxWindGustMph, current.MaxWindGustMph, thresholds.WindGustMilesPerHour, prefix+"outlook_") {
-		change.Message = date + ": " + change.Message
-		changes = append(changes, change)
-	}
-	for _, change := range compareIndicators(previous.Indicators, current.Indicators, prefix+"outlook_") {
-		change.Message = date + ": " + change.Message
-		changes = append(changes, change)
-	}
-	return changes
-}
-
-func outlookDaysFromDayparts(dayparts map[string]daypartSummaryStanza) map[string]outlookDay {
-	out := map[string]outlookDay{}
-	var keys []string
-	for key := range dayparts {
-		keys = append(keys, key)
-	}
-	sort.Strings(keys)
-	for _, key := range keys {
-		daypart := dayparts[key]
-		date := daypartDate(daypart)
-		if date == "" {
-			continue
-		}
-		day := out[date]
-		day.Date = date
-		low, high := parseTempRange(daypart.TempRangeF)
-		day.LowTempF = minInt(day.LowTempF, low)
-		day.HighTempF = maxInt(day.HighTempF, high)
-		day.MaxPopPercent = maxInt(day.MaxPopPercent, daypart.MaxPopPercent)
-		if daypart.MaxPopPercent != nil && day.MaxPopPercent != nil && *daypart.MaxPopPercent == *day.MaxPopPercent {
-			day.MaxPopTime = daypart.MaxPopTime
-		}
-		day.MaxWindGustMph = maxInt(day.MaxWindGustMph, daypart.MaxWindGustMph)
-		day.Indicators.Snow = day.Indicators.Snow || daypart.Snow
-		day.Indicators.Ice = day.Indicators.Ice || daypart.Ice
-		out[date] = day
-	}
-	return out
-}
-
-func daypartDate(daypart daypartSummaryStanza) string {
-	return daypart.Date
-}
-
-func minInt(a *int, b *int) *int {
-	if a == nil {
-		return copyInt(b)
-	}
-	if b != nil && *b < *a {
-		return copyInt(b)
-	}
-	return a
-}
-
-func maxInt(a *int, b *int) *int {
-	if a == nil {
-		return copyInt(b)
-	}
-	if b != nil && *b > *a {
-		return copyInt(b)
-	}
-	return a
-}
-
-func copyInt(value *int) *int {
-	if value == nil {
-		return nil
-	}
-	copied := *value
-	return &copied
-}

internal/changes/three_day_test.go

@@ -1,43 +0,0 @@
-package changes
-
-import (
-	"testing"
-
-	"gitea.maximumdirect.net/eric/weatherreporter/internal/module"
-)
-
-func TestCompareThreeDayDetectsDayChanges(t *testing.T) {
-	previous := outlookSnapshot(t, "2026-05-29", "70", 20, "9 AM", false)
-	current := outlookSnapshot(t, "2026-05-29", "78", 70, "12 PM", true)
-
-	changes, err := CompareThreeDay(previous, current, Thresholds{
-		TemperatureDegrees:       5,
-		PrecipProbabilityPoints:  20,
-		PrecipTimingShiftMinutes: 120,
-	})
-	if err != nil {
-		t.Fatalf("CompareThreeDay() error = %v", err)
-	}
-
-	if len(changes) == 0 {
-		t.Fatal("changes length = 0, want detected 3-day changes")
-	}
-	if countType(changes, "outlook_precip_probability_change") == 0 || countType(changes, "outlook_snow_risk_change") == 0 {
-		t.Fatalf("changes = %#v, want precipitation and snow changes", changes)
-	}
-}
-
-func outlookSnapshot(t *testing.T, date string, tempRange string, precip int, precipTime string, snow bool) module.Snapshot {
-	t.Helper()
-	return snapshot(t, module.Output{ID: module.DerivedDaypartSummaries, StanzaName: "derived_daypart_summaries", Value: map[string]daypartSummaryStanza{
-		date + "_morning": {
-			Date:          date,
-			PeriodBegins:  date + " at 6:00 AM",
-			PeriodEnds:    date + " at 10:00 AM",
-			TempRangeF:    tempRange,
-			MaxPopPercent: &precip,
-			MaxPopTime:    precipTime,
-			Snow:          snow,
-		},
-	}})
-}

internal/changes/weekend.go

@@ -1,19 +0,0 @@
-package changes
-
-import (
-	"fmt"
-
-	"gitea.maximumdirect.net/eric/weatherreporter/internal/module"
-)
-
-func CompareWeekend(previous module.Snapshot, current module.Snapshot, thresholds Thresholds) ([]Change, error) {
-	previousDayparts, err := requiredStanza[map[string]daypartSummaryStanza](previous, "derived_daypart_summaries")
-	if err != nil {
-		return nil, fmt.Errorf("previous weekend daypart summaries: %w", err)
-	}
-	currentDayparts, err := requiredStanza[map[string]daypartSummaryStanza](current, "derived_daypart_summaries")
-	if err != nil {
-		return nil, fmt.Errorf("current weekend daypart summaries: %w", err)
-	}
-	return compareOutlookDays(outlookDaysFromDayparts(previousDayparts), outlookDaysFromDayparts(currentDayparts), thresholds, "weekend_")
-}

internal/changes/weekend_test.go

@@ -1,19 +0,0 @@
-package changes
-
-import "testing"
-
-func TestCompareWeekendDetectsOutlookChanges(t *testing.T) {
-	previous := outlookSnapshot(t, "2026-05-30", "70", 10, "9 AM", false)
-	current := outlookSnapshot(t, "2026-05-30", "78", 10, "9 AM", true)
-
-	changes, err := CompareWeekend(previous, current, Thresholds{TemperatureDegrees: 5})
-	if err != nil {
-		t.Fatalf("CompareWeekend() error = %v", err)
-	}
-	if len(changes) == 0 {
-		t.Fatal("changes length = 0, want weekend changes")
-	}
-	if countType(changes, "weekend_outlook_snow_risk_change") == 0 {
-		t.Fatalf("changes = %#v, want snow risk change", changes)
-	}
-}

internal/cli/executor_factory.go

@@ -0,0 +1,59 @@
+package cli
+
+import (
+	"time"
+
+	promptkitadapter "gitea.maximumdirect.net/eric/weatherreporter/internal/adapters/promptkit"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/config"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptexec"
+)
+
+// PromptExecutorConfig is the project-owned construction input for one prompt
+// executor. It keeps adapter implementation types out of Runner's API.
+type PromptExecutorConfig struct {
+	Profile               string
+	ProfileFile           string
+	ProfileDirectory      string
+	Timeout               time.Duration
+	LocalEndpoint         string
+	LocalConcurrencyLimit int
+}
+
+// ExecutorFactory constructs one executor for an action.
+type ExecutorFactory func(PromptExecutorConfig) (promptexec.Executor, error)
+
+func (r Runner) promptExecutor(cfg config.PromptkitConfig) (promptexec.Executor, error) {
+	factory := r.ExecutorFactory
+	if factory == nil {
+		factory = newPromptkitExecutor
+	}
+	return factory(promptExecutorConfig(cfg))
+}
+
+func promptExecutorConfig(cfg config.PromptkitConfig) PromptExecutorConfig {
+	result := PromptExecutorConfig{
+		Profile:          cfg.Profile,
+		ProfileFile:      cfg.ProfileFile,
+		ProfileDirectory: cfg.ProfileDir,
+		Timeout:          cfg.Timeout,
+	}
+	if cfg.Local.Endpoint != "" {
+		result.LocalEndpoint = cfg.Local.Endpoint
+		result.LocalConcurrencyLimit = cfg.Local.ConcurrencyLimit
+	}
+	return result
+}
+
+func newPromptkitExecutor(cfg PromptExecutorConfig) (promptexec.Executor, error) {
+	return promptkitadapter.New(promptkitAdapterConfig(cfg))
+}
+
+func promptkitAdapterConfig(cfg PromptExecutorConfig) promptkitadapter.Config {
+	return promptkitadapter.Config{
+		ProfileDirectory:      cfg.ProfileDirectory,
+		ProfileFile:           cfg.ProfileFile,
+		LocalEndpoint:         cfg.LocalEndpoint,
+		LocalConcurrencyLimit: cfg.LocalConcurrencyLimit,
+		Timeout:               cfg.Timeout,
+	}
+}

internal/cli/executor_factory_test.go

@@ -0,0 +1,78 @@
+package cli
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	promptkitadapter "gitea.maximumdirect.net/eric/weatherreporter/internal/adapters/promptkit"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/config"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptexec"
+)
+
+func TestRunnerPromptExecutorMapsConfigurationOnce(t *testing.T) {
+	var calls int
+	var received PromptExecutorConfig
+	runner := Runner{ExecutorFactory: func(value PromptExecutorConfig) (promptexec.Executor, error) {
+		calls++
+		received = value
+		return factoryExecutor{}, nil
+	}}
+	executor, err := runner.promptExecutor(config.PromptkitConfig{
+		Profile:     "selected-profile",
+		ProfileFile: "/etc/weatherreporter/profile.yml",
+		Timeout:     45 * time.Second,
+		Local: config.PromptkitLocalConfig{
+			Endpoint:         "http://127.0.0.1:8080",
+			ConcurrencyLimit: 3,
+		},
+	})
+	if err != nil || executor == nil || calls != 1 {
+		t.Fatalf("executor/error/calls = %#v/%v/%d", executor, err, calls)
+	}
+	want := PromptExecutorConfig{
+		Profile: "selected-profile", ProfileFile: "/etc/weatherreporter/profile.yml", Timeout: 45 * time.Second,
+		LocalEndpoint: "http://127.0.0.1:8080", LocalConcurrencyLimit: 3,
+	}
+	if received != want {
+		t.Fatalf("factory config = %#v, want %#v", received, want)
+	}
+}
+
+func TestPromptExecutorConfigLeavesBlankLocalBackendUnregistered(t *testing.T) {
+	value := promptExecutorConfig(config.PromptkitConfig{
+		Timeout: 2 * time.Minute,
+		Local:   config.PromptkitLocalConfig{ConcurrencyLimit: 1},
+	})
+	if value.LocalEndpoint != "" || value.LocalConcurrencyLimit != 0 {
+		t.Fatalf("executor config = %#v, want no local backend", value)
+	}
+}
+
+func TestPromptkitAdapterConfigMapsExecutorSettings(t *testing.T) {
+	adapterConfig := promptkitAdapterConfig(PromptExecutorConfig{
+		ProfileDirectory: "/etc/weatherreporter/profiles",
+		Timeout:          30 * time.Second, LocalEndpoint: "http://127.0.0.1:8080", LocalConcurrencyLimit: 2,
+	})
+	want := promptkitadapter.Config{
+		ProfileDirectory: "/etc/weatherreporter/profiles",
+		Timeout:          30 * time.Second, LocalEndpoint: "http://127.0.0.1:8080", LocalConcurrencyLimit: 2,
+	}
+	if adapterConfig != want {
+		t.Fatalf("adapter config = %#v, want %#v", adapterConfig, want)
+	}
+}
+
+type factoryExecutor struct{}
+
+func (factoryExecutor) InspectPrompt(context.Context, string, string) (promptexec.PromptInspection, error) {
+	return promptexec.PromptInspection{}, nil
+}
+
+func (factoryExecutor) InspectProfile(context.Context, string) (promptexec.ProfileInspection, error) {
+	return promptexec.ProfileInspection{}, nil
+}
+
+func (factoryExecutor) Execute(context.Context, promptexec.ExecuteRequest, promptexec.PreparationCallback) (*promptexec.Execution, error) {
+	return nil, nil
+}

internal/cli/result.go

@@ -17,26 +17,27 @@ const (
 )
 
