sneak/clawpub
1
0
Fork 0
Code Issues 1 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Compare commits

base: sneak:update-poller-and-statemachine-docs
Branches Tags
sneak:main
sneak:update-poller-and-statemachine-docs
sneak:update-poller-docs
sneak:fix/update-poller-docs
sneak:fix/pii-and-conditional-email
sneak:add-notification-delivery-approaches
sneak:rewrite-setup-checklist-prompts
..
compare: sneak:main
Branches Tags
sneak:update-poller-and-statemachine-docs
sneak:main
sneak:update-poller-docs
sneak:fix/update-poller-docs
sneak:fix/pii-and-conditional-email
sneak:add-notification-delivery-approaches
sneak:rewrite-setup-checklist-prompts

No commits in common. "update-poller-and-statemachine-docs" and "main" have entirely different histories.
update-pol ... main

2 changed files with 233 additions and 381 deletions
Show Stats Expand all files Collapse all files

248
AUTOMATED_DEV.md
View File

@ -74,108 +74,103 @@ back to issues.
### PR State Machine ### PR State Machine
Once a PR exists, it enters a finite state machine tracked by Gitea labels. Each Once a PR exists, it enters a finite state machine tracked by Gitea labels and
PR has exactly one state label at a time, plus a `bot` label indicating it's the issue assignments. Labels represent the current state; the assignment field
agent's turn to act. represents who's responsible for the next action.
#### States (Gitea Labels) #### States (Gitea Labels)
| Label | Color | Meaning | | Label | Color | Meaning |
| -------------- | ------ | --------------------------------------------- | | -------------- | ------ | ------------------------------------------------- |
| `needs-review` | yellow | Code pushed, `docker build .` passes, awaiting review | | `needs-rebase` | red | PR has merge conflicts or is behind main |
| `needs-rework` | purple | Code review found issues that need fixing | | `needs-checks` | orange | `make check` does not pass cleanly |
| `merge-ready` | green | Reviewed clean, build passes, ready for human | | `needs-review` | yellow | Code review not yet done |
| `needs-rework` | purple | Code review found issues that need fixing |
| `merge-ready` | green | All checks pass, reviewed, rebased, conflict-free |
Earlier iterations included `needs-rebase` and `needs-checks` states, but we #### Transitions
eliminated them. Rebasing is handled inline by workers and reviewers (they
rebase onto the target branch as part of their normal work). And `docker build .`
is the only check — it's run by workers before pushing and by reviewers before
approving. There's no separate "checks" phase.
#### The `bot` Label + Assignment Model
The `bot` label signals that an issue or PR is the agent's turn to act. The
assignment field tracks who is actively working on it:
- **`bot` label + unassigned** = work available, poller dispatches an agent
- **`bot` label + assigned to agent** = actively being worked
- **No `bot` label** = not the agent's turn (either human's turn or done)
The notification poller assigns the agent account to the issue at dispatch time,
before the agent session even starts. This prevents race conditions — by the
time a second poller scan runs, the issue is already assigned and gets skipped.
When the agent finishes its step and spawns the next agent, it unassigns itself
first (releasing the lock). The next agent's first action is to verify it's the
only one working on the issue by checking comments for duplicate work.
At chain-end (`merge-ready`): the agent assigns the human and removes the `bot`
label. The human's PR inbox contains only PRs that are genuinely ready to merge.
#### Agent Chaining — No Self-Review
Each step in the pipeline is handled by a separate, isolated agent session.
Agents spawn the next agent in the chain via `openclaw cron add --session
isolated`. This enforces a critical rule: **the agent that wrote the code never
reviews it.**
The chain looks like this:
``` ```
Worker agent (writes/fixes code) New PR created
→ docker build . → push → label needs-review │
→ unassign self → spawn reviewer agent → STOP ▼
[needs-rebase] ──rebase onto main──▶ [needs-checks]
Reviewer agent (reviews code it didn't write) ▲ │
→ read diff + referenced issues → review │ run make check
→ PASS: rebase if needed → docker build . → label merge-ready │ (main updated, │
→ assign human → remove bot label → STOP │ conflicts) ┌─────────────┴──────────────┐
→ FAIL: comment findings → label needs-rework │ │ │
→ unassign self → spawn worker agent → STOP │ passes fails
│ │ │
│ ▼ ▼
│ [needs-review] [needs-checks]
│ │ (fix code, re-run)
│ code review
│ │
│ ┌─────────┴──────────┐
│ │ │
│ approved issues found
│ │ │
│ ▼ ▼
│ [merge-ready] [needs-rework]
│ │ │
│ assign human fix issues
│ │
│ ▼
└───────────────────────────── [needs-rebase]
(restart cycle)
``` ```
The cycle repeats (worker → reviewer → worker → reviewer → ...) until the The cycle can repeat multiple times: rebase → check → review → rework → rebase →
reviewer approves. Each agent is a fresh session with no memory of previous check → review → rework → ... until the PR is clean. Each iteration typically
iterations — it reads the issue comments and PR diff to understand context. addresses a smaller set of issues until everything converges.
