mirror of
https://github.com/abhigyanpatwari/GitNexus.git
synced 2026-10-02 02:11:29 +00:00
27 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Gergő Magyar
|
56feb85c97
|
chore: compile first-party packages with TypeScript 7 (#3311)
Some checks are pending
CodeQL / Analyze (python) (push) Waiting to run
Publish / RC guard (marker + release-PR skip) (push) Blocked by required conditions
Trivy Image Scan / Trivy (gitnexus-web) (push) Waiting to run
CodeQL / Analyze (javascript-typescript) (push) Waiting to run
Gitleaks / gitleaks (push) Waiting to run
Publish / Classify release event (push) Waiting to run
Publish / ci (push) Blocked by required conditions
Publish / Publish to npm (push) Blocked by required conditions
Publish / Build & Push RC Docker images (push) Blocked by required conditions
Scorecard / Scorecard analysis (push) Waiting to run
Trivy Image Scan / Trivy (gitnexus-cli) (push) Waiting to run
* fix(web): drop TypeScript 7-incompatible tsconfig paths Remove baseUrl and the dead ../shared include so web project references typecheck under TypeScript 7. Co-authored-by: Cursor <cursoragent@cursor.com> * test(cli): parse TypeScript with a TypeScript 6 API package Keep AST guards working after the named typescript package becomes 7, which no longer ships the Compiler API. Co-authored-by: Cursor <cursoragent@cursor.com> * chore(lint): pin root TypeScript to the 6 API package Give typescript-eslint a TypeScript 6 peer so syntax-only lint still installs after CLI and web move to TypeScript 7. Co-authored-by: Cursor <cursoragent@cursor.com> * chore(deps): compile first-party packages with TypeScript 7.0.2 Unify CLI and web on the same native compiler line as gitnexus-shared so typecheck and emit no longer split 5.x versus 7.x. Co-authored-by: Cursor <cursoragent@cursor.com> * docs(ci): describe parent TypeScript 7 as the shared compiler Stop saying web compiles shared with TypeScript 5 now that the parent lockfile is 7. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(ci): compile shared from parent TypeScript on Vercel and skill-evolution Stop isolated npm installs in gitnexus-shared so those paths do not pull a second TypeScript 7 optional-platform tree. Co-authored-by: Cursor <cursoragent@cursor.com> * docs: record TypeScript 7 typecheck and Dependabot major-split policy Keep contributor typecheck commands, and stop Dependabot from bumping shared onto a different TypeScript major than CLI and web. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(lint): pin root TypeScript to 5.9 so npm ci satisfies eslint peers typescript-eslint 8 peers typescript below 6.0.0, so the typescript6 alias made quality lint npm ci fail with ERESOLVE. Co-authored-by: Cursor <cursoragent@cursor.com> * test(cli): drop the TypeScript 6 Compiler API package TypeScript 7.0 has no classic createProgram surface, so parse-only guards now use Babel and Mode 4 uses the TypeScript 7 Checker. Co-authored-by: Cursor <cursoragent@cursor.com> * docs: align contributor setup with parent TypeScript 7 compile Stop telling clones to npm-install gitnexus-shared; CI and Vercel already emit that package from a parent lib/tsc.js shim. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(web): typecheck React JSX on TypeScript 7 with explicit DOM libs TypeScript 7 no longer implies DOM or auto-includes @types, so the web app must declare React/JSX settings while Vite keeps plugin-react. Co-authored-by: Cursor <cursoragent@cursor.com> * test: pin Vercel --include=dev and share parse-only string helpers Production npm ci omits the web TypeScript unless --include=dev is on that install. Move staticStringValue next to the other Babel walk helpers so CLI help and contract tests share one source. Co-authored-by: Cursor <cursoragent@cursor.com> * chore(autofix): apply prettier + eslint fixes via /autofix command --------- Co-authored-by: Gergo Magyar <gergomagyar0@gmail.com> Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Gergő Magyar
|
b1d87c1f33
|
fix(eval): sweep evidence handling and measurement health, with guarded comparator reuse (#3207)
* fix(eval): cut skill-evolution wall clock without shrinking the gate
Reuse matching incumbent/CE cells, sanitize each SHA once, and default
dispatch workers to 3 so weekly review generations finish inside the
EventBridge window. Cap the sweep from leftover instance uptime so a
Friday dispatch still uploads evidence.
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* perf(eval): pipeline graph setup and correct the wall-clock cost model
The evolution sweep paid `sanitize` + `analyze --pdg --index-only` for every
unique task SHA on the critical path, one at a time, with nothing overlapping.
`_run_sweep` now starts the next unpaid SHA's clone template and graph snapshot
on a prefetch thread as soon as the current task's cells are dispatched, so
every SHA but the first hides behind a paid session wave. The thread is joined
before that SHA is used and before the trees tempdir is torn down, and a
prefetch failure is recorded against the SHA exactly as an inline failure is.
Tasks whose cells are all reusable comparator rows are not prefetched: they
never build a graph, so priming one would be pure cost.
Adds `measure_evolution_cost.py`, the cost model behind these numbers. It reads
the review corpus, the evolve defaults, and the workflow's workers default —
it does not start a session. Its first version charged `copy_isolated_tree`
once per paid cell, serially. `run_cell` clones inside its own pool worker, so
the clones in a wave overlap and only one is on the critical path per wave;
the model now charges `ceil(cells / workers)` waves.
Estimated review generation at workers=3: cold 21570s, weekly 7710s.
Wall clock is quantised by `ceil(cells_per_task / workers)`. A cold review task
is 9 cells, so workers=4 buys the wall clock of workers=3 and pays host
contention for it. Documented in the workflow's rollout checklist.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* perf(eval): price the benchmark against measured cell durations
The cost model assumed every cell runs the 1140s mean. Cells are not uniform:
the 41 rows in Actions run 33912693948's artifact are 826s at the median,
1262s at the mean, 2976s at p90, with two pinned at the 5400s session ceiling.
A wave waits for its slowest cell, so a mean understates every concurrent
schedule — the previous model called workers=3 cold 5.99h when the same
schedule against real durations is 10.33h.
session_durations.json carries the sample in submission order with its
provenance and its caveat: every cell in that run returned unusable evidence,
so the durations are real but a clean run may sit lower. It is the only live
artifact; the 2026-07-22 green run's has expired.
The model now simulates the schedule cell by cell rather than multiplying a
mean by a wave count, averaged over all 41 rotations of the sample so no
single alignment between sample order and cell index decides the answer. It
prices today's barrier (wave_makespan) against a continuously fed pool
(fed_makespan) and reports both, and it charges the proposer session — one
per generation, measured at 344.7s — which it had been omitting entirely.
Measurement only; no runtime behaviour changes.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* perf(eval): price arms separately and stop inventing setup constants
Two errors in the model, both found by auditing it against the artifact it
claims to describe.
The arms are not interchangeable. `candidate_review` runs 1416s at the mean
against `review`'s 1204s and `ce_review`'s 1176s, and the weekly lane pays the
candidate arm and nothing else — reuse skips both incumbents. Pricing weekly
from a pooled sample charged it for arms it never runs: weekly is 4.59h, not
the 3.65h a pooled sample reported. Cells are also submitted run-major and
arm-minor, so at workers=3 every wave holds one cell of each arm and the
slowest arm sets the wave; the model now builds cells in that order.
The setup constants were invented. GRAPH_ANALYZE_SECONDS=600 and
TEMPLATE_SANITIZE_SECONDS=180 charged 3900s of per-SHA setup for a cold run —
more than the entire non-session time of the source run, which was 2541s for
41 cells and 5 SHAs. `duration_s` is the sum of a cell's Claude sessions
(runner_sessions.py), so that 2541s residual is every clone, graph build,
sandbox and teardown the sweep paid. The model now charges the measured
residual per cell, 62.0s, and no longer credits clone templates or graph
prefetch: both landed after that run and there is no measurement of them yet.
The residual bounds what they can be worth.
Cold 37452s (10.40h), weekly 16541s (4.59h), against a fed pool at 31683s and
16541s. Measurement only; no runtime behaviour changes.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* perf(eval): charge sweep overhead where more workers cannot dissolve it
Three defects, found by auditing the model against the artifact again.
