Compare commits
6 commits
0f868aefab
...
cde92d3db1
| Author | SHA1 | Date | |
|---|---|---|---|
| cde92d3db1 | |||
| 83526bc90e | |||
| ae860a1d06 | |||
| 878f6e06e3 | |||
| ac794f5c68 | |||
| 25a537d2e1 |
10 changed files with 152 additions and 19 deletions
|
|
@ -78,6 +78,9 @@ rsync $RSYNC_FLAGS diagnostics/ "$DIAGNOSTICS_DIR/"
|
|||
rsync $RSYNC_FLAGS agent-state/ "$AGENT_STATE_DIR/"
|
||||
[ -f research/research-session.sh ] && rsync $RSYNC_FLAGS research/research-session.sh /opt/teleo-eval/research-session.sh
|
||||
|
||||
# Safety net: ensure all .sh files are executable after rsync
|
||||
find /opt/teleo-eval -maxdepth 3 -name '*.sh' -not -perm -u+x -exec chmod +x {} +
|
||||
|
||||
log "Files synced"
|
||||
|
||||
# Restart services only if Python files changed
|
||||
|
|
|
|||
|
|
@ -191,10 +191,11 @@ print('no')
|
|||
else
|
||||
PR_TITLE=$(echo "$branch" | sed 's|/|: |;s/-/ /g')
|
||||
fi
|
||||
PAYLOAD=$(python3 -c "import sys,json; print(json.dumps({'title':sys.argv[1],'head':sys.argv[2],'base':'main'}))" "$PR_TITLE" "$branch")
|
||||
RESULT=$(curl -sf -X POST "http://localhost:3000/api/v1/repos/teleo/teleo-codex/pulls" \
|
||||
-H "Authorization: token $FORGEJO_TOKEN" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d "{\"title\":\"$PR_TITLE\",\"head\":\"$branch\",\"base\":\"main\"}" 2>/dev/null || echo "")
|
||||
-d "$PAYLOAD" 2>/dev/null || echo "")
|
||||
PR_NUM=$(echo "$RESULT" | grep -o '"number":[0-9]*' | head -1 | grep -o "[0-9]*" || true)
|
||||
if [ -n "$PR_NUM" ]; then
|
||||
log "Auto-created PR #$PR_NUM on Forgejo for $branch"
|
||||
|
|
@ -210,7 +211,7 @@ print('no')
|
|||
python3 -c "import sys,json; prs=json.load(sys.stdin); print(prs[0]['number'] if prs else '')" 2>/dev/null || true)
|
||||
fi
|
||||
fi
|
||||
if [ -n "$GH_PR_NUM" ]; then
|
||||
if [[ "$GH_PR_NUM" =~ ^[0-9]+$ ]] && [[ "$PR_NUM" =~ ^[0-9]+$ ]]; then
|
||||
sqlite3 "$PIPELINE_DB" "UPDATE prs SET github_pr = $GH_PR_NUM WHERE number = $PR_NUM;" 2>/dev/null && \
|
||||
log "Linked GitHub PR #$GH_PR_NUM -> Forgejo PR #$PR_NUM" || \
|
||||
log "WARN: Failed to link GitHub PR #$GH_PR_NUM to Forgejo PR #$PR_NUM in DB"
|
||||
|
|
@ -225,4 +226,57 @@ else
|
|||
log "No new GitHub-only branches"
