The classifier read the forge's PR `.diff`, whose context is fixed at 3
lines. A block moved into a glue module lost its enclosing gate (a
`config = lib.mkIf …` 13 to 191 lines up in the misfired moves #5199,
#5200, #5201), so the glue restating that gate read as a new condition.
The controller now builds the diff itself: it lists the PR's changed files,
reads each at the merge base and at the head through the git tree and blob
API with the token it already holds, and diffs them with 200 lines of
context. It sends the forge's `.diff` instead when the PR changes more than
100 files, the forge names no merge base, or the wide diff is over 256 KiB,
and the posted review then says so with the reason.
Fixes#5227
The try-out page gets an "open a PR" button. It posts the page's
classifications to the new POST /api/review-classifier/open-pr, which
merges them by name into the repo's rules file on the default branch
and has the review-classifier forge account commit the result on a new
branch, review-classifier/<user>-<8 hex>, through the contents API. The
commit's author is the forge account named like the session's
Remote-User, read with the controller's admin token. The answer links
to the forge's compare page, where the user opens the PR as themselves.
The push uses the account's existing token from the store
(swarm/services/review-classifier/forge/token, scope write:repository),
so the account needs write access to the repo; a refused push answers
403 naming that. In a YAML rules file, the entries the merge leaves
alone keep their text, as long as the result reads back as the merged
list; otherwise the file is written out whole.
DefaultBranchFiles now carries each file's blob sha, which the forge
needs to replace a file, and the repo's web URL for the link.
Fixes#5259
Refs #5096
The swarm settings gain `runtime` (`api-key`, the default, or `acp`) and
an `acp` provider record: an https base URL, the provider's model, and
its prices per million tokens. A PUT now changes only the fields its
body names, so the settings form that sends model, effort and limit
leaves the runtime alone; `null` clears `effort` or `acp`. The body stays
strict, and the stored document keeps #5192's lenient read.
The controller sends the runtime in each run request. On `acp` the
classifier runs one prompt on a new `opencode acp` session per
classification through hive-runtime's AcpRuntime, in a scratch
directory, with a config rendered from the settings. opencode runs
`read` and other tools without asking, so OPENCODE_PERMISSION
{"*":"deny"} takes every tool away from the model, and a deny-all policy
refuses any request on top. The title call, which resends the prompt,
is turned off. The deadline cancels the turn, and a turn that does not
end within 15s of that is dropped, which also covers an agent stuck
before its prompt. The answer is the final assistant text, as ACP has
no result event.
The provider key is read per run from
swarm/services/review-classifier/acp-provider, which the bao UI's
admins login may create and update, and reaches opencode through
AcpRuntime::with_provider_key and the trampoline's allowlist.
Each ACP classification's cost is computed from the configured prices
and the reported tokens, and added to
hyperhive.review_classifier.cost.usage labelled repo, pr, model and
currency.
Part of #5096
The classifier ran every classification on a hard-coded `haiku` with no
`--effort`, and the controller ran at most two requested reviews at once,
also hard-coded, so changing any of them took a code change and a
redeploy.
swarm-controller now keeps one settings document,
`{model, effort, max_concurrent_reviews}`, in its own
`review-classifier-settings` KV bucket under `all`, the way it keeps the
schedule definitions. No document means today's values: haiku, no
`--effort`, two reviews. `GET /api/review-classifier/settings` reads it;
`PUT` replaces it whole, needs the gateway's `Remote-User` like the
try-out POST, and refuses a bad model (the inference route's check), an
effort outside the five levels or a limit outside 1..=8 with
problem+json 400.
Every run request (try-out and requested review) now carries the model
and effort, and the classifier passes them to claude instead of its
constant, which is gone. A try-out reads the settings when it is posted;
a review reads them for the limit before it waits for a place and again
for the model and effort once it has one. The review semaphore is
replaced by a running count under a resizable limit, so a PUT, or the
next review's read, changes how many run without a restart, and a lower
limit lets the runs already going finish. MAX_WAITING_REVIEWS is
unchanged.
Closes#5151, part of #5096.
Every run is recorded when it ends: a try-out when its reply settles it,
a requested review once its review is posted or the post fails, and a
request turned away by a full queue once its comment is posted. A
duplicate request that starts nothing is not recorded. The newest 100
are one JSON array under `recent` in a new controller-owned KV bucket,
`review-classifier-runs`, written with compare-and-set as
`schedule-definitions` is (five attempts). A failed write is logged; the
review is already posted by then.
Each recorded run is also one info event, "review classifier run
finished", with the record's fields as tracing fields. The controller
logs natively to the journal, so they reach VictoriaLogs as F_<NAME>.
GET /api/review-classifier/runs returns the list, newest first, gated
by the gateway like the try-out GET. post_classifier_review now returns
the posted review's html_url, which the record keeps as review_url.
Closes#5153, part of #5096.
Eight classifications in .hyperhive/review-classifier.yml: no AI
advertising in commit messages, no committed secrets, no clippy
allow attributes, no debug leftovers, no dead code, tests with
behaviour changes, docs with operator-facing changes, one purpose per PR.
