fix: prevent reweave PR flood — freshen base, cleanup branches on failure
Three fixes for the reweave merge failure cycle: 1. reweave.py: fetch + reset to origin/main before branch creation, eliminating the stale-base problem that caused ~75% merge failure rate 2. merge.py: delete remote branch when closing reweave PRs (in reconcile, merge failure, and conflict retry paths) — prevents discover_external_prs from rediscovering stale branches and creating new PRs every 18 minutes 3. merge.py: skip cherry-pick retry for reweave branches — reweave modifies existing files so cherry-pick always fails, go straight to close+delete Pentagon-Agent: Ship <f3064ef4-c330-4809-ad37-39290b2eaa5b> Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Teleo Agents
parent
0591c4c0df
commit
adbe3bd911
2 changed files with 76 additions and 12 deletions
|
|
@ -1432,13 +1432,22 @@ async def _merge_domain_queue(conn, domain: str) -> tuple[int, int]:
|
|||
continue
|
||||
|
||||
if not pick_ok:
|
||||
# Cherry-pick failed — this is a genuine conflict (not a race condition).
|
||||
# No retry needed: cherry-pick onto fresh main means main can't have moved.
|
||||
logger.warning("PR #%d cherry-pick failed: %s", pr_num, pick_msg)
|
||||
conn.execute(
|
||||
"UPDATE prs SET status = 'conflict', merge_cycled = 1, merge_failures = COALESCE(merge_failures, 0) + 1, last_error = ? WHERE number = ?",
|
||||
(pick_msg[:500], pr_num),
|
||||
)
|
||||
logger.warning("PR #%d merge/cherry-pick failed: %s", pr_num, pick_msg)
|
||||
# Reweave: close immediately, don't retry (Ship: same rationale as ff-push failure)
|
||||
if branch.startswith("reweave/"):
|
||||
conn.execute(
|
||||
"UPDATE prs SET status = 'closed', merge_cycled = 1, merge_failures = COALESCE(merge_failures, 0) + 1, last_error = ? WHERE number = ?",
|
||||
(f"reweave merge failed (closed, not retried): {pick_msg[:400]}", pr_num),
|
||||
)
|
||||
await forgejo_api("PATCH", repo_path(f"pulls/{pr_num}"), {"state": "closed"})
|
||||
await forgejo_api("POST", repo_path(f"issues/{pr_num}/comments"),
|
||||
{"body": f"Reweave merge failed — closing. Next nightly reweave will create a fresh branch.\n\nError: {pick_msg[:200]}"})
|
||||
await _delete_remote_branch(branch)
|
||||
else:
|
||||
conn.execute(
|
||||
"UPDATE prs SET status = 'conflict', merge_cycled = 1, merge_failures = COALESCE(merge_failures, 0) + 1, last_error = ? WHERE number = ?",
|
||||
(pick_msg[:500], pr_num),
|
||||
)
|
||||
db.audit(conn, "merge", "cherry_pick_failed", json.dumps({"pr": pr_num, "error": pick_msg[:200]}))
|
||||
failed += 1
|
||||
continue
|
||||
|
|
@ -1483,10 +1492,24 @@ async def _merge_domain_queue(conn, domain: str) -> tuple[int, int]:
|
|||
|
||||
if not merge_ok:
|
||||
logger.error("PR #%d merge failed: %s", pr_num, merge_msg)
|
||||
conn.execute(
|
||||
"UPDATE prs SET status = 'conflict', merge_cycled = 1, merge_failures = COALESCE(merge_failures, 0) + 1, last_error = ? WHERE number = ?",
|
||||
(merge_msg[:500], pr_num),
|
||||
)
