feat(spec-6-2): quality gates + lifecycle hooks → v0.11.0 - #18
Merged
Conversation
… + double-finishRun dedup - RunRecord gains cwd (required), backend (required), pid? (claude) - run:meta event + scanMeta carry pid? + cwd (cross-process durability) - LiveSessionHandle.isAlive(): pi forwards SDK session state; claude checks disposed/proc.killed/exitCode/signalCode - Dedup: removed optimistic pre-session_init run:meta (was double-writing with the post-session_init append); finishRun guarded against double-fire - Audited all RunRecord construction sites (src + tests) for cwd/backend
…umulative tokenTotal The widget + Runs tab rendered 'tok' from tokenTotal (cumulative usage across all turns) next to a ctx% computed from contextTokens (live snapshot). In short runs the two are close so '27K tok 1%' looked right; on a long 50-turn run tokenTotal ballooned to 6.7M (cumulative re-sends of the growing context) while contextTokens stayed ~341K (35% of 976K) — exposing that 'tok' was the wrong field. Both segments now read contextTokens so the count and % are the same metric. Discovered dogfooding armory-fleet on its own SPEC-6-2 execution.
…emitProgress backend
…default lifecycle gates
…gate panel actions
# Conflicts: # package.json
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
SPEC-6-2: composable phase-exit quality-gate chain (4 builtin gates: verify/completenessCheck/gate/verification-before-completion) + two lifecycle hooks (challenge-step soft injection, session-liveness hybrid probe) + cross-cwd leak fix + widened CheckpointFn + /fleet Lifecycle view gate-line rendering.
12-task subagent-driven execution (dogfooding armory-fleet on itself). 438/438 tests (was 368). Final whole-branch review: ready, no Critical/Important.
Spec: docs/superpowers/specs/2026-07-28-spec-6-2-quality-gates-design.md
Plan: docs/superpowers/plans/2026-07-28-spec-6-2.md