feat(agent): cache control embedding index + auto-wire semantic pass (gated) #217

2026-07-21T11:12:16Z

sharang commented

2026-07-21 11:12:16 +00:00

Item 2 of the semantic-mapping follow-ups (after #215).

2a — cache the control embedding index. ControlIndex::load_or_build persists the embedded corpus to snapshot_dir keyed by a corpus hash (control ids + requirement text). A later scan reuses the embeddings unless the catalog changed, turning the per-scan re-embed of the ~13.6k master-control corpus into a one-time cost. Atomic write (temp + rename), self-invalidates on catalog change. ControlCheckSpec gains Serialize/Deserialize.

2b — auto-wire. Orchestrator Stage 5c runs semantic_stamp_findings after control triage, gated on breakpilot.semantic_mapping (env BREAKPILOT_SEMANTIC_MAPPING, default off). Stays off until verified live against a deployed master-controls catalog; safe no-op meanwhile (endpoint 400s pre-deploy, pass warns + returns 0).

Tests: index cache round-trip + corpus-hash stability/identity. All green locally (clippy -D warnings, fmt, full test suite).

🤖 Generated with Claude Code

Item 2 of the semantic-mapping follow-ups (after #215). **2a — cache the control embedding index.** `ControlIndex::load_or_build` persists the embedded corpus to `snapshot_dir` keyed by a corpus hash (control ids + requirement text). A later scan reuses the embeddings unless the catalog changed, turning the per-scan re-embed of the ~13.6k master-control corpus into a one-time cost. Atomic write (temp + rename), self-invalidates on catalog change. `ControlCheckSpec` gains Serialize/Deserialize. **2b — auto-wire.** Orchestrator Stage 5c runs `semantic_stamp_findings` after control triage, gated on `breakpilot.semantic_mapping` (env `BREAKPILOT_SEMANTIC_MAPPING`, default off). Stays off until verified live against a deployed master-controls catalog; safe no-op meanwhile (endpoint 400s pre-deploy, pass warns + returns 0). Tests: index cache round-trip + corpus-hash stability/identity. All green locally (clippy -D warnings, fmt, full test suite). 🤖 Generated with [Claude Code](https://claude.com/claude-code)

sharang added 1 commit 2026-07-21 11:12:17 +00:00

feat(agent): cache control embedding index + auto-wire semantic pass (gated)

CI / Check (push) Skipped

CI / Deploy Agent (pull_request) Skipped

Details

CI / Deploy Dashboard (pull_request) Skipped

Details

CI / Check (pull_request) Successful in 5m46s

Details

CI / Detect Changes (pull_request) Skipped

Details

CI / Deploy Docs (pull_request) Skipped

Details

CI / Deploy MCP (pull_request) Skipped

Details

8cf3d09a23

Item 2 of the semantic-mapping follow-ups.

Caching (2a): ControlIndex::load_or_build persists the embedded corpus to
snapshot_dir keyed by a corpus hash (control ids + requirement text). A later
scan reuses the embeddings unless the catalog changed, turning the per-scan
re-embed of the ~13.6k master-control corpus into a one-time cost. Atomic
write (temp + rename); self-invalidates on catalog change. ControlCheckSpec
gains Serialize/Deserialize to persist.

Auto-wire (2b): orchestrator Stage 5c runs semantic_stamp_findings after control
triage, gated on breakpilot.semantic_mapping (env BREAKPILOT_SEMANTIC_MAPPING,
default off). Stays off until verified live against a deployed master-controls
catalog; safe no-op meanwhile (the endpoint 400s pre-deploy and the pass warns +
returns 0).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

sharang merged commit 0ef2cd1b23 into main

2026-07-21 11:29:17 +00:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: sharang/compliance-scanner-agent#217