Merge pull request #23 from 0xWheatyz/claude/agent-spawn-git-pull-cf0abm

Fetch origin and cut agent branches from origin/HEAD at spawn
This commit is contained in:
Wyatt
2026-07-23 06:58:35 -04:00
committed by GitHub
14 changed files with 499 additions and 52 deletions
+8 -3
View File
@@ -342,9 +342,14 @@ All routes require `Authorization: Bearer <AUTH_TOKEN>`. `GET /health` is unauth
Wired into each agent as `python -m handler.hooks <event>`:
- **`Stop` / `SessionEnd`** — checkpoint. On `Stop`, run `mise run test`; on failure,
return `decision: "block"` with the output so the turn cannot end on red. Records
`tests_status` / `tested_at`; `status = 'done'` only ever accompanies a pass.
- **`Stop` / `SessionEnd`** — checkpoint + completion gate. On `Stop`, run
`mise run test` and check the tree deterministically: failing tests, uncommitted
changes, or commits that exist only locally each return `decision: "block"` with the
full blocker list, so a turn cannot end on red or walk away from unshipped work.
Records `tests_status` / `tested_at`; `status = 'done'` only ever accompanies a
passing gate (tests green, tree clean, everything pushed). The agent's final message
is captured from the session transcript onto the checkmark, so the dashboard always
shows a real checkpoint whether or not the agent thought to leave one.
- **`PreToolUse`** — two jobs. An `AskUserQuestion` is *deferred*: the question is
persisted, the checkmark set to `paused_for_input`, and the tool call denied so control
hands off to the async answer/resume flow. A `Bash` command running `git push` triggers
+54 -3
View File
@@ -82,6 +82,29 @@ def ahead_count(cwd: str) -> int | None:
return None
def has_origin(cwd: str) -> bool:
"""Whether the repo has an ``origin`` remote configured."""
ok, out = _run(["remote"], cwd)
return ok and "origin" in out.split()
def unpushed_count(cwd: str) -> int | None:
"""Commits reachable from HEAD that no ``origin/*`` ref contains.
0 means everything on the current line of history has been pushed *somewhere* on
origin. Works with or without an upstream — worktree branches are created with
``--no-track``, so an ``@{upstream}``-based count would come up empty for them.
``None`` when the count cannot be computed.
"""
ok, out = _run(["rev-list", "--count", "HEAD", "--not", "--remotes=origin"], cwd)
if not ok:
return None
try:
return int(out.strip())
except ValueError:
return None
def add(cwd: str, paths: list[str]) -> tuple[bool, str]:
return _run(["add", *paths], cwd)
@@ -114,6 +137,34 @@ def clone(
return _run(args, cwd=None, env=env, timeout=_NETWORK_TIMEOUT)
def pull_ff(cwd: str, env: dict[str, str] | None = None) -> tuple[bool, str]:
"""Fast-forward-only pull — never merges, so a diverged clone fails loudly."""
return _run(["pull", "--ff-only"], cwd, env=env, timeout=_NETWORK_TIMEOUT)
def fetch(cwd: str, env: dict[str, str] | None = None) -> tuple[bool, str]:
"""``git fetch origin`` — refreshes every ``origin/*`` ref.
Unlike a plain pull, this works no matter which branch the working tree has
checked out (or left parked), so the remote's state is always current locally.
"""
return _run(["fetch", "origin"], cwd, env=env, timeout=_NETWORK_TIMEOUT)
def set_default_head(cwd: str, env: dict[str, str] | None = None) -> tuple[bool, str]:
"""``git remote set-head origin --auto`` — (re)pin ``origin/HEAD``.
``origin/HEAD`` is how the remote's default branch is known locally; clones made
by older tooling can lack it, and the remote's default can change.