The overhead was charged inside the schedule. session_durations.json claimed
the residual was charged "per cell and serially - the pessimistic reading",
but task_cells folded it into each cell's duration, where the pool then
divided it by the worker count. The residual mixes per-cell work the pool
really does divide with per-SHA graph setup it cannot, and the artifact cannot
separate them, so it now sits outside the schedule: cold 11.09h, not 10.40h.
Alignment averaging weighted the shortest sample twice. The arm samples are 13,
14 and 14 long and the average ran over max()=14 offsets, so candidate_review's
first cell was counted twice and its last never. Averaging over lcm()=182
offsets weights every arm's sample evenly.
The wall assumed all 54 cells run. Replaying the sample's own error_kind
sequence through today's systemic_outage_streak trips the outage breaker at
cell 5 of 41. The source run executed all 41, so its runner did not break on
that sequence, but the current one would: these numbers price a HEALTHY sweep,
and a sweep with the sample's failure profile never reaches them. Stated on
generation_seconds and recorded next to the sample it qualifies.
Measurement only; no runtime behaviour changes.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix(eval): give the review agent somewhere it can actually write
Every review cell in the last recorded generation returned unusable evidence.
Not some — all 41, across all three arms and all six tasks, at $3653 for the
run. The transcripts say why, 127 times across 35 of 35 sessions:
EROFS: read-only file system,
open '/workspace/review-output.json.tmp.2.90a76e583b0c'
The review arm mounted the artifact as a writable FILE at
/workspace/review-output.json while binding /workspace read-only. The Write
tool writes atomically: it creates `<target>.tmp.<n>.<hex>` beside the target
and renames it. The parent was read-only, so the temp create failed and the
artifact was never written. A writable file inside a read-only directory is
not writable to anything that writes atomically. Agents tried
/proc/self/root/workspace/... and /proc/1/root/workspace/... to get around it;
all 41 artifacts came back 0 bytes.
The artifact now lives in its own writable directory bound at /review-output,
outside the workspace. That is what a rename needs, and it lets the workspace
get stricter rather than looser: the review phase may now change nothing there
at all (enforce_phase_workspace gained allowed_artifact=None), where before it
was entitled to one path inside it. The file is no longer pre-created — the
agent writes it, and absence is now meaningful evidence.
parse_review_output reported every one of these as "review output is not valid
UTF-8 JSON". The file was empty, and its except folded OSError, UnicodeError
and JSONDecodeError into that one string, so a sandbox that made writing
impossible was indistinguishable from an encoding fault. That is why this read
as an agent-quality problem for fifteen consecutive non-green runs. Each cause
now names itself: never written, empty, not valid UTF-8, not valid JSON with
the decoder's position. run_arm also keeps the FIRST error_detail, as it
already did for error_kind, so a phase-boundary violation is no longer buried
under the parse failure it causes.
The test double conflated sandbox.private_root with the clone, which put the
artifact directory inside the workspace and would have hidden the stricter
check. Regression tests pin the mount shape in the generated bwrap argv, the
contract path in the prompt, the four parse diagnostics, and the
untouched-workspace contract.
Verified by unit tests only: this container has unprivileged user namespaces
disabled, so bwrap cannot run here and the mount was not exercised end to end.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix(review): close the artifact path in every layer that gates it
Code review of this branch found the relocated review artifact was fixed in the
bwrap mount and nowhere else. Four independent layers decide whether the agent
can write it, and three still named the old location.
Claude Code applies its own filesystem policy to its own tools, and
build_claude_settings listed only /workspace, /tmp and /home/agent under
allowWrite with denyRead ["/"]. The artifact used to live under /workspace, so
this list was correct until it moved. SANDBOX_REVIEW_OUTPUT is now in allowWrite
and allowRead; without it the bwrap bind grants a write the CLI then refuses.
The task corpus still ran `test -s review-output.json` from the workspace, in a
separate sandbox invocation that never sees the artifact mount. Every review
cell would have been stamped verify-failed with resolved=False no matter how
good the review was, which also made those rows permanently unreusable and so
silently disabled this branch's own comparator reuse for review arms. The verify
and hidden-oracle commands now read the location from
GITNEXUS_BENCH_REVIEW_OUTPUT and get the directory bound read-only, mirroring
the mount-plus-env-var shape _run_hidden_oracle already used.
host_text and host_path did not translate the new path, so the host-unsafe
backend told the agent to write somewhere that exists on neither backend.
Adding the mapping exposed a second defect: host_text substituted every
occurrence of a target, and "/review-output" appears twice in
"/review-output/review-output.json" - once as the directory and once inside the
filename. Matching is now anchored to a path boundary.
Comparator reuse had three ways to accept evidence it should have rejected. A
row with no runtime_digest passed the drift lock because the guard only compared
when both sides were bound, and the branch's own test asserted that as correct;
absence is now a mismatch and the test states the rule. materialize_reused_row
overwrote recorded_at with the copy time while the age check read that field, so
a row copied forward each generation refreshed its own clock and never aged out;
the first measurement time is now preserved and aged against. A future-dated
stamp passed a one-sided bound and is now rejected as corrupt.
RUNTIME_DIGEST never reached the runner at all: runner_environment builds a
fixed dict and process_control replaces the child environment wholesale, so the
digest the workflow exports was dropped and the lock it feeds was inert. The
instance-window deadline was also checked only after run_proposer returned,
buying a proposal the generation had no room to benchmark.
The graph prefetch thread was started without copy_context, so it never saw the
cancellation ContextVar the rest of the sweep shares, and the outage breaker
returned without setting cancel_event - together, a tripped breaker would block
on joining a prefetch that was never told to stop. Both fixed, with outage
checked before cancellation at the two exits so an outage keeps exit 1 instead
of becoming a Ctrl-C's 130.
Both bwrap canaries that actually execute a write still bound the pre-fix shape
against a file this branch no longer creates, so they would have errored rather
than caught anything. They now bind the directory and write atomically - temp
file beside the target, then rename - which is the exact operation that failed
with EROFS. A source-text assertion over inspect.getsource(run_arm) was replaced
with one that inspects the real mount, and a wall-clock assertion was pinned to
a fixed monotonic clock.
Not applied, and why: binding task-asset and dependency digests into comparator
reuse needs asset snapshots prepared before the reuse decision rather than
inside the per-task loop, and shipping the comparison without that would add a
guard that silently never fires. Forcing a paid canary cell per incumbent arm
and folding reused rows into the outage streak are behaviour decisions, not
fixes. Clone-template reuse still has no test. The cost model's per-cell
residual still shrinks with arm count, overstating weekly savings by at most the
2541s residual; the docstring now says so rather than inventing a split.
585 eval tests pass, ruff clean, 29 workflow contract tests pass. The two
test_model_gateway.py failures are pre-existing and fail on main.
* fix(review): bind reuse to its environment and keep the health canary real
Applies the five findings the previous review round left open.
Comparator reuse ignored the environment a row was measured in. TaskReuseBinding
carried the task and oracle identity but not the task-asset or sandbox-dependency
digests, and this branch itself changes sandbox_dependencies in the review
corpus - so a reused comparator could be measured against one dependency set and
compared against a candidate built on another, handing the gate a false
comparison. Closing it needed the digests to exist before the reuse decision, so
asset snapshots are now prepared for every task up front instead of lazily
inside the per-task loop. That also removes the concurrent TaskAssetCache.prepare
the prefetch thread could otherwise race, which the file's own "plain dict,
read-then-write race" comment warned about. Both digests fail closed on either
side, matching the runtime digest.
The broken-incumbent canary could not fire when reuse was working. It read
`resolved`, which counts reused rows, so an arm whose cells were all reused
always looked healthy - in precisely the run where a broken environment would go
unnoticed. aggregate now also reports `resolved_fresh` and the canary reads it.
That count would be vacuous if an arm were reused end to end, so the sweep keeps
one paid cell per incumbent arm and says which one it kept.
Reused rows did not participate in the outage streak, so a run of failures could
carry across them and trip on stale history. A reused success now resets the
streak the way a paid success does.
