Merge pull request 'fix: fix: planner runs directly from cron — no action issues (#359)' (#384) from fix/issue-359 into main

This commit is contained in:
johba 2026-03-20 15:01:33 +01:00
commit 3e36709f92
8 changed files with 374 additions and 184 deletions

View file

@ -91,7 +91,7 @@ echo "=== 2/2 Function resolution ==="
# Functions provided by shared lib files (available to all agent scripts via source) # Functions provided by shared lib files (available to all agent scripts via source)
LIB_FUNS=$( LIB_FUNS=$(
for f in lib/agent-session.sh lib/env.sh lib/ci-helpers.sh lib/load-project.sh lib/file-action-issue.sh; do for f in lib/agent-session.sh lib/env.sh lib/ci-helpers.sh lib/load-project.sh lib/file-action-issue.sh lib/formula-session.sh; do
if [ -f "$f" ]; then get_fns "$f"; fi if [ -f "$f" ]; then get_fns "$f"; fi
done | sort -u done | sort -u
) )
@ -162,7 +162,7 @@ check_script gardener/gardener-poll.sh
check_script gardener/gardener-run.sh check_script gardener/gardener-run.sh
check_script review/review-pr.sh check_script review/review-pr.sh
check_script review/review-poll.sh check_script review/review-poll.sh
check_script planner/planner-poll.sh check_script planner/planner-run.sh
check_script supervisor/supervisor-poll.sh check_script supervisor/supervisor-poll.sh
check_script supervisor/update-prompt.sh check_script supervisor/update-prompt.sh
check_script vault/vault-agent.sh check_script vault/vault-agent.sh