#### TOCTOU Protection #### Assignment Rules
Just before changing labels or assignments, agents re-read all comments and - **PR in any state except `merge-ready`** → assigned to the agent. It's the
current labels via the API. If the state changed since they started (another agent's job to drive it forward through the state machine.
agent already acted), they report the conflict and stop. This prevents stale - **PR reaches `merge-ready`** → assigned to the human. This is the ONLY time a
agents from overwriting fresh state. PR should land in the human's queue.
- **Human requests changes during review** → PR moves back to `needs-rework`,
reassigned to agent.
#### Race Detection This means the human's PR inbox contains only PRs that are genuinely ready to
merge — no half-finished work, no failing CI, no merge conflicts. Everything
If an agent starts and finds its work was already done (e.g., a reviewer sees a else is the agent's problem.
review was already posted, or a worker sees a PR was already created), it
reports to the status channel and stops.
#### The Loop in Practice #### The Loop in Practice
A typical PR goes through this cycle: A typical PR might go through this cycle:
1. Worker agent creates PR, runs `docker build .`, labels `needs-review` 1. Agent creates PR, labels `needs-rebase`
2. Worker spawns reviewer agent 2. Agent rebases onto main → labels `needs-checks`
3. Reviewer reads diff — finds a missing error check → labels `needs-rework` 3. Agent runs `make check` — lint fails → fixes lint, pushes → back to
4. Reviewer spawns worker agent `needs-rebase` (new commit)
5. Worker fixes the error check, rebases, runs `docker build .`, labels 4. Agent rebases → `needs-checks` → runs checks → passes → `needs-review`
`needs-review` 5. Agent does code review — finds a missing error check → `needs-rework`
6. Worker spawns reviewer agent 6. Agent fixes the error check, pushes → `needs-rebase`
7. Reviewer reads diff — looks good → rebases → `docker build .` → labels 7. Agent rebases → `needs-checks` → passes → `needs-review`
`merge-ready`, assigns human 8. Agent reviews — looks good → `merge-ready`
8. Human reviews, merges 9. Agent assigns to human
10. Human reviews, merges
Steps 1-7 happen without human involvement. Each step is a separate agent Steps 1-9 happen without human involvement. The human sees a clean, reviewed,
session that spawns the next one. passing PR ready for a final look.
#### Safety Net #### Automated Sweep
The notification poller runs a periodic scan (every 2 minutes) of all watched A periodic cron job (every 4 hours) scans all open PRs across all repos:
repos for issues/PRs with the `bot` label that are unassigned. This catches
broken chains — if an agent crashes or times out without spawning the next agent, - **No label** → classify into the correct state
the poller will eventually re-dispatch. A 30-minute cooldown prevents duplicate - **`needs-rebase`** → spawn agent to rebase
dispatches during normal operation. - **`needs-checks`** → spawn agent to run checks and fix failures
- **`needs-review`** → spawn agent to do code review
- **`needs-rework`** → spawn agent to fix review feedback
- **`merge-ready`** → verify still true (main may have updated since), ensure
assigned to human
This catches PRs that fell through the cracks — an agent session that timed out
mid-rework, a rebase that became necessary when main moved forward, etc.
#### Why Labels + Assignments #### Why Labels + Assignments
@ -268,45 +263,26 @@ A practical setup:
- **DM with agent** — Private conversation, sitreps, sensitive commands - **DM with agent** — Private conversation, sitreps, sensitive commands
- **Project-specific channels** — For coordination with external collaborators - **Project-specific channels** — For coordination with external collaborators
### The Notification Poller + Dispatcher ### The Notification Poller
Because the agent can't see Gitea webhooks in Mattermost (bot-to-bot visibility Because the agent can't see Gitea webhooks in Mattermost (bot-to-bot visibility
issue), we built a Python script that both polls and dispatches. It polls the issue), we built a lightweight Python script that polls the Gitea notifications
Gitea notifications API every 15 seconds, triages each notification (checking API every 2 seconds and wakes the agent via OpenClaw's `/hooks/wake` endpoint
@-mentions and assignment), marks them as read, and spawns one isolated agent when new notifications arrive.
session per actionable item via `openclaw cron add --session isolated`.