 type generateSummary struct {
-	Command                 string                       `json:"command"`
+	Command              string                       `json:"command"`
-	ReportID                report.ID                    `json:"reportId"`
+	ReportID             report.ID                    `json:"reportId"`
-	ReportName              string                       `json:"reportName"`
+	ReportName           string                       `json:"reportName"`
-	PromptID                string                       `json:"promptId"`
+	PromptID             string                       `json:"promptId"`
-	RunID                   string                       `json:"runId"`
+	RunID                string                       `json:"runId"`
-	Status                  string                       `json:"status"`
+	Status               string                       `json:"status"`
-	GeneratedAt             time.Time                    `json:"generatedAt"`
+	GeneratedAt          time.Time                    `json:"generatedAt"`
-	ValidPeriod             timeutil.Period              `json:"validPeriod"`
+	ValidPeriod          timeutil.Period              `json:"validPeriod"`
-	ReportPath              string                       `json:"reportPath,omitempty"`
+	ReportPath           string                       `json:"reportPath,omitempty"`
-	OutputPath              string                       `json:"outputPath,omitempty"`
+	OutputPath           string                       `json:"outputPath,omitempty"`
-	MetadataPath            string                       `json:"metadataPath,omitempty"`
+	MetadataPath         string                       `json:"metadataPath,omitempty"`
-	DataPackagePath         string                       `json:"dataPackagePath,omitempty"`
+	DataPackagePath      string                       `json:"dataPackagePath,omitempty"`
-	PreflightPath           string                       `json:"preflightPath,omitempty"`
+	PreparationPath      string                       `json:"preparationPath,omitempty"`
-	GeneratedTextRawPath    string                       `json:"generatedTextRawPath,omitempty"`
+	ExecutionPath        string                       `json:"executionPath,omitempty"`
-	GeneratedTextResultPath string                       `json:"generatedTextResultPath,omitempty"`
+	LLMDebugPath         string                       `json:"llmDebugPath,omitempty"`
-	GeneratedTextPath       string                       `json:"generatedTextPath,omitempty"`
+	GeneratedTextRawPath string                       `json:"generatedTextRawPath,omitempty"`
-	RenderContextPath       string                       `json:"renderContextPath,omitempty"`
+	GeneratedTextPath    string                       `json:"generatedTextPath,omitempty"`
-	NotificationPath        string                       `json:"notificationPath,omitempty"`
+	RenderContextPath    string                       `json:"renderContextPath,omitempty"`
-	Notification            *generateNotificationSummary `json:"notification,omitempty"`
+	NotificationPath     string                       `json:"notificationPath,omitempty"`
-	Error                   string                       `json:"error,omitempty"`
+	Notification         *generateNotificationSummary `json:"notification,omitempty"`
+	Error                string                       `json:"error,omitempty"`
 }
 
 type generateNotificationSummary struct {
@@ -85,9 +86,10 @@ func newGenerateSummary(result *app.ReportResult, err error) generateSummary {
 	summary.OutputPath = result.OutputPath
 	summary.MetadataPath = result.MetadataPath
 	summary.DataPackagePath = result.DataPackagePath
-	summary.PreflightPath = result.PreflightPath
+	summary.PreparationPath = result.PreparationPath
+	summary.ExecutionPath = result.ExecutionPath
+	summary.LLMDebugPath = result.LLMDebugPath
 	summary.GeneratedTextRawPath = result.GeneratedTextRawPath
-	summary.GeneratedTextResultPath = result.GeneratedTextResultPath
 	summary.GeneratedTextPath = result.GeneratedTextPath
 	summary.RenderContextPath = result.RenderContextPath
 	summary.NotificationPath = result.NotificationPath

internal/cli/result_test.go

@@ -19,16 +19,17 @@ func TestNewGenerateSummaryForGeneratedTextReport(t *testing.T) {
 	startedAt := acceptedAt.Add(time.Minute)
 	finishedAt := startedAt.Add(time.Minute)
 	result := &app.ReportResult{
-		DataPackagePath:         "/runs/hourly/data_package.yaml",
+		DataPackagePath:      "/runs/hourly/data_package.yaml",
-		PreflightPath:           "/runs/hourly/preflight.json",
+		PreparationPath:      "/runs/hourly/preparation.json",
-		ReportPath:              "/runs/hourly/report.md",
+		ExecutionPath:        "/runs/hourly/execution.json",
-		OutputPath:              "/copies/hourly.md",
+		LLMDebugPath:         "/operator-debug/hourly/2026-05-29/run-123",
-		MetadataPath:            "/runs/hourly/metadata.json",
+		ReportPath:           "/runs/hourly/report.md",
-		GeneratedTextRawPath:    "/runs/hourly/generated_text_raw.json",
+		OutputPath:           "/copies/hourly.md",
-		GeneratedTextResultPath: "/runs/hourly/generated_text_result.json",
+		MetadataPath:         "/runs/hourly/metadata.json",
-		GeneratedTextPath:       "/runs/hourly/generated_text.json",
+		GeneratedTextRawPath: "/runs/hourly/generated_text_raw.json",
-		RenderContextPath:       "/runs/hourly/render_context.json",
+		GeneratedTextPath:    "/runs/hourly/generated_text.json",
-		NotificationPath:        "/runs/hourly/notification.json",
+		RenderContextPath:    "/runs/hourly/render_context.json",
+		NotificationPath:     "/runs/hourly/notification.json",
 		Metadata: state.Metadata{
 			ReportID:    report.Hourly,
 			PromptID:    "weather.hourly_generated_text",
@@ -58,7 +59,7 @@ func TestNewGenerateSummaryForGeneratedTextReport(t *testing.T) {
 	if summary.ReportID != report.Hourly || summary.ReportName != "Hourly Report" || summary.PromptID != "weather.hourly_generated_text" || summary.RunID != "20260529T133000Z_hourly" {
 		t.Fatalf("summary identity = %#v, want hourly report identity", summary)
 	}
-	if summary.GeneratedTextRawPath == "" || summary.GeneratedTextResultPath == "" || summary.GeneratedTextPath == "" || summary.RenderContextPath == "" {
+	if summary.PreparationPath == "" || summary.ExecutionPath == "" || summary.LLMDebugPath == "" || summary.GeneratedTextRawPath == "" || summary.GeneratedTextPath == "" || summary.RenderContextPath == "" {
 		t.Fatalf("generated-text paths = %#v, want generated-text artifact paths", summary)
 	}
 	if summary.Notification == nil || summary.Notification.RunID != "distributor-run" || summary.Notification.AcceptedAt == nil || !summary.Notification.AcceptedAt.Equal(acceptedAt) {
@@ -71,20 +72,23 @@ func TestNewGenerateSummaryForGeneratedTextReport(t *testing.T) {
 	if strings.Contains(string(data), "replace_older") || strings.Contains(string(data), "actions") {
 		t.Fatalf("summary JSON includes raw distributor report payload:\n%s", string(data))
 	}
+	if strings.Contains(string(data), "preflightPath") || strings.Contains(string(data), "generatedTextResultPath") || !strings.Contains(string(data), "preparationPath") || !strings.Contains(string(data), "executionPath") {
+		t.Fatalf("summary JSON does not use prompt artifact path names:\n%s", string(data))
+	}
 }
 
-func TestNewGenerateSummaryForMarkdownReportOmitsGeneratedTextAndNotification(t *testing.T) {
+func TestNewGenerateSummaryOmitsNotificationWhenNotAttempted(t *testing.T) {
 	generatedAt := time.Date(2026, 5, 29, 13, 30, 0, 0, time.UTC)
 	result := &app.ReportResult{
-		DataPackagePath: "/runs/three-day/data_package.yaml",
+		DataPackagePath: "/runs/daily/data_package.yaml",
-		PreflightPath:   "/runs/three-day/preflight.json",
+		PreparationPath: "/runs/daily/preparation.json",
-		ReportPath:      "/runs/three-day/report.md",
+		ReportPath:      "/runs/daily/report.md",
-		OutputPath:      "/copies/three-day.md",
+		OutputPath:      "/copies/daily.md",
-		MetadataPath:    "/runs/three-day/metadata.json",
+		MetadataPath:    "/runs/daily/metadata.json",
 		Metadata: state.Metadata{
-			ReportID:    report.ThreeDay,
+			ReportID:    report.Daily,
-			PromptID:    "weather.three_day_outlook",
+			PromptID:    "weather.daily_generated_text",
-			RunID:       "20260529T133000Z_three_day",
+			RunID:       "20260529T133000Z_daily",
 			GeneratedAt: generatedAt,
 			ValidPeriod: testSummaryPeriod(generatedAt),
 		},
@@ -92,8 +96,8 @@ func TestNewGenerateSummaryForMarkdownReportOmitsGeneratedTextAndNotification(t
 
 	summary := newGenerateSummary(result, nil)
 
-	if summary.ReportID != report.ThreeDay || summary.ReportName != "3-Day Outlook" || summary.Status != "succeeded" {
+	if summary.ReportID != report.Daily || summary.ReportName != "Daily Report" || summary.Status != "succeeded" {
-		t.Fatalf("summary = %#v, want successful 3-day summary", summary)
+		t.Fatalf("summary = %#v, want successful daily summary", summary)
 	}
 	if summary.Notification != nil || summary.NotificationPath != "" {
 		t.Fatalf("notification summary/path = %#v/%q, want omitted", summary.Notification, summary.NotificationPath)
@@ -102,18 +106,43 @@ func TestNewGenerateSummaryForMarkdownReportOmitsGeneratedTextAndNotification(t
 	if err != nil {
 		t.Fatalf("Marshal() error = %v", err)
 	}
-	for _, omitted := range []string{"generatedTextRawPath", "generatedTextResultPath", "generatedTextPath", "renderContextPath", "notification"} {
+	for _, omitted := range []string{"notification"} {
 		if strings.Contains(string(data), omitted) {
 			t.Fatalf("summary JSON contains %q, want omitted:\n%s", omitted, string(data))
 		}
 	}
 }
 
+func TestNewGenerateSummaryOmitsUnreachedArtifactPaths(t *testing.T) {
+	result := &app.ReportResult{
+		DataPackagePath: "/runs/daily/data_package.yaml",
+		PreparationPath: "/runs/daily/preparation.json",
+		Metadata: state.Metadata{
+			ReportID: report.Daily,
+			RunID:    "20260529T133000Z_daily",
+		},
+	}
+
+	data, err := json.Marshal(newGenerateSummary(result, errors.New("metadata write failed")))
+	if err != nil {
+		t.Fatalf("Marshal() error = %v", err)
+	}
+	text := string(data)
+	for _, omitted := range []string{"executionPath", "reportPath", "outputPath", "metadataPath", "generatedTextRawPath", "generatedTextPath", "renderContextPath", "notificationPath"} {
+		if strings.Contains(text, omitted) {
+			t.Fatalf("partial summary includes unreached field %q:\n%s", omitted, text)
+		}
+	}
+	if !strings.Contains(text, "dataPackagePath") || !strings.Contains(text, "preparationPath") {
+		t.Fatalf("partial summary omits reached paths:\n%s", text)
+	}
+}
+
 func TestNewGenerateSummaryForNotificationFailure(t *testing.T) {
 	generatedAt := time.Date(2026, 5, 29, 13, 30, 0, 0, time.UTC)
 	result := &app.ReportResult{
 		DataPackagePath:  "/runs/hourly/data_package.yaml",
-		PreflightPath:    "/runs/hourly/preflight.json",
+		PreparationPath:  "/runs/hourly/preparation.json",
 		ReportPath:       "/runs/hourly/report.md",
 		OutputPath:       "/copies/hourly.md",
 		MetadataPath:     "/runs/hourly/metadata.json",

internal/cli/root.go

@@ -7,6 +7,7 @@ import (
 	"io"
 
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/app"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/buildinfo"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/config"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/report"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/timeutil"
@@ -16,15 +17,13 @@ const helpText = `weatherreporter prepares weather reports from normalized forec
 
 Usage:
   weatherreporter --help
-  weatherreporter generate daily --date YYYY-MM-DD [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--quiet]
+  weatherreporter --version
-  weatherreporter generate today [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--date YYYY-MM-DD] [--quiet]
+  weatherreporter generate daily --date YYYY-MM-DD [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--llm-debug-dir PATH] [--quiet]
-  weatherreporter generate tomorrow [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--quiet]
+  weatherreporter generate today [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--date YYYY-MM-DD] [--llm-debug-dir PATH] [--quiet]
-  weatherreporter generate hourly [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--quiet]
+  weatherreporter generate tomorrow [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--llm-debug-dir PATH] [--quiet]
-  weatherreporter generate three-day [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--quiet]
+  weatherreporter generate hourly [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--llm-debug-dir PATH] [--quiet]
-  weatherreporter generate weekend [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--quiet]
+  weatherreporter run morning [--config PATH] [--units VALUE] [--tz NAME] [--out-dir PATH] [--llm-debug-dir PATH] [--quiet]
-  weatherreporter generate storm [--config PATH] [--units VALUE] [--tz NAME] [--out PATH] [--quiet] --start TIME --end TIME
+  weatherreporter run evening [--config PATH] [--units VALUE] [--tz NAME] [--out-dir PATH] [--llm-debug-dir PATH] [--quiet]
-  weatherreporter run morning [--config PATH] [--units VALUE] [--tz NAME] [--out-dir PATH] [--quiet]
-  weatherreporter run evening [--config PATH] [--units VALUE] [--tz NAME] [--out-dir PATH] [--quiet]
   weatherreporter inspect reports [--config PATH] [--limit N]
   weatherreporter inspect metadata [--config PATH] RUN_ID
   weatherreporter inspect modules [--config PATH] RUN_ID
@@ -34,16 +33,20 @@ Usage:
 