View file

@ -18,7 +18,8 @@ disinto/
├── review/ review-poll.sh, review-pr.sh — PR review ├── review/ review-poll.sh, review-pr.sh — PR review
├── gardener/ gardener-run.sh — files action issue for run-gardener formula ├── gardener/ gardener-run.sh — files action issue for run-gardener formula
│ gardener-poll.sh, gardener-agent.sh — recipe engine + grooming │ gardener-poll.sh, gardener-agent.sh — recipe engine + grooming
├── planner/ planner-poll.sh — files action issue for run-planner formula ├── planner/ planner-run.sh — direct cron executor for run-planner formula
│ planner/journal/ — daily raw logs from each planner run
│ prediction-poll.sh, prediction-agent.sh — evidence-based predictions │ prediction-poll.sh, prediction-agent.sh — evidence-based predictions
├── supervisor/ supervisor-poll.sh — health monitoring ├── supervisor/ supervisor-poll.sh — health monitoring
├── vault/ vault-poll.sh, vault-agent.sh, vault-fire.sh — action gating ├── vault/ vault-poll.sh, vault-agent.sh, vault-fire.sh — action gating
@ -154,36 +155,42 @@ P3 (degraded PRs, circular deps, stale deps), P4 (housekeeping).
### Planner (`planner/`) ### Planner (`planner/`)
**Role**: Five-phase strategic planning, executed as an action formula. **Role**: Strategic planning, executed directly from cron via tmux + Claude.
Phase 0 (preflight): pull latest code, load persistent memory from Phase 0 (preflight): pull latest code, load persistent memory from
`planner/MEMORY.md`. Phase 1: update the AGENTS.md documentation tree to `planner/MEMORY.md`. Phase 1 (prediction-triage): triage
reflect recent code changes (fast-track PR). Phase 1.5: triage
`prediction/unreviewed` issues filed by the [Predictor](#predictor-planner) — `prediction/unreviewed` issues filed by the [Predictor](#predictor-planner) —
for each prediction: promote to action, promote to backlog, watch (relabel to for each prediction: promote to action, promote to backlog, watch (relabel to
prediction/backlog), or dismiss with reasoning. Promoted predictions compete prediction/backlog), or dismiss with reasoning. Promoted predictions compete
with vision gaps for the per-cycle issue limit. Phase 2: strategic planning with vision gaps for the per-cycle issue limit. Phase 2 (strategic-planning):
via resource+leverage gap analysis — reasons about VISION.md, RESOURCES.md, resource+leverage gap analysis — reasons about VISION.md, RESOURCES.md,
formula catalog, and project state to create up to 5 total issues (including formula catalog, and project state to create up to 5 total issues (including
promotions) prioritized by leverage. Phase 3: persist learnings to promotions) prioritized by leverage. Phase 3 (journal-and-memory): write
`planner/MEMORY.md`. daily journal entry (committed to git) and update `planner/MEMORY.md`
(gitignored, local only). Phase 4 (commit-and-pr): one commit with all file
changes, push, create PR. AGENTS.md maintenance is handled by the
[Gardener](#gardener-gardener).
**Trigger**: `planner-poll.sh` runs weekly via cron. It files an `action` **Trigger**: `planner-run.sh` runs weekly via cron. It creates a tmux session
issue referencing `formulas/run-planner.toml`; the [action-agent](#action-action) with `claude --model opus`, injects `formulas/run-planner.toml` as context,
picks it up and executes the planning steps in an interactive Claude tmux session. monitors the phase file, and cleans up on completion or timeout. No action
issues — the planner is a nervous system component, not work.
**Key files**: **Key files**:
- `planner/planner-poll.sh` — Cron wrapper: memory guard, dedup check, files action issue - `planner/planner-run.sh` — Cron wrapper + orchestrator: lock, memory guard,
- `formulas/run-planner.toml` — Execution spec: five steps (preflight, agents-update, sources disinto project config, creates tmux session, injects formula prompt,
triage-predictions, strategic-planning, memory-update) with `needs` dependencies. monitors phase file, handles crash recovery, cleans up
Steps 2 and 3 are independent; step 4 depends on both. Claude executes all steps - `formulas/run-planner.toml` — Execution spec: five steps (preflight,
in a single interactive session with tool access prediction-triage, strategic-planning, journal-and-memory, commit-and-pr)
with `needs` dependencies. Claude executes all steps in a single interactive
session with tool access
- `planner/MEMORY.md` — Persistent memory across runs (gitignored, local only) - `planner/MEMORY.md` — Persistent memory across runs (gitignored, local only)
- `planner/journal/*.md` — Daily raw logs from each planner run (committed to git)
**Future direction**: The [Predictor](#predictor-planner) already reads `evidence/` JSON and files prediction issues for the planner to triage. The next step is evidence-gated deployment (see `docs/EVIDENCE-ARCHITECTURE.md`): replacing human "ship it" decisions with automated gates across dimensions (holdout, red-team, user-test, evolution fitness, protocol metrics, funnel). Not yet implemented. **Future direction**: The [Predictor](#predictor-planner) already reads `evidence/` JSON and files prediction issues for the planner to triage. The next step is evidence-gated deployment (see `docs/EVIDENCE-ARCHITECTURE.md`): replacing human "ship it" decisions with automated gates across dimensions (holdout, red-team, user-test, evolution fitness, protocol metrics, funnel). Not yet implemented.
**Environment variables consumed** (by the action-agent session): **Environment variables consumed**:
- `CODEBERG_TOKEN`, `CODEBERG_REPO`, `CODEBERG_API`, `PROJECT_NAME`, `PROJECT_REPO_ROOT` - `CODEBERG_TOKEN`, `CODEBERG_REPO`, `CODEBERG_API`, `PROJECT_NAME`, `PROJECT_REPO_ROOT`