"""
return _run(["remote", "set-head", "origin", "--auto"], cwd, env=env,
timeout=_NETWORK_TIMEOUT)
def default_branch_ref(cwd: str) -> str | None:
"""The remote default branch as a local ref name (``origin/main``), or ``None``."""
ok, out = _run(["symbolic-ref", "--quiet", "refs/remotes/origin/HEAD"], cwd)
if not ok or not out:
return None
return out.removeprefix("refs/remotes/") or None
def merge_ff(cwd: str, ref: str) -> tuple[bool, str]:
"""Fast-forward-only merge of ``ref`` — never merges, so a diverged checkout
fails loudly instead of silently growing a merge commit."""
return _run(["merge", "--ff-only", ref], cwd)
+5 -3
View File
@@ -337,13 +337,15 @@ class RunSupervisor:
)
# Hooks are the authority on agent status — they ran inside the run and
# may have set paused_for_input/blocked/done already. Only an agent still
# marked ``working`` needs the process's verdict.
# marked ``working`` needs the process's verdict — and ``done`` is a gate
# outcome, not an exit code: an agent still ``working`` after a clean
# exit means the Stop gate never recorded a verdict (hook misfired,
# identity missing), so nothing has verified its tests/commits/pushes.
# An operator cancel is the one completion that needs no gate.
agent = repo.get_agent_by_id(conn, self.agent["id"])
if finished and agent is not None and agent["status"] == "working":
if self._canceled:
repo.set_agent_status(conn, self.agent["id"], "done")
elif clean:
repo.set_agent_status(conn, self.agent["id"], "done")
else:
repo.set_agent_status(conn, self.agent["id"], "blocked")
if not clean and not self._canceled:
+24 -7
View File
@@ -1,4 +1,4 @@
"""Clone-or-pull a project's repository — the stateless "always pull" step.
"""Clone-or-fetch a project's repository — the stateless "always pull" step.
Where a clone lands on disk is Handler's concern, not the operator's: the API computes
``root_dir`` under ``PROJECTS_ROOT`` at registration, and this module makes the checkout
@@ -70,11 +70,16 @@ def ssh_env(git_remote: str | None, conn: Connection) -> dict[str, str]:
def sync_project(project: dict, conn: Connection | None = None) -> dict:
"""Clone the project's remote into ``root_dir``, or fast-forward an existing clone.
"""Clone the project's remote into ``root_dir``, or refresh an existing clone.
Idempotent by design — scheduled/stateless runs call this before every spawn so the
working tree always starts from the remote's latest state. Raises :class:`SyncError`
when the project has no remote or git fails.
working tree always starts from the remote's latest state. An existing clone is
``git fetch``\\ ed rather than pulled: a pull only moves the branch the root happens
to have checked out, and an agent parked on a feature branch used to leave
``origin/*`` (and therefore every branch cut for a new agent) hours stale. After
the fetch, ``origin/HEAD`` is re-pinned and the checkout is fast-forwarded only
when it is sitting on the default branch. Raises :class:`SyncError` when the
project has no remote or git fails.
"""
remote = project.get("git_remote")
root = project["root_dir"]
@@ -88,10 +93,22 @@ def sync_project(project: dict, conn: Connection | None = None) -> dict:
env, config = _auth_context(project, conn)
if gitops.is_repo(root):
ok, out = gitops.pull_ff(root, env=env)
ok, out = gitops.fetch(root, env=env)
if not ok:
raise SyncError(f"pull failed in {root}: {out}")
return {"action": "pulled", "root_dir": root, "detail": out}
raise SyncError(f"fetch failed in {root}: {out}")
# Best-effort: worktree spawns cut new branches from origin/HEAD, so keep it
# pinned even for clones that predate it (or whose remote default changed).
gitops.set_default_head(root, env=env)
detail = out
default_ref = gitops.default_branch_ref(root)
if default_ref and gitops.current_branch(root) == default_ref.split("/", 1)[1]:
ok, ff_out = gitops.merge_ff(root, default_ref)
if not ok:
raise SyncError(
f"fast-forward of {default_ref} failed in {root}: {ff_out}"
)
detail = ff_out or detail
return {"action": "pulled", "root_dir": root, "detail": detail}
os.makedirs(os.path.dirname(root) or ".", exist_ok=True)
ok, out = gitops.clone(remote, root, env=env, config=config)
+6 -4
View File
@@ -95,10 +95,12 @@ def spawn(
raise SpawnError(f"agent '{name}' already exists in project '{project_id}'")
# Stateless workflows: start every run from the remote's latest state. An
# existing clone is fast-forwarded (failure degrades to a note — a stale tree is
# usable, an offline forge shouldn't brick spawning); a missing/empty root is
# cloned, and that failing is fatal (there is nothing to run against). A
# non-empty root that isn't a git repo is left alone — it's manually managed.
# existing clone is fetched — refreshing origin/* even when the root checkout is
# parked on an agent's branch — and fast-forwarded when it sits on the default
# branch (failure degrades to a note — a stale tree is usable, an offline forge
# shouldn't brick spawning); a missing/empty root is cloned, and that failing is
# fatal (there is nothing to run against). A non-empty root that isn't a git
# repo is left alone — it's manually managed.
root = project["root_dir"]
if project.get("git_remote"):
if gitops.is_repo(root):
+30 -3
View File
@@ -35,6 +35,25 @@ def _slug(name: str) -> str:
return slug or "agent"
def _default_branch_start(project_root: str) -> str | None:
"""The remote default branch ref (``origin/main``) when the clone knows it.
New agent branches are cut from here rather than the root's ``HEAD``: the root
checkout can legitimately be parked on some earlier agent's branch, and cutting
from it handed fresh agents history that was hours behind the remote.
"""
result = subprocess.run(
["git", "-C", project_root, "symbolic-ref", "--quiet",
"refs/remotes/origin/HEAD"],
capture_output=True,
text=True,
)
ref = result.stdout.strip()
if result.returncode != 0 or not ref.startswith("refs/remotes/"):
return None
return ref.removeprefix("refs/remotes/")
def _branch_exists(project_root: str, branch: str) -> bool:
return (
subprocess.run(
@@ -69,13 +88,21 @@ def resolve_working_dir(
raise IsolationError(f"{target} escapes project root {project_root}")
# `git worktree add <path> <branch>` only checks out an *existing* ref; a fresh
# feature branch won't exist yet (spawn starts from the remote's latest state), so
# create it with -b. An existing local branch is checked out as-is; if it exists
# only on a remote, git DWIMs a tracking branch from the bare `add`.
# create it with -b — from origin/HEAD when the clone has a remote, so the new
# branch starts at the remote default branch's tip regardless of where the root
# checkout is parked (--no-track: the branch must not adopt the default branch as
# its upstream, or the agent's plain `git push` would aim at it). An existing
# local branch is checked out as-is; if it exists only on a remote, git DWIMs a
# tracking branch from the bare `add`.
cmd = ["git", "-C", project_root, "worktree", "add"]
if _branch_exists(project_root, worktree_branch):
cmd += [target, worktree_branch]
else:
cmd += ["-b", worktree_branch, target]
start = _default_branch_start(project_root)
if start:
cmd += ["--no-track", "-b", worktree_branch, target, start]
else:
cmd += ["-b", worktree_branch, target]
result = subprocess.run(cmd, capture_output=True, text=True)
if result.returncode != 0:
raise WorktreeError(
+96 -18
View File
@@ -1,14 +1,19 @@
"""Stop / SessionEnd — the checkpoint + verification gate (README 3.5).
On ``Stop`` the gate runs the project's own ``test`` task and blocks the turn on
failure, so a turn cannot end on a broken suite. The result feeds straight into the
schema: ``status = 'done'`` is only ever recorded alongside a passing test run — not a
claim taken on faith. ``SessionEnd`` cannot be blocked, so it just records a final
checkpoint with the end reason.
On ``Stop`` the gate runs the project's own ``test`` task and checks the working tree
deterministically: failing tests, uncommitted changes, or commits that exist only
locally each block the turn, so an agent cannot end on a broken suite or walk away
from work it never committed or pushed. ``status = 'done'`` is only ever recorded
alongside a passing gate — not a claim taken on faith. The agent's final message is
captured from the session transcript onto the checkmark, so the dashboard always has a
real checkpoint to show regardless of whether the agent thought to leave one.
``SessionEnd`` cannot be blocked, so it just records a final checkpoint with the end
reason.
"""
from __future__ import annotations
import json
from datetime import UTC, datetime
from sqlalchemy import Connection
@@ -84,16 +89,89 @@ def handle_mise_init_stop(conn: Connection, ident: Identity, hook_input: HookInp
return {}
def _completion_blockers(working_dir: str) -> list[str]:
"""The commit/push half of the completion gate — ``[]`` when the tree is settled.
Deterministic checks against git itself, not the agent's account of its work: a
dirty tree means work was never committed; commits no ``origin/*`` ref contains
mean work was never pushed. A working dir that isn't a git checkout (manually
managed roots, empty repos) has nothing to gate.
"""
if gitops.head_sha(working_dir) is None:
return []
blockers = []
if not gitops.is_clean(working_dir):
blockers.append("there are uncommitted changes — commit your work")
if gitops.has_origin(working_dir):
unpushed = gitops.unpushed_count(working_dir)
if unpushed:
blockers.append(
f"{unpushed} commit(s) exist only locally — push them "
"(`git push -u origin <branch>`)"
)
return blockers
def _final_assistant_text(transcript_path: str | None) -> str | None:
"""The agent's last assistant message from the session transcript.
Captured deterministically so the dashboard's checkpoint never depends on the
agent remembering to file one. Returns ``None`` when there is no transcript or no
text in it; never raises.
"""
if not transcript_path:
return None
try:
fh = open(transcript_path, encoding="utf-8")
except OSError:
return None
last = None
with fh:
for line in fh:
try:
entry = json.loads(line)
except ValueError:
continue
if entry.get("type") != "assistant":
continue
content = (entry.get("message") or {}).get("content")
if isinstance(content, str):
texts = [content]
elif isinstance(content, list):
texts = [
block.get("text", "")
for block in content
if isinstance(block, dict) and block.get("type") == "text"
]
else:
continue
text = "\n".join(t for t in texts if t).strip()
if text:
last = text
return last
def handle_stop(conn: Connection, ident: Identity, hook_input: HookInput) -> dict:
if ident.mise_init:
return handle_mise_init_stop(conn, ident, hook_input)
working_dir = ident.working_dir or hook_input.cwd or "."
ok, output = verify.run_test(working_dir)
tests_ok, output = verify.run_test(working_dir)
blockers = [] if tests_ok else ["the test suite is failing (`mise run test`)"]
blockers += _completion_blockers(working_dir)
now = datetime.now(UTC)
status = "done" if ok else "blocked"
tests_status = "pass" if ok else "fail"
summary = "checkpoint: tests passed" if ok else "checkpoint blocked: tests failed"
status = "done" if not blockers else "blocked"
tests_status = "pass" if tests_ok else "fail"
summary = (
"checkpoint: tests passed, work committed and pushed"
if not blockers
else "checkpoint blocked: " + "; ".join(blockers)
)
# A done agent's checkmark carries its own closing message — the substance the
# dashboard shows; a blocked one carries the blockers (the next turn will re-capture
# the narrative once the gate clears).
final_text = _final_assistant_text(hook_input.transcript_path)
where_it_stopped = final_text[:4000] if not blockers and final_text else summary
log_id = repo.insert_log_entry(
conn,
@@ -108,25 +186,25 @@ def handle_stop(conn: Connection, ident: Identity, hook_input: HookInput) -> dic
agent_id=ident.agent_id,
checkpoint_at=now,
status=status,
where_it_stopped=summary,
where_it_stopped=where_it_stopped,
log_entry_id=log_id,
tests_status=tests_status,
tested_at=now,
)
repo.set_agent_status(conn, ident.agent_id, status)
if not ok:
if blockers:
# Guard against an infinite block loop: if we already re-invoked once, record
# the failure but let the turn end rather than blocking forever.
if hook_input.stop_hook_active:
return {}
return {
"decision": "block",
"reason": (
"The test gate failed; the turn cannot end on a broken suite. "
f"`mise run test` output:\n{output[-4000:]}"
),
}
reason = (
"The completion gate failed — an agent is only done when its tests pass "
"and its work is committed and pushed. Blockers:\n- " + "\n- ".join(blockers)
)
if not tests_ok:
reason += f"\n\n`mise run test` output:\n{output[-4000:]}"
return {"decision": "block", "reason": reason}
return {}
+4
View File
@@ -44,6 +44,10 @@ class HookInput:
def message(self) -> str | None:
return self.raw.get("message")
@property
def transcript_path(self) -> str | None:
return self.raw.get("transcript_path")
@property
def stop_hook_active(self) -> bool:
return bool(self.raw.get("stop_hook_active"))
+3 -1
View File
@@ -81,7 +81,9 @@ def test_spawn_run_streams_events_and_completes(headless_env, tmp_path):
assert [e["seq"] for e in events] == [1, 2, 3]
# last_output is now derived from assistant text — the log the UI shows is real.
assert updated["last_output"] == "working on: build the thing"
assert updated["status"] == "done"
# done is a gate outcome, not an exit code: the fake claude never ran the Stop
# hook, so nothing verified tests/commits/pushes and the agent must not be done.
assert updated["status"] == "blocked"
assert updated["session_id"] == run["session_id"]
assert updated["worker_id"] == "w1"
# The session archive was uploaded at exit for cross-worker resume.
+112 -2
View File
@@ -20,13 +20,22 @@ def _fake_mise_state(monkeypatch, *, has_test, clean, ahead):
monkeypatch.setattr(gitops, "ahead_count", lambda cwd: ahead)
def _fake_git_state(monkeypatch, *, is_repo=True, clean=True, unpushed=0, has_origin=True):
monkeypatch.setattr(gitops, "head_sha", lambda cwd: "abc123" if is_repo else None)
monkeypatch.setattr(gitops, "is_clean", lambda cwd: clean)
monkeypatch.setattr(gitops, "has_origin", lambda cwd: has_origin)
monkeypatch.setattr(gitops, "unpushed_count", lambda cwd: unpushed)
def test_stop_blocks_on_failing_tests(conn, monkeypatch):
ident = _seed(conn)
monkeypatch.setattr(verify, "run_test", lambda cwd: (False, "1 failed"))
_fake_git_state(monkeypatch)
result = checkpoint.handle_stop(conn, ident, HookInput({"session_id": "s1"}, "stop"))
assert result["decision"] == "block"
assert "test gate failed" in result["reason"]
assert "test suite is failing" in result["reason"]
assert "1 failed" in result["reason"]
cm = repo.get_checkmark(conn, ident.agent_id)
assert cm["tests_status"] == "fail"
@@ -35,9 +44,59 @@ def test_stop_blocks_on_failing_tests(conn, monkeypatch):
assert repo.get_agent_by_name(conn, "p", "a")["status"] == "blocked"
def test_stop_allows_done_on_passing_tests(conn, monkeypatch):
def test_stop_blocks_on_uncommitted_changes_even_with_green_tests(conn, monkeypatch):
ident = _seed(conn)
monkeypatch.setattr(verify, "run_test", lambda cwd: (True, "ok"))
_fake_git_state(monkeypatch, clean=False)
result = checkpoint.handle_stop(conn, ident, HookInput({"session_id": "s1"}, "stop"))
assert result["decision"] == "block"
assert "uncommitted" in result["reason"]
cm = repo.get_checkmark(conn, ident.agent_id)
assert cm["tests_status"] == "pass" # tests still recorded honestly
assert cm["status"] == "blocked"
assert repo.get_agent_by_name(conn, "p", "a")["status"] == "blocked"
def test_stop_blocks_on_unpushed_commits(conn, monkeypatch):
ident = _seed(conn)
monkeypatch.setattr(verify, "run_test", lambda cwd: (True, "ok"))
_fake_git_state(monkeypatch, unpushed=3)
result = checkpoint.handle_stop(conn, ident, HookInput({"session_id": "s1"}, "stop"))
assert result["decision"] == "block"
assert "3 commit(s) exist only locally" in result["reason"]
assert repo.get_agent_by_name(conn, "p", "a")["status"] == "blocked"
def test_stop_reports_every_blocker_at_once(conn, monkeypatch):
ident = _seed(conn)
monkeypatch.setattr(verify, "run_test", lambda cwd: (False, "boom"))
_fake_git_state(monkeypatch, clean=False, unpushed=1)
result = checkpoint.handle_stop(conn, ident, HookInput({"session_id": "s1"}, "stop"))
assert "test suite is failing" in result["reason"]
assert "uncommitted" in result["reason"]
assert "exist only locally" in result["reason"]
def test_stop_skips_push_gate_without_an_origin_remote(conn, monkeypatch):
ident = _seed(conn)
monkeypatch.setattr(verify, "run_test", lambda cwd: (True, "ok"))
# Local-only project: commits exist that no remote has, but there is no origin
# to push them to — the push gate must not deadlock the agent.
_fake_git_state(monkeypatch, unpushed=5, has_origin=False)
result = checkpoint.handle_stop(conn, ident, HookInput({"session_id": "s1"}, "stop"))
assert result == {}
assert repo.get_checkmark(conn, ident.agent_id)["status"] == "done"
def test_stop_allows_done_when_tests_pass_and_tree_is_settled(conn, monkeypatch):
ident = _seed(conn)
monkeypatch.setattr(verify, "run_test", lambda cwd: (True, "ok"))
_fake_git_state(monkeypatch)
result = checkpoint.handle_stop(conn, ident, HookInput({"session_id": "s1"}, "stop"))
assert result == {} # no block
@@ -48,9 +107,60 @@ def test_stop_allows_done_on_passing_tests(conn, monkeypatch):
assert cm["log_entry_id"] is not None
def test_stop_allows_done_when_working_dir_is_not_a_repo(conn, monkeypatch):
# A manually managed root has nothing to gate beyond its tests.
ident = _seed(conn)
monkeypatch.setattr(verify, "run_test", lambda cwd: (True, "ok"))
_fake_git_state(monkeypatch, is_repo=False, clean=False, unpushed=9)
result = checkpoint.handle_stop(conn, ident, HookInput({"session_id": "s1"}, "stop"))
assert result == {}
assert repo.get_checkmark(conn, ident.agent_id)["status"] == "done"
def test_stop_captures_final_message_as_checkpoint(conn, monkeypatch, tmp_path):
ident = _seed(conn)
monkeypatch.setattr(verify, "run_test", lambda cwd: (True, "ok"))
_fake_git_state(monkeypatch)
transcript = tmp_path / "session.jsonl"
transcript.write_text(
'{"type": "user", "message": {"content": "do the thing"}}\n'
"this line is not json\n"
'{"type": "assistant", "message": {"content": [{"type": "text", '
'"text": "Working on it."}]}}\n'
'{"type": "assistant", "message": {"content": [{"type": "tool_use", "id": "x"},'
' {"type": "text", "text": "Shipped the fix in abc123; tests green."}]}}\n'
)
hi = HookInput({"session_id": "s1", "transcript_path": str(transcript)}, "stop")
result = checkpoint.handle_stop(conn, ident, hi)
assert result == {}
cm = repo.get_checkmark(conn, ident.agent_id)
# The webui checkpoint carries the agent's own closing message, captured
# deterministically from the transcript — not left to the agent's discretion.
assert cm["where_it_stopped"] == "Shipped the fix in abc123; tests green."
def test_blocked_stop_shows_blockers_not_narrative(conn, monkeypatch, tmp_path):
ident = _seed(conn)
monkeypatch.setattr(verify, "run_test", lambda cwd: (True, "ok"))
_fake_git_state(monkeypatch, clean=False)
transcript = tmp_path / "session.jsonl"
transcript.write_text(
'{"type": "assistant", "message": {"content": [{"type": "text", '
'"text": "All done!"}]}}\n'
)
hi = HookInput({"session_id": "s1", "transcript_path": str(transcript)}, "stop")
checkpoint.handle_stop(conn, ident, hi)
cm = repo.get_checkmark(conn, ident.agent_id)
assert "uncommitted" in cm["where_it_stopped"]
def test_stop_does_not_reblock_when_already_active(conn, monkeypatch):
ident = _seed(conn)
monkeypatch.setattr(verify, "run_test", lambda cwd: (False, "still failing"))
_fake_git_state(monkeypatch)
hi = HookInput({"session_id": "s1", "stop_hook_active": True}, "stop")
result = checkpoint.handle_stop(conn, ident, hi)
assert result == {} # recorded, but not an infinite block
+5 -3
View File
@@ -71,13 +71,15 @@ def test_spawn_via_api_then_worker_runs_headless_claude(client, auth, headless_e
assert got["result"]["name"] == "api"
# ...and the run's whole life shows up via the API: events stream in, the agent
# reconciles to done, last_output is the assistant's text.
# reconciles, last_output is the assistant's text. The fake claude never runs the
# Stop gate, so the clean exit reconciles to blocked, not done — done is only ever
# a gate verdict (tests pass, work committed and pushed).
def finished():
agents = client.get("/projects/proj/agents", headers=auth).json()
return agents if agents and agents[0]["status"] == "done" else None
return agents if agents and agents[0]["status"] == "blocked" else None
agents = _wait(finished)
assert agents is not None, "run never reconciled to done"
assert agents is not None, "run never reconciled"
agent = agents[0]
assert agent["name"] == "api"
assert agent["session_id"]
+13 -5
View File
@@ -150,7 +150,7 @@ def test_sync_endpoint_400_without_remote(client, auth, env, tmp_path):
@pytest.fixture
def fake_sync_gitops(monkeypatch):
"""Fake the clone/pull side of the gitops seam."""
state = {"clone": [], "pull": [], "config": [], "repos": set(), "ok": True, "out": ""}
state = {"clone": [], "fetch": [], "config": [], "repos": set(), "ok": True, "out": ""}
def is_repo(path):
return path in state["repos"]
@@ -162,17 +162,25 @@ def fake_sync_gitops(monkeypatch):
state["repos"].add(dest)
return state["ok"], state["out"]
def pull_ff(cwd, env=None):
state["pull"].append({"cwd": cwd, "env": env or {}})
def fetch(cwd, env=None):
state["fetch"].append({"cwd": cwd, "env": env or {}})
return state["ok"], state["out"]
def set_default_head(cwd, env=None):
return True, ""
def default_branch_ref(cwd):
return None
def config_local(cwd, key, value):
state["config"].append({"cwd": cwd, "key": key, "value": value})
return True, ""
monkeypatch.setattr(gitops, "is_repo", is_repo)
monkeypatch.setattr(gitops, "clone", clone)
monkeypatch.setattr(gitops, "pull_ff", pull_ff)
monkeypatch.setattr(gitops, "fetch", fetch)
monkeypatch.setattr(gitops, "set_default_head", set_default_head)
monkeypatch.setattr(gitops, "default_branch_ref", default_branch_ref)
monkeypatch.setattr(gitops, "config_local", config_local)
return state
@@ -192,7 +200,7 @@ def test_cmd_sync_clones_then_pulls(env, fake_sync_gitops):
result = worker.execute_command(command)
assert result["action"] == "pulled"
assert fake_sync_gitops["pull"][0]["cwd"] == "/tmp/r"
assert fake_sync_gitops["fetch"][0]["cwd"] == "/tmp/r"
def test_cmd_sync_failure_is_command_error(env, fake_sync_gitops):
+85
View File
@@ -0,0 +1,85 @@
"""``sync_project`` against real git repos — the fetch-not-pull regression.
A pull only moves whichever branch the root has checked out; with the root parked on
an agent's feature branch, ``origin/*`` went stale and every branch cut for a new
agent started several commits behind the remote's default branch. These tests use a
filesystem remote (no host, no credentials) so the git behaviour itself is exercised.
"""
from __future__ import annotations
import subprocess
import pytest
from handler.control import reposync
def _git(cwd, *args):
subprocess.run(["git", "-C", str(cwd), *args], check=True, capture_output=True)
def _sha(cwd, ref="HEAD") -> str:
return subprocess.run(
["git", "-C", str(cwd), "rev-parse", ref],
check=True, capture_output=True, text=True,
).stdout.strip()
@pytest.fixture
def remote_and_root(tmp_path):
"""An origin repo, a clone of it as the project root, then origin moves ahead."""
origin = tmp_path / "origin"
origin.mkdir()
_git(origin, "init", "-q", "-b", "main")
for repo_dir in (origin,):
_git(repo_dir, "config", "user.email", "t@t.co")
_git(repo_dir, "config", "user.name", "t")
_git(repo_dir, "config", "commit.gpgsign", "false")
_git(origin, "commit", "-q", "--allow-empty", "-m", "one")
root = tmp_path / "proj"
subprocess.run(
["git", "clone", "-q", str(origin), str(root)], check=True, capture_output=True
)
_git(root, "config", "user.email", "t@t.co")
_git(root, "config", "user.name", "t")
_git(root, "config", "commit.gpgsign", "false")
_git(origin, "commit", "-q", "--allow-empty", "-m", "two")
return origin, root
def _project(origin, root) -> dict:
return {"id": "p", "root_dir": str(root), "git_remote": str(origin)}
def test_sync_refreshes_origin_even_when_root_parked_on_agent_branch(
env, remote_and_root
):
origin, root = remote_and_root
_git(root, "checkout", "-q", "-b", "agent/old-work")
# Simulate a clone that never had origin/HEAD — sync must re-pin it too.
_git(root, "remote", "set-head", "origin", "-d")
result = reposync.sync_project(_project(origin, root))
assert result["action"] == "pulled"
assert _sha(root, "origin/main") == _sha(origin, "main")
assert _sha(root, "refs/remotes/origin/HEAD") == _sha(origin, "main")
# The parked checkout itself is left alone — only origin/* moves.
assert _sha(root, "HEAD") != _sha(origin, "main")
def test_sync_fast_forwards_a_checkout_sitting_on_the_default_branch(
env, remote_and_root
):
origin, root = remote_and_root
result = reposync.sync_project(_project(origin, root))
assert result["action"] == "pulled"
assert _sha(root, "HEAD") == _sha(origin, "main")
def test_sync_fails_loudly_when_the_default_branch_diverged(env, remote_and_root):
origin, root = remote_and_root
_git(root, "commit", "-q", "--allow-empty", "-m", "local divergence")
with pytest.raises(reposync.SyncError, match="fast-forward"):
reposync.sync_project(_project(origin, root))
+54
View File
@@ -31,6 +31,36 @@ def repo(tmp_path):
return root
@pytest.fixture
def cloned(tmp_path):
"""A root cloned from an origin whose main has since moved on.
Mirrors the spawn-time state after ``reposync.sync_project``: origin/* is fresh
(fetched), but the root's checkout still sits on the older commit.
"""
origin = tmp_path / "origin"
origin.mkdir()
_git(origin, "init", "-q", "-b", "main")
_git(origin, "config", "user.email", "t@t.co")
_git(origin, "config", "user.name", "t")
_git(origin, "config", "commit.gpgsign", "false")
_git(origin, "commit", "-q", "--allow-empty", "-m", "one")
root = tmp_path / "proj"
subprocess.run(
["git", "clone", "-q", str(origin), str(root)], check=True, capture_output=True
)
_git(origin, "commit", "-q", "--allow-empty", "-m", "two")
_git(root, "fetch", "-q", "origin")
return root
def _sha(cwd, ref="HEAD") -> str:
return subprocess.run(
["git", "-C", str(cwd), "rev-parse", ref],
check=True, capture_output=True, text=True,
).stdout.strip()
def _is_worktree(root, path) -> bool:
out = subprocess.run(
["git", "-C", str(root), "worktree", "list", "--porcelain"],
@@ -54,6 +84,30 @@ def test_creates_branch_when_it_does_not_exist(repo):
assert "feat/new-thing" in branches
def test_new_branch_is_cut_from_remote_default_not_root_head(cloned):
# The regression: new agent branches were cut from the root's HEAD, so a checkout
# sitting behind (or parked on an earlier agent's branch) produced branches several
# commits behind origin's default branch.
target = worktree.resolve_working_dir(
str(cloned), "agent", worktree_branch="feat/fresh"
)
assert _sha(target) == _sha(cloned, "origin/main")
assert _sha(target) != _sha(cloned, "HEAD")
def test_new_branch_from_remote_default_gets_no_upstream(cloned):
# --no-track: without it the new branch adopts origin/main as upstream, and the
# agent's plain `git push` would aim at the default branch.
target = worktree.resolve_working_dir(
str(cloned), "agent", worktree_branch="feat/fresh"
)
upstream = subprocess.run(
["git", "-C", target, "rev-parse", "--abbrev-ref", "@{upstream}"],
capture_output=True, text=True,
)
assert upstream.returncode != 0
def test_checks_out_existing_branch(repo):
_git(repo, "branch", "feat/existing")
target = worktree.resolve_working_dir(