The poller also runs a secondary **label scan** every 2 minutes, checking all
watched repos for open issues/PRs with the `bot` label that are unassigned
(meaning they need work but no agent has claimed them yet). This catches cases
where the agent chain broke — an agent timed out or crashed without spawning the
next one.
Key design decisions: Key design decisions:
- **The poller IS the dispatcher.** No flag files, no heartbeat dependency. The - **The poller never marks notifications as read.** That's the agent's job after
poller triages notifications and spawns agents directly. processing. Prevents the poller and agent from racing.
- **Marks notifications as read immediately.** Prevents re-dispatch on the next - **Tracks notification IDs, not counts.** Only fires on genuinely new
poll cycle. notifications, not re-reads of existing ones.
- **Assigns the agent account at dispatch time.** Before spawning the agent - **The wake message tells the agent to route output to Gitea/Mattermost, not
session, the poller assigns the bot user to the issue via API. This prevents DM.** Prevents chatty notification processing from disturbing the human.
race conditions — subsequent scans skip assigned issues. - **Zero dependencies.** Python stdlib only (`urllib`, `json`, `time`). Runs
- **Dispatched issues are tracked in a persistent JSON file.** Survives poller anywhere.
restarts. Entries auto-prune after 1 hour.
- **30-minute re-dispatch cooldown.** The poller won't re-dispatch for the same
issue within 30 minutes, even if it appears unassigned again.
- **Concurrency cap.** The poller checks how many agents are currently running
and defers dispatch if the cap is reached.
- **Stale agent reaper.** Kills agent sessions that have been running longer
than 10 minutes (the `--timeout-seconds` flag isn't always enforced).
- **`bot` label + `merge-ready` skip.** The label scan skips issues that are
already labeled `merge-ready` — those are in the human's court.
- **Zero dependencies.** Python stdlib only. Runs anywhere.
Response time: ~15-30 seconds from notification to agent starting work.
Full source code is available in Full source code is available in
[OPENCLAW_TRICKS.md](OPENCLAW_TRICKS.md#gitea-integration--notification-polling). [OPENCLAW_TRICKS.md](OPENCLAW_TRICKS.md#the-gitea-notification-poller).
## CI: Gitea Actions ## CI: Gitea Actions
@ -395,34 +371,42 @@ Everything gets a production URL with automatic TLS via Traefik.
Putting it all together, the development lifecycle looks like this: Putting it all together, the development lifecycle looks like this:
``` ```
1. Human labels issue with `bot` (or agent files issue) 1. Issue filed in Gitea (by human or agent)
↓ ↓
2. Poller detects `bot` label + unassigned → assigns agent → spawns worker 2. Agent picks up the issue (via notification poller)
↓ ↓
3. Worker agent clones repo, writes code, runs `docker build .` 3. Agent posts "starting work on #N" to Mattermost #git
↓ ↓
4. Worker creates PR "(closes #N)", labels `needs-review` 4. Agent (or sub-agent) creates branch, writes code, pushes
↓ ↓
5. Worker spawns reviewer agent → stops 5. Gitea webhook fires → #git shows the push
↓ ↓
6. Reviewer agent reads diff + referenced issues → reviews 6. CI runs docker build → passes or fails
↓ ↓
7a. Review PASS → reviewer rebases if needed → `docker build .` 7. Agent creates PR "(closes #N)"
→ labels `merge-ready` → assigns human → removes `bot`
↓ ↓
7b. Review FAIL → reviewer labels `needs-rework` 8. Gitea webhook fires → #git shows the PR
→ spawns worker agent → back to step 3
↓ ↓
8. Human reviews, merges 9. Agent reviews code, runs make check locally, verifies
↓ ↓
9. Gitea webhook fires → µPaaS deploys to production 10. Agent assigns PR to human when all checks pass
↓ ↓
10. Site/service is live 11. Human reviews, requests changes or approves
↓
12. If changes requested → agent reworks, back to step 6
↓
13. Human merges PR
↓
14. Gitea webhook fires → µPaaS deploys to production
↓
15. Gitea webhook fires → #git shows the merge
↓
16. Site/service is live on production URL
``` ```
Steps 2-7 happen without any human involvement, driven by agent-to-agent Steps 2-10 can happen without any human involvement. The human's role is reduced
chaining. The human's role is reduced to: label the issue, review the final PR, to: review the PR, approve or request changes, merge. Everything else is
merge. Everything else is automated. automated.