 Options:
   -h, --help       Show this help message.
+  --version        Show the Weatherreporter version.
   --config PATH    Load configuration from PATH instead of /usr/local/etc/weatherreporter/config.yml.
   --units VALUE    Override weather API units.
   --tz NAME        Override weather API timezone.
   --out PATH       Write an extra Markdown report copy where supported by the generate command.
+  --llm-debug-dir PATH  Write sensitive prompt debug artifacts outside the managed workspace.
   --out-dir PATH   Write extra Markdown report copies for run commands.
   --quiet          Suppress successful generate and run output.
 `
 
 type Runner struct {
-	Clock timeutil.Clock
+	Clock           timeutil.Clock
+	ExecutorFactory ExecutorFactory
+	Version         string
 }
 
 func Run(ctx context.Context, args []string, stdout io.Writer, stderr io.Writer) error {
@@ -58,6 +61,17 @@ func (r Runner) Run(ctx context.Context, args []string, stdout io.Writer, stderr
 		_, err := fmt.Fprint(stdout, helpText)
 		return err
 	}
+	if args[0] == "--version" {
+		if len(args) != 1 {
+			return fmt.Errorf("--version does not accept arguments")
+		}
+		version := r.Version
+		if version == "" {
+			version = buildinfo.Version
+		}
+		_, err := fmt.Fprintf(stdout, "weatherreporter %s\n", version)
+		return err
+	}
 
 	switch args[0] {
 	case "generate":
@@ -99,19 +113,18 @@ func (r Runner) Run(ctx context.Context, args []string, stdout io.Writer, stderr
 }
 
 type commonOptions struct {
-	ConfigPath string
+	ConfigPath  string
-	Units      string
+	Units       string
-	Timezone   string
+	Timezone    string
-	Output     string
+	Output      string
-	OutputDir  string
+	OutputDir   string
-	Quiet      bool
+	LLMDebugDir string
+	Quiet       bool
 }
 
 type generateOptions struct {
 	commonOptions
-	Date  string
+	Date string
-	Start string
-	End   string
 }
 
 type inspectOptions struct {
@@ -218,16 +231,22 @@ func (r Runner) resolveGenerateAction(args []string) (app.GenerateRequest, commo
 	if err != nil {
 		return app.GenerateRequest{}, commonOptions{}, err
 	}
+	executor, err := r.promptExecutor(cfg.Promptkit)
+	if err != nil {
+		return app.GenerateRequest{}, commonOptions{}, err
+	}
 	location, err := timeutil.LoadLocation(cfg.WeatherAPI.Timezone)
 	if err != nil {
 		return app.GenerateRequest{}, commonOptions{}, err
 	}
 
 	req := app.GenerateRequest{
-		Config:     cfg,
+		Config:      cfg,
-		Report:     reportKind,
+		Report:      reportKind,
-		OutputPath: opts.Output,
+		OutputPath:  opts.Output,
-		Now:        r.Clock.Now(),
+		LLMDebugDir: opts.LLMDebugDir,
+		Now:         r.Clock.Now(),
+		Executor:    executor,
 	}
 
 	switch reportKind {
@@ -248,19 +267,6 @@ func (r Runner) resolveGenerateAction(args []string) (app.GenerateRequest, commo
 				return app.GenerateRequest{}, commonOptions{}, err
 			}
 		}
-	case app.ReportStorm:
-		if opts.Start == "" {
-			return app.GenerateRequest{}, commonOptions{}, fmt.Errorf("generate storm requires --start")
-		}
-		if opts.End == "" {
-			return app.GenerateRequest{}, commonOptions{}, fmt.Errorf("generate storm requires --end")
-		}
-		period, err := report.ParseStormPeriod(opts.Start, opts.End, location)
-		if err != nil {
-			return app.GenerateRequest{}, commonOptions{}, err
-		}
-		req.StormStart = period.Start
-		req.StormEnd = period.End
 	}
 
 	return req, opts.commonOptions, nil
@@ -294,7 +300,11 @@ func (r Runner) resolveRunAction(args []string) (app.BatchRequest, commonOptions
 	if err != nil {
 		return app.BatchRequest{}, commonOptions{}, err
 	}
-	return app.BatchRequest{Config: cfg, Batch: batch, Now: r.Clock.Now(), OutputDir: opts.OutputDir}, opts, nil
+	executor, err := r.promptExecutor(cfg.Promptkit)
+	if err != nil {
+		return app.BatchRequest{}, commonOptions{}, err
+	}
+	return app.BatchRequest{Config: cfg, Batch: batch, Now: r.Clock.Now(), OutputDir: opts.OutputDir, LLMDebugDir: opts.LLMDebugDir, Executor: executor}, opts, nil
 }
 
 func resolveRun(args []string) (app.BatchRequest, error) {
@@ -310,10 +320,6 @@ func parseGenerateFlags(report app.ReportKind, args []string) (generateOptions,
 	if report == app.ReportDaily || report == app.ReportToday {
 		fs.StringVar(&opts.Date, "date", "", "report date in YYYY-MM-DD")
 	}
-	if report == app.ReportStorm {
-		fs.StringVar(&opts.Start, "start", "", "storm start time")
-		fs.StringVar(&opts.End, "end", "", "storm end time")
-	}
 	if err := fs.Parse(args); err != nil {
 		return generateOptions{}, err
 	}
@@ -376,6 +382,7 @@ func addCommonFlags(fs *flag.FlagSet, opts *commonOptions, includeOutput bool) {
 	fs.StringVar(&opts.ConfigPath, "config", "", "configuration file path")
 	fs.StringVar(&opts.Units, "units", "", "weather API units")
 	fs.StringVar(&opts.Timezone, "tz", "", "weather API timezone")
+	fs.StringVar(&opts.LLMDebugDir, "llm-debug-dir", "", "write sensitive prompt debug artifacts under PATH")
 	if includeOutput {
 		fs.StringVar(&opts.Output, "out", "", "extra Markdown report copy path")
 	}

internal/cli/run_test.go

@@ -0,0 +1,42 @@
+package cli
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptexec"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/timeutil"
+)
+
+func TestParseRunFlagsAcceptsPromptDebugDirectory(t *testing.T) {
+	opts, err := parseRunFlags([]string{"--llm-debug-dir", "/tmp/prompt-debug"})
+	if err != nil || opts.LLMDebugDir != "/tmp/prompt-debug" {
+		t.Fatalf("parseRunFlags() = %#v, %v", opts, err)
+	}
+}
+
+func TestResolveRunActionConstructsOneExecutor(t *testing.T) {
+	for _, command := range []string{"morning", "evening"} {
+		t.Run(command, func(t *testing.T) {
+			configPath := filepath.Join(t.TempDir(), "config.yml")
+			if err := os.WriteFile(configPath, []byte("workspace:\n  root: "+filepath.Join(t.TempDir(), "workspace")+"\n"), 0o600); err != nil {
+				t.Fatal(err)
+			}
+			calls := 0
+			executor := &factoryExecutor{}
+			runner := Runner{
+				Clock: timeutil.FixedClock{Time: time.Date(2026, 5, 29, 8, 0, 0, 0, time.UTC)},
+				ExecutorFactory: func(PromptExecutorConfig) (promptexec.Executor, error) {
+					calls++
+					return executor, nil
+				},
+			}
+			req, _, err := runner.resolveRunAction([]string{command, "--config", configPath, "--llm-debug-dir", "/tmp/debug"})
+			if err != nil || calls != 1 || req.Executor != executor || req.LLMDebugDir != "/tmp/debug" {
+				t.Fatalf("resolveRunAction() request/error/calls = %#v/%v/%d", req, err, calls)
+			}
+		})
+	}
+}

internal/config/config.go

@@ -27,7 +27,7 @@ type Config struct {
 	Secrets       SecretsConfig           `yaml:"secrets"`
 	Notify        NotifyConfig            `yaml:"notify"`
 	MissingSource MissingSourceConfig     `yaml:"missing_source"`
-	Scriptorium   ScriptoriumConfig       `yaml:"scriptorium"`
+	Promptkit     PromptkitConfig         `yaml:"promptkit"`
 	Workspace     WorkspaceConfig         `yaml:"workspace"`
 	Dayparts      []DaypartConfig         `yaml:"dayparts"`
 	RecentChange  RecentChangeConfig      `yaml:"recent_change"`
@@ -81,12 +81,17 @@ type MissingSourceConfig struct {
 	Sources map[string]MissingSourcePolicy `yaml:"sources"`
 }
 
-type ScriptoriumConfig struct {
+type PromptkitConfig struct {
-	Binary     string        `yaml:"binary"`
+	Profile     string               `yaml:"profile"`
-	ConfigPath string        `yaml:"config_path"`
+	ProfileFile string               `yaml:"profile_file"`
-	Profile    string        `yaml:"profile"`
+	ProfileDir  string               `yaml:"profile_dir"`
-	Timeout    time.Duration `yaml:"timeout"`
+	Timeout     time.Duration        `yaml:"timeout"`
-	ExtraArgs  []string      `yaml:"extra_args"`
+	Local       PromptkitLocalConfig `yaml:"local"`
+}
+
+type PromptkitLocalConfig struct {
+	Endpoint         string `yaml:"endpoint"`
+	ConcurrencyLimit int    `yaml:"concurrency_limit"`
 }
 
 type WorkspaceConfig struct {

internal/config/config_test.go

@@ -144,8 +144,8 @@ func TestLoadMinimalExampleConfig(t *testing.T) {
 	if cfg.WeatherAPI.Units != "us" {
 		t.Fatalf("Units = %q, want default us", cfg.WeatherAPI.Units)
 	}
-	if cfg.Scriptorium.Binary != "scriptorium" {
+	if cfg.Promptkit.Timeout != 2*time.Minute || cfg.Promptkit.Local.ConcurrencyLimit != 1 {
-		t.Fatalf("Scriptorium.Binary = %q, want default scriptorium", cfg.Scriptorium.Binary)
+		t.Fatalf("Promptkit defaults = %#v", cfg.Promptkit)
 	}
 	if cfg.Workspace.Root != "workspace" {
 		t.Fatalf("Workspace.Root = %q, want default workspace", cfg.Workspace.Root)
@@ -158,6 +158,13 @@ func TestLoadMinimalExampleConfig(t *testing.T) {
 	}
 }
 
+func TestLoadRejectsRetiredExecutionConfiguration(t *testing.T) {
+	_, err := LoadFile(writeConfig(t, "scriptorium:\n  binary: scriptorium\n"))
+	if err == nil || !strings.Contains(err.Error(), "migrate to promptkit") {
+		t.Fatalf("LoadFile() error = %v, want actionable migration error", err)
+	}
+}
+
 func TestLoadReportModuleOverrides(t *testing.T) {
 	path := writeConfig(t, `
 reports:
@@ -275,39 +282,6 @@ reports:
 	}
 }
 
