宜博 / lemongraph

New target projects never got .claude/agents/*.md deployed, so their first
Planner call always failed immediately (claude --agent planner finds nothing
in cwd) -- self-target usage never noticed since those files are already
committed as part of this repo. create_project() now deploys and commits
them alongside the existing .graphlemon/ init commit.

Also: unroutable execution failures were recorded as a bare
blocked_reason='execution_error' with no way to see what actually broke.
scheduler._block_task()/task_execution._mark_blocked() now persist the real
exception message into execution_event.payload (blocked_reason itself is
unchanged -- budget_guardrail matches its exact value elsewhere).

Found via a real console Start-button failure on a freshly created project;
see docs/implementation-gap-analysis.md for the full writeup.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Users had no way to actually start a queued goal from the console --
task.status just sits at 'queued' forever. Traced the root cause through
03-C: c_task_create's own contract ("若 max_concurrent_goals 已达上限，
任务落 queued 但不触发调度") implies task creation auto-triggers
scheduling otherwise, and 03-C/04-P repeatedly assume an always-on Org
Graph scheduler that watches the queue -- src/scheduler.py builds the
mechanism but nothing ever spins it up as a running process, so no
"start" button was ever designed because none was supposed to be needed.

Design (confirmed with user, both recommended options chosen):
- Pause/Stop are a soft stop, not a real subprocess kill -- the current
  in-flight `claude` call finishes naturally, only the next phase is
  withheld. Hard-killing would need Popen + PID tracking, out of scope.
- No new task.status enum value -- reuses blocked_pending_human with
  blocked_reason='user_paused'/'user_stopped', riding the existing
  manual_resume mechanism instead of a schema change.

New src/task_execution.py: run_or_resume_task_lifecycle() resumes from
whichever phase actually hasn't run yet (queued/planning_brd_prd_sdd/
coding), start_task_execution_in_background() runs it to completion on
its own daemon thread + sqlite connection, request_pause() blocks an
in-flight task. Extended /route's manual_resume handling so resuming
from a user-initiated pause/stop actually re-continues execution in the
background, not just flips the status field back.

Real gap found while building this: backend_server.create_server() never
stored db_path on the server object -- needed for the new background
thread to open its own connection to the same db.

22 new tests (14 src/test_task_execution.py + 8 TaskExecutionRouteTest in
test_backend_server.py, HTTP wiring mocked around the already-unit-tested
background thread mechanics). Verified against a real running server via
curl: /execute 409s a non-queued task, /pause 409s a queued task and a
double-pause, succeeds on a coding task. src/ suite: 496 tests, all green.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Two new console pages requested directly by the user, beyond 02-V's
original declared non-goal ("不做完整多项目管理 UI（项目列表/切换）"):

- v_project_list: full project list + rename + archive/reactivate.
  "Import an existing directory with real code" needs no new code --
  project_scaffold.create_project() already only ever adds .graphlemon/
  inside the target folder. New: src/project_query.py (list/get/update),
  GET/PUT/DELETE /api/projects[/:id]. DELETE archives (status='archived'),
  never a physical row delete -- project_id is FK-referenced from task/
  artifact/bug_record/etc., and 01-M's own active/archived enum already
  models this as soft-delete.

- v_goal_list: extends the existing v_task_board/v_task_detail rather than
  duplicating them. Added sort/order to task_query.list_tasks() (column
  whitelist, no injection surface) and edit/delete on v_task_detail, both
  restricted to status='queued' (task_query.TaskNotEditableError, HTTP 409)
  -- editing or deleting a goal after real work has referenced it would
  leave that history pointing at something that no longer matches reality.

Implemented directly rather than through graphlemon's own self-hosting
loop -- confirmed with the user first that implement_code() always uses a
hardcoded single-node manifest (no plan_work_graph() call for Coder), so a
multi-page/multi-endpoint feature like this would've been one unreviewable
Coder session with no way to decompose it.

Real bug found on first verification pass (not caught by the existing
_insert_task test helper, which never writes execution_event): a real
task_create.create_task() always writes an execution_event row in the same
transaction (01-M's FK, no ON DELETE CASCADE) -- even a never-touched
queued task already has one, so DELETE FROM task raised
sqlite3.IntegrityError. Fixed by clearing the task's own execution_event
rows first; new regression test goes through the real create_task() path.

474 tests green. Verified end-to-end against a real running server (every
new endpoint exercised via curl) since the Chrome extension is still
unavailable this session.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Attempt 13b was the first real run to get all the way through a real
cutover -- task lifecycle, classification, staging, health check (fixed
last commit), and a genuine blue-green cutover all succeeded for real. It
correctly landed in 'monitor' and then correctly couldn't finish: the real
production exit condition (deploy_monitor.MONITORING_WINDOW_HOURS=24h OR
MONITORING_MIN_TASK_COUNT=10 real tasks in the monitored project, NOT the
disposable per-cycle canary project) isn't practical to wait out in an
interactive session. This isn't a bug -- those are sensible real defaults
-- it's a testability gap: run_self_hosting_closed_loop already exposes
monitor_timeout_cycles as an override knob for exactly this kind of
situation, but never threaded the two constants that actually gate
"monitoring_window_clean" through to run_monitor_cycle.

Added monitor_window_hours/monitor_min_task_count params, defaulting to
deploy_monitor's real constants (production behavior unchanged), threaded
through to the actual run_monitor_cycle call. New assertion locks in that
overrides actually reach it.

Also documents the full run of 9 real bugs found and fixed across 13
attempts in development-plan.md's U-042 note.

564 tests green (441 src + 123 supervisor).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Attempts 7 and 11 both failed at exactly the same spot: process_alive read
'ok' within milliseconds of Popen, then http_health hit ECONNREFUSED in the
same second and gave up. Real cause: process_alive only confirms the
process EXISTS, not that backend_server.py has finished importing modules
and actually bound its listen socket -- a real, non-zero startup gap. The
old check_http_health did one urlopen(timeout=X) call; that timeout only
bounds how long to wait for a response once connected, not how long to
wait for the port to start accepting connections at all -- ECONNREFUSED
fires essentially instantly when nothing's listening yet, regardless of
timeout.

This touches an explicit 03-C design statement ("不重试——重试属于给坏版本
第二次机会"), so confirmed with the user before changing it rather than
just reinterpreting the policy unilaterally. Resolution: tolerating normal
startup latency within ONE health-check pass isn't "retrying a failed
check" -- check_process_alive already does exactly this (polls up to 30s
for the pid to exist). http_health now does the same, polling within its
own timeout for connection-refused-class errors specifically. A genuine
non-2xx HTTP response is still a definitive answer from a live server and
still fails immediately, no polling -- that boundary is unchanged.