|
||||
fi
|
||||
|
||||
# Step 6: Divergence alerting
|
||||
# After all sync steps, check if GitHub and Forgejo main still differ.
|
||||
# 2 consecutive divergent cycles (4 min) triggers a one-shot Telegram alert.
|
||||
DIVERGENCE_FILE="/opt/teleo-eval/logs/.divergence-count"
|
||||
git fetch forgejo main --quiet 2>/dev/null || true
|
||||
git fetch origin main --quiet 2>/dev/null || true
|
||||
GH_MAIN_FINAL=$(git rev-parse refs/remotes/origin/main 2>/dev/null || true)
|
||||
FG_MAIN_FINAL=$(git rev-parse refs/remotes/forgejo/main 2>/dev/null || true)
|
||||
|
||||
if [ -n "$GH_MAIN_FINAL" ] && [ -n "$FG_MAIN_FINAL" ] && [ "$GH_MAIN_FINAL" != "$FG_MAIN_FINAL" ]; then
|
||||
PREV=$(cat "$DIVERGENCE_FILE" 2>/dev/null || echo "0")
|
||||
if [ "$PREV" = "alerted" ]; then
|
||||
log "DIVERGENCE: still diverged (already alerted)"
|
||||
else
|
||||
COUNT=$((PREV + 1))
|
||||
echo "$COUNT" > "$DIVERGENCE_FILE"
|
||||
log "DIVERGENCE: cycle $COUNT — GitHub=$GH_MAIN_FINAL Forgejo=$FG_MAIN_FINAL"
|
||||
if [ "$COUNT" -ge 2 ]; then
|
||||
BOT_TOKEN=$(cat /opt/teleo-eval/secrets/telegram-bot-token 2>/dev/null || true)
|
||||
ADMIN_CHAT=$(cat /opt/teleo-eval/secrets/admin-chat-id 2>/dev/null || true)
|
||||
if [ -n "$BOT_TOKEN" ] && [ -n "$ADMIN_CHAT" ]; then
|
||||
ALERT_MSG=$(python3 -c "
|
||||
import json, sys
|
||||
msg = '⚠️ Mirror divergence detected\\n\\n'
|
||||
msg += f'GitHub main: {sys.argv[1][:8]}\\n'
|
||||
msg += f'Forgejo main: {sys.argv[2][:8]}\\n'
|
||||
msg += f'Diverged for {sys.argv[3]} consecutive cycles ({int(sys.argv[3])*2} min)\\n\\n'
|
||||
msg += 'Check sync-mirror.sh logs: /opt/teleo-eval/logs/sync.log'
|
||||
print(json.dumps({'chat_id': sys.argv[4], 'text': msg, 'parse_mode': 'HTML'}))
|
||||
" "$GH_MAIN_FINAL" "$FG_MAIN_FINAL" "$COUNT" "$ADMIN_CHAT")
|
||||
if curl -sf -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendMessage" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d "$ALERT_MSG" >> "$LOG" 2>&1; then
|
||||
log "DIVERGENCE: alert sent to admin"
|
||||
echo "alerted" > "$DIVERGENCE_FILE"
|
||||
else
|
||||
log "WARN: Failed to send divergence alert (will retry next cycle)"
|
||||
fi
|
||||
else
|
||||
log "WARN: Cannot send divergence alert — missing bot token or admin chat ID"
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
else
|
||||
if [ -f "$DIVERGENCE_FILE" ]; then
|
||||
PREV=$(cat "$DIVERGENCE_FILE" 2>/dev/null || echo "0")
|
||||
if [ "$PREV" != "0" ]; then
|
||||
log "DIVERGENCE: resolved — repos back in sync"
|
||||
fi
|
||||
rm -f "$DIVERGENCE_FILE"
|
||||
fi
|
||||
fi
|
||||
|
||||
log "Sync complete"
|
||||
|
|
|
|||
0
hermes-agent/install-hermes.sh
Normal file → Executable file
0
hermes-agent/install-hermes.sh
Normal file → Executable file
57
lib/db.py
57
lib/db.py
|
|
@ -9,7 +9,7 @@ from . import config
|
|||
|
||||
logger = logging.getLogger("pipeline.db")
|
||||
|
||||
SCHEMA_VERSION = 21
|
||||
SCHEMA_VERSION = 22
|
||||
|
||||
SCHEMA_SQL = """
|
||||
CREATE TABLE IF NOT EXISTS schema_version (
|
||||
|
|
@ -71,6 +71,7 @@ CREATE TABLE IF NOT EXISTS prs (
|
|||
cost_usd REAL DEFAULT 0,
|
||||
auto_merge INTEGER DEFAULT 0,
|
||||
github_pr INTEGER,
|
||||
source_channel TEXT,
|
||||
created_at TEXT DEFAULT (datetime('now')),
|
||||
merged_at TEXT
|
||||
);
|
||||
|
|
@ -196,6 +197,7 @@ def transaction(conn: sqlite3.Connection):