-func TestLoadReportModuleOverrideAliases(t *testing.T) {
-	path := writeConfig(t, `
-reports:
-  three-day-outlook:
-    deterministic_modules:
-      - metadata
-  weekend_outlook:
-    deterministic_modules:
-      - metadata
-  storm_report:
-    deterministic_modules:
-      - metadata
-`)
-
-	cfg, err := LoadFile(path)
-	if err != nil {
-		t.Fatalf("LoadFile() error = %v", err)
-	}
-	overrides, err := cfg.ReportModuleOverrides()
-	if err != nil {
-		t.Fatalf("ReportModuleOverrides() error = %v", err)
-	}
-	if len(overrides[report.ThreeDay]) != 1 || overrides[report.ThreeDay][0].ID != module.Metadata {
-		t.Fatalf("three-day alias override = %#v, want metadata override", overrides[report.ThreeDay])
-	}
-	if len(overrides[report.Weekend]) != 1 || overrides[report.Weekend][0].ID != module.Metadata {
-		t.Fatalf("weekend alias override = %#v, want metadata override", overrides[report.Weekend])
-	}
-	if len(overrides[report.Storm]) != 1 || overrides[report.Storm][0].ID != module.Metadata {
-		t.Fatalf("storm alias override = %#v, want metadata override", overrides[report.Storm])
-	}
-}
-
 func TestLoadReportDistributorPathOverrides(t *testing.T) {
 	path := writeConfig(t, `
 reports:
@@ -375,35 +349,6 @@ reports:
 	}
 }
 
-func TestLoadReportDistributorPathOverrideAliases(t *testing.T) {
-	path := writeConfig(t, `
-reports:
-  three-day-outlook:
-    distributor:
-      path_templates:
-        - "three-day/{valid_start_date}/index.md"
-  weekend_outlook:
-    distributor:
-      path_templates:
-        - "weekend/{valid_start_date}/index.md"
-`)
-
-	cfg, err := LoadFile(path)
-	if err != nil {
-		t.Fatalf("LoadFile() error = %v", err)
-	}
-	overrides, err := cfg.ReportDistributorPathOverrides()
-	if err != nil {
-		t.Fatalf("ReportDistributorPathOverrides() error = %v", err)
-	}
-	if !reflect.DeepEqual(overrides[report.ThreeDay], []string{"three-day/{valid_start_date}/index.md"}) {
-		t.Fatalf("three-day distributor override = %#v, want alias override", overrides[report.ThreeDay])
-	}
-	if !reflect.DeepEqual(overrides[report.Weekend], []string{"weekend/{valid_start_date}/index.md"}) {
-		t.Fatalf("weekend distributor override = %#v, want alias override", overrides[report.Weekend])
-	}
-}
-
 func TestValidateReportModuleKeysWithoutMutatingOptions(t *testing.T) {
 	cfg := Defaults()
 	rawOptions := map[string]any{
@@ -683,21 +628,6 @@ reports:
 `,
 			wantErr: `unknown report distributor field "paths"`,
 		},
-		{
-			name: "DuplicateReportAlias",
-			yaml: `
-reports:
-  three-day:
-    distributor:
-      path_templates:
-        - "three-day/{valid_start_date}/index.md"
-  three_day:
-    distributor:
-      path_templates:
-        - "three-day/latest.md"
-`,
-			wantErr: "duplicates report override",
-		},
 		{
 			name: "UnknownTemplateVariable",
 			yaml: `
@@ -754,17 +684,6 @@ reports:
 `,
 			wantErr: `reports.daily.distributor.path_templates renders duplicate path "daily/index.md"`,
 		},
-		{
-			name: "NonStormStormIDEmptyPathSegment",
-			yaml: `
-reports:
-  daily:
-    distributor:
-      path_templates:
-        - "daily/{storm_id}/index.md"
-`,
-			wantErr: "reports.daily.distributor.path_templates[0] must not render empty path segments",
-		},
 		{
 			name: "EmptyOverrideList",
 			yaml: `
@@ -790,23 +709,6 @@ reports:
 	}
 }
 
-func TestReportDistributorPathOverrideStormIDValidation(t *testing.T) {
-	_, err := LoadFile(writeConfig(t, `
-reports:
-  daily:
-    distributor:
-      path_templates:
-        - "daily/storm-{storm_id}.md"
-  storm:
-    distributor:
-      path_templates:
-        - "storm/{storm_id}/index.md"
-`))
-	if err != nil {
-		t.Fatalf("LoadFile() error = %v", err)
-	}
-}
-
 func TestReportDistributorPathOverridesConsistentForLoadedAndConstructedConfig(t *testing.T) {
 	yaml := `
 reports:
@@ -869,29 +771,6 @@ reports:
 			},
 			wantErr: "reports.moon",
 		},
-		{
-			name: "DuplicateReportAlias",
-			yaml: `
-reports:
-  three-day:
-    deterministic_modules:
-      - metadata
-  three_day:
-    deterministic_modules:
-      - metadata
-`,
-			reports: map[string]ReportConfig{
-				"three-day": {
-					DeterministicModules:    []ModuleConfigItem{{ID: module.Metadata}},
-					deterministicModulesSet: true,
-				},
-				"three_day": {
-					DeterministicModules:    []ModuleConfigItem{{ID: module.Metadata}},
-					deterministicModulesSet: true,
-				},
-			},
-			wantErr: "duplicates report override",
-		},
 		{
 			name: "UnknownModule",
 			yaml: `
@@ -1389,38 +1268,37 @@ func TestDistributorTemplateRendering(t *testing.T) {
 		ValidEndTime:    "0600",
 		ValidStartStamp: "2026-06-07T1800",
 		ValidEndStamp:   "2026-06-08T0600",
-		StormID:         "2026-06-07T1800-2026-06-08T0600",
 		BundleID:        "weatherreporter.home.daily",
 	}
 
-	bundleID, err := RenderDistributorBundleID("weatherreporter.{location_id}.{report_id}.{storm_id}", values)
+	bundleID, err := RenderDistributorBundleID("weatherreporter.{location_id}.{report_id}.{valid_start_date}", values)
 	if err != nil {
 		t.Fatalf("RenderDistributorBundleID() error = %v", err)
 	}
-	if bundleID != "weatherreporter.home.daily.2026-06-07T1800-2026-06-08T0600" {
+	if bundleID != "weatherreporter.home.daily.2026-06-07" {
 		t.Fatalf("bundleID = %q, want rendered value", bundleID)
 	}
 	values.BundleID = bundleID
 
-	pipelineID, err := RenderDistributorPipelineID("weatherreporter.{artifact_group}.{storm_id}.{bundle_id}", values)
+	pipelineID, err := RenderDistributorPipelineID("weatherreporter.{artifact_group}.{valid_start_stamp}.{bundle_id}", values)
 	if err != nil {
 		t.Fatalf("RenderDistributorPipelineID() error = %v", err)
 	}
-	if pipelineID != "weatherreporter.daily.2026-06-07T1800-2026-06-08T0600.weatherreporter.home.daily.2026-06-07T1800-2026-06-08T0600" {
+	if pipelineID != "weatherreporter.daily.2026-06-07T1800.weatherreporter.home.daily.2026-06-07" {
 		t.Fatalf("pipelineID = %q, want rendered pipeline ID", pipelineID)
 	}
 
-	idempotencyKey, err := RenderDistributorIdempotencyKey("{bundle_id}.{storm_id}.{run_id}", values)
+	idempotencyKey, err := RenderDistributorIdempotencyKey("{bundle_id}.{valid_end_stamp}.{run_id}", values)
 	if err != nil {
 		t.Fatalf("RenderDistributorIdempotencyKey() error = %v", err)
 	}
-	if idempotencyKey != "weatherreporter.home.daily.2026-06-07T1800-2026-06-08T0600.2026-06-07T1800-2026-06-08T0600.20260607T120000Z" {
+	if idempotencyKey != "weatherreporter.home.daily.2026-06-07.2026-06-08T0600.20260607T120000Z" {
 		t.Fatalf("idempotencyKey = %q, want rendered run key", idempotencyKey)
 	}
 
 	reportPaths, err := RenderDistributorReportPaths("reports.daily.distributor.path_templates", []string{
 		"{valid_start_date}/{artifact_group}/{valid_start_stamp}-{valid_end_stamp}-{run_id}.md",
-		"storm/{storm_id}/index.md",
+		"daily/{valid_start_date}/index.md",
 		"{valid_start_date}/{artifact_group}/latest.md",
 	}, values)
 	if err != nil {
@@ -1428,7 +1306,7 @@ func TestDistributorTemplateRendering(t *testing.T) {
 	}
 	wantPaths := []string{
 		"2026-06-07/daily/2026-06-07T1800-2026-06-08T0600-20260607T120000Z.md",
-		"storm/2026-06-07T1800-2026-06-08T0600/index.md",
+		"daily/2026-06-07/index.md",
 		"2026-06-07/daily/latest.md",
 	}
 	if strings.Join(reportPaths, "\n") != strings.Join(wantPaths, "\n") {

internal/config/defaults.go

@@ -43,9 +43,11 @@ func Defaults() Config {
 			Default: MissingSourceWarn,
 			Sources: map[string]MissingSourcePolicy{},
 		},
-		Scriptorium: ScriptoriumConfig{
+		Promptkit: PromptkitConfig{
-			Binary:  "scriptorium",
 			Timeout: 2 * time.Minute,
+			Local: PromptkitLocalConfig{
+				ConcurrencyLimit: 1,
+			},
 		},
 		Workspace: WorkspaceConfig{
 			Root:             "workspace",

internal/config/load.go

@@ -59,6 +59,9 @@ func mergeFile(cfg *Config, path string) error {
 	if err != nil {
 		return fmt.Errorf("read config %q: %w", path, err)
 	}
+	if err := rejectRetiredExecutionConfig(data); err != nil {
+		return fmt.Errorf("parse config %q: %w", path, err)
+	}
 	if err := yaml.Unmarshal(data, cfg); err != nil {
 		return fmt.Errorf("parse config %q: %w", path, err)
 	}
@@ -70,3 +73,20 @@ func mergeFile(cfg *Config, path string) error {
 	}
 	return nil
 }
+
+func rejectRetiredExecutionConfig(data []byte) error {
+	var document yaml.Node
+	if err := yaml.Unmarshal(data, &document); err != nil {
+		return err
+	}
+	if len(document.Content) == 0 || document.Content[0].Kind != yaml.MappingNode {
+		return nil
+	}
+	root := document.Content[0]
+	for i := 0; i+1 < len(root.Content); i += 2 {
+		if root.Content[i].Value == "scriptorium" {
+			return fmt.Errorf("scriptorium configuration is no longer supported; migrate to promptkit configuration")
+		}
+	}
+	return nil
+}

internal/config/notify_templates.go

@@ -18,7 +18,6 @@ type DistributorTemplateValues struct {
 	ValidEndTime    string
 	ValidStartStamp string
 	ValidEndStamp   string
-	StormID         string
 	BundleID        string
 }
 
@@ -42,7 +41,6 @@ var distributorTemplateVariables = map[string]struct{}{
 	"valid_end_time":    {},
 	"valid_start_stamp": {},
 	"valid_end_stamp":   {},
-	"storm_id":          {},
 }
 
 var distributorIdempotencyTemplateVariables = map[string]struct{}{
@@ -57,7 +55,6 @@ var distributorIdempotencyTemplateVariables = map[string]struct{}{
 	"valid_end_time":    {},
 	"valid_start_stamp": {},
 	"valid_end_stamp":   {},
-	"storm_id":          {},
 	"bundle_id":         {},
 }
 
