Complete runner lifecycle refactor

This commit is contained in:
2026-09-04 01:21:37 +00:00
parent dbda2a0161
commit 2e69c14898
18 changed files with 176 additions and 165 deletions

View File

@@ -155,11 +155,21 @@ durability guarantee. Callers reload after a returned save error before retrying
## Execution Semantics
The application runner marks an executing stage running and then succeeded or
failed in the session manifest, persisting each transition. On success it records
outputs, logs, generated configuration references, metadata, and—when the
stage implements the optional contract—a versioned semantic-configuration
fingerprint. Artifact
Planning and execution share one pure pre-execution decision over the recorded
stage status, force selection, and normalized resume-validation result. That
decision identifies run versus reuse and any required stale and dependent
invalidation transition. Planning applies it only to a cloned manifest.
Execution remains the sole owner of observed stage results and persistence.
For each selected stage, the application runner computes semantic evidence,
performs any eligible resume validation, applies the pre-execution decision,
and persists required invalidation before either reusing the existing success
or beginning an attempt. The same one-stage execution owner marks the attempt
running before invoking the stage and then records and persists its failed,
skipped, or successful terminal state before a later stage may start. On
success it records outputs, logs, generated configuration references, metadata,
and—when the stage implements the optional contract—a versioned
semantic-configuration fingerprint. Artifact
records may include optional contract and external provenance objects; old
manifests remain compatible when those fields are absent. A successful forced
rerun marks only succeeded transitive dependent session-stage records stale.
@@ -237,9 +247,9 @@ invalidates only stages whose semantic configuration changed. When a private
external-tool model, module, prompt, or profile changes behind an unchanged
configured identifier, use `--force` for the affected work.
`session plan` computes the same current fingerprint and applies the same
comparison and invalidation rules to a cloned manifest. It predicts the runner
decision without persisting session state. The shared helper
`session plan` computes the same current fingerprint and applies the shared
decision and invalidation rules to a cloned manifest. It predicts the runner
decision without persisting session state. The semantic fingerprint owner
hashes deterministic JSON from stage-owned typed structs; stage providers must
exclude secrets, complete effective-configuration dumps, and operational
values that cannot affect canonical results. Concrete coverage is owned by the