|
|||
# Branch prefix → (agent, commit_type) mapping.
|
||||
# Single source of truth — used by merge.py at INSERT time and migration v7 backfill.
|
||||
# Unknown prefixes → ('unknown', 'unknown') + warning log.
|
||||
# Keep in sync with _CHANNEL_MAP below.
|
||||
BRANCH_PREFIX_MAP = {
|
||||
"extract": ("pipeline", "extract"),
|
||||
"ingestion": ("pipeline", "extract"),
|
||||
|
|
@ -228,6 +230,31 @@ def classify_branch(branch: str) -> tuple[str, str]:
|
|||
return result
|
||||
|
||||
|
||||
# Keep in sync with BRANCH_PREFIX_MAP above.
|
||||
_CHANNEL_MAP = {
|
||||
"extract": "telegram",
|
||||
"ingestion": "telegram",
|
||||
"rio": "agent",
|
||||
"theseus": "agent",
|
||||
"astra": "agent",
|
||||
"vida": "agent",
|
||||
"clay": "agent",
|
||||
"leo": "agent",
|
||||
"oberon": "agent",
|
||||
"reweave": "maintenance",
|
||||
"epimetheus": "maintenance",
|
||||
"fix": "maintenance",
|
||||
}
|
||||
|
||||
|
||||
def classify_source_channel(branch: str, *, github_pr: int = None) -> str:
|
||||
"""Derive source_channel from branch prefix and github_pr flag."""
|
||||
if github_pr is not None or branch.startswith("gh-pr-"):
|
||||
return "github"
|
||||
prefix = branch.split("/", 1)[0] if "/" in branch else branch
|
||||
return _CHANNEL_MAP.get(prefix, "unknown")
|
||||
|
||||
|
||||
def migrate(conn: sqlite3.Connection):
|
||||
"""Run schema migrations."""
|
||||
conn.executescript(SCHEMA_SQL)
|
||||
|
|
@ -562,6 +589,34 @@ def migrate(conn: sqlite3.Connection):
|
|||
conn.commit()
|
||||
logger.info("Migration v21: added github_pr column + index to prs")
|
||||
|
||||
if current < 22:
|
||||
try:
|
||||
conn.execute("ALTER TABLE prs ADD COLUMN source_channel TEXT")
|
||||
except sqlite3.OperationalError:
|
||||
pass
|
||||
conn.execute("""
|
||||
UPDATE prs SET source_channel = CASE
|
||||
WHEN github_pr IS NOT NULL THEN 'github'
|
||||
WHEN branch LIKE 'gh-pr-%%' THEN 'github'
|
||||
WHEN branch LIKE 'theseus/%%' THEN 'agent'
|
||||
WHEN branch LIKE 'rio/%%' THEN 'agent'
|
||||
WHEN branch LIKE 'astra/%%' THEN 'agent'
|
||||
WHEN branch LIKE 'clay/%%' THEN 'agent'
|
||||
WHEN branch LIKE 'vida/%%' THEN 'agent'
|
||||
WHEN branch LIKE 'oberon/%%' THEN 'agent'
|
||||
WHEN branch LIKE 'leo/%%' THEN 'agent'
|
||||
WHEN branch LIKE 'reweave/%%' THEN 'maintenance'
|
||||
WHEN branch LIKE 'epimetheus/%%' THEN 'maintenance'
|
||||
WHEN branch LIKE 'fix/%%' THEN 'maintenance'
|
||||
WHEN branch LIKE 'extract/%%' THEN 'telegram'
|
||||
WHEN branch LIKE 'ingestion/%%' THEN 'telegram'
|
||||
ELSE 'unknown'
|
||||
END
|
||||
WHERE source_channel IS NULL
|
||||
""")
|
||||
conn.commit()
|
||||
logger.info("Migration v22: added source_channel to prs + backfilled from branch prefix")
|
||||
|
||||
if current < SCHEMA_VERSION:
|
||||
conn.execute(
|
||||
"INSERT OR REPLACE INTO schema_version (version) VALUES (?)",
|
||||
|
|
|
|||
|
|
@ -9,6 +9,15 @@ Extracted from merge.py Phase 6 of decomposition (Ganymede-approved plan).
|
|||
import yaml
|
||||
|
||||
|
||||
def _yaml_quote(value: str) -> str:
|
||||
"""Quote a YAML list value if it contains characters that would break parsing."""