@@ -246,8 +243,6 @@ func distributorTemplateValue(variable string, values DistributorTemplateValues)
 		return values.ValidStartStamp
 	case "valid_end_stamp":
 		return values.ValidEndStamp
-	case "storm_id":
-		return values.StormID
 	case "bundle_id":
 		return values.BundleID
 	default:

internal/config/promptkit_test.go

@@ -0,0 +1,101 @@
+package config
+
+import (
+	"strings"
+	"testing"
+	"time"
+
+	"gopkg.in/yaml.v3"
+)
+
+func TestPromptkitDefaultsAndYAML(t *testing.T) {
+	cfg := Defaults()
+	if cfg.Promptkit.Timeout != 2*time.Minute || cfg.Promptkit.Local.ConcurrencyLimit != 1 {
+		t.Fatalf("Promptkit defaults = %#v", cfg.Promptkit)
+	}
+	if err := yaml.Unmarshal([]byte(`
+promptkit:
+  profile: selected
+  profile_file: /etc/weatherreporter/profile.yml
+  timeout: 45s
+  local:
+    endpoint: http://127.0.0.1:8080
+    concurrency_limit: 0
+`), &cfg); err != nil {
+		t.Fatalf("Unmarshal() error = %v", err)
+	}
+	if cfg.Promptkit.Profile != "selected" || cfg.Promptkit.ProfileFile != "/etc/weatherreporter/profile.yml" || cfg.Promptkit.Timeout != 45*time.Second || cfg.Promptkit.Local.Endpoint != "http://127.0.0.1:8080" || cfg.Promptkit.Local.ConcurrencyLimit != 0 {
+		t.Fatalf("Promptkit YAML = %#v", cfg.Promptkit)
+	}
+	if err := Validate(cfg); err != nil {
+		t.Fatalf("Validate() error = %v", err)
+	}
+}
+
+func TestValidatePromptkit(t *testing.T) {
+	tests := []struct {
+		name    string
+		mutate  func(*PromptkitConfig)
+		wantErr string
+	}{
+		{
+			name: "profile sources conflict",
+			mutate: func(cfg *PromptkitConfig) {
+				cfg.ProfileFile = "profile.yml"
+				cfg.ProfileDir = "profiles"
+			},
+			wantErr: "profile_file",
+		},
+		{
+			name: "nonpositive timeout",
+			mutate: func(cfg *PromptkitConfig) {
+				cfg.Timeout = 0
+			},
+			wantErr: "timeout",
+		},
+		{
+			name: "invalid local endpoint",
+			mutate: func(cfg *PromptkitConfig) {
+				cfg.Local.Endpoint = "not a URL"
+			},
+			wantErr: "local.endpoint",
+		},
+		{
+			name: "negative local concurrency",
+			mutate: func(cfg *PromptkitConfig) {
+				cfg.Local.ConcurrencyLimit = -1
+			},
+			wantErr: "concurrency_limit",
+		},
+		{
+			name: "unlimited local concurrency",
+			mutate: func(cfg *PromptkitConfig) {
+				cfg.Local.Endpoint = "http://127.0.0.1:8080"
+				cfg.Local.ConcurrencyLimit = 0
+			},
+		},
+		{
+			name: "unregistered local backend",
+			mutate: func(cfg *PromptkitConfig) {
+				cfg.Local.Endpoint = ""
+				cfg.Local.ConcurrencyLimit = 1
+			},
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			cfg := Defaults()
+			test.mutate(&cfg.Promptkit)
+			err := Validate(cfg)
+			if test.wantErr == "" {
+				if err != nil {
+					t.Fatalf("Validate() error = %v", err)
+				}
+				return
+			}
+			if err == nil || !strings.Contains(err.Error(), test.wantErr) {
+				t.Fatalf("Validate() error = %v, want %q", err, test.wantErr)
+			}
+		})
+	}
+}

internal/config/reports.go

@@ -128,14 +128,10 @@ func validateReportDistributorPathTemplates(reportKey string, reportID report.ID
 }
 
 func sampleDistributorTemplateValues() DistributorTemplateValues {
-	return sampleDistributorTemplateValuesForReport(report.Storm)
+	return sampleDistributorTemplateValuesForReport(report.Daily)
 }
 
-func sampleDistributorTemplateValuesForReport(reportID report.ID) DistributorTemplateValues {
+func sampleDistributorTemplateValuesForReport(_ report.ID) DistributorTemplateValues {
-	stormID := ""
-	if reportID == report.Storm {
-		stormID = "2026-05-29T0000-2026-05-30T0000"
-	}
 	return DistributorTemplateValues{
 		LocationID:      "location",
 		ReportID:        "report",
@@ -148,7 +144,6 @@ func sampleDistributorTemplateValuesForReport(reportID report.ID) DistributorTem
 		ValidEndTime:    "0000",
 		ValidStartStamp: "2026-05-29T0000",
 		ValidEndStamp:   "2026-05-30T0000",
-		StormID:         stormID,
 	}
 }
 

internal/config/validate.go

@@ -59,11 +59,8 @@ func Validate(cfg Config) error {
 		return err
 	}
 
-	if cfg.Scriptorium.Binary == "" {
+	if err := validatePromptkit(cfg.Promptkit); err != nil {
-		return fmt.Errorf("scriptorium.binary is required")
+		return err
-	}
-	if cfg.Scriptorium.Timeout <= 0 {
-		return fmt.Errorf("scriptorium.timeout must be greater than zero")
 	}
 	if cfg.Workspace.Root == "" {
 		return fmt.Errorf("workspace.root is required")
@@ -85,6 +82,25 @@ func Validate(cfg Config) error {
 	return nil
 }
 
+func validatePromptkit(cfg PromptkitConfig) error {
+	if cfg.ProfileFile != "" && cfg.ProfileDir != "" {
+		return fmt.Errorf("promptkit.profile_file and promptkit.profile_dir cannot both be configured")
+	}
+	if cfg.Timeout <= 0 {
+		return fmt.Errorf("promptkit.timeout must be greater than zero")
+	}
+	if cfg.Local.Endpoint != "" {
+		parsed, err := url.Parse(cfg.Local.Endpoint)
+		if err != nil || parsed.Scheme == "" || parsed.Host == "" {
+			return fmt.Errorf("promptkit.local.endpoint must be an absolute URL when configured")
+		}
+	}
+	if cfg.Local.ConcurrencyLimit < 0 {
+		return fmt.Errorf("promptkit.local.concurrency_limit must be zero or greater")
+	}
+	return nil
+}
+
 func validateDistributorNotify(cfg DistributorNotifyConfig) error {
 	if !cfg.Enabled {
 		return nil

internal/facts/facts.go

@@ -82,7 +82,6 @@ type DerivedFacts struct {
 	DailySummaries              []forecast.DailySummary
 	DaypartSummaries            []forecast.DaypartSummary
 	PrecipTiming                forecast.PrecipTiming
-	StormWindowSummary          *forecast.DaypartSummary
 }
 
 func (f DerivedFacts) FirstDailySummary() *forecast.DailySummary {
@@ -121,16 +120,6 @@ func BuildDerived(req BuildDerivedRequest) (DerivedFacts, error) {
 			return DerivedFacts{}, err
 		}
 		derived.DailySummaries = []forecast.DailySummary{*summary}
-	case report.ThreeDay, report.Weekend:
-		summaries, err := forecast.BuildPeriodDailySummaries(bundle, period, location, req.Dayparts)
-		if err != nil {
-			return DerivedFacts{}, err
-		}
-		derived.DailySummaries = summaries
-	case report.Storm:
-		summary := forecast.SummarizeDaypart("storm window", period, derived.ValidPeriodHourlyPeriods)
-		summary.AlertOverlaps = derived.AlertOverlaps
-		derived.StormWindowSummary = &summary
 	default:
 		return DerivedFacts{}, fmt.Errorf("derived facts are not implemented for report %q", req.Resolved.Definition.ID)
 	}
@@ -144,9 +133,6 @@ func collectDaypartSummaries(derived DerivedFacts) []forecast.DaypartSummary {
 	for _, summary := range derived.DailySummaries {
 		out = append(out, summary.Dayparts...)
 	}
-	if derived.StormWindowSummary != nil {
-		out = append(out, *derived.StormWindowSummary)
-	}
 	return out
 }
 

internal/facts/facts_test.go

@@ -100,42 +100,9 @@ func TestBuildDerivedDailySlicesDaypartsAndAlerts(t *testing.T) {
 	}
 }
 
-func TestBuildDerivedOutlookBuildsPartialDaySummariesWithMissingOptionalSources(t *testing.T) {
+func TestBuildDerivedTomorrow(t *testing.T) {
 	location := testLocation()
-	resolved := resolveForTest(t, report.ThreeDay, mustParse("2026-05-29T08:00:00-05:00"), location)
+	for _, id := range []report.ID{report.Tomorrow} {
-	bundle := testBundle(location)
-	bundle.Narrative = nil
-	bundle.Alerts = nil
-	bundle.Discussion = nil
-	bundle.WeatherStory = nil
-
-	derived, err := BuildDerived(BuildDerivedRequest{
-		Resolved:  resolved,
-		Timezone:  location.String(),
-		Dayparts:  testDayparts(),
-		Collected: BuildCollected(bundle),
-	})
-	if err != nil {
-		t.Fatalf("BuildDerived() error = %v", err)
-	}
-
-	if len(derived.DailySummaries) != 3 {
-		t.Fatalf("DailySummaries length = %d, want 3 partial-day summaries", len(derived.DailySummaries))
-	}
-	if len(derived.ValidPeriodNarrativePeriods) != 0 {
-		t.Fatalf("ValidPeriodNarrativePeriods length = %d, want 0 for missing optional source", len(derived.ValidPeriodNarrativePeriods))
-	}
-	if len(derived.AlertOverlaps) != 0 {
-		t.Fatalf("AlertOverlaps = %#v, want none for missing optional alerts", derived.AlertOverlaps)
-	}
-	if derived.DailySummaries[0].Period.Start.Format(time.RFC3339) != "2026-05-29T08:00:00-05:00" {
-		t.Fatalf("first summary start = %s, want valid-period start", derived.DailySummaries[0].Period.Start.Format(time.RFC3339))
-	}
-}
-
-func TestBuildDerivedWeekendAndTomorrow(t *testing.T) {
-	location := testLocation()
-	for _, id := range []report.ID{report.Tomorrow, report.Weekend} {
 		resolved := resolveForTest(t, id, mustParse("2026-05-29T08:00:00-05:00"), location)
 		derived, err := BuildDerived(BuildDerivedRequest{
 			Resolved:  resolved,
@@ -183,8 +150,8 @@ func TestBuildDerivedHourlyUsesRollingWindowFacts(t *testing.T) {
 	if len(derived.ValidPeriodNarrativePeriods) != 1 {
 		t.Fatalf("ValidPeriodNarrativePeriods length = %d, want overlapping narrative period", len(derived.ValidPeriodNarrativePeriods))
 	}
-	if len(derived.DailySummaries) != 0 || len(derived.DaypartSummaries) != 0 || derived.StormWindowSummary != nil {
+	if len(derived.DailySummaries) != 0 || len(derived.DaypartSummaries) != 0 {
-		t.Fatalf("hourly summaries daily=%#v daypart=%#v storm=%#v, want none", derived.DailySummaries, derived.DaypartSummaries, derived.StormWindowSummary)
+		t.Fatalf("hourly summaries daily=%#v daypart=%#v, want none", derived.DailySummaries, derived.DaypartSummaries)
 	}
 	if derived.PrecipTiming.FirstPrecipitation == nil || derived.PrecipTiming.FirstPrecipitation.Time.Format(time.RFC3339) != "2026-05-29T08:00:00-05:00" {
 		t.Fatalf("PrecipTiming.FirstPrecipitation = %#v, want first selected rainy hour", derived.PrecipTiming.FirstPrecipitation)
@@ -209,36 +176,6 @@ func TestBuildDerivedHourlyUsesRollingWindowFacts(t *testing.T) {
 	}
 }
 