The cost model charged sweep overhead per cell, which credited a weekly
generation for shrinking work it still performs: it pays one arm instead of
three but builds exactly the same graphs. Overhead is charged per SHA now.
Weekly is 5.20h rather than the 4.80h the per-cell rate reported; cold is
10.86h. The residual still cannot be split between per-SHA and per-cell work
from one artifact, so session_durations.json records that assumption and the
direction it errs in, rather than leaving a number nobody can trace.
Clone-template reuse - the branch's core speedup, taken on essentially every
multi-cell sweep - now has a test that builds a real sanitized template, asserts
the cell runs against the copy with the template's HEAD, and fails if run_cell
re-clones. A second test asserting only on a namespace built inside the test was
written and deleted: it exercised nothing, which is the failure this review
round penalised elsewhere.
589 eval tests pass, ruff clean, 29 workflow contract tests pass. The two
test_model_gateway.py failures are pre-existing and fail on main.
* refactor(eval): consolidate duplicated harness logic after the review round
Simplification pass over the branch. Behavior-preserving throughout; three
reviewers, nine findings applied, two skipped.
The review-artifact block in _run_hidden_oracle was unreachable. That function
runs only in run_arm's non-review branch, while the directory it probes for is
created only in the review branch, and each sandbox serves exactly one arm - so
`review_artifact.parent.is_dir()` could never be true. It was added an hour
earlier to make the hidden oracle resolve the moved artifact; the oracle never
runs for review tasks, so the guard was dead on arrival. Deleting it also
removes the duplication it had with the verify-command wiring.
EXCLUDED_ERROR_KINDS is now one definition. runner.py and comparator_reuse.py
each carried the same six-member frozenset, kept in sync by a comment. Only one
direction is possible: runner already imports from comparator_reuse, so the
reverse import fails at module-init with a circular-import error. That is now
stated where the alias lives, so nobody tries it the other way.
ensure_task_graph and prefetch_next_graph shared ten keyword parameters, passed
through two call sites and forwarded whole between them. They now take a
GraphBuildEnv, mirroring TaskCellContext, which already bundles per-cell state
in this file. Its ready_keys() replaces an inline four-set union at the call
site.
Smaller consolidations: _sha256_file's hand-rolled chunk loop becomes
hashlib.file_digest (3.11+, already used in runner_artifacts); _copy_owner_only
reuses task_assets._write_all and COPY_CHUNK_BYTES instead of repeating the
short-write retry; its stat-then-open existence check becomes the O_EXCL failure
it was already relying on, which is atomic rather than merely narrow; and
runner_environment reads the digest through comparator_reuse.current_runtime_digest
instead of re-parsing the environment variable.
Three test docstrings summarised the branch's own history ("the branch's core
speedup", "the regression that produced fifteen runs") rather than the invariant
under test. Rewritten to state the constraint, which is what survives the merge.
Repaired the indentation left behind by the outage-streak edit and flattened the
prefetch dispatch from three nested conditionals to one.
Skipped: consolidating comparator_reuse._real_directory onto proposer_sandbox's
same-named helper - they differ, the sandbox one rejects any symlink in the
resolved path while this one checks only the leaf, so sharing it would tighten
behavior rather than preserve it. That needs a decision about which policy the
reuse path wants, not a simplification.
589 eval tests pass, ruff clean, 29 workflow contract tests pass. Unrelated and
pre-existing: two test_model_gateway.py failures, and
test_process_control.py::test_timeout_kills_term_ignoring_descendants_before_they_write,
which is a TERM-to-KILL timing flake (passes 2 of 3 in isolation) in a file this
branch does not touch.
* refactor(eval): name the reuse directory check for the promise it makes
The simplification pass left one finding open: comparator_reuse and
proposer_sandbox both defined `_real_directory`, same name and same shape, with
different guarantees. The sandbox one rejects every symlink hop in the path; the
reuse one checks only the leaf and resolves through parents. Sharing the name
invites a consolidation that would silently tighten one of them.
They should not be merged, so the name stops claiming they could be.
proposer_sandbox guards a mount root, where a symlink hop changes what an
untrusted session is handed. comparator_reuse guards a data directory whose
contents are already validated one file at a time - reads go through
_regular_file, which lstats and rejects symlinks, and writes through O_NOFOLLOW.
A symlinked parent therefore grants nothing those guards do not already cover,
while refusing one would reject a symlinked artifacts directory or macOS's /var
for no gain.
Renamed to _resolved_directory, with the reasoning recorded at the definition,
and a test that pins both halves: a symlinked parent is accepted and resolved, a
symlinked leaf is still refused. Behavior is unchanged.
591 eval tests pass, ruff clean. The two test_model_gateway.py failures are
pre-existing and fail on main.
* test(eval): measure the sweep scheduler instead of modelling it
measure_evolution_cost predicts wall clock from a model of what
sweep_task_cells does. This runs the real thing - real threads, the real wave
barrier, the real outage breaker - with only the paid agent session replaced by
a sleep, and times it.
Durations are the measured per-arm samples divided by 5000, so a 1416s cell
takes ~0.28s. The shape is kept on purpose: the median cell is 826s against a
5400s ceiling, and that spread is the entire reason a barrier costs anything.
Uniform random sleeps would erase the effect under test. All schedulers consume
one identical seeded plan, so a comparison cannot be an artifact of one of them
drawing luckier cells.
The model survives contact: it tracks real execution within about 10%, and
workers=1 - which runs without a pool at all - sits at 0.95, so the residual
above 1.0 at higher worker counts is per-wave thread overhead rather than a
modelling error. Two structural claims that were arithmetic are now observed.
Weekly is flat from workers=3: 3.59, 3.59, 3.59, 3.60, 3.59, 3.59 across w=3..8.
workers=4 buys nothing over workers=3 on cold, 7.68 against 7.78.
Two prototype schedulers are measured beside it, deliberately before any
production code exists. A continuously fed pool per task is worth more than the
model claimed on cold, -27.3% against a predicted -17.9%, and exactly nothing on
weekly, +0.0%, because a weekly task is one wave with nothing to feed. One pool
across all tasks beats both: -40.7% weekly and -42.9% cold at workers=3, rising
to -65.7% and -63.9% at workers=8. It also subsumes the fed pool, since packing
across tasks is a fed pool.
That reorders the backlog. Cross-task packing moves from second to first: it
dominates on both profiles, and it is the only thing that moves weekly at all.
Raising the worker count is worth nothing until it lands - under the barrier
weekly does not improve from w=3 to w=8, and speedup against serial is 1.58x for
three workers and only 2.40x for eight.
The bound on all of it: sleeping threads do not contend. Real sandboxed sessions
compete for CPU, page cache and disk, and the duration sample was itself
measured at workers=1, so it carries no contention either. These speedups are
upper bounds. The ordering is trustworthy because the schedulers were compared
under identical conditions; the magnitudes are not. The packed prototype is also
a bare ThreadPoolExecutor with no breaker folding, no per-task graph lifecycle
and no reuse binding - which is the actual cost of building it, and is not
measured here.
* test(eval): carry the sweep invariants into the packed prototype
The first packed prototype was a bare ThreadPoolExecutor. It reported -43% and
none of the invariants the shipped scheduler holds, so it priced an idea nobody
could ship. This one carries them: a global submission order continued across
task boundaries, in-order folding, the real outage breaker, and per-task graph
readiness gating behind a serial builder.
The fidelity check first reported the two schedulers tripping on different
cells, 17 against 16. That was my instrumentation, not a divergence -
sweep_task_cells folds an entire wave before it evaluates the breaker, so the
last cell folded is not the cell that tripped. With the harness mirroring the
breaker's own evaluation the two agree exactly, across failures starting at
cell 0, 4 and 12, with overrun inside the workers-1 bound the wave docstring
promises.
Two results worth the exercise.
Head-of-line blocking, not the barrier, is what a naive in-order design pays.
Holding submission to `workers` cells beyond the fold pointer leaves the
faithful scheduler at -8.1% cold and -2.7% weekly: one slow cell stalls the
pointer, the window cannot slide, and it reproduces the wave almost exactly.
That is the number to quote if anyone proposes the obvious implementation.