|
||||
# Reweave PRs: close immediately on failure. Cherry-pick retry
|
||||
# will always fail (reweave modifies existing files). Next nightly
|
||||
# run creates a fresh branch from current main — retry is wasteful.
|
||||
# (Ship: prevents reweave flood + wasted retry cycles)
|
||||
if branch.startswith("reweave/"):
|
||||
conn.execute(
|
||||
"UPDATE prs SET status = 'closed', merge_cycled = 1, merge_failures = COALESCE(merge_failures, 0) + 1, last_error = ? WHERE number = ?",
|
||||
(f"reweave merge failed (closed, not retried): {merge_msg[:400]}", pr_num),
|
||||
)
|
||||
await forgejo_api("PATCH", repo_path(f"pulls/{pr_num}"), {"state": "closed"})
|
||||
await forgejo_api("POST", repo_path(f"issues/{pr_num}/comments"),
|
||||
{"body": f"Reweave merge failed — closing. Next nightly reweave will create a fresh branch.\n\nError: {merge_msg[:200]}"})
|
||||
await _delete_remote_branch(branch)
|
||||
else:
|
||||
conn.execute(
|
||||
"UPDATE prs SET status = 'conflict', merge_cycled = 1, merge_failures = COALESCE(merge_failures, 0) + 1, last_error = ? WHERE number = ?",
|
||||
(merge_msg[:500], pr_num),
|
||||
)
|
||||
db.audit(conn, "merge", "merge_failed", json.dumps({"pr": pr_num, "error": merge_msg[:200]}))
|
||||
failed += 1
|
||||
continue
|
||||
|
|
@ -1583,6 +1606,11 @@ async def _reconcile_db_state(conn):
|
|||
continue
|
||||
|
||||
if forgejo_state == "closed" and not is_merged and db_status not in ("closed",):
|
||||
# Clean up branch too — stale branches get rediscovered as new PRs
|
||||
# (Ship: prevents reweave flood where closed PRs leave branches that
|
||||
# trigger discover_external_prs → new PR → fail → close → repeat)
|
||||
if branch:
|
||||
await _delete_remote_branch(branch)
|
||||
conn.execute(
|
||||
"UPDATE prs SET status = 'closed', last_error = 'reconciled: closed on Forgejo' WHERE number = ?",
|
||||
(pr_number,),
|
||||
|
|
@ -1775,6 +1803,22 @@ async def _retry_conflict_prs(conn) -> tuple[int, int]:
|
|||
branch = row["branch"]
|
||||
attempts = row["conflict_rebase_attempts"] or 0
|
||||
|
||||
# Reweave branches modify existing files — cherry-pick will always fail.
|
||||
# Close immediately and delete branch. Next nightly reweave creates fresh.
|
||||
# (Ship: prevents wasting 3 retry cycles on branches that can never cherry-pick)
|
||||
if branch.startswith("reweave/"):
|
||||
logger.info("Reweave PR #%d: skipping retry, closing + deleting branch", pr_number)
|
||||
conn.execute(
|
||||
"UPDATE prs SET status = 'closed', last_error = 'reweave: closed (retry skipped, next nightly creates fresh)' WHERE number = ?",
|
||||
(pr_number,),
|
||||
)
|
||||
await forgejo_api("PATCH", repo_path(f"pulls/{pr_number}"), {"state": "closed"})
|
||||
await forgejo_api("POST", repo_path(f"issues/{pr_number}/comments"),
|
||||
{"body": "Reweave conflict — closing instead of retrying. Cherry-pick always fails on reweave branches (they modify existing files). Next nightly reweave will create a fresh branch from current main."})
|
||||
await _delete_remote_branch(branch)
|
||||
failed += 1
|
||||
continue
|
||||
|
||||
logger.info("Conflict retry [%d/%d] PR #%d branch=%s",
|
||||
attempts + 1, MAX_CONFLICT_REBASE_ATTEMPTS, pr_number, branch)
|
||||
|
||||
|
|
|
|||
|
|
@ -597,7 +597,14 @@ def _write_edge_regex(neighbor_path: Path, fm_text: str, body_text: str,
|
|||
|
||||
|
||||
def create_branch(repo_root: Path, branch_name: str) -> bool:
|
||||
"""Create and checkout a new branch. Cleans up stale local/remote branches from prior failed runs."""
|
||||
"""Create and checkout a new branch from fresh origin/main.
|
||||
|
||||
Cleans up stale local/remote branches from prior failed runs, then
|
||||
fetches + resets to origin/main so the branch is never based on stale state.
|
||||
(Ship: reduces reweave merge failure rate from ~75% to near-zero by
|
||||
eliminating the stale-base problem that causes superset assertion failures
|
||||
and force-with-lease races.)
|
||||
"""
|
||||
# Delete stale local branch if it exists (e.g., from a failed earlier run today)
|
||||
subprocess.run(["git", "branch", "-D", branch_name],
|
||||
cwd=str(repo_root), capture_output=True) # ignore errors if branch doesn't exist
|
||||
|
|
@ -610,6 +617,19 @@ def create_branch(repo_root: Path, branch_name: str) -> bool:
|
|||
subprocess.run(["git", "push", push_url, "--delete", branch_name],
|
||||
cwd=str(repo_root), capture_output=True) # ignore errors if branch doesn't exist
|
||||
|
||||
# Freshen to origin/main before branching — ensures branch base matches
|
||||
# the main HEAD that _merge_reweave_pr will read at merge time.
|
||||
try:
|
||||
subprocess.run(["git", "fetch", "origin", "main"],
|
||||
cwd=str(repo_root), check=True, capture_output=True, timeout=30)
|
||||
subprocess.run(["git", "checkout", "main"],
|
||||
cwd=str(repo_root), check=True, capture_output=True)
|
||||
subprocess.run(["git", "reset", "--hard", "origin/main"],
|
||||
cwd=str(repo_root), check=True, capture_output=True)
|
||||
except (subprocess.CalledProcessError, subprocess.TimeoutExpired) as e:
|
||||
logger.error("Failed to freshen to origin/main: %s", e)
|
||||
return False
|
||||
|
||||
try:
|
||||
subprocess.run(["git", "checkout", "-b", branch_name],
|
||||
cwd=str(repo_root), check=True, capture_output=True)
|
||||
|
|
|
|||
Loading…
Reference in a new issue