### Observability ### Observability

366
OPENCLAW_TRICKS.md
View File

@ -197,46 +197,33 @@ OpenClaw runs on a Mac Studio on a home LAN.
The solution: a Python script that both polls and dispatches. It polls the Gitea The solution: a Python script that both polls and dispatches. It polls the Gitea
notifications API every 15 seconds, triages each notification (checking notifications API every 15 seconds, triages each notification (checking
@-mentions and assignments), marks them as read, and spawns one isolated agent assignment and @-mentions), marks them as read, and spawns one isolated agent
session per actionable item via `openclaw cron add --session isolated`. session per actionable item via `openclaw cron add --session isolated`.
The poller also runs a secondary **label scan** every 2 minutes, checking all The poller also runs a secondary **assignment scan** every 2 minutes, checking
watched repos for open issues/PRs with the `bot` label that are unassigned. This all watched repos for open issues/PRs assigned to the bot that were recently
catches cases where the agent chain broke — an agent timed out or crashed updated and still need a response. This catches cases where notifications aren't
without spawning the next agent. It also picks up newly-labeled issues that generated (e.g. self-assignment, API-created issues).
didn't trigger a notification.
Key design decisions: Key design decisions:
- **The poller IS the dispatcher.** No flag files, no heartbeat dependency. The - **The poller IS the dispatcher.** No flag files, no heartbeat dependency. The
poller triages notifications and spawns agents directly. poller triages notifications and spawns agents directly.
- **Marks notifications as read immediately.** Prevents re-dispatch on the next - **Marks notifications as read immediately.** Each notification is marked read
poll cycle. as it's processed, preventing re-dispatch on the next poll.
- **Assigns the bot user at dispatch time.** Before spawning the agent, the - **One agent per issue.** Each spawned agent gets a `SCOPE` instruction
poller assigns the bot account to the issue via API. This prevents race limiting it to one specific issue/PR. Agents post results as Gitea comments,
conditions — subsequent scans skip assigned issues. The spawned agent doesn't not DMs.
need to claim ownership; it's already claimed. - **Dedup tracking.** An in-memory `dispatched_issues` set prevents spawning
- **Persistent dispatch tracking.** Dispatched issues are tracked in a JSON multiple agents for the same issue within one poller lifetime.
file on disk (not just in memory), surviving poller restarts. Entries - **`--no-deliver` instead of `--announce`.** Agents report via Gitea API
auto-prune after 1 hour. directly. The `--announce` flag on isolated sessions had delivery failures.
- **30-minute re-dispatch cooldown.** Safety net for broken agent chains. Normal - **Assignment scan filters by recency.** Only issues updated in the last 5
operation uses agent-to-agent chaining (each agent spawns the next), so the minutes are considered, preventing re-dispatch for stale assigned issues.
poller only re-dispatches if the chain breaks. - **Zero dependencies.** Just Python stdlib. Runs anywhere.
- **Concurrency cap.** The poller checks how many agents are currently running
(`openclaw cron list`) and defers dispatch if the cap is reached.
- **Stale agent reaper.** Each scan cycle, kills agent sessions running longer
than 10 minutes. The `--timeout-seconds` flag isn't always enforced by
OpenClaw, so the poller handles cleanup itself.
- **`merge-ready` skip.** The label scan skips issues already labeled
`merge-ready` — those are in the human's court.
- **Template-based prompts.** The poller reads two workspace files (a dispatch
header with `{{variable}}` placeholders, and a workflow rules document),
concatenates them, substitutes variables, and passes the result as the
agent's `--message`. This keeps all instructions in version-controlled
workspace files with a single source of truth.
- **Zero dependencies.** Python stdlib only. Runs anywhere.
Response time: ~15–30s from notification to agent starting work. Response time: ~15–60s from notification to agent comment (vs ~30 min with the
old heartbeat approach).
