LOGFILE=/var/chat/chat.log is unwritable on read-only rootfs; move to
/tmp/chat.log (tmpfs-backed). Add CapDrop=ALL assertion to verify script
so removing cap_drop from compose is caught.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Introduce FORGE_API_BASE (bare API root without repo path) in lib/env.sh
and lib/load-project.sh. Replace all cross-repo curl calls in
architect-run.sh that incorrectly used ${FORGE_API}/repos/${FORGE_OPS_REPO}
(which expanded to .../repos/owner/repo/repos/owner/ops-repo) with
${FORGE_API_BASE}/repos/${FORGE_OPS_REPO}.
Also fix a same-repo label URL that duplicated the repos segment.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three fixes:
1. architect-run.sh:722 — extract `.result` not `.content` from claude JSON
output. All other callers (dev-agent, formula-session) use `.result`;
this was the direct cause of every pitch being empty.
2. lib/agent-sdk.sh — reset `_AGENT_LAST_OUTPUT=""` at the top of each
`agent_run` call so stale data from a prior invocation can't bleed
into the next caller when claude crashes or returns empty.
3. lib/agent-sdk.sh — scope the diagnostics file by `$LOG_AGENT` instead
of hardcoding `dev/`. Concurrent agents (architect, gardener, planner,
predictor) no longer clobber each other's diag output.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The CI smoke test's get_candidates awk pattern falsely matches
underscore-containing variable names (like digested_files+=) as
unresolved function calls. Rename to batchfiles to avoid the match.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add digest-specific timeout (PROFILE_DIGEST_TIMEOUT, default 300s) instead
of relying on the global 2h CLAUDE_TIMEOUT
- Cap journals per digest run (PROFILE_DIGEST_MAX_BATCH, default 5) to bound
prompt size and let remaining journals drain over subsequent runs
- Only archive the journals that were actually included in the batch, not all
- On timeout/failure, preserve previous lessons-learned.md instead of leaving
a near-empty file — journals stay unarchived for retry on next run
- Detect suspiciously small output (<=16 bytes) as failed digestion
- Add PROFILE_DIGEST_THRESHOLD env var (default 10) for digest trigger
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Removed state=closed filter so all issues with "Decomposed from #N" are found
- Per-issue state check in all_subissues_closed() correctly handles open/closed
agent_run() stores its output in $_AGENT_LAST_OUTPUT but never emits
it to stdout. The old subshell capture always yielded an empty string,
so pitches silently failed even after the signature fix.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
agent_run() now adds -p, --output-format, --max-turns, --dangerously-skip-permissions,
and --model internally. The old call site passed these flags explicitly, causing the
prompt to be parsed as "-p" and claude to error with "Input must be provided".
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Use $'\n' instead of literal \n in summary comment builder
- Query closed issues in Method 1 to find sub-issues regardless of state
- Document automated vision issue closure lifecycle in AGENTS.md
Gate both flock call sites (agent_run main invocation and nudge) behind
CLAUDE_EXTERNAL_LOCK env var. Default off — the native Claude Code
proper-lockfile-based OAuth refresh lock handles concurrency. Set
CLAUDE_EXTERNAL_LOCK=1 to re-enable the external flock for rollback.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Root cause: review formula had no infrastructure-file-specific checklist and
no scope discipline check. The reviewer treated a docker-compose.yml rewrite
the same as any code change, and lessons-learned biased toward approval.
Changes:
- Add step 3c (infrastructure file review) to formulas/review-pr.toml:
compose-specific checklist for volumes, bind mounts, env vars, restart
policy, security options
- Add step 3d (scope discipline) to formulas/review-pr.toml: compare
actual diff size against issue scope, block on infra-file scope violations
- Add investigation writeup in docs/
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