Two new real regression tests: a real server that starts listening 0.3s
late is correctly waited for and passes; a real 500 response still fails
immediately without being mistaken for "not up yet".

564 tests green (441 src + 123 supervisor).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

…be04-main-checkout-drift

Attempt 10 crashed immediately in the fix committed last: git add -A --
. ':!.graphlemon-worktrees' throws "paths are ignored by one of your
.gitignore files" (exit 1, not just advisory text -- confirmed even with
advice.addIgnoredFile=false suppressed) the moment that path is ALSO
gitignored, which it now always is. Reproduced locally.

Plain `git add -A` (no explicit pathspec) already skips gitignored paths
correctly on its own -- the explicit exclude was redundant now that
.gitignore covers it, and actively conflicting. Simplified
ensure_worktree_committed() back down. Also added the same .gitignore
entry to test_work_node_run.py's _init_git_repo() fixture so real-worktree
tests match production config instead of coincidentally not hitting this.

562 tests green (441 src + 121 supervisor).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Attempts 8 and 9 both hit "local changes would be overwritten by merge"
again, despite the earlier _check_prd_consistency worktree-isolation fix.
Root cause is deeper: git worktrees deliberately SHARE project identity
with their main checkout (same .git, just another checkout) -- a real
`claude -p` call's memory:project write doesn't reliably respect the cwd it
was invoked with, and can land directly on the main checkout regardless of
which specific call triggered it. Worktree-wrapping one call (as done for
_check_prd_consistency) only moves around which call happens to trigger
this; it doesn't fix the underlying issue.

ensure_worktree_committed() now also runs against repo_path itself (not
just the worktree) right before every merge_worktree() call, in both
work_node_run.run_work_node() and e2e_pipeline._check_prd_consistency().
Same already-tested mechanism, now applied generically regardless of which
real call caused the drift or why.

Fixing this surfaced a second real bug in the fix itself: running `git add
-A` against repo_path while a node's own .graphlemon-worktrees/<id>/
checkout is still present on disk picks it up as a gitlink-like entry,
which then shows as "deleted" the instant remove_worktree() runs right
after. Fixed by excluding .graphlemon-worktrees/ from both the dirty-check
and the add via pathspec (not relying on the caller repo's own .gitignore),
plus added it to graphlemon's own .gitignore for correctness generally.

New regression test: test_drift_on_main_checkout_is_auto_committed_before_merge
reproduces a run_fn writing directly to repo_path instead of its worktree,
and confirms a second node's own merge isn't affected by it.

562 tests green (441 src + 121 supervisor).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

The 7th real self-hosting attempt was the first to actually reach a real
health check against a real candidate process -- it correctly failed and
triggered rollback_path_a for real: candidate terminated, git revert landed
cleanly. But the candidate's `git worktree add --detach` checkout
(candidate_instance_dir, tracked since U-037 specifically to know where
this lives) was never removed -- left permanently on disk and still
registered in `git worktree list`. A confirmed-bad candidate is never
needed again after path A, unlike a successful cutover's candidate (which
correctly becomes previous_instance_dir, kept until the monitoring window
closes) -- these are different lifecycles that shouldn't share the same
"leave it" behavior.

rollback_path_a gains an optional candidate_instance_dir parameter
(default None, existing tests unaffected) and removes the worktree before
git revert when provided. self_hosting_e2e.py now threads through the
value stage_deployment() already returns. New regression test uses a real
`git worktree add --detach` checkout and confirms both the directory and
its git worktree registration are gone after rollback.

Also cleaned up 3 orphaned processes left by earlier test_deploy_rollback.py
runs (backing temp dirs already gone) and the real leftover candidate
worktree from this run.

561 tests green (440 src + 121 supervisor).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

The 6th real self-hosting attempt (first to reach the full 4-node doc-writing
graph after the previous five bugs) hit a genuinely new failure: this real
graph_manifest had no edges at all, not just wrong field names -- worse than
the case _normalize_graph_manifest already handled. With zero dependency
info to normalize from, topological_order() scheduled 'benchmark' before
'sdd' (alphabetically first among zero-in-degree nodes), and build_prompt()
crashed with KeyError: 'sdd_content' trying to format a template needing
sdd's not-yet-produced output.

_PROMPT_TEMPLATE always asks for exactly the same fixed 4-node linear chain
-- that's a constant architectural fact, not something that should be
re-inferred from the LLM's output every call. _normalize_graph_manifest now
deterministically enforces brd->prd->sdd->benchmark whenever all four
canonical artifact_types are present, regardless of what depends_on/edges
the LLM did or didn't provide. Same "机制用代码" principle as
ensure_worktree_committed and the earlier normalize logic.

Three new regression tests: zero dependency info still gets the chain
enforced, node_id != artifact_type still resolves to the real node_id (not
a guessed string), and a partial set (missing one of the four types) is
correctly left alone rather than guessed at.

560 tests green (440 src + 120 supervisor).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

The 4th real self-hosting attempt (first to reach the actual doc-writing
Work Graph after the previous three bugs) hit a real git merge failure:
"local changes would be overwritten by merge", exit code 2.

Root cause: _check_prd_consistency() calls execute_work_graph() directly
against target_folder_path, completely bypassing work_node_run.run_work_node's
worktree isolation. It uses agentType='planner' with memory:project, which
writes a real update to .claude/agent-memory/planner/MEMORY.md in whatever
cwd it runs with. Every prior real run of this check only ever targeted a
throwaway clone, so this never mattered -- until self-targeting, where cwd
IS the main checkout: the memory write landed as an uncommitted local
change on master, which then blocked the SDD node's own (correctly
isolated) worktree merge right after it.

Fix: apply 05 §5.8's same unconditional self-target worktree rule here,
reusing work_node_run's existing create_worktree/ensure_worktree_committed/
merge_worktree/remove_worktree rather than inventing a new mechanism.
Non-self-target calls are unaffected (verified by both regression tests).

Also cleaned up the real, now-recovered state from the failed 4th attempt:
merged a real SDD-node worktree branch that got stranded uncommitted
(conflict was just two near-identical memory file wordings, resolved by
hand), and removed three orphaned worktrees left by earlier test runs.