A swarm-controller test parses the real file so it can't rot, and the
rust source fileset in nix/rust.nix includes it so the test finds it
in the build sandbox.
Two read-only routes feed them: GET /api/pulls/repos lists the repos with an
open pull request, and GET /api/pulls?repo=owner/name lists a repo's open
pull requests, highest number first. The page offers the lists through the
browser's own suggestion list and keeps both fields free text, since a run
also works on a merged or closed PR.
Requesting the forge account `review-classifier` as a reviewer now runs the
repo's rules against the PR and posts the result as that account's review,
on the head commit the run read. A push starts no run; only a fresh review
request does.
- An instance-wide `pull_request_review_request` system hook delivers to
`/webhook/forge/review-request`. A request for any other reviewer, or a
removed request, does nothing.
- The controller reads the PR, loads the rules with the same reader as
`GET /api/review-classifier/rules`, sends one request on the try-out
subject, and posts APPROVED or REQUEST_CHANGES with the table as the body.
- With no clean verdict (PR or rules don't load, the run fails, or any
classification has no answer) it posts a COMMENT saying why, never an
approval. The event is one function, `no_clean_verdict_event`.
- Table cells are flattened, markup-escaped, and every `@` gets a
zero-width space, so a model's reason can't break the table or mention
anyone.
- At most two requested reviews run at once; the rest wait in memory.
- The account is minted the way hive accounts are: a five-minute pass
queues a `MintClassifierForgeToken` node when the token at
`swarm/services/review-classifier/forge/token` is missing or stale. The
token is `write:repository`. The controller's bao policy gains that leaf
(create/read/update), pinned in module-eval bao-grants. The classifier
never sees the token.
The account gets no repo access automatically; a repo admin adds it by
hand. A re-request retires the account's earlier review: Forgejo clears
`official` on a reviewer's earlier reviews when it is requested again
(models/issues/review.go AddReviewRequest, v16.0.5), and approvals and
rejection blocks count official reviews only.
Refs #5137
The rules file is now read with the existing forgejo-api client: the
commit's root tree, then the `.hyperhive` tree, then the
`review-classifier.{yml,json}` blob, base64-decoded. Every request takes
single-segment path parameters, so nothing depends on how a nested path
is escaped, and the controller keeps one HTTP transport to the forge.
The second reqwest client, `Client::with_token` and `raw_file_url` are
gone.
A tree the forge truncated is an error, not a missing file. A 404 on a
tree or blob doesn't come back as a forge 404, so only the repo lookup's
404 reads as "no such repo".
The `is_repo_not_found` doc comment is back on its function.
Part of #5096.
forgejo-api escapes the whole file path of a raw-file request, so the
rules file went out as `raw/.hyperhive%2Freview-classifier.yml` and
reached the forge only if every proxy and router in between decoded the
`%2F`. The controller now sends that one request itself: `raw_file_url`
escapes each path segment on its own and joins them with `/`, and
`forge::Client` holds a second HTTP client with the same token for it.
A 404 from the default-branch lookup now means "no commit on the
default branch", like an empty repo, instead of falling through to the
route's "no repo" answer. Only the repo lookup's 404 still means the
repo doesn't exist.
Tests cover the URL shape, the reads against a loopback stub forge
that serves only the literal path, the branch 404, 503 with no forge
access, 503 at the forge deadline on a paused clock, and a bad
polarity value.
Part of #5096.
`GET /api/review-classifier/rules?repo=owner/name` reads
`.hyperhive/review-classifier.yml` or `.json` from the repo's default
branch with the controller's forge token, on every request, and answers
the classifications in the try-out POST's shape, plus the file, the
branch and the commit it was read at. The swarm UI's try-out page loads
them into its editor (#5134).
The file is one `classifications` list of the try-out's `Classification`.
A missing file, both files, a parse error, any unknown key, an empty list
or more than ten entries is a problem+json error, never a pass. The
checks the POST makes on its classifications move into one function both
paths call.
The doc names the file and its schema, replacing the placeholders, and
documents the route.
Part of #5096.
The routes' annotations now list every 400 reason (including the JSON
shape rejections), the 503 causes, the 31-minute running window, the
404 after a controller restart, and that an errored row reads
not-applicable with certainty 0 and an empty reason, so the page keys
off error, and that overall can be approve beside errored rows.
POST /api/review-classifier/try-out validates the run (owner/name repo,
a PR number, one to ten classifications with distinct names, thresholds
up to 100), reads the PR's head commit, commits and diff with the
controller's forge token, sends one request to the review classifier on
the queue and answers 202 with an id. GET .../try-out/{id} reports the
run as running, done (rows and overall verdict) or failed (the error).
Results live in memory for an hour after the reply; there is no run
store. POST then GET because a run can outlast the gateway's 60-second
proxy read timeout. Both routes are utoipa-annotated, so they show on
/api/docs/.
