paqad-ai 1.76.1 → 1.76.3

package/CHANGELOG.md

@@ -1,5 +1,33 @@
 # paqad-ai
 
+## 1.76.3
+
+### Patch Changes
+
+- 457fcc0: fix(#472): reconcile the completion receipt so its headline and per-stage block agree
+
+  The end-of-change receipt (#325) composed two independent subsystems without reconciling them: the verdict headline (`formatVerdictSummary`, driven by `verdict.ok`, computed from gates only) and the per-stage evidence block (the stage-evidence fold). A feature-development change whose gates all passed but whose mandatory `review`/`checks` stages had no evidence rendered a self-contradicting receipt — `Safe to merge / N/N checks held` beside `🟡 review/checks — not recorded`. It happened whenever a mandatory-stage gap did not flip `verdict.ok` (for example `stages_mode=warn`, where the stage-evidence gate is `skipped`).
+
+  The receipt now reconciles **down** (the contract's own over-trust guard): when a feature-development change's gates all pass but a mandatory stage is not provably done, the developer-facing verdict word becomes **Inconclusive** and names the offending stages, so the headline agrees with the per-stage block. The true `🟢 N/N checks held for you.` line is kept, so gate evidence is still credited.
+
+  `verdict.ok` stays gate-derived, so git/CI exit codes and warn-mode non-blocking semantics are unchanged — Inconclusive is "do not over-trust", never a hard block. (Defect 2, the #409 narration advisory, was already fixed by #476; this closes Defect 1.)
+
+## 1.76.2
+
+### Patch Changes
+
+- 7ce4c34: fix: stop the `Stop says:` narration leak — silence Stop-hook `{systemMessage}` prose
+
+  Claude Code changed how it renders Stop-hook output: a Stop-hook `{systemMessage}` now renders on Desktop as literal `Stop says:` lines, inverting the premise the #368/#409 narration design was built on (that the channel was invisible, so the agent speaks the receipt and the hook echo is a silent backchannel). With the host inverted, paqad's three Stop-event emitters poured user-facing prose into that channel on every turn, across every onboarded repo and machine — duplicating the receipt the agent already speaks and leaking the model-only narration advisory into the developer's chat.
+
+  The Stop hooks no longer emit user-facing `{systemMessage}` prose:
+
+  - `runtime/scripts/verify-backstop.mjs` (`hook-completion`): writes nothing on a pass/inconclusive turn and only a model-only `{decision:'block'}` reason on a hard failure. Enforcement is unchanged — the block reason reaches the model (never rendered on either host) and the git/CI backstop still hard-fails with exit 2.
+  - `runtime/hooks/capability-gate.mjs` (`completion` seam): no longer echoes narration on the allow path; the `pre-mutation` (PreToolUse) seam is unchanged.
+  - `runtime/hooks/stage-marker-parse.mjs`: still records every parsed marker to the ledger; only the chat echo is removed.
+
+  The developer-facing channel is the agent's own final message (the #409 contract), which was always the intended primary channel. The narration contract docs and the verification module doc are corrected to state the new host behavior. Decision `D-01KZV9HFGDXZ03J0S6P9BTQ53Q` records the approach.
+
 ## 1.76.1
 
 ### Patch Changes

package/dist/cli/index.js

@@ -36251,7 +36251,7 @@ init_cancelled_error();
 init_events();
 
 // src/index.ts
-var VERSION = "1.76.1";
+var VERSION = "1.76.3";
 
 // src/cli/commands/audit.ts
 init_esm_shims();