557 tests green (437 src + 120 supervisor).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

The third real self-hosting attempt (first to actually reach stage_deployment
itself, past the earlier bootstrap/commit bugs) hit an uncaught
FileNotFoundError: _copy_prod_db() assumed prod_db_path always exists and
shutil.copy2()'d it unconditionally. graphlemon has never actually run as a
persistent service, so ~/.graphlemon/graphlemon.db never existed.
stage_deployment() already handles this exact class of "no prior state"
bootstrap case for previous_commit_hash/previous_instance_dir -- prod_db_path
never got the same treatment, and every existing test seeds a prod db in
setUp so this was never exercised.

Fix: when prod_db_path doesn't exist, create a fresh schema'd db instead of
copying -- semantically correct, since a genuinely-first deployment has no
production data to inherit. New regression test (BootstrapProdDbTest) covers
it. 555 tests green (435 src + 120 supervisor).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

A real self-hosting run (U-042, first real exercise of needs_worktree=True
since U-035 forces it unconditionally for self-target) exposed a real bug
RealGitWorktreeIsolationTest never caught: its own run_fn always committed
its edits, but a real Coder isn't instructed anywhere to git commit its own
changes. The Coder genuinely edited src/org_loop_route.py and verified it
in its own test_report -- but never committed, so merge_worktree()'s `git
merge` was a true no-op ("Already up to date"), and remove_worktree() then
silently discarded the dirty worktree along with the real work. code_diff
came out empty; the change never reached the branch at all.

Adds ensure_worktree_committed(): checks `git status --porcelain` in the
worktree before merging and auto-commits any dirty state found. A no-op
when the worktree is legitimately clean (e.g. a pure investigation task).
Same "判断用 Agent，机制用代码" principle already used elsewhere in this
codebase -- don't rely on persona prompt-engineering for a mechanical
correctness guarantee that the system itself should hold.

Two new regression tests: one reproducing the exact "edited but never
committed" scenario, one confirming a legitimately-clean worktree still
merges fine. 554 tests green (435 src + 119 supervisor).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Adds src/deployment_query.py (list_deployments/get_current_deployment/
get_deployment -- no project_id filter needed, deployment has no project_id
column since there's exactly one graphlemon self-target) + three new
backend_server.py routes (GET /api/deployments, /current, /:id, the last
with recent deploy_health_signal history) + a new v_deployment_status page
in frontend/app.js polling every 5s (deployment.status changes don't go
through c_ws_subscribe -- Deploy Supervisor writes deployment/
deploy_health_signal directly, no execution_event of its own).

No 02-V spec exists for this view (PH5 was added after 02-V was written) --
DOM/class conventions follow the existing pages' own patterns. Verified
against a real running server via urllib (browser extension unavailable
this session), plus 9 deployment_query unit tests and 5 real HTTP route
tests.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Adds supervisor/self_hosting_e2e.py: run_self_hosting_closed_loop() chains
every PH5 module built this session (U-034~U-041) with the Graph Engine's
own scheduler (U-032) into one real, callable path matching self-development-
feasibility.md's 9-step scenario -- self-target Goal -> Planner/Coder/
Validator -> core_engine classification -> stage -> health check -> cutover
(or rollback path A if health check fails) -> monitor until either
monitoring_window_clean (finalized) or anomaly_detected (rollback path B).
Both real outcome paths are branches of the same call, not two separate
scripted scenarios. Explicitly documented as this acceptance scenario's own
orchestration glue, not a claim about Deploy Supervisor's eventual
production poll loop (U-036's discovery-loop hook is still unfilled;
building that is future work).

Mocked wiring tests (6, run in normal regression) stub each already
independently-tested module boundary and only verify the branching logic.

The real, literal acceptance test is built and ready (RealSelfHostingClosedLoopTest,
reproduces the document's own "loop_round > 3 should be >= 3" example) but
gated behind RUN_REAL_SELF_HOSTING_E2E=1 -- deliberately a separate,
distinctly-named env var from this project's usual RUN_REAL_AGENT_E2E, since
this is the highest-blast-radius action in the project (can replace the
running graphlemon process and git-revert commits on this real repo).
Per this Unit's own explicit build instruction, not executed as part of
implementing it -- doing so requires checking with the user first.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Adds supervisor/deploy_rollback.py: rollback_path_a (pre-cutover, health
check failed -- terminate candidate, delete its one-time DB copy, git
revert, record a bug_record(core_engine) audit trail) and rollback_path_b
(post-cutover, anomaly detected -- stop the bad Live, revive
previous_instance_dir, re-run the same three health-check signals directly
against it, git revert only once re-verification passes).

Design choices follow established conventions rather than inventing new
ones: no unified rollback() entry point (deployment has no PID columns,
same reason deploy_stage/deploy_cutover already require callers to pass
pids explicitly); ROLLBACK_FAILED is the raised error name while the
persisted deployment.status is 'blocked_pending_human' (same pattern
CheckoutFailedError/CutoverFailedError already use). git revert conflicts
fold into the same rollback-itself-failed fallback both paths share, per
design doc §10 open question 3's own recommendation, with `git revert
--abort` run afterward so a failed attempt doesn't leave the repo mid-conflict.

This is PH5's highest-rework-risk Unit per development-plan.md's own flag,
so its own "rollback itself fails" fallback is tested for real, not assumed:
a genuinely broken previous_instance_dir (a real empty directory with no
Python package in it) that really fails to bind its port, and a genuinely
conflicting git history (a later commit touching the same line the
self-modification changed) that really fails `git revert` -- both correctly
land on blocked_pending_human without retrying forever or silently
succeeding, and the conflict case leaves the repo clean afterward.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Adds supervisor/deploy_monitor.py: run_monitor_cycle() is one sampling
pass, called repeatedly by Deploy Supervisor's own poll loop (03-C's own
text: not a one-shot call). process_alive/http_health/canary_task/
validator_approval_rate sampled in order, stopping at the first anomaly.

validator_approval_rate's "approve rate" has no literal definition anywhere
in 01-M/03-C/04-P (no such execution_event type exists) -- derived instead
from a verified structural fact in scheduler.finish_task_lifecycle: PASS
closes straight to done with no bug_record ever created, FAIL/INCONCLUSIVE
always creates one via judge_root_cause. A task counts as approved iff no
bug_record(source='validator') exists for it. Baseline is computed by the
same function looking back MONITORING_WINDOW_HOURS from cutover_at rather
than persisted as a new column; baseline=None (cold start) never flags an
anomaly rather than defaulting to 0.