-func TestBuildDerivedStormBuildsWindowSummary(t *testing.T) {
-	location := testLocation()
-	resolved := resolveStormForTest(t, location)
-	derived, err := BuildDerived(BuildDerivedRequest{
-		Resolved:  resolved,
-		Timezone:  location.String(),
-		Dayparts:  testDayparts(),
-		Collected: BuildCollected(testBundle(location)),
-	})
-	if err != nil {
-		t.Fatalf("BuildDerived() error = %v", err)
-	}
-
-	if len(derived.ValidPeriodHourlyPeriods) != 2 {
-		t.Fatalf("ValidPeriodHourlyPeriods length = %d, want 2 storm-window hours", len(derived.ValidPeriodHourlyPeriods))
-	}
-	if len(derived.ValidPeriodDailyPeriods) != 1 {
-		t.Fatalf("ValidPeriodDailyPeriods length = %d, want 1 daily period", len(derived.ValidPeriodDailyPeriods))
-	}
-	if derived.StormWindowSummary == nil {
-		t.Fatal("StormWindowSummary = nil, want summary")
-	}
-	if derived.StormWindowSummary.MaxPrecipitationProbability == nil || derived.StormWindowSummary.MaxPrecipitationProbability.Value != 80 {
-		t.Fatalf("StormWindowSummary = %#v, want peak precipitation", derived.StormWindowSummary)
-	}
-	if len(derived.StormWindowSummary.AlertOverlaps) != 1 {
-		t.Fatalf("StormWindowSummary.AlertOverlaps length = %d, want 1", len(derived.StormWindowSummary.AlertOverlaps))
-	}
-}
-
 func TestBuildDerivedSelectsSPCConvectiveOutlooksByValidPeriod(t *testing.T) {
 	location := testLocation()
 	now := mustParse("2026-05-29T08:00:00-05:00")
@@ -263,24 +200,6 @@ func TestBuildDerivedSelectsSPCConvectiveOutlooksByValidPeriod(t *testing.T) {
 			wantOutlookIDs: []string{"sat-enhanced"},
 			wantDiscussion: []string{"day2"},
 		},
-		{
-			name:           "three day",
-			resolved:       resolveForTest(t, report.ThreeDay, now, location),
-			wantOutlookIDs: []string{"fri-high", "fri-storm", "fri-low", "fri-missing-rank", "fri-probabilistic", "sat-enhanced", "sun-slight"},
-			wantDiscussion: []string{"day1 early", "day1 late", "day2", "day3"},
-		},
-		{
-			name:           "weekend",
-			resolved:       resolveForTest(t, report.Weekend, now, location),
-			wantOutlookIDs: []string{"sat-enhanced", "sun-slight"},
-			wantDiscussion: []string{"day2", "day3"},
-		},
-		{
-			name:           "storm",
-			resolved:       resolveStormForTest(t, location),
-			wantOutlookIDs: []string{"fri-storm", "fri-low"},
-			wantDiscussion: []string{"day1 early", "day1 late"},
-		},
 	}
 
 	for _, tt := range tests {
@@ -476,20 +395,6 @@ func resolveForTest(t *testing.T, id report.ID, now time.Time, location *time.Lo
 	return resolved
 }
 
-func resolveStormForTest(t *testing.T, location *time.Location) report.Resolved {
-	t.Helper()
-	resolved, err := report.Resolve(report.Storm, report.ResolveRequest{
-		Now:        mustParse("2026-05-29T08:00:00-05:00"),
-		Location:   location,
-		StormStart: mustParse("2026-05-29T11:30:00-05:00"),
-		StormEnd:   mustParse("2026-05-29T13:30:00-05:00"),
-	})
-	if err != nil {
-		t.Fatalf("resolve storm: %v", err)
-	}
-	return resolved
-}
-
 func testLocation() *time.Location {
 	location, err := time.LoadLocation("America/Chicago")
 	if err != nil {

internal/forecast/derive.go

@@ -217,62 +217,6 @@ func BuildDailySummary(bundle *weatherdata.Bundle, date time.Time, location *tim
 	return summary, nil
 }
 
-func BuildPeriodDailySummaries(bundle *weatherdata.Bundle, period timeutil.Period, location *time.Location, dayparts []DaypartDefinition) ([]DailySummary, error) {
-	if !period.IsValid() {
-		return nil, fmt.Errorf("valid forecast period is required")
-	}
-	if location == nil {
-		location = time.UTC
-	}
-	var summaries []DailySummary
-	for day := timeutil.CivilDay(period.Start, location); day.Start.Before(period.End); day = timeutil.CivilDay(day.Start.AddDate(0, 0, 1), location) {
-		overlap, ok := day.Intersection(period)
-		if !ok {
-			continue
-		}
-		summary, err := buildDailySummaryForPeriod(bundle, overlap, location, dayparts)
-		if err != nil {
-			return nil, err
-		}
-		summaries = append(summaries, *summary)
-	}
-	return summaries, nil
-}
-
-func buildDailySummaryForPeriod(bundle *weatherdata.Bundle, period timeutil.Period, location *time.Location, dayparts []DaypartDefinition) (*DailySummary, error) {
-	if bundle == nil {
-		return nil, fmt.Errorf("forecast bundle is required")
-	}
-	if bundle.Hourly == nil || len(bundle.Hourly.Periods) == 0 {
-		return nil, fmt.Errorf("hourly forecast data is required")
-	}
-	windows, err := ResolveDayparts(period.Start, location, dayparts)
-	if err != nil {
-		return nil, err
-	}
-	alerts := AlertOverlaps(bundle.Alerts, period)
-	summary := &DailySummary{
-		Date:             period.Start.In(location).Format(timeutil.DateLayout),
-		Period:           period,
-		NarrativePeriods: SelectNarrativePeriods(bundle, period),
-		AlertOverlaps:    alerts,
-		Discussion:       SelectDiscussion(bundle),
-		SourceWarnings:   bundle.Warnings,
-		SourceProvenance: bundle.Sources,
-	}
-	for _, window := range windows {
-		clipped, ok := window.Period.Intersection(period)
-		if !ok {
-			continue
-		}
-		periods := SelectHourlyPeriods(bundle.Hourly, clipped)
-		daypartSummary := SummarizeDaypart(window.Name, clipped, periods)
-		daypartSummary.AlertOverlaps = overlapsWithin(alerts, clipped)
-		summary.Dayparts = append(summary.Dayparts, daypartSummary)
-	}
-	return summary, nil
-}
-
 func SelectHourlyPeriods(run *weatherdata.ForecastRun, period timeutil.Period) []weatherdata.ForecastPeriod {
 	if run == nil {
 		return nil

internal/forecast/derive_test.go

@@ -154,41 +154,6 @@ func TestBuildDailySummaryRequiresHourlyData(t *testing.T) {
 	}
 }
 
-func TestBuildPeriodDailySummariesClipsPartialDays(t *testing.T) {
-	location := time.FixedZone("Test", -5*60*60)
-	bundle := &weatherdata.Bundle{Hourly: &weatherdata.ForecastRun{Periods: []weatherdata.ForecastPeriod{
-		hour(location, "2026-05-29T05:00:00-05:00", "2026-05-29T06:00:00-05:00", "Before", 50, nil, nil, nil, nil),
-		hour(location, "2026-05-29T08:00:00-05:00", "2026-05-29T09:00:00-05:00", "Showers", 60, nil, ptr(60), nil, nil),
-		hour(location, "2026-05-30T14:00:00-05:00", "2026-05-30T15:00:00-05:00", "Hot", 95, nil, nil, nil, nil),
-		hour(location, "2026-05-31T20:00:00-05:00", "2026-05-31T21:00:00-05:00", "Wind", 70, nil, nil, nil, ptr(35)),
-	}}}
-	period := timeutil.Period{
-		Start: mustParse("2026-05-29T07:00:00-05:00").In(location),
-		End:   mustParse("2026-06-01T00:00:00-05:00").In(location),
-	}
-
-	summaries, err := BuildPeriodDailySummaries(bundle, period, location, []DaypartDefinition{
-		{Name: "morning", Start: "06:00", End: "12:00"},
-		{Name: "afternoon", Start: "12:00", End: "18:00"},
-		{Name: "evening", Start: "18:00", End: "24:00"},
-	})
-	if err != nil {
-		t.Fatalf("BuildPeriodDailySummaries() error = %v", err)
-	}
-	if len(summaries) != 3 {
-		t.Fatalf("summaries length = %d, want 3", len(summaries))
-	}
-	if summaries[0].Period.Start.Format(time.RFC3339) != "2026-05-29T07:00:00-05:00" {
-		t.Fatalf("first period start = %s, want clipped start", summaries[0].Period.Start.Format(time.RFC3339))
-	}
-	if len(summaries[0].Dayparts[0].HourlyPeriods) != 1 || summaries[0].Dayparts[0].HourlyPeriods[0].TextDescription != "Showers" {
-		t.Fatalf("first morning periods = %#v, want only post-start hour", summaries[0].Dayparts[0].HourlyPeriods)
-	}
-	if summaries[2].Dayparts[2].PeakWindGust == nil || summaries[2].Dayparts[2].PeakWindGust.Value != 35 {
-		t.Fatalf("third evening gust = %#v, want 35", summaries[2].Dayparts[2].PeakWindGust)
-	}
-}
-
 func TestAlertOverlap(t *testing.T) {
 	location := time.FixedZone("Test", -5*60*60)
 	raw := json.RawMessage(`{"event":"Flood Watch","headline":"Flooding possible","severity":"Moderate","effective":"2026-05-29T07:00:00-05:00","expires":"2026-05-29T10:00:00-05:00"}`)

internal/generatedtext/catalog.go

@@ -6,6 +6,7 @@ import (
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/briefing"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/facts"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/module"
+	"gitea.maximumdirect.net/eric/weatherreporter/internal/promptassets"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/report"
 	"gitea.maximumdirect.net/eric/weatherreporter/internal/reporttemplate"
 )
@@ -69,9 +70,6 @@ var catalog = []catalogEntry{
 }
 
 func LookupDefinition(definition report.Definition) (Handler, error) {
-	if definition.GenerationMode != report.GenerationModeGeneratedTextTemplate {
-		return Handler{}, fmt.Errorf("report %q uses generation mode %q, not %q", definition.ID, definition.GenerationMode, report.GenerationModeGeneratedTextTemplate)
-	}
 
 	var schemaKnown, templateKnown bool
 	for _, entry := range catalog {
@@ -109,7 +107,7 @@ func (h Handler) TemplateID() string {
 }
 
 func (h Handler) Schema() ([]byte, error) {
-	data, err := reporttemplate.Schema(h.schemaID)
+	data, err := promptassets.Schema(h.schemaID)
 	if err != nil {
 		return nil, fmt.Errorf("load generated text schema %q for report %q: %w", h.schemaID, h.reportID, err)
 	}

internal/generatedtext/catalog_test.go

@@ -9,9 +9,6 @@ import (
 
 func TestCatalogCompleteForGeneratedTextTemplateReports(t *testing.T) {
 	for _, definition := range report.DefaultRegistry().All() {
-		if definition.GenerationMode != report.GenerationModeGeneratedTextTemplate {
-			continue
-		}
 		t.Run(string(definition.ID), func(t *testing.T) {
 			handler, err := LookupDefinition(definition)
 			if err != nil {
@@ -96,7 +93,6 @@ func TestCatalogLookupRejectsUnsupportedSchemaAndTemplate(t *testing.T) {
 func TestCatalogLookupSupportsTodayDefinition(t *testing.T) {
 	definition := report.Definition{
 		ID:                    report.Today,
-		GenerationMode:        report.GenerationModeGeneratedTextTemplate,
 		GeneratedTextSchemaID: "today",
 		TemplateID:            "today",
 	}
@@ -122,7 +118,6 @@ func TestCatalogLookupSupportsTodayDefinition(t *testing.T) {
 func TestCatalogLookupSupportsDailyDefinitionAssets(t *testing.T) {
 	definition := report.Definition{
 		ID:                    report.Daily,
-		GenerationMode:        report.GenerationModeGeneratedTextTemplate,
 		GeneratedTextSchemaID: "daily",
 		TemplateID:            "daily",
 	}
@@ -184,7 +179,6 @@ func TestCatalogValidationDispatchSupportsKnownSchemas(t *testing.T) {
 
 	todayHandler, err := LookupDefinition(report.Definition{
 		ID:                    report.Today,
-		GenerationMode:        report.GenerationModeGeneratedTextTemplate,
 		GeneratedTextSchemaID: "today",
 		TemplateID:            "today",
 	})
@@ -207,7 +201,6 @@ func TestCatalogValidationDispatchSupportsKnownSchemas(t *testing.T) {
 
 	dailyHandler, err := LookupDefinition(report.Definition{
 		ID:                    report.Daily,
-		GenerationMode:        report.GenerationModeGeneratedTextTemplate,
 		GeneratedTextSchemaID: "daily",
 		TemplateID:            "daily",
 	})
@@ -262,7 +255,6 @@ func TestCatalogBuildRenderContextRejectsMismatchedGeneratedText(t *testing.T) {
 
 	todayHandler, err := LookupDefinition(report.Definition{
 		ID:                    report.Today,
-		GenerationMode:        report.GenerationModeGeneratedTextTemplate,
 		GeneratedTextSchemaID: "today",
 		TemplateID:            "today",
 	})
@@ -282,7 +274,6 @@ func TestCatalogBuildRenderContextRejectsMismatchedGeneratedText(t *testing.T) {
 
 	dailyHandler, err := LookupDefinition(report.Definition{
 		ID:                    report.Daily,
-		GenerationMode:        report.GenerationModeGeneratedTextTemplate,
 		GeneratedTextSchemaID: "daily",
 		TemplateID:            "daily",
 	})
@@ -304,7 +295,6 @@ func TestCatalogBuildRenderContextRejectsMismatchedGeneratedText(t *testing.T) {
 func TestCatalogBuildRenderContextSupportsDaily(t *testing.T) {
 	handler, err := LookupDefinition(report.Definition{
 		ID:                    report.Daily,
-		GenerationMode:        report.GenerationModeGeneratedTextTemplate,
 		GeneratedTextSchemaID: "daily",
 		TemplateID:            "daily",
 	})

internal/promptassets/assets/prompts/common/data_package.user.md

@@ -16,8 +16,8 @@ These products have already been filtered or matched to the forecast location. T
 
 - Active warnings are urgent and should dominate the lead and relevant sections.
 - Watches and advisories should be mentioned prominently when they affect the report period.
-- Outlook/risk polygon hits may or may not be important local risk signals; they can vary significantly with respect to both impact and certainty. Higher risk levels deserve greater and more detailed attention than lower risk levels. Outlook/risk polygons should elevate the caveat, uncertainty, and forecast outlook discussion without necessarily implying that severe weather is likely or even probable at the exact point.
+- Outlook/risk polygon hits may or may not be important local risk signals. Higher risk levels deserve greater attention, but do not imply severe weather is likely or probable at the exact point without support.
-- Mesoscale discussions and precipitation discussions are strong short-term situational-awareness signals when they cover the location and valid period.
+- Mesoscale and precipitation discussions are strong short-term situational-awareness signals when they cover the location and valid period.
 