But the overrun bound turns out to be set by the worker count, not the window.
Only `workers` cells can be running when the breaker trips; everything queued
behind them short-circuits on the halt flag. Overrun is 3 at an unbounded
window exactly as at 6, and the trip cell never moves off 16. So H2 does not
have to trade breaker fidelity for speed - a wide window takes -42% with the
semantics intact. The tension I assumed was there is not, and window=12 already
captures 97% of it.
Still an upper bound: sleeping threads do not contend, and the sample was
measured at workers=1. What this establishes is that the invariants are
affordable, which was the thing blocking H2. Not built here: the trees tempdir
lifecycle, reuse-row binding, and the cancel_event path.
591 eval tests pass, ruff clean.
* test(eval): put the scheduler comparison under real CPU contention
Every Phase 2 number so far came from sleeping threads, which contend for
nothing, against a duration sample measured at workers=1, which contains no
contention either. That was the standing caveat on the whole result, so this
measures it.
A cell now waits for its API share and then burns a fixed number of sha256
rounds in a subprocess. Work-bounded rather than wall-clock bounded, so it takes
longer when cores are busy - that is the effect under test. A subprocess because
Python threads burning Python would measure the GIL rather than the machine.
Calibrated at 519k rounds/s, stable within 2% across three probes.
The first run of this was worthless and is recorded as such: on a 24-core host
with 3 to 6 workers nothing ever contends, since cpu_fraction 0.5 at 6 workers
is about 3 cores of demand out of 24. It measured an absence. Re-run pinned with
taskset to 4 and 2 cores.
The packing advantage survives. It holds between -40% and -47% across every host
size and CPU fraction tested, including a genuinely oversubscribed 2-core box at
cpu_fraction 0.5 with 6 workers.
But contention erodes packing more than it erodes waves, for a structural
reason: packing is what creates the concurrency. Moving from 24 cores to 2 at
cpu 0.5 and 6 workers, the faithful scheduler slows 13% while the wave slows
3.7%, and the gain narrows from 45.0% to 39.8%. Packing and a higher worker
count are therefore not independent wins - packing spends the contention
headroom first, so raising workers has to be re-argued after it lands rather
than added to it.
Three things this still does not measure, and they bound the result. The real
CPU fraction of a benchmark cell is a guess informed by roughly 180 tool calls
per session; nobody has profiled one. The evolution runner's core count decides
which column applies and is unknown here. And the burn is sha256, pure CPU,
while real cells run vitest and analyze, which are memory and IO heavy - so this
is a floor on contention, not a ceiling.
591 eval tests pass, ruff clean.
* perf(eval): add a packed sweep scheduler, and correct the bound I claimed for it
sweep_task_cells finishes one task before starting the next and drains a wave
before refilling it, so a task with fewer cells than workers leaves workers
idle and one slow cell stalls its whole wave. sweep_packed_cells feeds every
task's cells through a single pool instead. Measured against the review corpus
it is worth about 40% of a cold sweep, and it is the only change that moves a
seeded weekly run at all - there a task is three cells and a wave is never full.
The breaker keeps its exact meaning. Cells carry a total submission order
continued across task boundaries, a folder walks results in that order, and
consecutive systemic failures are counted there, so a doomed run aborts on the
same cell it would have under waves. Verified at three failure positions.
This commit also corrects a finding from the Phase 2 prototype. I claimed the
overrun bound was set by the worker count rather than the submission window,
and that packing therefore cost nothing in breaker fidelity. That was derived
from a window sweep that only ever injected failures at one position. Driving
the real function at other positions shows the halt flag does not bound overrun
at all: the folder walks in order, so a slow early cell lets workers race ahead
and the trip is detected after those cells have already paid. An unbounded
queue overran by 11 cells where waves overrun by 2.
So the window is load-bearing and the trade is real, measured at workers=3 with
failures injected at four positions:
window 3 -> -8% wall, overrun 2 (the wave scheduler's own bound)
window 6 -> -27% wall, overrun 4
window 12 -> -42% wall, overrun 9
window 54 -> -44% wall, overrun 11
Overrun is wasted paid sessions at roughly $70 each. The default multiplier is
2, keeping the worst case within twice the wave bound while taking most of the
gain; the curve is in the constant's comment so raising it is an informed
decision rather than a guess.
Not wired in yet: _run_sweep still calls sweep_task_cells per task. Moving the
per-task graph, trees tempdir and reuse binding out of that loop behind
await_ready is the larger and riskier half, and it belongs in its own change.
595 eval tests pass, ruff clean.
* fix(eval): judge harness health on execution, not on how many tasks resolved
broken_incumbent_arms infers "the environment is broken" from an arm resolving
zero tasks. That inference does not hold: a reviewer can be wrong about every
task in a hard corpus while every process, mount and capture worked perfectly.
Actions run 33962002890 is exactly that shape - 51 cells, all resolved=False
with error_kind=oracle-failed, median score 0.212, and a healthy harness.
Someone already knew this, and patched it by excluding review arms at the call
site. That leaves the unsound inference in place for workflow and
workflow_direct, and leaves review arms with no health check at all - so the
run that genuinely was broken, 33912693948, where the mount made an atomic
write impossible and all 41 artifacts came back empty, could not have been
caught here either.
So this replaces the inference rather than adding another exemption. aggregate
now classifies fresh rows into execution failures (the process or its tooling
did not complete), evidence failures (it completed but produced nothing
trustworthy or scoreable), and admissible measurements. An arm is unhealthy
only when it has fresh attempts, zero admissible measurements, and at least one
execution or evidence failure. Resolution count is no longer consulted. Arms
with only reused rows report current health as UNKNOWN rather than good.
With the inference corrected, review arms are checked again, which is what lets
the empty-artifact case be caught at all.
Deliberately unchanged: comparator reuse eligibility, quality denominators,
promotion thresholds, model settings, skill prompts and scheduler behaviour.
Failures that stop being called infrastructure failures still surface in the
counts and reasons - an agent-originated failure must not vanish from reporting
because it was reclassified. broken_incumbent_arms and its tests are left in
place; deleting behaviour belongs in its own change.
Seven regression tests, built from both runs' shapes and labelled as
reconstructed from logged observations, since 33962002890's results.jsonl did
not survive the instance shutdown. They pin: a badly-scoring reviewer is
healthy; an all-zero score is still a valid negative; empty artifacts are
unhealthy; one admissible cell keeps an arm healthy while its failures stay
visible; reused rows alone leave health unknown; reused successes do not mask
fresh failures; and a parseable artifact does not excuse a failed session.
602 eval tests pass, ruff clean.
* fix(eval): pin the health guard below the breaker, and stop calling mixed runs healthy
Two corrections to the health-classification patch.
The regression I wrote could not have proved what it claimed. A fixture of 41
empty artifacts aborts through the outage breaker long before finalization:
review-evidence-invalid is in SYSTEMIC_ERROR_KINDS and the limit is 5, so it
trips at cell 5 through the pre-existing path. It demonstrated failure
detection, not the new guard. The decisive test now uses ONE fresh unusable
cell, asserts the streak stays under the breaker threshold, and only then
requires finalization to abort - leaving the new check as the only thing that
can catch it. Removing the call makes that test fail; restoring it passes.
The accurate defect statement is narrower than the last message claimed. Review
arms were excluded from the final incumbent-health check while the consecutive-
failure breaker gave them separate, partial coverage. They were not unguarded.
Second: "one admissible cell plus two execution failures" was asserted as
healthy. That converts "not wholly unusable" into "ran reliably", which is how
a partly-broken sweep passes review. Arms now report UNKNOWN, OBSERVED_OK,
DEGRADED or UNUSABLE. Only UNUSABLE is fatal, so eligibility and promotion are
untouched - this changes what is reported, not what is allowed.
The guard is extracted as enforce_measurement_health so it can be driven
directly, and it now reports a status line per arm. It names no cause: an empty
artifact establishes that evidence is unusable, not that a mount rejected the
write, so it prints cause=undetermined rather than guessing EROFS. It still
runs after report.md and promotion.json are written, so a failing sweep leaves
its evidence behind.
ce_review is named explicitly at the call site. It is a comparator rather than
a candidate, so it is absent from CANDIDATE_ARMS.values(), and dropping the
review exclusion alone would have left it unclassified.