Crash-count/consecutive-http-fail windows are approximated by sample count
(N = CRASH_WINDOW / MONITOR_SAMPLE_INTERVAL) rather than a true rolling
time window -- documented simplification, correct as long as sampling stays
roughly interval-paced.

Caught my own design misreading via the tests: process_alive's monitoring-
phase anomaly condition is MAX_CRASH_COUNT crashes within CRASH_WINDOW (a
crash-loop detector), not "currently not alive" -- unlike U-038's health
check where any single failure fails closed. A single dead reading during
monitoring is recorded but must not trigger an immediate rollback by itself.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Adds supervisor/deploy_cutover.py: stops the old Live process, retires the
health-check-mode candidate, and relaunches the same already-verified
candidate checkout bound to LIVE_PORT/PROD_DB_PATH -- http.server has no
live socket-rebind operation, so "switch to production port/db" is
implemented as stop-then-relaunch-from-the-same-dir rather than an in-place
rebind (functionally equivalent, the only mechanism stdlib actually offers).

Adds LIVE_PORT=8420 to 05 §5.9's MVP-fixed parameter table -- the one
parameter that table was missing (frontend/app.js never needed one, same-
origin relative fetches don't care, but successive deployments need to keep
landing on the same port for a human bookmark to keep working).

"在途 work_node_execution 重启后可恢复" is satisfied by relying on the
existing REQ-06 recovery machinery unchanged -- cutover doesn't add any
special-case logic, a cutover-triggered restart is just another interruption
REQ-06 already survives.

A real (not mocked) test caught a real bug: deploy_supervisor.is_alive()'s
os.kill(pid, 0) check can't distinguish "truly running" from "exited but
never reaped by its own parent" -- a zombie's PID slot answers kill(pid, 0)
successfully until waited on. U-036's own subprocess test never caught this
because that skeleton deletes its own PID file before exiting, sidestepping
is_alive() entirely; deploy_cutover's test is the first one to actually poll
for a stopped process to disappear, and it hung until fixed. Added
reap_if_exited() (real os.waitpid for processes we spawned ourselves, falls
back to is_alive() for pids from a prior session where ChildProcessError
means we're not the real parent) and switched deploy_cutover._stop_process,
deploy_health_check.check_process_alive, and deploy_supervisor.stop() to use
it.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Adds supervisor/deploy_health_check.py: run_health_check() runs the three
pre-cutover checks in order, stopping at the first failure (03-C: "任一检查项
fail 立即整体判定 health_check_failed，不等待其余检查项跑完") and persisting
a deploy_health_signal row for every check that actually ran.

- process_alive: polls deploy_supervisor.is_alive() up to HEALTH_CHECK_STARTUP_TIMEOUT.
- http_health: hits the candidate's /api/health -- added to backend_server.py
  (U-037 deliberately left this for U-038). Not just "process exists" --
  runs a real SELECT 1 to catch a wedged sqlite connection a live-but-stuck
  process would otherwise pass.
- canary_task: a real (not mocked) project+task creation round-trip against
  the candidate over HTTP -- no real Org Graph/claude calls, since
  c_task_create's synchronous 'queued' landing is already a deterministic,
  always-should-pass result, which is what a canary needs.

Timeouts are the MVP-fixed drafts from 05 §5.9, explicitly flagged there as
needing real calibration later, not hardcoded as authoritative.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Adds supervisor/deploy_stage.py: stage_deployment() creates a deployment row,
git-worktree-checks-out the target commit into a fresh directory (--detach,
never in-place git pull), copies the production DB to a one-time candidate
copy, and Popens a real candidate backend process on a free port.

Return value follows 04-P §4.6's state-machine table (status after the call
is 'candidate_starting') rather than 03-C's one-line 'staged' summary --
04-P's own trigger text ("c_deploy_supervisor_stage 完成" moves the row to
candidate_starting) is the more detailed/authoritative source when the two
disagree, same precedent used throughout this project.

Found and closed two real gaps along the way:
- deployment's own field list never included where a candidate's checkout
  directory lives -- added candidate_instance_dir to schema.py (also what
  the NEXT staging call's previous_instance_dir bootstraps from once a
  deployment reaches 'finalized').
- backend_server.py had no CLI entry point at all since U-007 -- create_server()
  was only ever instantiated in-process by tests. Added main() (argparse +
  serve_forever + SIGTERM->shutdown() from a separate thread, per
  http.server's own same-thread-deadlock warning).

RealCandidateLaunchTest spawns and HTTP-probes a genuine
`python3 -m src.backend_server` subprocess against a real git-worktree
checkout of this repo (not mocked) -- caught a real ordering issue doing so:
git worktree only sees committed content, so testing before this Unit's own
commit landed would check out backend_server.py without main() at all.
Fixed by using `git stash create` (builds a commit object from the current
working tree without touching HEAD/index) as the commit-to-test-against,
falling back to plain HEAD once the tree is clean post-commit.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Ports graphloop's test_isolated_coding_workspace.py/test_workspace_security.py/
test_change_manifest.py/test_selective_apply.py into supervisor/isolation/
(only the import path changed -- the graphlemon modules were already adapted
verbatim from graphloop, confirmed API-identical) plus a few extra edge
cases the originals didn't cover. 52 tests green, replacing what had been a
single manual smoke test since these modules were staged.

Adds supervisor/deploy_supervisor.py: process lifecycle only (PID file,
atomic status file, start/stop/is_running), no deploy decision logic yet --
that's U-037+'s job, injected via the poll_fn hook run_foreground() calls on
a schedule. PID/status conventions adapted (not imported) from graphloop's
hermes_watchdog.py atomic-write pattern. Fail-closed: any exit path
(normal, SIGTERM, or an exception from poll_fn) unconditionally writes
status='stopped' and removes the PID file, so is_running() never lies.
RealSubprocessLifecycleTest actually spawns and stops a real
`python3 -m supervisor.deploy_supervisor` process rather than mocking it,
per this Unit's own "能独立启停" Done criterion.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Adds paths.repo_root()/is_self_target() and forces needs_worktree=True in
work_graph_orchestrate.run_graph() whenever target_folder_path is graphlemon's
own checkout, regardless of caller intent -- 05 §5.8's unconditional rule,
since a self-target in-place edit risks corrupting the currently-running
process's own source out from under it.

Adds src/core_engine_classify.py (path-based rule: .claude/agents/*.md,
src/*, supervisor/* = core_engine; frontend/, docs/ = not) and
bug_record.record_core_engine_change() (a PASS-path audit record, distinct
from create_bug_record's FAIL-path root-cause attribution -- no route
decision, status='resolved' from creation). scheduler.finish_task_lifecycle()
records this audit trail as an additive side effect after close_task_done()
on self-target PASS closures.

Found and resolved a real SDD-internal conflict (confirmed with the user via
AskUserQuestion) before wiring this up: supervisor-auto-rollback-design.md §1
triggers Deploy Supervisor on self-target+Validator-PASS alone, but 03-C
§3.11/04-P §4.6 literally gate it on an existing core_engine bug_record --
and task_create.py confirms goal-type self-improvement tasks (the exact
self-development-feasibility.md walkthrough scenario) never produce a
bug_record on their happy path, which would silently defeat that whole task
class under the literal reading. Resolved per user decision: trigger on
self-target+PASS alone; the bug_record is a byproduct, not a gate.
p_deploy_supervisor_blue_green (04-P §4.6) never touches task.status, so
close_task_done() still runs unconditionally -- Deploy Supervisor is a fully
decoupled state machine, matching §2's "no shared failure domain" principle.

org_loop_route.py is intentionally untouched -- fast_lane/full_replan is
FAIL-path retry routing, orthogonal to this PASS-path trigger; deployment
row creation stays U-037's job per its own Done criterion.

417 tests green; RealGitWorktreeIsolationTest (U-013/REQ-03's real git
worktree regression) re-verified passing per this Unit's own Done criterion.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Adds the two Deploy Supervisor entities from 01-M §1.15/§1.16 (17 tables
total): deployment (full 15-value blue-green state machine, per 01-M's own
text rather than supervisor-auto-rollback-design.md §3's abbreviated
summary table) and deploy_health_signal (append-only health/monitoring
samples). ux_deployment_active enforces 01-M's "only one non-terminal
deployment at a time" constraint via an expression-based unique index
(CREATE UNIQUE INDEX ... ON deployment((1)) WHERE status NOT IN (...)) --
the same partial-unique-index idiom work_graph_run already uses, just with
a constant instead of a real grouping column since there's exactly one
graphlemon self-target.

bug_record.root_cause_category's schema-level CHECK now accepts
core_engine, but bug_record.py's own application-layer whitelist
deliberately does not follow yet -- classifying a bug as core_engine is a
file-path-based rule (05 §5.8), not something the Validator's existing
3-perspective judge_root_cause can produce, and wiring that classification
+ c_org_loop_route's routing is U-035's job.

392 tests green.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

CLAUDE.md is explicit that PH5 (self-modification/auto-rollback) must not
start until PH4 has genuinely closed -- not just "all unit tests green,"
but 06-验收与测试锚点.md's REQ-01~14 happy/boundary/failure cases actually
covered. A REQ-by-REQ audit (the same discipline that caught U-031's
integration gap) found 5 real gaps:

- REQ-03 failure: work_node_execution.status jumped straight
  running->retrying, skipping 'reflecting' (declared in the schema enum,
  never once written by any code).
- REQ-05 failure / REQ-09 boundary: the "scheduler keeps serving other
  queued tasks past one blocked_pending_human" scenario was never tested
  against a real scheduler -- the old test literally said "no scheduler
  exists yet to test against directly" (stale since U-032).
- REQ-06 / REQ-07 / REQ-14 failure (the biggest gap, shared root cause):
  CorruptPersistedStateError, ClassifierBlockedError, and
  UsageLimitWaitTimeoutError were each correctly raised and each correctly
  marked their own work_node_execution 'blocked', but nothing ever routed
  that to task.status='blocked_pending_human' with the blocked_reason each
  REQ's acceptance text names. e2e_pipeline.run_end_to_end is split into
  run_task_lifecycle() so scheduler.py's run_goal_to_completion can create
  the task itself and catch these three specific exceptions, following the
  same UPDATE+execution_event pattern budget_guardrail.check_budget()
  already established for REQ-10.
- REQ-02 boundary: PRD internal-contradiction check (verifying->reflecting)
  had no implementation anywhere -- artifact_write always marked
  validation_status='passed' unconditionally. Added an optional verify_fn
  hook to work_graph_orchestrate.run_graph() (one regeneration attempt,
  then ConsistencyCheckFailedError) and a real consistency-check agent()
  call scoped to the PRD node only. The first real run of this new call
  caught a genuine bug: the model returned "consistent": "false" as a JSON
  string, not a boolean, which `if ok:` silently treated as truthy -- fixed
  with explicit _coerce_bool().
- REQ-13 failure: minor test-assertion weakness (WS 404 rejection test
  didn't check the JSON error body).

384 tests green. REQ-01~14 now have real, exercised coverage rather than a
"tests are green" assumption -- PH4 can be treated as genuinely closed.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Reviews every real invocation of the migrated Planner/Coder/Validator personas
since U-004's initial 2026-07-31 verdict (U-011's "SOUL 原则 #10" reference,
U-014's full real snake-game closed loop, U-031's agentType spike + full
plan_documents run) and finds no new persona-content deviation beyond the
three already fixed in U-004 (Feishu Base token, lark-cli coupling,
--dangerously-skip-permissions instruction). The disallowedTools bug found
along the way (05 §5.4.1.2) is a tool-permission-layer Claude Code behavior,
not persona content, so it doesn't extend A-2's deviation scope.

Final verdict: stays "部分成立" (not upgraded to confirmed) -- the Coder
rewrite already happened and later clean runs don't retroactively undo that
-- but the deviation scope is now confirmed closed rather than open-ended,
which is what U-033 exists to establish before PH5 planning.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

04-P's blocked_pending_human branch, 01-M's task-table indexing rationale,
and REQ-09's boundary case all presume an autonomous dispatcher scans queued
tasks and keeps serving the queue past a blocked one -- but no such component
existed. org_node_lifecycle._check_concurrency (U-010) only gates a single
trigger call; e2e_pipeline.run_end_to_end (U-014) drives exactly one task,
synchronously, only ever called from tests.

Adds src/scheduler.py: run_scheduler_once() dispatches multiple Goals via
ThreadPoolExecutor bounded by org_concurrency_config.max_concurrent_goals,
each worker opening its own sqlite connection (with a busy_timeout) rather
than sharing one across threads -- U-027's SIGSEGV already proved that needs
a hand-held lock, which would just serialize everything back to front.

Also closes a gap run_end_to_end's own docstring already flagged: it never
called close_task_done (PASS) or org_level_loop.run_fix_loop (FAIL), leaving
every task stuck at 'validating'. finish_task_lifecycle() applies that step
without changing run_end_to_end's own tested behavior or scope.

