Capture native execution facts and complete scoped debug evidence

This commit is contained in:
2026-11-22 03:19:43 +00:00
parent 8680060400
commit 9f66421f4f
24 changed files with 1688 additions and 543 deletions

View File

@@ -1440,6 +1440,34 @@ incremental recording failure, finalization failure, and no completion retarget.
## Stage 31: Attach Native Execution Facts And Complete Debug Evidence
**Status:** Complete. Runner invocations now enroll initial, coordinated, and
nested validator executions in one native ExecutionGroup, preserving native
identity, terminal coverage, and unknown usage without copied totals. Scoped
capture composes existing observers and lightweight preparation callbacks, reuses
split-preparation details on hits, and records native events, prepared contracts,
results, exact response text, and full readable exchanges. Undelivered responses
are explicitly unassessed; result-less and preparation failures retain availability
and error evidence. Capture failures preserve primary causes and cannot trigger
semantic retries or permissive fallback.
Added frozen secret-aware application/PromptKit configuration and source snapshots,
resolved composition, self-contained source/reference/incoming-artifact inputs,
codec candidates, complete findings/guidance, interpretation and correction inputs,
normalization originals/mappings/proposals, deterministic/fallback outcomes, and
cache decisions/artifact bytes. Native credential omissions and exact adopted
configuration sensitivity paths are preserved without scanning application text;
runtime options are not reserialized outside native inspection. Removed the old
completion decorator, synthetic IDs, duplicate accounting, and heuristic content
scrubbing. Evidence is written incrementally without whole-run content retention.
Focused native helper/runner/assessment tests, isolated real-kit configuration
capture tests, vet, repeated race checks, recorder/cache/contracts/generic/Seriatim/
reconciliation/asset tests, production framework/config builds, and diff checks
pass. Concrete D&D normalizer/validator and full CLI/pipeline suites remain blocked
at setup by legacy removed reporting-package imports and old ConfigKit's YAML
plugin/limit dependency; their runtime results, including the new normalization
capture regression, are not claimed passing. Scheduled cleanup and final verification
must execute them. Native run-handler composition and final reporting remain in
their assigned later stages.
**Goal:** use native observations/snapshots instead of parallel execution accounting.
**Inspect/change:** helper/validator request observers, runner operation boundaries,