Add a re-evaluate-backlog step to the predictor formula between
collect-signals and analyze-and-predict. For each open prediction/backlog
issue, the predictor now reads the original context and planner comments,
extracts the assumptions that made it "watch, don't act", and re-checks
those conditions against current system state.
Three outcomes:
- CONDITIONS_CHANGED → file new prediction/unreviewed, close old as superseded
- STALE (30+ days, conditions stable) → close as prediction/actioned
- UNCHANGED_RECENT → skip (existing behavior)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When Claude finishes a response but hasn't written to the PHASE file,
the stop hook now injects a nudge into the tmux session instead of just
marking idle. This gives Claude another chance to complete the phase
protocol before the monitor loop times out.
Key changes:
- on-idle-stop.sh: check phase file emptiness, nudge via tmux (max 2)
- agent-session.sh: pass phase_file + session to stop hook, clean up
nudge counter on session teardown
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Rename the CTA link from 'Watch it work' to 'See active issues' so
visitors know the link leads to the issue tracker, not a demo or live view.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Source the canonical read_phase() from lib/agent-session.sh instead of
maintaining a local copy that could drift.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The BACKLOG_NUMS associative array was built to track which issue numbers
are in the backlog, but the DFS cycle-detection code used NODE_COLOR as
a membership guard instead. This meant deps pointing to non-backlog issues
were only skipped by coincidence (they weren't in NODE_COLOR either).
Three changes:
- Remove SC2034 suppression since BACKLOG_NUMS is now actually queried
- Initialize NODE_COLOR from BACKLOG_NUMS keys (all backlog issues) instead
of DEPS_OF keys (only issues with dependencies), so every backlog issue
gets a proper DFS color
- Replace the NODE_COLOR membership check with BACKLOG_NUMS in the DFS, so
the guard explicitly asks "is this dep a backlog issue?" rather than
relying on NODE_COLOR initialization as a proxy
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Pipeline #936 (same commit) passed all steps. #935 agent-smoke
failed intermittently on BusyBox awk function resolution.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Root cause: two code paths injected merge curl commands into Claude's
session (review-poll.sh APPROVE injection and dev-agent.sh prompt
instructions). The PreToolUse guard correctly blocked these, causing
Claude to write PHASE:escalate instead of merging.
The bash phase handler already handles merging via do_merge() — which
runs outside Claude tool use and is not subject to the guard. Remove
the merge/close curl instructions from both Claude-facing prompts so
the bash orchestrator handles merges as intended.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The sed watermark-update pattern stripped the closing --> from 9 of 10
AGENTS.md files, making entire file bodies invisible in rendered markdown.
Fix by appending --> to the affected lines.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Update AGENTS.md watermarks to current HEAD (9ec0c02)
- lib/AGENTS.md: document parse-deps.sh inline scan now skips fenced
code blocks to prevent false positives from code examples in issue bodies
- No blocked issues to review
- Pending actions: none
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The agent-smoke function resolution check flags underscore-containing
identifiers as potential undefined bash functions. Rename in_code to
incode to match the convention used by the existing capture variable.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
