eric/notarius
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Cleanup and complete the pipeline refactor

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-07 15:32:35 -05:00
parent a9d8505cdb
commit 582c5dceed
14 changed files with 164 additions and 160 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docs/internal/modules.md
View File

@@ -149,9 +149,10 @@ text, or secrets.
Package: `internal/modules/extract/dnd/spells`
The `dnd/spells` extractor owns D&D spell-cast extraction semantics. It
supplies the embedded Scriptorium prompt ID, prompt version, transcript and
reference input materials, response schema, and session ID to the runtime; then
returns the structured LLM `spell_casts` response as raw JSON.
supplies the embedded Scriptorium prompt ID, prompt version, chunk-scoped
transcript input material, reference input materials, response schema, and
session ID to the runtime; then returns the structured LLM `spell_casts`
response as raw JSON.
Its LLM-facing source-reference schema uses integer `start_unit_id` and
`end_unit_id` values matching source-unit IDs.

14
docs/internal/pipeline.md
View File

@@ -60,10 +60,11 @@ extractor, merger, or normalizer request. LLM-backed modules pass that material
onward as named Scriptorium prompt inputs.
The CLI carries raw input bytes into `pipeline.RunInput`. Input adapters parse
those bytes into the source document, while LLM-backed modules that need the
original transcript material can pass the same bytes as a prompt input with
origin metadata. The raw input payload is not written to manifests or default
diagnostics.
those bytes into the source document. Chunk, merge, and normalize requests
receive the original source material as `SourceInput`; extraction requests
receive chunk-scoped source material built from the current `SourceChunk`
content, media type, and origin metadata. The raw input payload is not written
to manifests or default diagnostics.
The CLI also carries an optional run `session_id`. The runner makes it available
to chunk, extract, merge, and normalize requests; LLM-backed modules forward it
@@ -186,6 +187,11 @@ Runner-side raw validation chains receive the raw module output plus
stage, lane, module, source, and chunk provenance. Empty raw validation chains
approve output by default.
Pipeline-configured validator lists are not part of the current runner
contract. Non-empty configured validator lists are rejected during configuration
validation or resolved-run validation so they cannot appear in manifests without
executing.
Validator rejection is a non-fatal run outcome: the rejected output is recorded
in `RunOutput.Rejected` and does not pass to the next stage. Validator execution
errors are framework-level errors and retry according to the relevant binding.