|
||||
s = str(value)
|
||||
if ":" in s or s.startswith(("{", "[", "'", '"', "*", "&", "!", "|", ">")):
|
||||
escaped = s.replace('"', '\\"')
|
||||
return f'"{escaped}"'
|
||||
return s
|
||||
|
||||
|
||||
# Edge field names recognized in claim frontmatter.
|
||||
# Order matters: serialize_edge_fields writes them in this order when appending new fields.
|
||||
REWEAVE_EDGE_FIELDS = ("supports", "challenges", "challenged_by", "depends_on", "related", "reweave_edges")
|
||||
|
|
@ -101,7 +110,7 @@ def serialize_edge_fields(raw_fm_text: str, merged_edges: dict[str, list]) -> st
|
|||
if edges:
|
||||
result_lines.append(f"{matched_field}:")
|
||||
for edge in edges:
|
||||
result_lines.append(f"- {edge}")
|
||||
result_lines.append(f"- {_yaml_quote(edge)}")
|
||||
# Don't increment i — it's already past the old field
|
||||
continue
|
||||
else:
|
||||
|
|
@ -115,7 +124,7 @@ def serialize_edge_fields(raw_fm_text: str, merged_edges: dict[str, list]) -> st
|
|||
if edges:
|
||||
result_lines.append(f"{field}:")
|
||||
for edge in edges:
|
||||
result_lines.append(f"- {edge}")
|
||||
result_lines.append(f"- {_yaml_quote(edge)}")
|
||||
|
||||
return "\n".join(result_lines)
|
||||
|
||||
|
|
|
|||
|
|
@ -125,7 +125,8 @@ async def on_eval_complete(conn, forgejo_pr: int, *, outcome: str, review_text:
|
|||
if outcome == "approved":
|
||||
body = "**Evaluation: Approved**\n\nYour contribution passed automated review and is queued for merge."
|
||||
if review_text:
|
||||
body += f"\n\n<details>\n<summary>Review details</summary>\n\n{review_text[:3000]}\n\n</details>"
|
||||
safe_text = review_text[:3000].replace("</details>", "</details>")
|
||||
body += f"\n\n<details>\n<summary>Review details</summary>\n\n{safe_text}\n\n</details>"
|
||||
elif outcome == "rejected":
|
||||
body = "**Evaluation: Changes Requested**\n\n"
|
||||
if issues:
|
||||
|
|
@ -133,7 +134,8 @@ async def on_eval_complete(conn, forgejo_pr: int, *, outcome: str, review_text:
|
|||
for issue in issues:
|
||||
body += f"- {issue}\n"
|
||||
if review_text:
|
||||
body += f"\n<details>\n<summary>Full review</summary>\n\n{review_text[:3000]}\n\n</details>"
|
||||
safe_text = review_text[:3000].replace("</details>", "</details>")
|
||||
body += f"\n<details>\n<summary>Full review</summary>\n\n{safe_text}\n\n</details>"
|
||||
body += (
|
||||
"\n\nThe pipeline will attempt automated fixes where possible. "
|
||||
"If fixes fail, the PR will be closed — you're welcome to resubmit."
|
||||
|
|
|
|||
14
lib/merge.py
14
lib/merge.py
|
|
@ -20,7 +20,7 @@ import shutil
|
|||
from collections import defaultdict
|
||||
|
||||
from . import config, db
|
||||
from .db import classify_branch
|
||||
from .db import classify_branch, classify_source_channel
|
||||
from .contributor import record_contributor_attribution
|
||||
from .dedup import dedup_evidence_blocks
|
||||
from .domains import detect_domain_from_branch
|
||||
|
|
@ -117,6 +117,7 @@ async def discover_external_prs(conn) -> int:
|
|||
priority = "high" if origin == "human" else None
|
||||
domain = None if not is_pipeline else detect_domain_from_branch(pr["head"]["ref"])
|
||||
agent, commit_type = classify_branch(pr["head"]["ref"])
|
||||
source_channel = classify_source_channel(pr["head"]["ref"])
