golem15/msd-core
3
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix(#2289): context-monitor emits injection envelope only for supported events (#2324)

Browse Source 
* fix(#2289): context-monitor emits injection envelope only for supported events

gsd-context-monitor is wired to Codex Stop/SubagentStart/SubagentStop/PreCompact
(#772), but it emitted a hookSpecificOutput.additionalContext envelope for every
event. Codex's Stop schema rejects that shape ("hook returned invalid stop hook
JSON output") exactly when context is low.

Use a positive allowlist: emit only for context-injection events (PostToolUse,
AfterTool, and the pre-existing Gemini missing-name fallback); exit 0 silently
for Stop and every other event. Debounce and critical-session bookkeeping still
run on silenced events. Behavioral regression tests drive the real hook.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs(#2289): backfill PR number 2324 into changeset

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(#2285): de-flake per-plan use_worktree property test on duplicate briefs

The fast-check property in claude-orchestration.test.cjs located each plan's
agent() call via indexOf on the brief, but only plan IDs were unique — briefs
could collide (fast-check shrinks toward short strings). On a colliding seed the
lookup found the first duplicate's line and misattributed its isolation, failing
"use_worktree:true must carry isolation" intermittently (surfaced on macOS CI).
emitWorkflowScript is correct for duplicate briefs (verified); suffix the unique
id onto each agent() label so the test probe is unambiguous.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Tom Boucher
2026-07-16 00:56:07 -04:00
committed by GitHub
parent 52fab7d9d7
commit 5ea3401d4f
16 changed files with 309 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
hooks/gsd-context-monitor.js
View File

@@ -180,15 +180,33 @@ process.stdin.on('end', () => {
'starting new complex work.';
}
const output = {
hookSpecificOutput: {
hookEventName: (data.hook_event_name && data.hook_event_name.trim())
|| (process.env.GEMINI_API_KEY ? "AfterTool" : "PostToolUse"),
additionalContext: message
}
};
// #2289: the hookSpecificOutput.additionalContext envelope is only a valid
// output shape for the context-injection events (PostToolUse, and AfterTool
// for the Gemini dialect). This hook is also wired to other lifecycle events
// on some hosts — Codex registers it under Stop / SubagentStart /
// SubagentStop / PreCompact (#772) — and those reject the envelope
// ("hook returned invalid stop hook JSON output"). Use a POSITIVE allowlist:
// emit only for injection-capable events; every other event, and a
// missing/unrecognized name, exits 0 with no stdout. A Stop-only blacklist is
// not enough — a missing name would still fall through to the injection path.
// All side effects above (debounce counter, one-time critical-session
// recording) have already run regardless of whether output is emitted.
const eventName = (data.hook_event_name && data.hook_event_name.trim()) || "";
// Preserve the pre-#2289 Gemini fallback: a missing event name under a
// Gemini-dialect runtime (GEMINI_API_KEY set) still means AfterTool, so its
// advisory output is unchanged. A missing name on any other host is silent.
const geminiFallback = eventName === "" && !!process.env.GEMINI_API_KEY;
const injectionSupported = eventName === "PostToolUse" || eventName === "AfterTool" || geminiFallback;
process.stdout.write(JSON.stringify(output));
if (injectionSupported) {
const output = {
hookSpecificOutput: {
hookEventName: eventName || "AfterTool",
additionalContext: message
}
};
process.stdout.write(JSON.stringify(output));
}
} catch (e) {
// Silent fail -- never block tool execution
process.exit(0);