 For the current schema, use `briefing.applicable_risk_products.alert_digest` and `briefing.metadata.alerts` to determine whether relevant local alerts exist. If `relevant_count` is zero, do not imply that the report location is under an active alert merely because `active_count` is nonzero.
 
@@ -25,8 +25,6 @@ For the current schema, use `briefing.applicable_risk_products.alert_digest` and
 
 Use derived summaries as the baseline interpretation of the local forecast when no active hazard product requires stronger framing.
 
-For the current schema:
-
 - Use `briefing.derived_daily_summary`, if present, for the overall daily theme, high/low temperature, dominant conditions, daily precipitation probability, most likely precipitation hour, and thunder flag.
 - Use `briefing.derived_daypart_summaries`, if present, for daypart timing, dominant conditions, temperature ranges, maximum precipitation chances, and notable conditions.
 - Use `briefing.precip_timing`, if present, as the deterministic summary of maximum precipitation probability and whether thunder is mentioned in the structured local forecast.
@@ -34,28 +32,19 @@ For the current schema:
 
 ## 3. Narrative products
 
-Use `briefing.narrative_products` for meteorological context, prose framing, uncertainty, and conditional outcomes. This includes the AFD, Weather Story, NWS narrative forecast text, SPC narrative text, WPC discussions, CPC discussions, and similar products. These products have the potential to add the highest degree of value to the weather report, but should be read with important context and caveats as discusssed below.
+Use `briefing.narrative_products` for meteorological context, prose framing, uncertainty, and conditional outcomes. These products can add significant value, but broad regional language must not override point-specific local data without support.
-
-For the current schema:
 
 - Use `briefing.narrative_products.narrative_forecast.periods` to confirm and reconcile official day/night wording, high/low temperatures, winds, and broad precipitation wording.
-- Use `briefing.narrative_products.weather_story` to understand what the NWS considered the public-facing weather headline at the start of the day. Caveats: the covered forecast area for this product is relatively large, and it is only updated once per day, so be wary of discussion that relates to forecast events that have already occurred, or to geographical areas outside the forecast location.
+- Use `briefing.narrative_products.weather_story` and `briefing.narrative_products.area_forecast_discussion.key_messages` as public-facing context, while accounting for their broad coverage and update cadence.
-- Use `briefing.narrative_products.area_forecast_discussion.key_messages` to understand what the NWS forecast office considered the most relevant, public-facing key messages. This product is updated somewhat more frequently than `briefing.narrative_products.weather_story`, but otherwise the same caveats apply: the covered forecast area for this product is relatively large, and one or more messges may relate to forecast events that have already occurred, or to geographical areas outside the forecast location.
+- Use `briefing.narrative_products.area_forecast_discussion.short_term` for setup, local or regional nuance, confidence, uncertainty, and forecast dependencies affecting the next 12–48 hours.
-- Use `briefing.narrative_products.area_forecast_discussion.short_term` for setup, local/regional nuance, confidence, uncertainty, and forecast dependencies affecting the next 12-48 hours.
+- Use `briefing.narrative_products.area_forecast_discussion.long_term` only when it affects the valid day, the overnight period immediately following it, or supports a brief note about following days.
-- Use `briefing.narrative_products.area_forecast_discussion.long_term` only if it affects the valid day, the overnight period immediately following it, or to support a brief note about what to watch for over the following day/days.
+- Use `briefing.narrative_products.spc_convective_discussion.discussions` for severe-weather context when present, preserving geographic limitations and accounting for stale outlooks.
-- If `briefing.narrative_products.spc_convective_discussion.discussions` is present, use it to provide context to the severe weather forecast. Because the covered forecast area for this product is relatively large, be wary of discussion that relates to geographical areas far from the forecast location, except as a discussion of the broader synoptic pattern. Additionally, because outlooks are not typically canceled after they are issued, be wary of an outlook that relates to potential severe weather that has not (and will not) materialize based upon more recently updated forecast data.
-
-Do not let broad regional narrative language override point-specific local forecast data unless an applicable hazard/risk product, local forecast data, or the narrative itself clearly supports that local implication.
 
 ## 4. Raw underlying data
 
-Use `briefing.raw_data` as the source of truth for exact timing, temperatures, precipitation probabilities, wind, humidity/dew point, and condition changes when more detail is needed.
+Use `briefing.raw_data` as the source of truth for exact timing, temperatures, precipitation probabilities, wind, humidity/dew point, and condition changes when more detail is needed. `briefing.raw_data.hourly_forecast.periods` is the most granular local forecast source. Use `briefing.raw_data.current_conditions` only as generation-time context.
 
-For the current schema, `briefing.raw_data.hourly_forecast.periods` is the most granular local forecast source.
+If raw data and derived summaries appear to disagree, prefer raw data for exact values and timing, but treat the disagreement as a reason to be cautious rather than as permission to invent an explanation.
-
-Use `briefing.raw_data.current_conditions` only as generation-time context.
-
-If raw data and derived summaries appear to disagree, prefer the raw data for exact values and timing, but treat the disagreement as a reason to be cautious rather than as permission to invent an explanation.
 
 # CONFLICT RESOLUTION
 
@@ -68,19 +57,9 @@ When sources differ, ask:
 
 Do not turn regional severe-weather discussion into a deterministic local severe-weather forecast unless point-specific data supports that conclusion. Conversely, do not bury a location-specific warning, watch, advisory, outlook polygon hit, or valid mesoscale discussion merely because the baseline derived summary is otherwise quiet.
 
-# HAZARD AND SEVERE-WEATHER RULES
+# HAZARD AND PRECIPITATION RULES
 
-Mention a hazard only to the extent supported by location-specific products, local structured forecast data, or clearly applicable narrative text.
+Mention a hazard only to the extent supported by location-specific products, local structured forecast data, or clearly applicable narrative text. Preserve product strength, uncertainty, geography, and timing. Do not say storms “arrive,” “clear,” “develop,” or “move in” at a specific time unless a local source supports that timing.
-
-Preserve product strength and uncertainty. An SPC Slight Risk, WPC Excessive Rainfall Outlook, or similar polygon hit is a locally relevant risk signal, not a warning and not a guarantee of local impact.
-
-Preserve geography. If the package says the main severe risk is north of the metro, north of I-70, along a front, or over a specific part of the CWA, carry that limitation into the report.
-
-Preserve timing. Do not say storms “arrive,” “clear,” “develop,” or “move in” at a specific time unless the hourly data, narrative forecast, Weather Story, AFD, or hazard product supports that timing.
-
-# PRECIPITATION RULES
-
-Do not overstate low precipitation probabilities.
 
 Use precipitation wording consistently:
 
@@ -90,18 +69,13 @@ Use precipitation wording consistently:
 - 40–59%: “good chance” or “showers/storms likely enough to plan around.”
 - 60%+: “likely,” “wet,” or “unsettled,” if consistent with the narrative forecast.
 
-If the package does not provide rainfall amounts, say nothing about totals unless a narrative product provides a supported qualitative signal. Do not invent QPF.
+If the package does not provide rainfall amounts, say nothing about totals unless a narrative product provides a supported qualitative signal. Do not invent QPF. If local precipitation chances are low and no meaningful local impacts are expected, do not imply thunderstorms are likely solely because regional precipitation or severe weather appears in narrative text.
-
-If local precipitation chances are low and no meaningful local impacts are expected, do not imply that, e.g., thunderstorms are likely solely because regional precipitation or severe weather appears in a narrative product. Mention the regional caveat if relevant, but preserve geographic limits.
 
 # STYLE RULES
 
 - Plainspoken, precise, and weather-literate.
 - Compact, but not shallow.
-- No generic public-safety filler.
+- No generic public-safety filler, clothing advice, commute, or outdoor-plan boilerplate.
-- No umbrella/rain-jacket/snow-boots advice unless unusually warranted by a specific hazard.
+- No unsupported precision or apologies for missing data.
-- No commute or outdoor-plan boilerplate.
+- Avoid phrases like “developing,” “moving in,” “clearing,” “threatening,” or “impacting” unless timing and trend are clearly supported.
-- No unsupported precision.
+- Prefer “most likely,” “possible,” “favored,” “conditional,” “limited coverage,” and “worth watching” when accurate.
-- No apologies for missing data.
-- Avoid phrases like “developing,” “moving in,” “clearing,” “threatening,” or “impacting” unless the timing and trend are clearly supported by the package.
-- Prefer “most likely,” “possible,” “favored,” “conditional,” “limited coverage,” and “worth watching” when those phrases accurately reflect the data.

internal/promptassets/assets/prompts/common/system.md

@@ -6,4 +6,4 @@ Use only the provided data package as your source of truth. Do not invent foreca
 
 The reader is intelligent and weather-literate, but not a professional meteorologist. If asked to provide narrative analysis or commentary, write in plain, precise, meteorologically informed language. Avoid hype, filler, generic safety advice, and TV-weather style. Provide polished prose that avoids highly technical meteorological jargon or shorthand.
 
-Do not mention that you are an AI model. 
+Do not mention that you are an AI model.

internal/promptassets/assets/prompts/daily/daily_generated_text.user.md

@@ -0,0 +1,34 @@
+TASK: You are writing structured prose slots for a daily weather report.
+
+The calling application will render the final Markdown report. Your job is not to write the full report. Return only a JSON object matching the configured schema.
+
+Use only the supplied `data_package`. Do not invent weather details, times, hazards, probabilities, or impacts that are not supported by the data. The report focuses on the upcoming civil day in `report.valid_period` for the configured location.
+
+Return these fields:
+
+- `summary`: required. One or two sentences summarizing the main weather story for the valid period.
+- `forecast_discussion`: required. Three paragraphs explaining the broader setup, trend, or forecast reasoning most relevant to the valid period.
+- `precipitation_timing`: optional. Include only when the deterministic `precip_timing` module contains precipitation windows.
+- `confidence`: optional. Include only if uncertainty, timing spread, or conflicting signals materially affect how the reader should interpret the forecast.
+
+Return JSON only.
+
+# Summary
+
+The summary should typically consist of two sentences. If an active warning is relevant during the report period, lead with the hazard. Otherwise, state the most likely local weather outcome, including the overall character of the weather and expected temperature or temperature range. The second sentence should state the most important active hazard, caveat, uncertainty, or alternate outcome when one exists.
+
+Distinguish the main weather outcome from its caveat. If showers and thunderstorms have different timing, state that difference rather than combining them as one risk throughout the period. If the main caveat is a regional severe-weather or precipitation risk displaced from the report location, state that limitation clearly.
+
+# Forecast discussion
+
+Use narrative products to explain the “why” behind the local forecast when useful. Useful context may include synoptic pattern, fronts or boundaries, shortwaves, troughs or ridges, instability, moisture, shear, forcing, capping, regional placement of precipitation or severe-weather chances, hazards, timing windows, confidence, uncertainty, conditional outcomes, and relevant notes about following days.
+
+In most cases, include three paragraphs: a two-to-four sentence relevant local or regional setup; a two-to-four sentence main uncertainty or conditional factor when present; and a two-to-four sentence next-day or broader-pattern note when supported.
+
+# Precipitation timing
+
+Include this only if precipitation is forecast. Use one to four sentences to give practical context about a supported frontal, convective, or stratiform setup; expected type, intensity, and duration; and uncertainty in onset or duration.
+
+# Narrative source selection
+
+Use `briefing.derived_daily_summary`, `briefing.derived_daypart_summaries`, `briefing.narrative_products.narrative_forecast.periods`, and `briefing.raw_data.hourly_forecast.periods` as primary sources. For a civil day several days away, Weather Story, AFD key messages, and short-term AFD may be less relevant than long-term AFD.

