DeepSeek/deepseek-harness
1
0
Fork 0
mirror of https://github.com/deepseek-ai/deepseek-harness synced 2026-08-15 21:04:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

restore hook/result durationMs — review keeps wall-clock audit timing durable

Browse Source 
Reverses item 3 of the tighten-hook-protocol-contract RFC per review:
a persistence log is written for future readers, and hook wall-clock
runtime is audit signal (which hook made a turn slow). runHook keeps
its injected now clock and RunHookResult wrapper, the bridges pass the
measured duration through HookResultRecord, the snapshot normalizer
keeps its replay scrub, and the hook fixtures carry the field again.
The RFC records the reversal; the other three prunes stand.
This commit is contained in:
Tianyi Cui
2026-07-04 22:00:12 +08:00
parent 19ae955009
commit 0b97b2f7c1
27 changed files with 122 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md
View File

@@ -27,7 +27,7 @@ Thirteen scenarios under `examples/acp-agent/tests/snapshots/`, naming `hook-<di
- **Authored, no model turn** (keyless, no sidecar — the derived replay script is empty; the `rejected` turn carrying `hook/*` events is compared): `hook-cc-promptsubmit-block`, `hook-codex-promptsubmit-block`.
- **Recorded against the real API, hook active during recording** (the model's reaction to the decision is part of the captured transcript, replayed keyless thereafter): `hook-{cc,codex}-promptsubmit-context` (allow + additionalContext fold), `hook-cc-pretool-deny` / `hook-codex-pretool-block` (deny → `isError` tool result), `hook-cc-pretool-ask` (ask → degrades to deny with the approval-required reason), `hook-{cc,codex}-posttool-block` (block with feedback), `hook-{cc,codex}-posttool-context` (accept + additionalContext), `hook-{cc,codex}-stop-continue` (a blocking Stop hook forces one extra step via steering).
Each hook command emits only FIXED LITERAL strings (no timestamps/pids/`$RANDOM`/cwd echoes), and a `hook/result` carries only deterministic fields (`decision`/`exitCode`/`stderrSummary`), so the hook events need no scrubbing beyond the normalizer's generic `time` zeroing. The `Stop` scenarios self-limit with a marker file (`.stop_fired`) so the force-continue does not loop — the `stop_hook_active` loop-guard is still a bridge `TODO`, so an unconditional Stop hook would force-continue every step.
Each hook command emits only FIXED LITERAL strings (no timestamps/pids/`$RANDOM`/cwd echoes); the snapshot normalizer scrubs the one volatile field a `hook/result` carries (`durationMs`). The `Stop` scenarios self-limit with a marker file (`.stop_fired`) so the force-continue does not loop — the `stop_hook_active` loop-guard is still a bridge `TODO`, so an unconditional Stop hook would force-continue every step.
### Three hook points are deliberately NOT snapshotted