Verify native recovery, fallback reuse boundaries, and operator schemas

This commit is contained in:
2026-11-22 06:00:52 +00:00
parent 854d23b91e
commit 5b6854e975
3 changed files with 369 additions and 4 deletions

View File

@@ -1780,6 +1780,36 @@ them; live OpenRouter/local services are not default validation requirements.
## Stage 37: Verify Assembled Recovery And Native Command Workflows
**Status:** Complete. Added two focused native CLI recovery contracts using the
maintained ordered D&D composition, existing provider fake, real domain modules,
typed generated references, filesystem cache, and capture. They include semantic
normalization and the real combat-semantics LLM validator on one limited backend
with one shared worker. A final-turn corrected scene is stored under the initial
prepared message hash; a downstream failure preserves accepted predecessors and
the chunk plan, and fixed reruns execute only the previously failed work. Full
hits retain capture without native executions or historical accounting. Native
failure causes, session/model/backend selections, unknown usage, terminal group
coverage, domain payloads, and source identity remain intact.
A failed permissive NPC refresh emits one qualified fallback, forces actual
generated-reference consumers to execute without reuse, leaves unrelated lanes
cached, and preserves earlier accepted files. Restoring ordinary mode reuses those
files without provider work. Operator-schema tests now execute the same prepared
handle and verify the custom provider constraint and native validation for inline,
source-relative, and external-root schemas; missing replacement roots do not fall
back to embedded schemas. No compatibility/configuration translation was added.
Reviewed and retained the existing focused producer/assessment/cache/capture,
worker/admission, command/preflight, and report/subprocess coverage for structural
failure with nil error, result-less/undelivered responses, full ordered guidance,
final-turn assessment, unchanged candidates, native overrides, cancellation,
stream/delivery outcomes, and no duplicate debug preparation. Explicit test repair
budgets use complete native output contracts, without pinning upstream defaults.
All four prescribed package suites and vet pass, as do repeated focused CLI and
shared observer/coordinator/backend race checks and `git diff --check`. No real
credentials, external inference, or model-quality claim is involved. Stage 46
still owns final whole-roadmap verification after documentation updates.
**Goal:** prove the cross-boundary behavior most likely to regress in this cutover.
**Inspect/change:** CLI assembled/command/cache contracts, module integration