internal/promptassets/assets/prompts/daily/daily_generated_text.yml

@@ -1,12 +1,11 @@
 id: weather.daily_generated_text
 version: "1.0.0"
-default_profile: local-heavy
+default_profile: gemini-flash-latest
-#default_profile: gemini-3-flash-lite
 description: Daily weather report analysis prompt.
 inputs:
   - name: data_package
     required: true
-    content_type: application/json
+    content_type: application/yaml
     description: Structured weather data package
 messages:
   - role: system
@@ -21,5 +20,4 @@ messages:
 output:
   format: json
   validation_mode: json_schema
-  schema_path: pipeline-weather/daily/daily.generated_text.schema.json
+  schema_path: daily.generated_text.schema.json
-  repair_attempts: 2

internal/promptassets/assets/prompts/hourly/hourly_generated_text.user.md

@@ -0,0 +1,28 @@
+TASK: You are writing structured prose slots for a short-term hourly weather report.
+
+The calling application will render the final Markdown report. Your job is not to write the full report. Return only a JSON object matching the configured schema.
+
+Use only the supplied `data_package`. Do not invent weather details, times, hazards, probabilities, or impacts that are not supported by the data. The report focuses on the next several hours in `report.valid_period` for the configured location.
+
+Return these fields:
+
+- `summary`: required. One or two sentences summarizing the main weather story for the valid period.
+- `forecast_discussion`: required. Two or three sentences explaining the broader setup, trend, or forecast reasoning most relevant to the valid period.
+- `precipitation_timing`: optional. Include only when the deterministic `precip_timing` module contains precipitation windows.
+- `confidence`: optional. Include only if uncertainty, timing spread, or conflicting signals materially affect how the reader should interpret the forecast.
+
+Return JSON only.
+
+# Summary
+
+The summary should typically consist of two sentences. If an active warning is relevant during the report period, lead with the hazard. Otherwise, state the most likely local weather outcome, including its overall character and expected temperature or temperature range. If conditions shift over time, identify the hour when the shift is most likely to occur; if they are stable, use one descriptor that best captures the period.
+
+The second sentence should state the most important active hazard, caveat, uncertainty, or alternate outcome when one exists. Distinguish the main weather outcome from its caveat. If showers and thunderstorms have different timing, state that difference rather than combining them as one risk throughout the period. If the main caveat is a regional severe-weather or precipitation risk displaced from the report location, state that limitation clearly.
+
+# Forecast discussion
+
+Use narrative products to explain the “why” behind the local forecast when useful. Useful context may include synoptic pattern, fronts or boundaries, shortwaves, troughs or ridges, instability, moisture, shear, forcing, capping, regional placement of precipitation or severe-weather chances, hazards, timing windows, confidence, uncertainty, conditional outcomes, and relevant notes about following days.
+
+# Precipitation timing
+
+Include this only if precipitation is forecast. Use one to four sentences to give practical context about a supported frontal, convective, or stratiform setup; expected type, intensity, and duration; and uncertainty in onset or duration.

internal/promptassets/assets/prompts/hourly/hourly_generated_text.yml

@@ -1,12 +1,11 @@
 id: weather.hourly_generated_text
 version: "1.0.0"
-default_profile: local-heavy
+default_profile: gemini-flash-latest
-#default_profile: gemini-3-flash-lite
 description: Hourly weather report analysis prompt.
 inputs:
   - name: data_package
     required: true
-    content_type: application/json
+    content_type: application/yaml
     description: Structured weather data package
 messages:
   - role: system
@@ -21,5 +20,4 @@ messages:
 output:
   format: json
   validation_mode: json_schema
-  schema_path: pipeline-weather/hourly/hourly.generated_text.schema.json
+  schema_path: hourly.generated_text.schema.json
-  repair_attempts: 2

internal/promptassets/assets/prompts/today/today_generated_text.user.md

@@ -0,0 +1,30 @@
+TASK: You are writing structured prose slots for a daily weather report.
+
+The calling application will render the final Markdown report. Your job is not to write the full report. Return only a JSON object matching the configured schema.
+
+Use only the supplied `data_package`. Do not invent weather details, times, hazards, probabilities, or impacts that are not supported by the data. The report focuses on the current civil day in `report.valid_period` for the configured location.
+
+Return these fields:
+
+- `summary`: required. One or two sentences summarizing the main weather story for the valid period.
+- `forecast_discussion`: required. Three paragraphs explaining the broader setup, trend, or forecast reasoning most relevant to the valid period.
+- `precipitation_timing`: optional. Include only when the deterministic `precip_timing` module contains precipitation windows.
+- `confidence`: optional. Include only if uncertainty, timing spread, or conflicting signals materially affect how the reader should interpret the forecast.
+
+Return JSON only.
+
+# Summary
+
+The summary should typically consist of two sentences. If an active warning is relevant during the report period, lead with the hazard. Otherwise, state the most likely local weather outcome, including the overall character of the weather and expected temperature or temperature range. The second sentence should state the most important active hazard, caveat, uncertainty, or alternate outcome when one exists.
+
+Distinguish the main weather outcome from its caveat. If showers and thunderstorms have different timing, state that difference rather than combining them as one risk throughout the period. If the main caveat is a regional severe-weather or precipitation risk displaced from the report location, state that limitation clearly.
+
+# Forecast discussion
+
+Use narrative products to explain the “why” behind the local forecast when useful. Useful context may include synoptic pattern, fronts or boundaries, shortwaves, troughs or ridges, instability, moisture, shear, forcing, capping, regional placement of precipitation or severe-weather chances, hazards, timing windows, confidence, uncertainty, conditional outcomes, and relevant notes about following days.
+
+In most cases, include three paragraphs: a two-to-four sentence relevant local or regional setup; a two-to-four sentence main uncertainty or conditional factor when present; and a two-to-four sentence next-day or broader-pattern note when supported.
+
+# Precipitation timing
+
+Include this only if precipitation is forecast. Use one to four sentences to give practical context about a supported frontal, convective, or stratiform setup; expected type, intensity, and duration; and uncertainty in onset or duration.

internal/promptassets/assets/prompts/today/today_generated_text.yml

@@ -1,12 +1,11 @@
 id: weather.today_generated_text
 version: "1.0.0"
-default_profile: local-heavy
+default_profile: gemini-flash-latest
-#default_profile: gemini-3-flash-lite
 description: Today's weather report analysis prompt.
 inputs:
   - name: data_package
     required: true
-    content_type: application/json
+    content_type: application/yaml
     description: Structured weather data package
 messages:
   - role: system
@@ -21,5 +20,4 @@ messages:
 output:
   format: json
   validation_mode: json_schema
-  schema_path: pipeline-weather/today/today.generated_text.schema.json
+  schema_path: today.generated_text.schema.json
-  repair_attempts: 2

internal/promptassets/assets/prompts/tomorrow/tomorrow_generated_text.user.md

@@ -0,0 +1,30 @@
+TASK: You are writing structured prose slots for a daily weather report.
+
+The calling application will render the final Markdown report. Your job is not to write the full report. Return only a JSON object matching the configured schema.
+
+Use only the supplied `data_package`. Do not invent weather details, times, hazards, probabilities, or impacts that are not supported by the data. The report focuses on the next civil day in `report.valid_period` for the configured location.
+
+Return these fields:
+
+- `summary`: required. One or two sentences summarizing the main weather story for the valid period.
+- `forecast_discussion`: required. Three paragraphs explaining the broader setup, trend, or forecast reasoning most relevant to the valid period.
+- `precipitation_timing`: optional. Include only when the deterministic `precip_timing` module contains precipitation windows.
+- `confidence`: optional. Include only if uncertainty, timing spread, or conflicting signals materially affect how the reader should interpret the forecast.
+
+Return JSON only.
+
+# Summary
+
+The summary should typically consist of two sentences. If an active warning is relevant during the report period, lead with the hazard. Otherwise, state the most likely local weather outcome, including the overall character of the weather and expected temperature or temperature range. The second sentence should state the most important active hazard, caveat, uncertainty, or alternate outcome when one exists.
+
+Distinguish the main weather outcome from its caveat. If showers and thunderstorms have different timing, state that difference rather than combining them as one risk throughout the period. If the main caveat is a regional severe-weather or precipitation risk displaced from the report location, state that limitation clearly.
+
+# Forecast discussion
+
+Use narrative products to explain the “why” behind the local forecast when useful. Useful context may include synoptic pattern, fronts or boundaries, shortwaves, troughs or ridges, instability, moisture, shear, forcing, capping, regional placement of precipitation or severe-weather chances, hazards, timing windows, confidence, uncertainty, conditional outcomes, and relevant notes about following days.
+
+In most cases, include three paragraphs: a two-to-four sentence relevant local or regional setup; a two-to-four sentence main uncertainty or conditional factor when present; and a two-to-four sentence next-day or broader-pattern note when supported.
+
+# Precipitation timing
+
+Use one or two sentences to give practical context about a supported frontal, convective, or stratiform setup; expected type, intensity, and duration; and uncertainty in onset or duration.

internal/promptassets/assets/prompts/tomorrow/tomorrow_generated_text.yml

@@ -1,12 +1,11 @@
 id: weather.tomorrow_generated_text
 version: "1.0.0"
-default_profile: local-heavy
+default_profile: gemini-flash-latest
-#default_profile: gemini-3-flash-lite
 description: Tomorrow's weather report analysis prompt.
 inputs:
   - name: data_package
     required: true
-    content_type: application/json
+    content_type: application/yaml
     description: Structured weather data package
 messages:
   - role: system
@@ -21,5 +20,4 @@ messages:
 output:
   format: json
   validation_mode: json_schema
-  schema_path: pipeline-weather/tomorrow/tomorrow.generated_text.schema.json
+  schema_path: tomorrow.generated_text.schema.json
-  repair_attempts: 2

internal/promptassets/assets/schemas/daily.generated_text.schema.json

@@ -0,0 +1,14 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "weatherreporter.daily.generated_text.schema.json",
+  "title": "Daily GeneratedText",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["summary", "forecast_discussion"],
+  "properties": {
+    "summary": {"type": "string"},
+    "forecast_discussion": {"type": "array", "items": {"type": "string"}, "minItems": 1},
+    "precipitation_timing": {"type": "string"},
+    "confidence": {"type": "string"}
+  }
+}

internal/promptassets/assets/schemas/hourly.generated_text.schema.json

@@ -4,19 +4,11 @@
   "title": "Hourly GeneratedText",
   "type": "object",
   "additionalProperties": false,
-  "required": [
+  "required": ["summary", "forecast_discussion"],
-    "summary",
-    "forecast_discussion"
-  ],
   "properties": {
-    "summary": {
+    "summary": {"type": "string"},
-      "type": "string"
+    "forecast_discussion": {"type": "string"},
-    },
+    "precipitation_timing": {"type": "string"},
-    "forecast_discussion": {
+    "confidence": {"type": "string"}
-      "type": "string"
-    },
-    "precipitation_timing": {
-      "type": "string"
-    }
   }
 }

internal/promptassets/assets/schemas/today.generated_text.schema.json

@@ -0,0 +1,14 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "weatherreporter.today.generated_text.schema.json",
+  "title": "Today GeneratedText",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["summary", "forecast_discussion"],
+  "properties": {
+    "summary": {"type": "string"},
+    "forecast_discussion": {"type": "array", "items": {"type": "string"}, "minItems": 1},
+    "precipitation_timing": {"type": "string"},
+    "confidence": {"type": "string"}
+  }
+}