```python ```python
#!/usr/bin/env python3 #!/usr/bin/env python3
@ -244,25 +231,20 @@ Response time: ~15–30s from notification to agent starting work.
Gitea notification poller + dispatcher. Gitea notification poller + dispatcher.
Two polling loops: Two polling loops:
1. Notification-based: detects new @-mentions and assignments, dispatches 1. Notification-based: detects new notifications (mentions, assignments by
agents for actionable notifications. other users) and dispatches agents for actionable ones.
2. Label-based: periodically scans for issues/PRs with the 'bot' label 2. Assignment-based: periodically checks for open issues/PRs assigned to
that are unassigned (available for work). Catches broken agent chains the bot that have no recent bot comment. Catches cases where
and newly-labeled issues. notifications aren't generated (e.g. self-assignment, API-created issues).
The poller assigns the bot user to the issue BEFORE spawning the agent,
preventing race conditions where multiple scans dispatch for the same issue.
Required env vars: Required env vars:
GITEA_URL - Gitea instance URL GITEA_URL - Gitea instance URL
GITEA_TOKEN - Gitea API token GITEA_TOKEN - Gitea API token
Optional env vars: Optional env vars:
POLL_DELAY - Seconds between notification polls (default: 15) POLL_DELAY - Delay between polls in seconds (default: 15)
COOLDOWN - Seconds between dispatch batches (default: 30) COOLDOWN - Minimum seconds between dispatches (default: 30)
BOT_SCAN_INTERVAL - Seconds between label scans (default: 120) ASSIGNMENT_INTERVAL - Seconds between assignment scans (default: 120)
MAX_CONCURRENT_AGENTS - Max simultaneous agents (default: 10)
REAP_AGE_SECONDS - Kill agents older than this (default: 600)
OPENCLAW_BIN - Path to openclaw binary OPENCLAW_BIN - Path to openclaw binary
""" """
@ -278,50 +260,18 @@ GITEA_URL = os.environ.get("GITEA_URL", "").rstrip("/")
GITEA_TOKEN = os.environ.get("GITEA_TOKEN", "") GITEA_TOKEN = os.environ.get("GITEA_TOKEN", "")
POLL_DELAY = int(os.environ.get("POLL_DELAY", "15")) POLL_DELAY = int(os.environ.get("POLL_DELAY", "15"))
COOLDOWN = int(os.environ.get("COOLDOWN", "30")) COOLDOWN = int(os.environ.get("COOLDOWN", "30"))
BOT_SCAN_INTERVAL = int(os.environ.get("BOT_SCAN_INTERVAL", "120")) ASSIGNMENT_INTERVAL = int(os.environ.get("ASSIGNMENT_INTERVAL", "120"))
MAX_CONCURRENT_AGENTS = int(os.environ.get("MAX_CONCURRENT_AGENTS", "10")) OPENCLAW_BIN = os.environ.get("OPENCLAW_BIN", "/opt/homebrew/bin/openclaw")
REAP_AGE_SECONDS = int(os.environ.get("REAP_AGE_SECONDS", "600")) BOT_USER = "clawbot" # Change to your bot's Gitea username
REDISPATCH_COOLDOWN = 1800 # 30 min safety net for broken agent chains
OPENCLAW_BIN = os.environ.get("OPENCLAW_BIN", "openclaw")
BOT_USER = os.environ.get("BOT_USER", "clawbot")
WORKSPACE = os.path.expanduser("~/.openclaw/workspace") # Repos to scan for assigned issues
DISPATCH_HEADER = os.path.join(
WORKSPACE, "taskprompts", "how-to-handle-gitea-notifications.md"
)
WORKFLOW_DOC = os.path.join(
WORKSPACE, "taskprompts", "how-to-work-on-a-gitea-issue-or-pr.md"
)
DISPATCH_STATE_PATH = os.path.join(
os.path.dirname(os.path.abspath(__file__)), ".dispatch-state.json"
)
# Repos to watch for bot-labeled issues
WATCHED_REPOS = [ WATCHED_REPOS = [
# "org/repo1", # "org/repo1",
# "org/repo2", # "org/repo2",
] ]
# Dispatch tracking (persisted to disk) # Track dispatched issues to prevent duplicates
dispatched_issues: dict[str, float] = {} dispatched_issues = set()
def _load_dispatch_state() -> dict[str, float]:
try:
with open(DISPATCH_STATE_PATH) as f:
state = json.load(f)
now = time.time()
return {k: v for k, v in state.items() if now - v < 3600}
except (FileNotFoundError, json.JSONDecodeError):
return {}
def _save_dispatch_state():
try:
with open(DISPATCH_STATE_PATH, "w") as f:
json.dump(dispatched_issues, f)
except OSError as e:
print(f"WARN: Could not save dispatch state: {e}", file=sys.stderr)
def gitea_api(method, path, data=None): def gitea_api(method, path, data=None):
@ -340,91 +290,17 @@ def gitea_api(method, path, data=None):
return None return None
def load_template() -> str: def needs_bot_response(repo_full, issue_number):
"""Load dispatch header + workflow doc, concatenated.""" """True if the bot is NOT the author of the most recent comment."""
parts = [] comments = gitea_api("GET", f"/repos/{repo_full}/issues/{issue_number}/comments")
for path in [DISPATCH_HEADER, WORKFLOW_DOC]: if comments and len(comments) > 0:
try: if comments[-1].get("user", {}).get("login") == BOT_USER:
with open(path) as f: return False
parts.append(f.read()) return True
except FileNotFoundError:
print(f"ERROR: File not found: {path}", file=sys.stderr)
sys.exit(1)
return "\n\n---\n\n".join(parts)
def render_template(template, repo_full, issue_number, title,
subject_type, reason):
return (
template
.replace("{{repo_full}}", repo_full)
.replace("{{issue_number}}", str(issue_number))
.replace("{{title}}", title)
.replace("{{subject_type}}", subject_type)
.replace("{{reason}}", reason)
.replace("{{gitea_url}}", GITEA_URL)
.replace("{{gitea_token}}", GITEA_TOKEN)
.replace("{{openclaw_bin}}", OPENCLAW_BIN)
.replace("{{bot_user}}", BOT_USER)
# Add your own variables here (e.g. git_channel)
)
def count_running_agents() -> int:
try:
result = subprocess.run(
[OPENCLAW_BIN, "cron", "list"],
capture_output=True, text=True, timeout=10,
)
return sum(1 for line in result.stdout.splitlines()
if "running" in line or "idle" in line)
except Exception:
return 0
def spawn_agent(template, repo_full, issue_number, title,
subject_type, reason):
dispatch_key = f"{repo_full}#{issue_number}"
last = dispatched_issues.get(dispatch_key)
if last and (time.time() - last) < REDISPATCH_COOLDOWN:
return
if count_running_agents() >= MAX_CONCURRENT_AGENTS:
print(f" → Concurrency limit reached, deferring {dispatch_key}",
flush=True)
return
dispatched_issues[dispatch_key] = time.time()
# Assign bot user immediately to prevent races
gitea_api("PATCH", f"/repos/{repo_full}/issues/{issue_number}",
{"assignees": [BOT_USER]})
repo_short = repo_full.split("/")[-1]
job_name = f"gitea-{repo_short}-{issue_number}-{int(time.time())}"
msg = render_template(template, repo_full, issue_number, title,
subject_type, reason)
try:
result = subprocess.run(
[OPENCLAW_BIN, "cron", "add",
"--name", job_name, "--at", "1s",
"--message", msg, "--delete-after-run",
"--session", "isolated", "--no-deliver",
"--thinking", "low", "--timeout-seconds", "300"],
capture_output=True, text=True, timeout=15,
)
if result.returncode == 0:
_save_dispatch_state()
else:
dispatched_issues.pop(dispatch_key, None)
except Exception as e:
print(f"Spawn error: {e}", file=sys.stderr, flush=True)
dispatched_issues.pop(dispatch_key, None)
def is_actionable(notif): def is_actionable(notif):
"""Check if a notification warrants spawning an agent.""" """Returns (actionable, reason, issue_number)."""
subject = notif.get("subject", {}) subject = notif.get("subject", {})
repo = notif.get("repository", {}) repo = notif.get("repository", {})
repo_full = repo.get("full_name", "") repo_full = repo.get("full_name", "")
@ -437,88 +313,68 @@ def is_actionable(notif):
if not issue: if not issue:
return False, "couldn't fetch issue", number return False, "couldn't fetch issue", number
# Check for @-mentions in the latest comment assignees = [a.get("login") for a in (issue.get("assignees") or [])]
comments = gitea_api( if BOT_USER in assignees:
"GET", f"/repos/{repo_full}/issues/{number}/comments" if needs_bot_response(repo_full, number):
) return True, f"assigned to {BOT_USER}", number
return False, "assigned but already responded", number
issue_body = issue.get("body", "") or ""
if f"@{BOT_USER}" in issue_body and issue.get("user", {}).get("login") != BOT_USER:
if needs_bot_response(repo_full, number):
return True, f"@-mentioned in body", number
comments = gitea_api("GET", f"/repos/{repo_full}/issues/{number}/comments")
if comments: if comments:
last = comments[-1] last = comments[-1]
if last.get("user", {}).get("login") == BOT_USER: if last.get("user", {}).get("login") == BOT_USER:
return False, "own comment is latest", number return False, "own comment is latest", number
if f"@{BOT_USER}" in (last.get("body") or ""): if f"@{BOT_USER}" in (last.get("body") or ""):
return True, "@-mentioned in comment", number return True, f"@-mentioned in comment", number
# Check for @-mention in issue body return False, "not mentioned or assigned", number
body = issue.get("body", "") or ""
if f"@{BOT_USER}" in body:
return True, "@-mentioned in body", number
return False, "not mentioned", number
def scan_bot_labeled(template): def spawn_agent(repo_full, issue_number, title, subject_type, reason):
"""Scan for issues/PRs with 'bot' label that are unassigned.""" dispatch_key = f"{repo_full}#{issue_number}"
for repo_full in WATCHED_REPOS: if dispatch_key in dispatched_issues:
for issue_type in ["issues", "pulls"]: return
items = gitea_api( dispatched_issues.add(dispatch_key)
"GET",
f"/repos/{repo_full}/issues?state=open&type={issue_type}"
f"&labels=bot&sort=updated&limit=10",
) or []
for item in items:
number = str(item["number"])
dispatch_key = f"{repo_full}#{number}"
last = dispatched_issues.get(dispatch_key) repo_short = repo_full.split("/")[-1]
if last and (time.time() - last) < REDISPATCH_COOLDOWN: job_name = f"gitea-{repo_short}-{issue_number}-{int(time.time())}"
continue msg = (
f"Gitea: {reason} on {subject_type} #{issue_number} "
assignees = [ f"'{title}' in {repo_full}.\n"
a.get("login", "") for a in item.get("assignees") or [] f"API: {GITEA_URL}/api/v1 | Token: {GITEA_TOKEN}\n"
] f"SCOPE: Only {subject_type} #{issue_number} in {repo_full}.\n"
if BOT_USER in assignees: f"Read all comments, do the work, post results as Gitea comments."
continue )
try:
labels = [ subprocess.run(
l.get("name", "") for l in item.get("labels") or [] [OPENCLAW_BIN, "cron", "add",
] "--name", job_name, "--at", "1s",
if "merge-ready" in labels: "--message", msg, "--delete-after-run",
continue "--session", "isolated", "--no-deliver",
"--thinking", "low", "--timeout-seconds", "300"],
kind = "PR" if issue_type == "pulls" else "issue" capture_output=True, text=True, timeout=15,
spawn_agent( )
template, repo_full, number, except Exception as e:
item.get("title", "")[:60], print(f"Spawn error: {e}", file=sys.stderr, flush=True)
"pull" if issue_type == "pulls" else "issue", dispatched_issues.discard(dispatch_key)
"bot label, unassigned",
)
def main(): def main():
global dispatched_issues print(f"Poller started (poll={POLL_DELAY}s, cooldown={COOLDOWN}s)", flush=True)
dispatched_issues = _load_dispatch_state() seen_ids = set(n["id"] for n in (gitea_api("GET", "/notifications?status-types=unread") or []))
if not GITEA_URL or not GITEA_TOKEN:
print("ERROR: GITEA_URL and GITEA_TOKEN required", file=sys.stderr)
sys.exit(1)
template = load_template()
print(f"Poller started (poll={POLL_DELAY}s, cooldown={COOLDOWN}s, "
f"bot_scan={BOT_SCAN_INTERVAL}s, repos={len(WATCHED_REPOS)})",
flush=True)
seen_ids = set(
n["id"] for n in
(gitea_api("GET", "/notifications?status-types=unread") or [])
)
last_dispatch = 0 last_dispatch = 0
last_bot_scan = 0 last_assign_scan = 0
while True: while True:
time.sleep(POLL_DELAY) time.sleep(POLL_DELAY)
