feat(agent): add executor gatekeeper hook

This commit is contained in:
aruo
2026-07-08 02:01:49 +08:00
parent 050cbc8fee
commit c5e496e715
23 changed files with 1343 additions and 30 deletions
@@ -0,0 +1,51 @@
# Decisions: executor-gatekeeper-hook
## Key Decisions
### Gatekeeper stays in VerifierInputHook
Decision: Gatekeeper is integrated inside `VerifierInputHook`, after Executor output parsing and before Verifier model execution.
Reason: The user explicitly chose to keep this version in the Verifier hook and not move validation into Executor hook. This preserves the current workflow orchestration.
### No retry in this phase
Decision: Gatekeeper failure does not trigger automatic Executor retry.
Reason: Retry behavior is intentionally deferred. This phase only validates, exposes, and audits deterministic failures.
### Initial rule set is intentionally small
Decision: Stage two implements only `schema.executor_v2` and `evidence.invocation_ref` as hard checks.
Reason: These rules catch the highest-confidence physical failures with low implementation risk. Excerpt similarity, hallucination phrases, and evidence utilization remain later enhancements.
### No new database schema
Decision: Persist `gatekeeper_result` in existing `diagnosis_session.self_evaluation.verifier_evaluation`.
Reason: The user asked to keep database fields minimal. Existing JSON audit storage is enough for this phase.
### Internal interface impact
Decision: This is an L2 internal interface extension.
Impact:
- Verifier payload gains `gatekeeper_result`.
- `VerifierContextHolder` gains Gatekeeper result storage.
- `self_evaluation.verifier_evaluation` gains `gatekeeper_result`.
- No external API, DTO, database table, or schema migration changes.
## Deferred Decisions
- Whether Gatekeeper should later trigger Executor retry.
- Whether `evidence.excerpt_similarity` should be hard fail or warn-only.
- Whether hallucination phrase and evidence utilization rules should be config-driven from metadata files.
- How Verifier V2 `claim_checks` should enforce Gatekeeper failures in code, beyond prompt instruction.
## Remaining Risks
- Verifier prompt compliance is not a deterministic guarantee; stage three should make Gatekeeper fail incompatible with PASS in Verifier V2 behavior.
- Excerpt authenticity is not checked in this phase, so real invocation ids can still be paired with misleading excerpt text until a later rule is implemented.