The wiring test reads _run_sweep's compiled code object for the referenced
global rather than matching source text. It is honest about its limit: it
proves the call exists and would catch its removal, but no test here drives
_run_sweep end to end, which needs bwrap and a sandbox.
broken_incumbent_arms is marked LEGACY and NON-AUTHORITATIVE with removal
tracked. It has no production caller.
608 eval tests pass, ruff clean. The two test_model_gateway.py failures are
test_locked_litellm_translates_messages_to_offline_responses and
test_openai_gateway_never_leaves_proxy_output_on_an_undrained_pipe; both fail
identically on origin/main in this environment, checked directly rather than
carried forward as an inherited label.
* fix(eval): review artifact path, evidence classification, comparator reuse
Extracted from the combined skill-evolution branch. This is the runtime change
set: everything that alters how a sweep executes and what it records. The
packed scheduler and its measurement harness were separated onto
perf/skill-evolution-packed-scheduler, which is purely additive.
Correctness. The review artifact was mounted as a writable FILE inside a
read-only workspace while the agent's Write tool writes atomically - temp file
beside the target, then rename - so the temp create failed EROFS and the
artifact was never written. Four layers gate that path and three named the old
location: the CLI's own allowWrite/allowRead policy, the task corpus verify
command run in its own sandbox invocation, and host_text/host_path for the
host-unsafe backend. Fixing the translator exposed a second defect, since
"/review-output" appears twice in "/review-output/review-output.json"; matching
is now anchored to a path boundary. parse_review_output folded OSError,
UnicodeError and JSONDecodeError into one message, so an artifact that was
never written looked like an encoding fault; each cause now names itself.
Health classification. broken_incumbent_arms inferred a broken environment from
an arm resolving zero tasks, which a reviewer facing a hard corpus falsifies -
Actions run 33962002890 is exactly that shape. Arms are now classified from
fresh execution and evidence outcomes as UNKNOWN, OBSERVED_OK, DEGRADED or
UNUSABLE, and only UNUSABLE aborts. Resolution count is not consulted. The
guard names no cause: an empty artifact establishes unusable evidence, not that
a mount rejected the write.
Comparator reuse. Reuse accepted evidence it should have rejected: a row
without a runtime_digest passed the drift lock, recorded_at was overwritten with
the copy time so a row could outlive its own max_age, and the binding ignored
task-asset and dependency digests although this change alters
sandbox_dependencies in the review corpus. Closing the last one required
preparing asset snapshots before the reuse decision, which also removes the
concurrent TaskAssetCache.prepare the prefetch thread could race.
These three concerns share aggregate() and _run_sweep, which is why they ship
together: separating them further would mean hunk-level surgery on a function
all three modify, and the risk of a silent omission outweighs the reviewability
gain.
592 eval tests pass at this base. The two test_model_gateway.py failures,
test_locked_litellm_translates_messages_to_offline_responses and
test_openai_gateway_never_leaves_proxy_output_on_an_undrained_pipe, fail
identically on origin/main in this environment.
Known gap, and the reason this is not ready to merge: no test drives _run_sweep
end to end. enforce_measurement_health is unit-tested including the
below-breaker unusable case, and the caller wiring is pinned structurally by
reading _run_sweep's compiled code object, but interruption semantics, exit
precedence and persisted artifacts are not exercised through the real path.
* fix(eval): address PR review feedback (#3207)
- aggregate: count admissible rows directly instead of subtracting the
execution and evidence counters, which double-charged a row that is both
a session error and invalid review evidence and could report UNUSABLE for
an arm holding real measurements.
- run_proposer: bound the session timeout by what is left of
--max-runtime-seconds, so clearing the sweep minimum cannot start a
full-length session past the instance window.
- comparator reuse: hold one O_NOFOLLOW descriptor for the size check,
digest and copy, and prove it is the inode that was checked, closing the
swap window a concurrent writer of the reuse directory had.
- Drive the review-artifact mount assertion through run_arm and the
clone-template assertion through run_cell, instead of rebuilding the
expected values in the tests (also removes the CodeQL unnecessary lambda).
- Assert the workflow invokes run-evolution.sh rather than that its YAML
mentions --max-runtime-seconds, which only appears in a comment.
- Correct the parse_review_output failure-mode claim: the fold was empty
artifacts reported as "not valid UTF-8 JSON"; a never-created file raised
FileNotFoundError.
- prettier: wrap the over-long readFileSync call flagged by PR autofix.
Note: pre-existing failure in tests/test_model_gateway.py::test_locked_litellm_translates_messages_to_offline_responses (local LiteLLM proxy never becomes ready in this environment) not addressed by this PR.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix(eval): address the second round of PR review feedback (#3207)
- Refuse a symlinked `transcripts` component on both sides of comparator
reuse. O_NOFOLLOW guards the leaf only, so a link there redirected the
read or the copy out of the results directory; checked per component as
evolution._require_directory_chain does.
- Base the paid incumbent canary on the cells this sweep PLANS. Reuse
selection accepts any prior run index, so a results directory produced
with more runs left extra keys, the equality never held, and the canary
stopped firing. Extracted as drop_canary_reuse_key and unit-tested.
- Start the runtime clock in main(). --max-runtime-seconds is measured from
/proc/uptime before exec, so parsing, task I/O, preflight and gateway
setup were being handed back to the sweep out of the upload reserve.
- Do not fall back to shutil.copytree when the managed clone copy was
cancelled or timed out; that fallback is for a filesystem that cannot
reflink, and copytree cannot be cancelled.
- Assert the review session's writable mount, not only the verifier's
read-only one: the EROFS bug is about the agent's write.
- Exercise ref isolation in the copy_isolated_tree test rather than
comparing an initial HEAD a shared namespace would also match.
- Point the stale-symlink fixture at the sentinel via os.path.relpath, and
skip the reuse symlink tests where symlink creation needs privilege.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix(eval): close the runtime-cap gap and pin the reuse directory
Both were left open on #3207 as approach decisions rather than nits.
Runtime cap: run-evolution.sh computed the budget in its own
`uv run python -c` and passed a number, so the script's remaining
provenance work and the CLI's own startup were spent by nobody and charged
to the sweep — out of the upload reserve the cap exists to protect. The
script now passes --max-runtime-from-instance-window and evolve reads
/proc/uptime itself, on the line after it starts the clock the budget is
measured against, so no interval exists to lose. Also removes an
interpreter start from the script and lets --dry-run print the real argv.
Reuse directory: _real_child_directory lstat-checked `transcripts` and
returned its pathname, so a concurrent writer could rename the directory
and leave a symlink before the name was used again — O_NOFOLLOW guards
only the leaf. Every artifact is now resolved against a held descriptor:
_open_real_directory opens with O_DIRECTORY|O_NOFOLLOW (check and open in
one syscall), and _open_regular / _copy_owner_only take dir_fd. The reuse
path is therefore POSIX-only; _require_openat says so and fails closed,
which the runner already treats as "run a paid cell". _resolved_directory
still tolerates a symlinked reuse root, unchanged and still tested.