- `PRIMARY_BRANCH` - `PRIMARY_BRANCH`, `CLAUDE_MODEL` (set to opus by planner-run.sh)
- `MATRIX_TOKEN`, `MATRIX_ROOM_ID`, `MATRIX_HOMESERVER` - `MATRIX_TOKEN`, `MATRIX_ROOM_ID`, `MATRIX_HOMESERVER`
### Predictor (`planner/`) ### Predictor (`planner/`)
@ -284,7 +291,8 @@ sourced as needed.
| `lib/load-project.sh` | Parses a `projects/*.toml` file into env vars (`PROJECT_NAME`, `CODEBERG_REPO`, `WOODPECKER_REPO_ID`, monitoring toggles, Matrix config, etc.). | env.sh (when `PROJECT_TOML` is set), supervisor-poll (per-project iteration) | | `lib/load-project.sh` | Parses a `projects/*.toml` file into env vars (`PROJECT_NAME`, `CODEBERG_REPO`, `WOODPECKER_REPO_ID`, monitoring toggles, Matrix config, etc.). | env.sh (when `PROJECT_TOML` is set), supervisor-poll (per-project iteration) |
| `lib/parse-deps.sh` | Extracts dependency issue numbers from an issue body (stdin → stdout, one number per line). Matches `## Dependencies` / `## Depends on` / `## Blocked by` sections and inline `depends on #N` patterns. Not sourced — executed via `bash lib/parse-deps.sh`. | dev-poll, supervisor-poll | | `lib/parse-deps.sh` | Extracts dependency issue numbers from an issue body (stdin → stdout, one number per line). Matches `## Dependencies` / `## Depends on` / `## Blocked by` sections and inline `depends on #N` patterns. Not sourced — executed via `bash lib/parse-deps.sh`. | dev-poll, supervisor-poll |
| `lib/matrix_listener.sh` | Long-poll Matrix sync daemon. Dispatches thread replies to the correct agent via well-known files (`/tmp/{agent}-escalation-reply`). Handles supervisor, gardener, dev, review, vault, and action reply routing. Run as systemd service. | Standalone daemon | | `lib/matrix_listener.sh` | Long-poll Matrix sync daemon. Dispatches thread replies to the correct agent via well-known files (`/tmp/{agent}-escalation-reply`). Handles supervisor, gardener, dev, review, vault, and action reply routing. Run as systemd service. | Standalone daemon |
| `lib/file-action-issue.sh` | `file_action_issue()` — dedup check, label lookup, and issue creation for formula-driven cron wrappers. Sets `FILED_ISSUE_NUM` on success. | gardener-run.sh, planner-poll.sh | | `lib/formula-session.sh` | `acquire_cron_lock()`, `check_memory()`, `load_formula()`, `build_context_block()`, `start_formula_session()`, `formula_phase_callback()` — shared helpers for formula-driven cron agents (lock, memory guard, formula loading, tmux session, crash recovery). | planner-run.sh |
| `lib/file-action-issue.sh` | `file_action_issue()` — dedup check, label lookup, and issue creation for formula-driven cron wrappers. Sets `FILED_ISSUE_NUM` on success. | gardener-run.sh |
| `lib/agent-session.sh` | Shared tmux + Claude session helpers: `create_agent_session()`, `inject_formula()`, `agent_wait_for_claude_ready()`, `agent_inject_into_session()`, `agent_kill_session()`, `monitor_phase_loop()`, `read_phase()`. `create_agent_session(session, workdir, [phase_file])` optionally installs a PostToolUse hook (matcher `Bash\|Write`) that detects phase file writes in real-time — when Claude writes to the phase file, the hook writes a marker so `monitor_phase_loop` reacts on the next poll instead of waiting for mtime changes. Also installs a StopFailure hook (matcher `rate_limit\|server_error\|authentication_failed\|billing_error`) that writes `PHASE:failed` with an `api_error` reason to the phase file and touches the phase-changed marker, so the orchestrator discovers API errors within one poll cycle instead of waiting for idle timeout. When `MATRIX_THREAD_ID` is exported, also installs a Stop hook (`on-stop-matrix.sh`) that streams each Claude response to the Matrix thread. `monitor_phase_loop` sets `_MONITOR_LOOP_EXIT` to one of: `done`, `idle_timeout`, `idle_prompt` (Claude returned to `` for 3 consecutive polls without writing any phase — callback invoked with `PHASE:failed`, session already dead), `crashed`, or a `PHASE:*` string. Agents must handle `idle_prompt` in both their callback and their post-loop exit handler. | dev-agent.sh, gardener-agent.sh, action-agent.sh | | `lib/agent-session.sh` | Shared tmux + Claude session helpers: `create_agent_session()`, `inject_formula()`, `agent_wait_for_claude_ready()`, `agent_inject_into_session()`, `agent_kill_session()`, `monitor_phase_loop()`, `read_phase()`. `create_agent_session(session, workdir, [phase_file])` optionally installs a PostToolUse hook (matcher `Bash\|Write`) that detects phase file writes in real-time — when Claude writes to the phase file, the hook writes a marker so `monitor_phase_loop` reacts on the next poll instead of waiting for mtime changes. Also installs a StopFailure hook (matcher `rate_limit\|server_error\|authentication_failed\|billing_error`) that writes `PHASE:failed` with an `api_error` reason to the phase file and touches the phase-changed marker, so the orchestrator discovers API errors within one poll cycle instead of waiting for idle timeout. When `MATRIX_THREAD_ID` is exported, also installs a Stop hook (`on-stop-matrix.sh`) that streams each Claude response to the Matrix thread. `monitor_phase_loop` sets `_MONITOR_LOOP_EXIT` to one of: `done`, `idle_timeout`, `idle_prompt` (Claude returned to `` for 3 consecutive polls without writing any phase — callback invoked with `PHASE:failed`, session already dead), `crashed`, or a `PHASE:*` string. Agents must handle `idle_prompt` in both their callback and their post-loop exit handler. | dev-agent.sh, gardener-agent.sh, action-agent.sh |
--- ---