|
||||
|
||||
# For human PRs, submitted_by is the Forgejo author.
|
||||
# For pipeline PRs, submitted_by is set later by extract.py (from source proposed_by).
|
||||
|
|
@ -125,9 +126,9 @@ async def discover_external_prs(conn) -> int:
|
|||
conn.execute(
|
||||
"""INSERT OR IGNORE INTO prs
|
||||
(number, branch, status, origin, priority, domain, agent, commit_type,
|
||||
prompt_version, pipeline_version, submitted_by)
|
||||
VALUES (?, ?, 'open', ?, ?, ?, ?, ?, ?, ?, ?)""",
|
||||
(pr["number"], pr["head"]["ref"], origin, priority, domain, agent, commit_type, config.PROMPT_VERSION, config.PIPELINE_VERSION, submitted_by),
|
||||
prompt_version, pipeline_version, submitted_by, source_channel)
|
||||
VALUES (?, ?, 'open', ?, ?, ?, ?, ?, ?, ?, ?, ?)""",
|
||||
(pr["number"], pr["head"]["ref"], origin, priority, domain, agent, commit_type, config.PROMPT_VERSION, config.PIPELINE_VERSION, submitted_by, source_channel),
|
||||
)
|
||||
db.audit(
|
||||
conn,
|
||||
|
|
@ -507,9 +508,8 @@ async def _merge_reweave_pr(branch: str) -> tuple[bool, str]:
|
|||
branch_fm, _branch_raw_fm, branch_body = parse_yaml_frontmatter(branch_content)
|
||||
|
||||
if main_fm is None or branch_fm is None:
|
||||
# Parse failure = something unexpected. Fail the merge, don't fallback
|
||||
# to cherry-pick. (Theseus: loud failure, not silent retry)
|
||||
return False, f"frontmatter parse failed on {fpath} — manual review needed"
|
||||
logger.warning("Reweave merge: frontmatter parse failed on %s — skipping file, continuing PR", fpath)
|
||||
continue
|
||||
|
||||
# Superset assertion + merge in one pass.
|
||||
# Reweave only adds edges. If branch is missing an edge that main has,
|
||||
|
|
|
|||
0
research/research-session.sh
Normal file → Executable file
0
research/research-session.sh
Normal file → Executable file
|
|
@ -535,8 +535,9 @@ def _write_edge_regex(neighbor_path: Path, fm_text: str, body_text: str,
|
|||
field_re = re.compile(rf"^{edge_type}:\s*$", re.MULTILINE)
|
||||
inline_re = re.compile(rf'^{edge_type}:\s*\[', re.MULTILINE)
|
||||
|
||||
entry_line = f'- {orphan_title}'
|
||||
rw_line = f'- {orphan_title}|{edge_type}|{date_str}'
|
||||
from lib.frontmatter import _yaml_quote
|
||||
entry_line = f'- {_yaml_quote(orphan_title)}'
|
||||
rw_line = f'- {_yaml_quote(orphan_title + "|" + edge_type + "|" + date_str)}'
|
||||
|
||||
if field_re.search(fm_text):
|
||||
# Multi-line list exists — find end of list, append
|
||||
|
|
|
|||
|
|
@ -47,12 +47,21 @@ async def stage_loop(name: str, interval: int, func, conn, breaker: CircuitBreak
|
|||
workers = breaker.max_workers()
|
||||
succeeded, failed = await func(conn, max_workers=workers)
|
||||
if failed > 0 and succeeded == 0:
|
||||
breaker.record_failure()
|
||||
try:
|
||||
breaker.record_failure()
|
||||
except Exception:
|
||||
logger.warning("Stage %s: breaker write failed", name)
|
||||
elif succeeded > 0:
|
||||
breaker.record_success()
|
||||
try:
|
||||
breaker.record_success()
|
||||
except Exception:
|
||||
logger.warning("Stage %s: breaker write failed", name)
|
||||
except Exception:
|
||||
logger.exception("Stage %s: unhandled error in cycle", name)
|
||||
breaker.record_failure()
|
||||
try:
|
||||
breaker.record_failure()
|
||||
except Exception:
|
||||
logger.warning("Stage %s: breaker write failed", name)
|
||||
|
||||
# Wait for interval or shutdown, whichever comes first
|
||||
try:
|
||||
|
|
|
|||
Loading…
Reference in a new issue