evolution._require_directory_chain is still lstat-per-component. It guards
a different surface (candidate overlay reads) that neither review raised,
so it is left alone rather than widened into here.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix(eval): sample the proposer budget where it is spent, digest what is copied
Four findings against
|
||
|
Gergo Magyar
|
1054e3e038 | fix(eval): make evolution evidence valid and bounded | ||
|
Gergo Magyar
|
6925fb344d |
feat(eval): evolve review skills against historical PRs
Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|
Gergo Magyar
|
167642ec9d |
feat(ci): let a dispatched evolution run start from a blank slate
Seeding is unconditional today, so the next run would inherit the rejected proposal from a generation whose proposer could still read the hidden oracles. That taint propagates: each generation stages the previous proposal, so one contaminated proposal survives until the artifact expires. Scheduled runs still always seed — memoryless weekly runs would re-propose the same rejected candidate forever. Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|
Gergo Magyar
|
d541105340 |
fix(workflow-bench): repair the harness defects the verbose proposer logs exposed
The first fully-logged skill-evolution run failed for five deterministic reasons that had nothing to do with the candidate under test. Each is fixed at the layer that actually owns the contract: - Strict provider adapters materialize omitted optional string arguments as "". The MCP alias normalizer now treats a blank optional alias as absent (a blank REQUIRED target is still rejected), and a trusted PreToolUse hook strips blank strings before Read/GitNexus tool calls. - MCP semantic errors rode home in a successful envelope and logged as result=ok. SessionProgress now inspects the payload and reports them as semantic-error. - Claude Code's nested sandbox overlays absent root dotfiles with device nodes, which the provenance snapshot read as unauthorized workspace changes. Those names are excluded at the workspace root and hidden from git via an immutable excludes file. - The proposer could not read /evidence from Bash (missing allowRead entry) and had no offline gitnexus runner, so it fell back to npx and hit the network. Both are now mounted; ripgrep is installed in CI. - selected-rows.json advertised host artifact names that do not exist in the mount. Rows now name their staged patch_file/transcript_files, the prompt describes the real layout, and oversized bundles compact artifacts before dropping evidence rows so no row is silently lost. Also replaces two benchmark scenarios that main already satisfies (trivial-version-alias, inv-bug-pdg-note) with non-vacuous ones, verified to fail against a pristine checkout. Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|
Gergo Magyar
|
3c2648b3c9 |
fix(eval): trim oversized proposer evidence instead of aborting
Selected rows can exceed the 2MiB sandbox bundle even when each file is capped; shrink the seed and stage path so a fat prior artifact no longer kills the evolution job. Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|
Gergo Magyar
|
b580c96501 |
fix(ci): wait for host OOM guard before evolution preflight
The runner stamps job processes at 500 faster than the host rewrite; a single read failed a live OpenAI dispatch before any model work. Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|
Gergo Magyar
|
37415cb1ca |
feat(eval): route skill evolution through OpenAI
Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|
Gergo Magyar
|
45f97045e0 |
refactor(eval): simplify sweep internals and needrestart check (#2785)
Reuse the incumbent skill digest instead of walking the tree twice, and keep the needrestart grep a literal match that actionlint accepts. Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|
Gergo Magyar
|
b7e621df4c |
fix(ci): gate evolution runs on runner readiness (#2785)
Prevent paid scheduled work until host survival protections and the proven three-worker rollout are explicitly in place. Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|
Gergo Magyar
|
999b7bbede |
fix(eval): close skill evolution review gaps (#2785)
Keep promotion decisions monotonic and evidence-bound while preserving paid sweep results, redacting live failures, and hardening prior-run seeding. Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|
Abhinav Pandey
|
c3eb5991c1
|
fix(eval): preserve complete evolution evidence | ||
|
Abhinav Pandey
|
aeb853b9cb
|
fix(ci): harden evolution evidence reuse | ||
|
Gergo Magyar
|
a5251d6b08 |
docs(ci): record why the runner box must not restart services mid-job
A run spans ~15h and apt-daily-upgrade.timer fires daily around 06:34, so every scheduled run crosses it. On 2026-08-02 unattended-upgrades upgraded openssl at 07:54:02 and needrestart restarted the Actions runner five seconds later. The job went to Canceled 14s after that, and a cancelled job skips even `if: always()` — so the evidence artifact died with it, which is the one outcome the rest of this workflow's budget nesting exists to prevent. This is a plausible contributor to the unexplained mid-run failures in the July dispatch cluster, none of which left an artifact behind either. The box config itself is applied out-of-band like the rest of the instance setup; the checklist now carries the requirement so a rebuilt box does not silently reintroduce it. |
||
|
Gergo Magyar
|
2fbd5ee515 |
fix(ci): make the task repo resolve the ref its tasks name
Every task in tasks.scenarios.yaml names `ref: main`, and resolving it is
the first thing task binding does. actions/checkout only creates a local
ref for the ref it checked out, so `main^{commit}` resolves on a main run
and dies with "unknown revision" on any other — which is what a
workflow_dispatch from a branch hits, before a single session starts.
The step that points the benchmark at the checkout now also makes that
checkout able to answer for the refs the tasks name. On a main run the
fetch is a no-op.
|
||
|
Gergo Magyar
|
8076b98fcc |
refactor(ci): address the evidence path directly instead of threading it
The upload step needs a path that does not depend on the sweep step
surviving. It did not need shared state to get one: `runner.temp` is
available in a step, only not in a job-level `env:`, so each of the three
consumers can name `${RUNNER_TEMP}/wfevolve` itself. That deletes the
env var and the step that published it — the previous fix swapped one
threading channel for a sturdier one where no channel was required.
Also from the same review pass:
- `announce`/`keep` drop their default-argument capture of `task["id"]`
and `per_arm`. Late binding only bites a closure invoked after the loop
moves on; these are called synchronously inside `sweep_task_cells`,
which blocks until every wave completes. The trick was guarding against
a race that cannot happen here, while implying to the next reader that
it can.
- `_stub_cell_dependencies` returns the list its teardown appends to
rather than taking it as an out-parameter, dropping the boilerplate
from every call site.
- The workflow's `WORKERS` comment points at the `--workers` help text
instead of restating it, so the rationale has one home.
|
||
|
Gergo Magyar
|
d18dbd4143 |
fix(ci): publish the evidence path from a step, not a job-level env
`${{ runner.temp }}` does not exist in a job-level `env:` block — the
runner context is only available to steps — so OUT_ROOT would have
resolved to a bare `/wfevolve` at the filesystem root. The sweep would
have failed writing there, and the upload would have pointed at nothing.
actionlint caught it; this repo lints workflows for exactly this reason.
The property that mattered is kept: the path is fixed before anything can
fail, rather than read from the sweep step's outputs — that being the
step whose death is the reason the upload matters. The first step now
publishes it to GITHUB_ENV, which every later step sees, including the
`if: always()` upload after a killed sweep.
The contract test pins the step's position and its exact line, so the
context cannot creep back into the job block.