View file

@ -1,13 +1,18 @@
# formulas/run-planner.toml — Strategic planning formula # formulas/run-planner.toml — Strategic planning formula
# #
# Executed by the action-agent via cron-filed action issues. # Executed directly by planner-run.sh via cron — no action issues.
# planner-poll.sh files an action issue referencing this formula weekly; # planner-run.sh creates a tmux session with Claude (opus) and injects
# action-poll.sh picks it up and spawns a tmux session where Claude # this formula as context. Claude executes all steps autonomously.
# executes these steps autonomously. #
# Steps: preflight → prediction-triage → strategic-planning
# → journal-and-memory → commit-and-pr
#
# AGENTS.md maintenance is handled by the gardener (#246).
# All git writes (journal entry) happen in one commit at the end.
name = "run-planner" name = "run-planner"
description = "Strategic planning: update docs, triage predictions, resource+leverage gap analysis" description = "Strategic planning: triage predictions, resource+leverage gap analysis, journal"
version = 1 version = 2
model = "opus" model = "opus"
[context] [context]
@ -27,7 +32,7 @@ Set up the working environment for this planning run.
git checkout "$PRIMARY_BRANCH" --quiet git checkout "$PRIMARY_BRANCH" --quiet
git pull --ff-only origin "$PRIMARY_BRANCH" --quiet git pull --ff-only origin "$PRIMARY_BRANCH" --quiet
3. Record the current HEAD SHA you will need it for AGENTS.md watermarks: 3. Record the current HEAD SHA:
HEAD_SHA=$(git rev-parse HEAD) HEAD_SHA=$(git rev-parse HEAD)
echo "$HEAD_SHA" > /tmp/planner-head-sha echo "$HEAD_SHA" > /tmp/planner-head-sha
@ -37,59 +42,7 @@ Set up the working environment for this planning run.
""" """
[[steps]] [[steps]]
id = "agents-update" id = "prediction-triage"
title = "Update AGENTS.md documentation tree"
description = """
Check all AGENTS.md files for staleness and update any that are outdated.
1. Read the HEAD SHA from preflight:
HEAD_SHA=$(cat /tmp/planner-head-sha)
2. Find all AGENTS.md files:
find "$PROJECT_REPO_ROOT" -name "AGENTS.md" -not -path "*/.git/*"
3. For each file, read the watermark from line 1:
<!-- last-reviewed: <sha> -->
4. Check for changes since the watermark:
git log --oneline <watermark>..HEAD -- <directory>
If zero changes, the file is current skip it.
5. For stale files:
- Read the AGENTS.md and the source files in that directory
- Update the documentation to reflect code changes since the watermark
- Set the watermark to the HEAD SHA from the preflight step
- Conventions: max ~200 lines, architecture and WHY not implementation details
6. If you made changes:
a. Create a branch:
git checkout -B "chore/planner-agents-$(date -u +%Y%m%d)"
b. Stage only AGENTS.md files:
find . -name "AGENTS.md" -not -path "./.git/*" -exec git add {} +
c. Commit:
git commit -m "chore: planner update AGENTS.md tree"
d. Push:
git push -f origin "chore/planner-agents-$(date -u +%Y%m%d)"
e. Create a PR (failure here is non-fatal log and continue):
curl -sf -X POST \
-H "Authorization: token $CODEBERG_TOKEN" \
-H "Content-Type: application/json" \
"$CODEBERG_API/pulls" \
-d '{"title":"chore: planner update AGENTS.md tree",
"head":"<branch>","base":"<primary-branch>",
"body":"Automated AGENTS.md update — review-agent fast-tracks doc-only PRs."}'
f. Return to primary branch:
git checkout "$PRIMARY_BRANCH"
7. If no AGENTS.md files need updating, skip this step entirely.
CRITICAL: If this step fails for any reason, log the failure and move on.
Do NOT let an AGENTS.md failure prevent prediction triage or strategic planning.
"""
needs = ["preflight"]
[[steps]]
id = "triage-predictions"
title = "Triage prediction/unreviewed issues" title = "Triage prediction/unreviewed issues"
description = """ description = """
Triage prediction issues filed by the predictor (goblin). Triage prediction issues filed by the predictor (goblin).
@ -213,7 +166,7 @@ Read these inputs:
- Open issues (fetched via API) what's already planned - Open issues (fetched via API) what's already planned
- $FACTORY_ROOT/metrics/supervisor-metrics.jsonl operational trends (may not exist) - $FACTORY_ROOT/metrics/supervisor-metrics.jsonl operational trends (may not exist)
- Planner memory (loaded in preflight) - Planner memory (loaded in preflight)
- Promoted predictions from triage-predictions (these count toward the - Promoted predictions from prediction-triage (these count toward the
per-cycle issue limit they compete with vision gaps for priority) per-cycle issue limit they compete with vision gaps for priority)
Reason through these five questions: Reason through these five questions:
@ -238,7 +191,7 @@ Reason through these five questions:
Things that depend on blocked resources or aren't high-leverage Things that depend on blocked resources or aren't high-leverage
right now. Do NOT create issues for these. right now. Do NOT create issues for these.
Then create up to 5 issues total (including promotions from triage-predictions), Then create up to 5 issues total (including promotions from prediction-triage),
prioritized by leverage: prioritized by leverage:
For formula-matching gaps, include YAML front matter in the body: For formula-matching gaps, include YAML front matter in the body:
@ -271,13 +224,42 @@ Rules:
If there are no gaps, note that the backlog is aligned with the vision. If there are no gaps, note that the backlog is aligned with the vision.
""" """
needs = ["agents-update", "triage-predictions"] needs = ["prediction-triage"]
[[steps]] [[steps]]
id = "memory-update" id = "journal-and-memory"
title = "Persist learnings to planner/MEMORY.md" title = "Write journal entry and update planner memory"
description = """ description = """
Reflect on this planning run and write the updated memory file. Two outputs from this step:
### 1. Journal entry (committed to git)
Create a daily journal file at:
$FACTORY_ROOT/planner/journal/$(date -u +%Y-%m-%d).md
If the file already exists (multiple runs per day), append a new section
with a timestamp header.
Format:
# Planner run — YYYY-MM-DD HH:MM UTC
## Predictions triaged
- #NNN: PROMOTE_ACTION/PROMOTE_BACKLOG/WATCH/DISMISS — reasoning
(or "No unreviewed predictions" if none)
## Issues created
- #NNN: title — why
(or "No new issues — backlog aligned with vision" if none)
## Observations
- Key patterns, resource state, metric trends noticed during this run
## Deferred
- Items considered but deferred, and why
Keep each entry concise 30-50 lines max.
### 2. Memory update (gitignored, local only)
Write to: $FACTORY_ROOT/planner/MEMORY.md (replace the entire file) Write to: $FACTORY_ROOT/planner/MEMORY.md (replace the entire file)
@ -298,3 +280,46 @@ Rules:
Format: simple markdown with dated sections. Format: simple markdown with dated sections.
""" """
needs = ["strategic-planning"] needs = ["strategic-planning"]
[[steps]]
id = "commit-and-pr"
title = "One commit with all file changes, push, create PR"
description = """
Collect all file changes from this run into a single commit.
API calls (issue creation, prediction triage) already happened during the
run only file changes (journal entries) need the PR.
1. Check for staged or unstaged changes:
cd "$PROJECT_REPO_ROOT"
git status --porcelain
If there are no file changes, skip this entire step no commit, no PR.
2. If there are changes:
a. Create a branch:
BRANCH="chore/planner-$(date -u +%Y%m%d-%H%M)"
git checkout -B "$BRANCH"
b. Stage journal entries:
git add planner/journal/ 2>/dev/null || true
c. Stage any other tracked files modified during the run:
git add -u
d. Check if there is anything to commit:
git diff --cached --quiet && echo "Nothing staged" && skip
e. Commit:
git commit -m "chore: planner run $(date -u +%Y-%m-%d)"
f. Push:
git push -u origin "$BRANCH"
g. Create a PR:
curl -sf -X POST \
-H "Authorization: token $CODEBERG_TOKEN" \
-H "Content-Type: application/json" \
"$CODEBERG_API/pulls" \
-d '{"title":"chore: planner run journal",
"head":"<branch>","base":"<primary-branch>",
"body":"Automated planner run — journal entry from strategic planning session."}'
h. Return to primary branch:
git checkout "$PRIMARY_BRANCH"
3. If the PR creation fails, log and continue the journal is committed locally.
"""
needs = ["journal-and-memory"]

View file

@ -29,6 +29,8 @@ export PROJECT_TOML="${1:-}"
source "$FACTORY_ROOT/lib/env.sh" source "$FACTORY_ROOT/lib/env.sh"
# shellcheck source=../lib/agent-session.sh # shellcheck source=../lib/agent-session.sh
source "$FACTORY_ROOT/lib/agent-session.sh" source "$FACTORY_ROOT/lib/agent-session.sh"
# shellcheck source=../lib/formula-session.sh
source "$FACTORY_ROOT/lib/formula-session.sh"
LOG_FILE="$SCRIPT_DIR/gardener.log" LOG_FILE="$SCRIPT_DIR/gardener.log"
SESSION_NAME="gardener-${PROJECT_NAME}" SESSION_NAME="gardener-${PROJECT_NAME}"
@ -275,32 +277,15 @@ matrix_send "gardener" "🌱 Gardener session started for ${CODEBERG_REPO}" 2>/d
# ── Phase monitoring loop ───────────────────────────────────────────────── # ── Phase monitoring loop ─────────────────────────────────────────────────
log "Monitoring phase file: ${PHASE_FILE}" log "Monitoring phase file: ${PHASE_FILE}"
GARDENER_CRASH_COUNT=0 _FORMULA_CRASH_COUNT=0
gardener_phase_callback() { gardener_phase_callback() {
local phase="$1" # Gardener-specific cleanup before shared crash recovery
log "phase: ${phase}" if [ "$1" = "PHASE:crashed" ]; then
case "$phase" in rm -f "$RESULT_FILE"
PHASE:crashed) touch "$RESULT_FILE"
if [ "$GARDENER_CRASH_COUNT" -gt 0 ]; then fi
log "ERROR: session crashed again after recovery — giving up" formula_phase_callback "$1"
return 0
fi
GARDENER_CRASH_COUNT=$((GARDENER_CRASH_COUNT + 1))
log "WARNING: tmux session died unexpectedly — attempting recovery"
rm -f "$RESULT_FILE"
touch "$RESULT_FILE"
if create_agent_session "${_MONITOR_SESSION:-$SESSION_NAME}" "$PROJECT_REPO_ROOT" "$PHASE_FILE" 2>/dev/null; then
agent_inject_into_session "${_MONITOR_SESSION:-$SESSION_NAME}" "$PROMPT"
log "Recovery session started"
else
log "ERROR: could not restart session after crash"
fi
;;
PHASE:done|PHASE:failed|PHASE:needs_human|PHASE:merged)
agent_kill_session "${_MONITOR_SESSION:-$SESSION_NAME}"
;;
esac
} }
monitor_phase_loop "$PHASE_FILE" 7200 "gardener_phase_callback" monitor_phase_loop "$PHASE_FILE" 7200 "gardener_phase_callback"

125
lib/formula-session.sh Normal file
View file

@ -0,0 +1,125 @@
#!/usr/bin/env bash
# formula-session.sh — Shared helpers for formula-driven cron agents
#
# Provides reusable functions for the common cron-wrapper + tmux-session
# pattern used by planner-run.sh and gardener-agent.sh.
#
# Functions:
# acquire_cron_lock LOCK_FILE — PID lock with stale cleanup
# check_memory [MIN_MB] — skip if available RAM too low
# load_formula FORMULA_FILE — sets FORMULA_CONTENT
# build_context_block FILE [FILE ...] — sets CONTEXT_BLOCK
# start_formula_session SESSION WORKDIR PHASE_FILE — create tmux + claude
# formula_phase_callback PHASE — standard crash-recovery callback
#
# Requires: lib/agent-session.sh sourced first (for create_agent_session,
# agent_kill_session, agent_inject_into_session).
# Globals used by formula_phase_callback: SESSION_NAME, PHASE_FILE,
# PROJECT_REPO_ROOT, PROMPT (set by the calling script).
# ── Cron guards ──────────────────────────────────────────────────────────
# acquire_cron_lock LOCK_FILE
# Acquires a PID lock. Exits 0 if another instance is running.
# Sets an EXIT trap to clean up the lock file.
acquire_cron_lock() {
_CRON_LOCK_FILE="$1"
if [ -f "$_CRON_LOCK_FILE" ]; then
local lock_pid
lock_pid=$(cat "$_CRON_LOCK_FILE" 2>/dev/null || true)
if [ -n "$lock_pid" ] && kill -0 "$lock_pid" 2>/dev/null; then
log "run: already running (PID $lock_pid)"
exit 0
fi
rm -f "$_CRON_LOCK_FILE"
fi
echo $$ > "$_CRON_LOCK_FILE"
trap 'rm -f "$_CRON_LOCK_FILE"' EXIT
}
# check_memory [MIN_MB]
# Exits 0 (skip) if available memory is below MIN_MB (default 2000).
check_memory() {
local min_mb="${1:-2000}"
local avail_mb
avail_mb=$(free -m | awk '/Mem:/{print $7}')
if [ "${avail_mb:-0}" -lt "$min_mb" ]; then
log "run: skipping — only ${avail_mb}MB available (need ${min_mb})"
exit 0
fi
}
# ── Formula loading ──────────────────────────────────────────────────────
# load_formula FORMULA_FILE
# Reads formula TOML into FORMULA_CONTENT. Exits 1 if missing.
load_formula() {
local formula_file="$1"
if [ ! -f "$formula_file" ]; then
log "ERROR: formula not found: $formula_file"
exit 1
fi
# shellcheck disable=SC2034 # consumed by the calling script
FORMULA_CONTENT=$(cat "$formula_file")
}
# build_context_block FILE [FILE ...]
# Reads each file from $PROJECT_REPO_ROOT and builds CONTEXT_BLOCK.
build_context_block() {
CONTEXT_BLOCK=""
local ctx ctx_path
for ctx in "$@"; do
ctx_path="${PROJECT_REPO_ROOT}/${ctx}"
if [ -f "$ctx_path" ]; then
CONTEXT_BLOCK="${CONTEXT_BLOCK}
### ${ctx}
$(cat "$ctx_path")
"
fi
done
}
# ── Session management ───────────────────────────────────────────────────
# start_formula_session SESSION WORKDIR PHASE_FILE
# Kills stale session, resets phase file, creates new tmux + claude session.
# Returns 0 on success, 1 on failure.
start_formula_session() {
local session="$1" workdir="$2" phase_file="$3"
agent_kill_session "$session"
rm -f "$phase_file"
log "Creating tmux session: ${session}"
if ! create_agent_session "$session" "$workdir" "$phase_file"; then
log "ERROR: failed to create tmux session ${session}"
return 1
fi
}
# formula_phase_callback PHASE
# Standard crash-recovery phase callback for formula sessions.
# Requires globals: SESSION_NAME, PHASE_FILE, PROJECT_REPO_ROOT, PROMPT.
# Uses _FORMULA_CRASH_COUNT (auto-initialized) for single-retry limit.
# shellcheck disable=SC2154 # SESSION_NAME, PHASE_FILE, PROJECT_REPO_ROOT, PROMPT set by caller
formula_phase_callback() {
local phase="$1"
log "phase: ${phase}"
case "$phase" in
PHASE:crashed)
if [ "${_FORMULA_CRASH_COUNT:-0}" -gt 0 ]; then
log "ERROR: session crashed again after recovery — giving up"
return 0
fi
_FORMULA_CRASH_COUNT=$(( ${_FORMULA_CRASH_COUNT:-0} + 1 ))
log "WARNING: tmux session died unexpectedly — attempting recovery"
if create_agent_session "${_MONITOR_SESSION:-$SESSION_NAME}" "$PROJECT_REPO_ROOT" "$PHASE_FILE" 2>/dev/null; then
agent_inject_into_session "${_MONITOR_SESSION:-$SESSION_NAME}" "$PROMPT"
log "Recovery session started"
else
log "ERROR: could not restart session after crash"
fi
;;
PHASE:done|PHASE:failed|PHASE:needs_human|PHASE:merged)
agent_kill_session "${_MONITOR_SESSION:-$SESSION_NAME}"
;;
esac
}