now = time.time() now = time.time()
# --- Notification polling --- # Notification polling
notifs = gitea_api("GET", "/notifications?status-types=unread") or [] notifs = gitea_api("GET", "/notifications?status-types=unread") or []
current_ids = {n["id"] for n in notifs} current_ids = {n["id"] for n in notifs}
new_ids = current_ids - seen_ids new_ids = current_ids - seen_ids
@ -532,14 +388,28 @@ def main():
repo = n["repository"]["full_name"] repo = n["repository"]["full_name"]
title = n["subject"]["title"][:60] title = n["subject"]["title"][:60]
stype = n["subject"].get("type", "").lower() stype = n["subject"].get("type", "").lower()
spawn_agent(template, repo, num, title, stype, reason) spawn_agent(repo, num, title, stype, reason)
last_dispatch = now last_dispatch = now
seen_ids = current_ids seen_ids = current_ids
# --- Bot label scan (less frequent) --- # Assignment scan (less frequent)
if now - last_bot_scan >= BOT_SCAN_INTERVAL: if now - last_assign_scan >= ASSIGNMENT_INTERVAL:
scan_bot_labeled(template) for repo in WATCHED_REPOS:
last_bot_scan = now for itype in ["issues", "pulls"]:
items = gitea_api("GET",
f"/repos/{repo}/issues?state=open&type={itype}"
f"&assignee={BOT_USER}&sort=updated&limit=10") or []
for item in items:
num = str(item["number"])
if f"{repo}#{num}" in dispatched_issues:
continue
# Only recently updated items (5 min)
# ... add is_recently_updated() check here
if needs_bot_response(repo, num):
spawn_agent(repo, num, item["title"][:60],
"pull" if itype == "pulls" else "issue",
f"assigned to {BOT_USER}")
last_assign_scan = now
if __name__ == "__main__": if __name__ == "__main__":
@ -884,27 +754,25 @@ From REPO_POLICIES.md and our operational experience:
#### The PR Pipeline #### The PR Pipeline
Our agent follows a strict PR lifecycle using agent-to-agent chaining. Each step Our agent follows a strict PR lifecycle:
is handled by a separate, isolated agent session — the agent that writes code
never reviews it:
```markdown ```markdown
## PR pipeline (every PR, no exceptions) ## PR pipeline (every PR, no exceptions)
Worker agent → docker build . → push → label needs-review → spawn reviewer 1. **Review/rework loop**: code review → rework → re-review → repeat until clean
Reviewer agent → review diff → PASS: docker build . → label merge-ready 2. **Check/rework loop**: `make check` + `docker build .` → rework → re-check →
→ FAIL: label needs-rework → spawn worker repeat until clean
Repeat until reviewer approves. 3. Only after BOTH loops pass with zero issues: assign to human
- docker build . is the ONLY authoritative check (runs make check inside) - "Passes checks" ≠ "ready for human"
- Never weaken tests/linters. Fix the code. - Never weaken tests/linters. Fix the code.
- Pre-existing failures are YOUR problem. Fix them as part of your PR. - Pre-existing failures are YOUR problem. Fix them as part of your PR.
``` ```
The agent chain doesn't just create a PR and hand it off — it drives the PR The agent doesn't just create a PR and hand it off — it drives the PR through
through review, rework, and verification until it's genuinely ready. A PR review, rework, and verification until it's genuinely ready. A PR assigned to
assigned to the human means: build passes, code reviewed by a separate agent, the human means: all checks pass, code reviewed, review feedback addressed,
review feedback addressed, rebased. Anything less is still in the agent chain. rebased against main, no conflicts. Anything less is the agent's open task.
#### New Repo Bootstrap #### New Repo Bootstrap
@ -1756,12 +1624,12 @@ For complex coding tasks, spawn isolated sub-agents.
### Sub-Agent PR Quality Gate (MANDATORY) ### Sub-Agent PR Quality Gate (MANDATORY)
- `docker build .` must pass. This is identical to CI and the only - `make check` must pass with ZERO failures. No exceptions.
authoritative check. No exceptions.
- Pre-existing failures are YOUR problem. Fix them as part of your PR. - Pre-existing failures are YOUR problem. Fix them as part of your PR.
- NEVER modify linter config to make checks pass. Fix the code. - NEVER modify linter config to make checks pass. Fix the code.
- Every PR must include full `make check` output
- Rebase before and after committing - Rebase before and after committing
- Never self-review — each agent spawns a separate agent for review - Never self-review
``` ```
--- ---