|
||
|
Gergo Magyar
|
edb24da1e8 |
feat(ci): expose benchmark cell concurrency to the evolution lane
`--workers` reaches the sweep from evolve.py and from a workflow_dispatch input. Both default to 1, so nothing about the scheduled lane changes: the runner is sized for one cell at a time, and a cell starved of CPU drifts toward its session timeout, which the gate counts as an excluded run and refuses to decide on. generation_timeout_seconds is left alone deliberately — it is a worst-case sum-of-every-timeout bound (843h at current settings), already far looser than any real run, and concurrency only makes it looser. Raising the input is gated on the runner resize; the contract test pins the default so the lane cannot start running 3-way on a 2-vCPU box by accident. |
||
|
Gergo Magyar
|
01be282667 |
fix(ci): make the evolution lane survive its own deadlines and remember prior runs
An end-to-end pass over the lane — instance start, job, artifacts, promotion — found three ways it loses work that has already been paid for. **Evidence died with the job.** Three budgets have to nest: EventBridge keeps the box up 24h from ~02:45, the job timeout was also 1440min, and the sweep had no budget of its own. A job-level timeout CANCELS the job, so the upload step never runs; and since the box stops 24h after it starts while a scheduled run can begin well after the cron (the 2026-08-01 run was queued 65min late), the box always won that race — the runner would simply vanish mid-step. The job now gets 21h, the sweep step 19h, so a wedged generation fails the step, keeps the job alive, and still uploads. The nesting is asserted in the contract test. **The upload could be skipped.** Its path came from an output the sweep step wrote — the same step whose death is the reason the upload matters. OUT_ROOT is now a job-level env constant known before anything runs, and the upload is unconditional: results.jsonl and transcripts are appended as the sweep goes, so a killed generation still holds the evidence that explains why it died. **The lane was memoryless.** `--seed-results` is how a run sees what already lost (summarize_gate feeds the prior promotion.json to the proposer), and with the default --generations 1 there is no earlier generation in-process to supply it — the workflow never passed it, so every Saturday proposed from a blank slate and could re-propose the same rejected candidate forever. The lane now seeds from the last successful run's artifact, best-effort: a first run, an expired artifact, a missing gh, or a failed download proceeds without it rather than costing a generation. Also guards the silent-promotion path: `.claude/skills/*` is gitignored with a hand-maintained per-skill allowlist, and `git status --porcelain` — how the workflow detects an applied promotion — is blind to ignored paths. A candidate skill missing from that allowlist would report "No promotion this run" after the gate said promote. A test now asserts every CANDIDATE_SKILLS entry is visible in all three shipped trees. |
||
|
Gergo Magyar
|
5a017f2722 |
feat(eval): report evolution progress while the generation is still running
Run 29907431284 printed its whole 14h45m of output at one timestamp (00:02:59.32) as the process exited: stdout is a pipe, so CPython block-buffered it, and there was no way to tell a live run from a wedged one. Three changes make the lane observable in the Actions log: - PYTHONUNBUFFERED for the driver (workflow step) and for the benchmark subprocess (its env is an explicit minimal dict and inherits nothing), so lines reach the log when they are written. - run_managed grows `echo_stdout`, a passthrough that streams a child's stdout to stderr as it arrives while leaving the bounded tail intact. evolve.py enables it for the benchmark sweep — the multi-hour phase, whose per-run lines previously surfaced only as a tail, and only on failure. It stays off everywhere else: a Claude session's stdout is the evidence stream and is written out only after redaction. - The sweep now announces each cell as it starts (`3/18, 47m elapsed`) and reports `took=` and `error_kind=` when it finishes, so an excluded run — the thing that actually blocks promotion — is visible live instead of only in results.jsonl. evolve.py also reports the proposer's duration, turns, and cost once the proposal lands. |
||
|
Gergo Magyar
|
bb09ce28e0 |
fix(eval): stop discarding completed benchmark sessions as unverifiable
The evolution loop has not been able to promote anything since it went online. Run 29907431284 (the last green run) reached the gate and threw away 5 of its 18 runs, and the gate requires zero excluded runs in both paired arms — so the generation could never produce a verdict on merit. Two causes, both in the session layer: 1. Claude Code drains background-task bookkeeping after the final result event (`background_tasks_changed`, `task_updated`, `task_notification`, all `type: "system"`). The parent-stream check required the result to be the literal last event, so three sessions that had exited 0 with a complete result and usage payload were recorded as session errors. Trailing `system` events carry no tool_use/tool_result/usage payload and cannot forge skill or cost evidence; anything else after the result still fails closed. 2. The 3600s per-session ceiling killed two `workflow` incumbent runs on inv-bug-pdg-note mid-verification. Successful `workflow` rows in the same run finished in ~1600-2600s across both sessions, so the ceiling moves to 5400s and now lives in one shared constant instead of two argparse defaults that could drift apart. Also marks the activation checklist against reality: the secrets, the Environment, the runner, and the validation dispatch are all in place; the repository variable GITNEXUS_EVOLUTION_ENABLED is the one remaining gap, and until it is set the Saturday cron skips the job in seconds while the EventBridge schedule still starts the runner for the day. |
||
|
dependabot[bot]
|
47f3932c8c
|
chore(deps): bump actions/setup-node from 6.4.0 to 7.0.0
Bumps [actions/setup-node](https://github.com/actions/setup-node) from 6.4.0 to 7.0.0.
- [Release notes](https://github.com/actions/setup-node/releases)
- [Commits](
|
||
|
Gergő Magyar
|
5549403082
|
fix(eval): self-hosted skill-evolution runner + sandbox Python 3 trust fix (#2600)
* fix(eval): move skill-evolution to a self-hosted runner and fix the sandbox's Python 3 trust gap GitHub-hosted runners hard-cap job execution at 6 hours, which is too short once a benchmark session actually invokes Skill/MCP tools for real (the --bare fix in #2584 means sessions no longer no-op). Move the job onto a self-hosted runner (5-day cap instead) and document the activation step in the workflow's own checklist. Validating the self-hosted run surfaced a real bug: gitnexus-plan sessions inside the bwrap sandbox failed with "planning must create or modify exactly one plan artifact; observed 0". Root cause: evidence-provenance.mjs's atomic plan-writer only trusts a Python 3 binary owned by root or by the current process. Inside this --unshare-user sandbox only the calling uid is mapped (root isn't), so the real, root-owned /usr/bin/python3 surfaces as the kernel's overflow uid and gets correctly refused as untrusted. Fix: provision a small, self-owned wrapper script (same pattern already used for shell-prefix) that execs the real interpreter, so the sandbox has a Python 3 candidate the existing trust check can actually accept -- without touching that security-sensitive validation logic at all. Also add visibility so this class of failure isn't quiet next time: report.md now shows why each row failed (error_kinds), not just resolved 0/1, and the benchmark now exits non-zero when an incumbent arm -- the currently-shipped skill -- resolves zero across every task, since that reads as a broken harness rather than a normal candidate miss. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> * fix(eval): close the broken_incumbent_arms zero-valid-runs gap; document runner exposure tradeoff Addresses the two MEDIUM findings from the gitnexus-review-agent on this PR (https://github.com/abhigyanpatwari/GitNexus/pull/2600#issuecomment-5033363096). broken_incumbent_arms required valid_runs > 0 before flagging an incumbent, so an incumbent that fails every run with an excluded-but-non-systemic error_kind (e.g. evidence-unverified, which the outage-streak breaker explicitly resets on rather than accumulates) never accumulated a single valid run and sailed through silently -- the exact quiet no-promotion outcome this guard exists to catch, and arguably worse than the some-runs-resolved-zero case since here nothing completed at all. aggregate() never marks an excluded/unverifiable row resolved=True, so dropping the valid_runs requirement and checking resolved == 0 alone correctly covers both cases. Added a test for exactly this all-excluded scenario, which none of the existing three did. Updated the workflow's own activation checklist to reflect what's actually true now (the gitnexus-evolution environment's branch policy and the self-hosted runner are both live, codified in infra/gitnexus-evolution/ in a companion PR) and documented the exposure-window tradeoff the review flagged: the runner is stopped between runs but not destroyed/recreated per run, so it isn't fully ephemeral. Stopping already bounds the exposure window to the job's own runtime on one day out of seven; full per-job ephemeral provisioning is a deliberate non-goal for a job that runs at most weekly, revisit if that changes. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> * docs(eval): remove public infra/ pointers from the activation checklist PR #2603 (the Terraform codification this checklist pointed to) got closed -- publishing the exact IAM roles, security group rules, and self-hosted runner topology for a real, live AWS account isn't safe to do in a public repo, even with no literal secrets or resource IDs in the diff. The underlying AWS/GitHub setup is unaffected and still documented privately; this just removes the now-dangling references to a directory that won't exist in this repo. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> * ci(actionlint): register the gitnexus-evolution self-hosted runner label actionlint rejected `runs-on: [self-hosted, linux, x64, gitnexus-evolution]` in gitnexus-skill-evolution.yml because it can't discover custom runner labels. Register it in .github/actionlint.yaml so the Workflow Lint check passes. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com> |
||
|
Claude
|
eea9ac92dc |
ci: move Node pins to the 22.18 floor