0
planner/journal/.gitkeep Normal file
View file

View file

@ -1,73 +0,0 @@
#!/usr/bin/env bash
# =============================================================================
# planner-poll.sh — Cron wrapper: files action issue for run-planner formula
#
# Runs weekly (or on-demand). Guards against concurrent runs and low memory.
# Files an action issue referencing formulas/run-planner.toml; the action-agent
# picks it up and executes the planning steps in an interactive Claude session.
# =============================================================================
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
FACTORY_ROOT="$(dirname "$SCRIPT_DIR")"
# shellcheck source=../lib/env.sh
source "$FACTORY_ROOT/lib/env.sh"
# shellcheck source=../lib/file-action-issue.sh
source "$FACTORY_ROOT/lib/file-action-issue.sh"
LOG_FILE="$SCRIPT_DIR/planner.log"
LOCK_FILE="/tmp/planner-poll.lock"
log() { echo "[$(date -u +%Y-%m-%dT%H:%M:%S)Z] $*" >> "$LOG_FILE"; }
# ── Lock ──────────────────────────────────────────────────────────────────
if [ -f "$LOCK_FILE" ]; then
LOCK_PID=$(cat "$LOCK_FILE" 2>/dev/null || true)
if [ -n "$LOCK_PID" ] && kill -0 "$LOCK_PID" 2>/dev/null; then
log "poll: planner running (PID $LOCK_PID)"
exit 0
fi
rm -f "$LOCK_FILE"
fi
echo $$ > "$LOCK_FILE"
trap 'rm -f "$LOCK_FILE"' EXIT
# ── Memory guard ──────────────────────────────────────────────────────────
AVAIL_MB=$(free -m | awk '/Mem:/{print $7}')
if [ "${AVAIL_MB:-0}" -lt 2000 ]; then
log "poll: skipping — only ${AVAIL_MB}MB available (need 2000)"
exit 0
fi
log "--- Planner poll start ---"
# ── File action issue for run-planner formula ─────────────────────────────
ISSUE_BODY="---
formula: run-planner
model: opus
---
Periodic strategic planning run. The action-agent reads \`formulas/run-planner.toml\`
and executes the five phases: preflight, AGENTS.md update, prediction triage,
strategic planning (resource+leverage gap analysis), and memory update.
Filed automatically by \`planner-poll.sh\`."
_rc=0
file_action_issue "run-planner" "action: run-planner — periodic strategic planning" "$ISSUE_BODY" || _rc=$?
case "$_rc" in
0) ;;
1) log "poll: open run-planner action issue already exists — skipping"
log "--- Planner poll done ---"
exit 0 ;;
2) log "ERROR: 'action' label not found — cannot file planner issue"
exit 1 ;;
*) log "ERROR: failed to create action issue for run-planner"
exit 1 ;;
esac
log "Filed action issue #${FILED_ISSUE_NUM} for run-planner formula"
matrix_send "planner" "Filed action #${FILED_ISSUE_NUM}: run-planner — periodic strategic planning" 2>/dev/null || true
log "--- Planner poll done ---"

120
planner/planner-run.sh Executable file
View file

@ -0,0 +1,120 @@
#!/usr/bin/env bash
# =============================================================================
# planner-run.sh — Cron wrapper: direct planner execution via Claude + formula
#
# Runs weekly (or on-demand). Guards against concurrent runs and low memory.
# Creates a tmux session with Claude (opus) reading formulas/run-planner.toml.
# No action issues — the planner is a nervous system component, not work.
#
# The planner plans for ALL projects (harb + disinto) but is itself disinto
# infrastructure — always sources projects/disinto.toml.
# =============================================================================
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
FACTORY_ROOT="$(dirname "$SCRIPT_DIR")"
# Source disinto project config — the planner is disinto infrastructure
export PROJECT_TOML="$FACTORY_ROOT/projects/disinto.toml"
# shellcheck source=../lib/env.sh
source "$FACTORY_ROOT/lib/env.sh"
# shellcheck source=../lib/agent-session.sh
source "$FACTORY_ROOT/lib/agent-session.sh"
# shellcheck source=../lib/formula-session.sh
source "$FACTORY_ROOT/lib/formula-session.sh"
LOG_FILE="$SCRIPT_DIR/planner.log"
SESSION_NAME="planner-${PROJECT_NAME}"
PHASE_FILE="/tmp/planner-session-${PROJECT_NAME}.phase"
# shellcheck disable=SC2034 # read by monitor_phase_loop in lib/agent-session.sh
PHASE_POLL_INTERVAL=15
log() { echo "[$(date -u +%Y-%m-%dT%H:%M:%S)Z] $*" >> "$LOG_FILE"; }
# ── Guards ────────────────────────────────────────────────────────────────
acquire_cron_lock "/tmp/planner-run.lock"
check_memory 2000
log "--- Planner run start ---"
# ── Load formula + context ───────────────────────────────────────────────
load_formula "$FACTORY_ROOT/formulas/run-planner.toml"
build_context_block VISION.md AGENTS.md RESOURCES.md
# ── Read planner memory ─────────────────────────────────────────────────
MEMORY_BLOCK=""
MEMORY_FILE="$FACTORY_ROOT/planner/MEMORY.md"
if [ -f "$MEMORY_FILE" ]; then
MEMORY_BLOCK="
### planner/MEMORY.md (persistent memory from prior runs)
$(cat "$MEMORY_FILE")
"
fi
# ── Build prompt ─────────────────────────────────────────────────────────
PROMPT="You are the strategic planner for ${CODEBERG_REPO}. Work through the formula below. You MUST write PHASE:done to '${PHASE_FILE}' when finished — the orchestrator will time you out if you return to the prompt without signalling.
## Project context
${CONTEXT_BLOCK}${MEMORY_BLOCK}
## Formula
${FORMULA_CONTENT}
## Codeberg API reference
Base URL: ${CODEBERG_API}
Auth header: -H \"Authorization: token \$CODEBERG_TOKEN\"
Read issue: curl -sf -H \"Authorization: token \$CODEBERG_TOKEN\" '${CODEBERG_API}/issues/{number}' | jq '.body'
Create issue: curl -sf -X POST -H \"Authorization: token \$CODEBERG_TOKEN\" -H 'Content-Type: application/json' '${CODEBERG_API}/issues' -d '{\"title\":\"...\",\"body\":\"...\",\"labels\":[LABEL_ID]}'
Relabel: curl -sf -H \"Authorization: token \$CODEBERG_TOKEN\" -X PUT -H 'Content-Type: application/json' '${CODEBERG_API}/issues/{number}/labels' -d '{\"labels\":[LABEL_ID]}'
Comment: curl -sf -H \"Authorization: token \$CODEBERG_TOKEN\" -X POST -H 'Content-Type: application/json' '${CODEBERG_API}/issues/{number}/comments' -d '{\"body\":\"...\"}'
Close: curl -sf -H \"Authorization: token \$CODEBERG_TOKEN\" -X PATCH -H 'Content-Type: application/json' '${CODEBERG_API}/issues/{number}' -d '{\"state\":\"closed\"}'
List labels: curl -sf -H \"Authorization: token \$CODEBERG_TOKEN\" '${CODEBERG_API}/labels'
NEVER echo or include the actual token value in output — always reference \$CODEBERG_TOKEN.
## Environment
FACTORY_ROOT=${FACTORY_ROOT}
PROJECT_REPO_ROOT=${PROJECT_REPO_ROOT}
PRIMARY_BRANCH=${PRIMARY_BRANCH}
## Phase protocol (REQUIRED)
When all work is done:
echo 'PHASE:done' > '${PHASE_FILE}'
On unrecoverable error:
printf 'PHASE:failed\nReason: %s\n' 'describe error' > '${PHASE_FILE}'"
# ── Create tmux session ─────────────────────────────────────────────────
export CLAUDE_MODEL="opus"
if ! start_formula_session "$SESSION_NAME" "$PROJECT_REPO_ROOT" "$PHASE_FILE"; then
exit 1
fi
agent_inject_into_session "$SESSION_NAME" "$PROMPT"
log "Prompt sent to tmux session"
matrix_send "planner" "Planner session started for ${CODEBERG_REPO}" 2>/dev/null || true
# ── Phase monitoring loop ────────────────────────────────────────────────
log "Monitoring phase file: ${PHASE_FILE}"
_FORMULA_CRASH_COUNT=0
monitor_phase_loop "$PHASE_FILE" 7200 "formula_phase_callback"
FINAL_PHASE=$(read_phase "$PHASE_FILE")
log "Final phase: ${FINAL_PHASE:-none}"
if [ "$FINAL_PHASE" != "PHASE:done" ]; then
case "${_MONITOR_LOOP_EXIT:-}" in
idle_prompt)
log "planner: Claude returned to prompt without writing phase signal"
;;
idle_timeout)
log "planner: timed out after 2h with no phase signal"
;;
*)
log "planner finished without PHASE:done (phase: ${FINAL_PHASE:-none}, exit: ${_MONITOR_LOOP_EXIT:-})"
;;
esac
fi
matrix_send "planner" "Planner session finished (${FINAL_PHASE:-no phase})" 2>/dev/null || true
log "--- Planner run done ---"