Real-write concurrency (multiple threads, separate connections, same db
file) is stress-tested for real in test_scheduler.py without spending API
budget -- the actually-new risk surface here is the threading/connection
design, not the already-validated (U-031/U-017) work itself.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

U-031: closes a structural integration gap found during the REQ-01~14 regression
audit -- plan_work_graph/execute_work_graph/run_work_node were each individually
tested but never actually called together in production code (e2e_pipeline.py's
only validated closed loop bypassed all three via flat org_node_trigger calls).
Adds work_graph_orchestrate.py (topological sort over graph_manifest + one
one-node dynamic-workflow agent() call per Work Node, needed for REQ-06's
per-node breakpoint recovery), rewires e2e_pipeline.py's plan_documents/
implement_code onto the real chain, and fixes two bugs a real API run
surfaced: graph_manifest's id/node_id/depends_on normalization
(work_graph_plan._normalize_graph_manifest) and a missing repo_path in
run_work_node's cwd resolution. work_node_run.py also now marks a node
'blocked' instead of leaving it stuck 'running' on any unretryable run_fn
exception.

U-024.5: the regression audit also found REQ-12's reconnect boundary case
(refetch a snapshot after a dropped WS reconnects) was never implemented --
only the dashboard reacted to onStatusChange, and even it never refetched.
Fixes mountDashboard/mountTaskBoard/mountTaskDetail (which embeds
v_graph_visualizer) to refetch their current snapshot on reconnect.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

三个都是 config_id='default' 单例配置，首次使用即创建、之后原地更新
（upsert），不需要单独的初始化流程：

- c_concurrency_config_update：新增 src/settings_config.py（
  org_concurrency_config 之前完全没人碰过），校验 max_concurrent_goals
  落在 1-50。
- c_budget_config_update：budget_guardrail.py 新增 upsert_budget_config()
  ——跟 U-019 已有的 update_budget_limit_and_resume()（只更新已存在的
  行）不是一回事，这个是真正完整的设置页控制器，支持首次创建，沿用
  同一套"额度调高后自动恢复 budget_exceeded 阻塞任务"副作用（提取成
  _resume_budget_blocked_tasks() 共享）。
- c_log_retention_config_update：同样在 settings_config.py 里，校验
  retention_days > 0。

三处校验都在业务层做完整检查，HTTP 层额外兜了 except (InvalidParamError,
TypeError)——payload 数值字段缺失时 None<=0 这类比较会抛 TypeError 而
不是业务异常，两个都要接住才能保证返回干净的 400 而不是裸 500。
backend_server.py 第一次加了 do_PUT。

前端三个页面共享一个 renderSettingsSubnav() 小组件模拟 02-V 原型里的
设置下拉菜单。真实服务器端到端验证过三个 PUT/GET 的完整读写循环。

PH3（人机交互控制台）至此全部完成：U-022~U-030。

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

c_skill_diff 和 U-028 的 c_artifact_get 一样，只存在于机器可读的
sdd-mvcp-contract.json，03-C 正文从未写出来，已订正补全。
c_skill_list/c_skill_get 两份文档都没定义，是 v_skill_library/
v_skill_audit_log 自己的展示需求倒逼出来的缺口。

新增 src/skill_query.py：list_skills()、get_skill_audit_log()、
get_diff()（git diff <before> <after>——skill_update.py 的
_write_and_commit 把每次迭代做成原子单文件 commit，整仓库范围的 diff
天然只涉及那一个 Skill 文件）。

关键安全考量：Skill 库活在 graphlemon 自己的仓库里，c_skill_rollback
会真的在这个仓库里跑 git commit——如果 HTTP 层写死指向真实仓库根目
录，任何针对这条路由的测试都会在正在跑的这个 graphlemon 仓库里留下
真实提交。参照 db_path 已有的做法，给 create_server() 加了
skill_repo_path 参数（默认 graphlemon 真实仓库根，测试传临时仓库），
不通过 HTTP 暴露这个参数，避免变成任意写入的口子。记录在 05
§5.4.1.4。

真实服务器 + 临时仓库端到端验证过完整的 update→diff→rollback 闭环，
确认过跑完之后 graphlemon 自己仓库的 git log 完全没变化。

v_skill_library/v_skill_audit_log 不检查"当前项目"——Skill 是平台级
资产，跟项目无关。

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

c_artifact_get 在机器可读的 sdd-mvcp-contract.json 里其实定义过
（GET /api/artifacts/:artifact_id），只是 03-C 正文一直没写出来，已订正
补全。c_artifact_list 连 MVCP JSON 里都没有 operation 定义，纯粹是
v_artifact_browser 自己的过滤字段倒逼出来的缺口，跟 U-025 补 c_task_list
是同一类问题。

新增 src/artifact_query.py：list_artifacts() 返回裸数组（跟已有的
list_tasks() 保持同款风格）；get_artifact() 把血缘链（按
depends_on_artifact_ids 往回走，只走第一个依赖——这条流水线的实际产出
只有线性 BRD→PRD→SDD 链）和文件内容（artifact 表本身没有 content 列，
走 project.target_folder_path + artifact.file_path 现读磁盘）一起返回，
预览面板一次请求就够。

前端预览统一用 <pre> 纯文本展示，不做 Markdown 渲染/代码高亮——02-V
原文想要那个效果，但需要引入第一个前端第三方库，跟这个控制台一贯的纯
vanilla JS、无构建步骤做法冲突，是有意简化。顺手给 index.html 常驻导航
栏加上了"产物"链接。

真实服务器验证过三级血缘链（BRD→PRD→SDD）返回顺序正确。

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

execution_log_file 的行生命周期 U-013 早就管好了，但从来没有代码真的往
日志文件里写过内容——src/execution_log.py 新增 append_log() 补上这条
缺失的写路径，设计成 run_fn 执行过程中随时可调用，不关心节点在做什么。
get_log() 按 offset/limit 分页读，download=true 时走原始文件流。

c_ws_log_tail（WS /api/ws/work-nodes/:node_exec_id/log）复用 U-024 手写
的 RFC 6455 机制，轮询 execution_event(log_appended)；节点一旦转终态
（done/blocked/failed）服务端主动发关闭帧断开，不让客户端一直轮询。

p_log_retention_cleanup 实现成纯函数 run_log_retention_cleanup()：过期
扫描 + max_total_size_mb 超限按最旧优先追加候选 + 单个文件删除失败只
记录不阻塞其余项，没有配调度器（不在本 Unit 覆盖范围），留给未来的
调度进程周期调用。

过程中意外抓到一个真的并发 bug：_Server.server_close() 关闭共享
sqlite 连接时原来没拿 conn_lock，如果这时候正好有个 WS 轮询线程在
另一边持锁执行 SQL，两个线程无同步地并发操作同一个 C 级 sqlite3 连接
对象，实测直接把解释器崩了（SIGSEGV）——U-024 就已经有这个隐患，这次
高频 WS 测试把时序窗口撞开了。修好后连续跑几十次全部稳定通过，记录
在 05 §5.4.1.3。

frontend/app.js 的 v_log_viewer 挂在 v_task_detail 每个 to-do 节点的
展开详情里，首次展开才建连接（懒加载），运行中态走 c_ws_log_tail 实时
滚动、终态走 c_execution_log_get 静态拉取，活跃连接在任务级刷新/离开
页面时统一关闭。真实服务器 + Node 原生 WebSocket/fetch 端到端验证过
实时追加与终态自动断开的完整链路。

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

纯前端 Unit，数据已经在 U-025 的 c_task_get 里，只是 task_query.py
的 _work_nodes_for_run 补上了 hover tooltip 需要但当时没取的字段
（input_schema_ref/output_schema_ref/quota_limit_type/
quota_wait_started_at）。

frontend/app.js 新增 computeGraphLayers()：按 graph_manifest 节点的
depends_on 边做拓扑分层，渲染成按执行层级排布的行，fan-out/fan-in
都能正确分层——用一个 n1→[n2,n3]→n4 的真实 graph_manifest 验证过，
直接从 app.js 里取出 computeGraphLayers 本体（不是重新实现一份逻辑）
跑真实服务器返回的 JSON，分层结果完全正确。节点按 03-C 3.6 节六态
配色，waiting_for_quota 态 hover 展示 quota_limit_type + 已等待时长。

02-V §2.7 原描述还包含一份 Org Graph 层，但 v_task_detail 页面顶部
已有等价的 org-strip 面板，这里判断重复渲染没有意义，只做了 Work
Graph DAG 层，Org Graph 复用页面已有的那个。

嵌入位置：v_task_detail 里原来"随 U-026 补上"的占位提示换成了真实
的 DAG 面板。

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

三个页面需要的读接口此前都不存在，本 Unit 一并建了：

- c_task_list/c_task_get（03-C §3.2，此前无 Unit 认领）：新增
  src/task_query.py + GET /api/tasks、GET /api/tasks/:task_id。
  c_task_get 的返回比 03-C 字面契约更完整——额外带上
  work_graph_run（含解析后的 graph_manifest）+ 每个 run 的
  work_node_execution 列表，因为 v_task_detail 的 to-do 树需要这份数据，
  03-C 已订正补全。
- c_org_loop_route（U-016 已实现 route_org_loop()，从未接 HTTP）第一次
  接上 POST /api/tasks/:task_id/route，v_task_detail 的人工干预
  （manual_resume）按钮需要它。
- 预算护栏此前没有任何读接口（03-C 只写了 PUT），新增
  budget_guardrail.list_budget_configs() + GET /api/settings/budget
  给仪表盘预算条用。

frontend/app.js 补上真实的 #/（org graph 三节点卡片、当前任务概要、
预算条、事件时间线，全部通过 c_ws_subscribe 实时刷新）、#/tasks
（关键字/状态/org_node 过滤）、#/tasks/:task_id（task 字段、to-do 树、
关联 artifact/bug_record、blocked_pending_human 告警条 + manual_resume
按钮）。路由改成对象形式支持挂载态清理，切页面时关掉上一个页面的
WebSocket 连接。v_graph_visualizer/v_log_viewer 子模块明确标成占位
提示（随 U-026/U-027 补上），不是假造内容。

顺带把 U-023 里因 c_task_list 当时不存在而简化的 related_task_id
换回真下拉，goal_composer/bug_feedback 提交成功后也改回跳转真实的
v_task_detail。

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Python stdlib 没有 WebSocket 支持，src/ws_subscribe.py 手写 RFC 6455
握手（hashlib+base64 算 Sec-WebSocket-Accept）+ 帧编解码（服务端帧不
加掩码，客户端帧强制解掩码），不引入 websockets 之类第三方库
（05 §5.7）。

推送用轮询而非写路径 hook：execution_event 的写入分散在十几个调用点
（org_node_trigger/work_graph_execute/work_node_run/task_create/
bug_record/...），没有单一写入路径可以插桩，backend_server.py 的
_handle_ws_subscribe 劫持 ThreadingHTTPServer 连接后每 0.5 秒按
rowid 增量查一次 execution_event（project_id/可选 task_id 过滤），
轻松满足 REQ-12 的 ≤2 秒目标。断线重连按 03-C §3.14 走 REST 快照，不
在 WS 层做消息重放，新连接只看连接那一刻起的新事件。

daemon_threads = True 避免长连接 WS 线程阻塞进程退出。

验证：test_backend_server.py 用原始 socket 走真实握手+推送延迟断言；
另外用 Node 原生 WebSocket 客户端做跨实现互操作性验证，连真实运行的
服务器，从建连到收到 c_task_create 触发的真实推送全程走通。

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

c_task_create（U-009 已实现的 task_create.create_task()）第一次接上
POST /api/tasks。c_bug_report_create 此前完全没有实现，新增
bug_record.create_bug_report() + POST /api/bug-reports。

发现并订正 03-C 一处输入契约遗漏：c_bug_report_create 的
input_contract 没写 project_id，但 execution_event.project_id 是
NOT NULL、bug_record 表自己没有 project_id 列可以在 related_task_id
留空时兜底推导，字面上无法满足约束——按 c_task_create 同款处理方式把
project_id 变成必填，03-C 已订正。

frontend/app.js 补上 #/goals/new、#/bugs/new 真实交互；控制台还没有
"当前项目"状态的正式载体（v_dashboard 是 U-025 才做），project_id 暂存
localStorage，v_project_setup 创建成功时写入。related_task_id 因为
c_task_list 未被任何 Unit 认领，简化成文本输入而非下拉，等 U-025 补上
任务列表后再换。提交成功后原型写的是跳转 v_task_detail，该页面也是
U-025 才建，暂时改成原页面内展示确认信息。

端到端冒烟时额外发现一个真 bug：create_bug_report() 原本没校验
project_id/related_task_id 是否存在，坏 project_id 会在 execution_event
插入时触发未捕获的 IntegrityError，请求直接 500——补了存在性校验，
改为干净的 INVALID_PARAM/400。

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

c_pick_folder 补上 Windows（PowerShell FolderBrowserDialog）和 Linux
（zenity 优先、回退 kdialog）实现，三平台都覆盖到。c_project_create
（U-002 已实现的 project_scaffold.create_project()）第一次接上 HTTP
路由 POST /api/projects——backend_server.py 因此第一次需要持有 sqlite
连接，schema.connect() 加 check_same_thread=False 参数，配合
server.conn_lock 序列化 ThreadingHTTPServer 各请求线程的访问。
frontend/app.js 补上 #/setup 真实交互（选文件夹→校验 Git 仓库→非
Git 仓库二次确认→创建→跳转仪表盘），DOM class 命名对齐
docs/wireframes/v_project_setup.html。

REQ-11 完整 happy 用例（含创建 task）还需要 U-023 的
v_goal_composer/c_task_create，本 Unit 只完成 v_project_setup/
c_pick_folder/c_project_create 部分，development-plan.md 已记录。

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

now 默认值从 time.monotonic 改成 time.time（墙钟），使 quota 等待的
已耗时计算能在进程重启后正确续算；run_work_node 对已 done 的节点直接
返回存量结果不重跑，对 retrying/waiting_for_quota 节点从持久化的
retry_count/quota_wait_started_at 续算而非清零；needs_worktree=True
时复用已存在的 worktree 而不是重新 create。新增
resume_work_graph_run() 返回一次 run 里尚未完成的 node_exec_id 列表，
并对内部不一致的持久化状态统一抛 CorruptPersistedStateError。

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Re-checking REQ-14's boundary case against the letter of its text found a
real functional gap, not just a testing gap: U-013's opus handling only
did "skip backoff" -- it never actually retried on a downgraded model,
just failed immediately. REQ-14 boundary says "不走退避轮询，直接降级到非
Opus 模型重试" (skip backoff, retry immediately on a non-opus model) --
the retry was the part that was missing.

Fixed: run_fn's signature is now run_fn(cwd, model=None); an opus quota
signal retries immediately (no backoff) with opus_downgrade_model
(default "claude-sonnet-5"). If the downgraded model somehow also reports
an opus signal (shouldn't happen -- it's not using Opus), this doesn't
loop forever chasing it, raises UsageLimitWaitTimeoutError instead.

work_graph_execute.py's own opus handling (U-012) deliberately NOT changed
to match: REQ-14's coverage only names c_work_node_run/c_org_node_trigger,
and that mechanism (a multi-agent dynamic workflow, no single top-level
--agent identity) has no one "the model" to downgrade -- a deeper A-1
question, documented as out of scope rather than silently left
inconsistent without explanation.

Also filled in a real test gap: quota_limit_type=weekly (detection +
recovery, and the 9-day timeout) was never tested despite the mechanism
already supporting it since U-013.

11 new/changed stdlib unittest cases across work_node_run.py's test suite
(all existing run_fn lambdas updated for the new signature). 178 total
across U-001-020, all passing.

This closes PH2-S3 alongside U-019. REQ-14 is now genuinely complete, not
just "mostly right."

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Found running U-014's full real closed loop: the Validator gave an
INCONCLUSIVE verdict and explicitly said it had no Bash tool, despite its
frontmatter granting one. Isolated with a minimal test subagent: any
"Bash(...)" scoped pattern (e.g. "Bash(git commit:*)") in a subagent's
disallowedTools frontmatter field disables Bash *entirely*, not just that
subcommand -- confirmed by comparing a disallowedTools=[Edit,Write] agent
(Bash works) against one adding a single Bash(git commit:*) entry (Bash
breaks completely). The CLI's own --disallowedTools flag documents this
exact scoped syntax as supported; subagent frontmatter just doesn't honor
it the same way, and nothing in the docs says so.

Fixed agent_profile.py's validator FRONTMATTER to disallowedTools=
[Edit, Write] only -- dropping the four Bash(git *) entries that were
silently breaking test execution. The "don't commit/push/reset/clean"
constraint now relies on the prose instruction already in the migrated
AGENTS.md instead of a tool-level block that never actually worked; fixed
that file's own (now-false) claim that it was enforced at the tool level,
and documented the finding centrally in 05-实施约束与依赖.md §5.4.1.2 since
it'll matter for any future agent definition, not just this one.

Verified for real, redeployed: Bash now works for the actual Validator
identity, Edit/Write remain correctly blocked.

1 test fixed (was asserting the now-removed scoped pattern) + 1 new test
(disallowedTools frontmatter must never contain "Bash(" again). 174 total
across U-001-019, all passing.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

check_budget(): accumulates current_usage on success (04-P monitoring->
monitoring), and on reaching/exceeding limit_value transitions the task to
blocked_pending_human with blocked_reason='budget_exceeded' (never
'usage_limit_wait_timeout' -- 04-P is explicit these two guardrails, human-
configured budget vs Claude Code's own plan quota, must not share a
blocked_reason) and raises BudgetExceededError rather than returning
allowed=false silently, matching 03-C §3.12's own errors list.

update_budget_limit_and_resume(): REQ-10's boundary case needs "raise the
limit -> paused tasks resume" to be real; built the minimal version this
Unit needs rather than the full settings-page controller
(c_budget_config_update, U-030/PH3's job) -- reuses U-016's manual_resume
(org_loop_route.route_org_loop) for the actual status restoration instead
of reimplementing it.

6 new stdlib unittest cases, all real (sqlite, no mocking needed). 173
total across U-001-019, all passing.

Also: the U-014 full real closed-loop run that's been going in a detached
background process since earlier this session finished -- 957s (~16min).
All 4 real BRD/PRD/SDD/Benchmark docs, a real JS snake-game implementation
(engine.js/engine.test.js/index.html/app.js) from the Coder, and a
genuinely careful INCONCLUSIVE verdict from the Validator: it explicitly
refused to accept the Coder's own claimed "10/10 passed, verified with
headless Chrome" without being able to reproduce it, correctly citing its
own migrated SOUL.md rule ("工具错误和权限不足属于INCONCLUSIVE，不能洗成PASS").
It also caught a real test-fidelity gap (T3/T7 not matching the Benchmark's
literal wording) via careful static tracing. Result preserved at
/private/tmp/.../scratchpad/snake-game-result for inspection. The Validator
also reported no Bash tool available despite its frontmatter granting one
-- investigating that as a follow-up, separate from this commit.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>