With the supported minimum raised to Node 22.18, retarget every lane and pinned runtime that sat at a lower version so nothing builds or runs the package on an unsupported (EBADENGINE-warning) Node: - ci-tests.yml: node-floor-compat 22.14 -> 22.18.0 (name, comment, pin, version assertion) so the floor gate guards the new minimum; its #2372 registerHooks failure mode cannot recur above 22.15. Containment-canary pin 22.16.0 -> 22.18.0. - gitnexus-review-agent.yml + the pinned review/canary runtime: the reproducible runtime is version-locked in lockstep across .github/{gitnexus-review-runtime,claude-canary-runtime}/package.json and their lockfiles (engines), the workflow's node-version, its two 'node --version = v22.18.0' assertions, the lockfile-engines guard, and NODE_VERSION. Moved all of them 22.16.0 -> 22.18.0. - gitnexus-skill-evolution.yml: pinned runtime 22.16.0 -> 22.18.0. - CONTRIBUTING.md prerequisite floor updated. - review-agent-workflow.test.ts, which enforces the runtime lock, updated to expect 22.18.0. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|
Abhigyan Patwari
|
2ea00a2b22
|
fix(ci): install root and shared node_modules for the evolution benchmark (#2575)
* fix(ci): install root and shared node_modules for the evolution benchmark The first real workflow_dispatch of the skill-evolution loop failed at task binding: capture_task_dependency_binding aborted with SandboxError: sandbox_copy path is unavailable: node_modules: No such file or directory The benchmark tasks sandbox-copy node_modules from three locations (tasks.scenarios.yaml) — the monorepo root, gitnexus-shared, and gitnexus — mirroring a full dev checkout. The install step only ran `npm ci` in gitnexus/, so the root and gitnexus-shared node_modules never existed and the loop died before any agent ran. Install all three (root, then build gitnexus-shared, then build gitnexus), matching the per-package install in ci-tests.yml plus the root deps the tasks require. A new contract test pins all three installs so this fails in CI rather than on the next real run — the same guard the workflow's other two P1 fixes got. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ * fix(ci): only add the missing root install; the subpackage steps already exist The initial fix redundantly rebuilt gitnexus-shared and gitnexus inside the gitnexus step — but the workflow already builds both in their own dedicated steps. Only the monorepo root node_modules was missing. Add a single "Install monorepo root dependencies" step and leave the two subpackage build steps untouched, so the benchmark's root sandbox_copy resolves without double-building. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ --------- Co-authored-by: Gergo Magyar <gergomagyar@icloud.com> Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Gergő Magyar
|
becac9a5d3
|
feat(eval): run the skill-evolution loop online (#2571)
* feat(eval): run the skill-evolution loop online Add a scheduled + dispatch-gated workflow that runs the offline propose -> benchmark -> gate loop (workflow_bench.evolve) in CI with the pinned Claude canary runtime and bubblewrap containment, uploads the benchmark evidence as an artifact, and on a gate-passed promotion opens a human-reviewed PR via the release App token. The applied overlay is bounded to the canonical skill tree and its shipped mirrors; any escape fails the run instead of reaching a PR. The scheduled lane ships disabled behind GITNEXUS_EVOLUTION_ENABLED and requires the new GITNEXUS_BENCH_AUTH_TOKEN secret (benchmark sessions bill real API usage), mirroring the review agent's staged rollout. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ * fix(ci): restructure promotion-PR script so no lint suppression is needed Replace the inline single-quoted credential helper with a GIT_ASKPASS file written via a quoted heredoc (the App token still reaches git only through step env at push time), and assemble the PR body from quoted heredocs plus double-quoted printf instead of a backtick-laden single-quoted template. Every run script in the workflow now passes shellcheck with zero findings and zero disables; the body and askpass rendering are smoke-tested. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ * fix(ci): apply gate-passing overlays in the evolution loop The loop invoked workflow_bench.evolve without --apply, so apply_promoted_overlay (its only working-tree writer, gated by `if args.apply:`) never ran. git status stayed clean, promoted=false was emitted every run, and the App-token/PR-open steps were unreachable dead code — a gate-passing run went green as "No promotion this run". validate_promotion_for_apply already runs before the apply gate, so adding --apply lets a passing candidate reach the tree without weakening the deterministic gate; the boundary check then confirms it stayed in the skill trees. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ * fix(ci): provision ~/GitNexus so the benchmark repo resolves on CI Every scenario in tasks.scenarios.yaml addresses the target repo as ~/GitNexus; runner_tasks.py resolves it with expanduser().resolve() then `git -C <repo> rev-parse`, which raises when the path is missing. On a hosted runner the checkout lands in $GITHUB_WORKSPACE and nothing created ~/GitNexus, so the first real run failed at task-binding. Symlink ~/GitNexus -> $GITHUB_WORKSPACE before the loop. The checkout uses fetch-depth: 0 (full history for the parentless clone), and the benchmark only clones the repo copy-on-write and mounts deps read-only, so the checkout is never mutated. GITNEXUS_BENCH_ORACLE_ROOT stays unset — it defaults to the in-repo oracles dir and is staged by the harness. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ * fix(ci): harden promotion summary output and PR branch recovery Three fixes to the promotion-detection and PR-open steps: - GITHUB_OUTPUT summary used a fixed `PROMOTION_EOF` heredoc delimiter; a value containing that marker on its own line could close the block early and inject output keys. Use a per-run random delimiter, matching the pattern already in tree-sitter-upgrade-readiness.yml. - The summary concatenated every generation's promotion.json (including rejected ones), so the PR body could show a losing generation's decisions. The loop returns on the first promotion, so emit only the highest-numbered gen-N/bench/promotion.json — the decision that fired. - The promotion branch name omitted the run attempt. GITHUB_RUN_ID is stable across re-runs, so a re-run after push-succeeds/PR-create-fails could never push. Include ${GITHUB_RUN_ATTEMPT} (the artifact name already does). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ * fix(ci): least-privilege the promotion App token and gate on an Environment The Mint-App-Token step passed only app-id + private-key, so the minted token inherited every permission the Release App installation holds (including Workflows: write) — far more than "push a branch, open a PR". Switch to `client-id` (as publish.yml does) and request only permission-contents: write + permission-pull-requests: write. Bind the job to a protected Environment (gitnexus-evolution) so promotion runs can be gated server-side. workflow_dispatch runs the workflow and in-tree evolve.py from the *dispatched ref*, so a code-side ref guard is removable by the dispatched branch itself; an Environment deployment-branch rule (main only) is the boundary that holds. The admin steps to create it and scope the secrets are documented in the activation checklist. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ * fix(ci): correct upload-artifact pin comment and add shell strict-mode - The upload-artifact SHA 043fb46d… is v7.0.1 (labeled so in the sibling workflows that pin it); the comment mislabeled it # v6.0.0. Correct the comment; the pin is unchanged. - Add `set -euo pipefail` to the two build steps that lacked it, matching every other run block in the file (GitHub's default shell already sets -eo pipefail; this adds -u and consistency). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ * docs(ci): complete the skill-evolution activation checklist - Add RELEASE_APP_ID / RELEASE_APP_PRIVATE_KEY to the required-secrets checklist (the Mint step hard-fails without them on a promotion) and the App-install-scope verification. - Document the protected Environment admin step and why it is the real boundary for the workflow_dispatch ref-secret exposure. - Note that workflow_dispatch runs the billing loop regardless of GITNEXUS_EVOLUTION_ENABLED. - Justify the weekly cron against the README's ~90-day guidance and note the 355-minute timeout ceiling. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ * fix(eval): redact API tokens from diagnostic fields before artifact upload results.jsonl (runner.py) and proposer-session.json (evolve.py) serialize session records whose error_detail can carry a stderr_tail that echoed the API key. Transcripts are redacted before persistence, but these two sinks were not, and both land in the 14-day evolution artifact. Run each record's serialized JSON through the existing redact_text with the run's auth token before writing. Scoped to these diagnostic sinks only: the promoted overlay and proposal.md are left untouched (the overlay is the applied artifact and must stay byte-identical for apply and the shipped-skills-sync guard). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ * test(ci): add a contract test for the skill-evolution workflow No test exercised this workflow's path, which is why both P1 blockers (missing --apply, unresolvable ~/GitNexus task repo) reached production. Parse the workflow YAML and assert the structural contract: --apply is passed, the task repo is provisioned, the promotion branch carries the run attempt, the App token is permission-scoped and the job is Environment- gated, the output summary uses a random delimiter and a single generation, the artifact pin is labelled correctly, and every multi-line shell step sets strict mode. Follows the review-agent-workflow.test.ts precedent. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ * feat(ci): run the proposer on its own (stronger) model One `model` input drove both the benchmark arms and the proposer/diagnosis session. Split them: `model` stays the benchmark arms (match the model your skill users run, so a promotion is valid for them and the tasks aren't ceiling-saturated), and a new `proposer_model` input runs the proposer — the harder meta-reasoning task that writes the candidate skill, and only one session per generation, so a stronger model is cheap here. evolve.py already supports --proposer-model; the workflow just didn't expose it. Defaults: arms = claude-sonnet-5, proposer = claude-opus-4-8 (both overridable via workflow_dispatch). The weekly cadence bounds the added spend. Contract test asserts the split stays wired. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |