nisse-core records each model call of every agent into a file beside its
state store (<state>.calls.db), for the status page (L7, X6):
- the request body exactly as sent (never headers), the raw response with
its reasoning, the model asked and the one that answered, time, tokens
and llama-server's own prompt reuse (timings.cache_n);
- its work item, role, run and purpose: Driver.run and nisse-dev's
delegation loop open runs, nested; compaction, expert consults, the
classifier and the go-ahead reader label their calls;
- provenance, worked out in BudgetedClient by comparing the events at
each stage: each event sent with its log id and content as sent, which
a compaction replaced, which fitting shortened (by how much) and
dropped.
Content is stored once by hash, compressed. It is diagnostic only: the
agent never reads it, a failed write is logged once and recording stops
while the call goes on, and the file is deleted when the agent starts,
so its layout never migrates; CallReader refuses a layout it doesn't
know. While recording, the system prompt ends with one sentence saying
so. `call_record: false` in either agent's YAML turns it off.
The benchmark records each run beside that run's own state store, and
`--keep-runs DIR` keeps both for the page.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
The reviewer is read-only (R3), so Gitea refuses it resolving a thread.
Now each reply says whether it settles its thread, and a settled reply
carries <!-- nisse-review: settled -->. nisse-dev, as the author, resolves
every comment on that thread's line when it watches the PR, and doesn't
take the settled reply as a point to answer. scripts/resolve_settled.py
does the same for PRs made by hand.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
On #166 the reviewer called post_review with two points unanswered, was
refused, answered them, then only skipped already-answered points until the
40-turn cap: the review went out as partial, its summary lost. A refused
ending call is now held, and the driver ends the run with it as soon as the
last point is settled (a new due hook in nisse-core's driver; nisse-dev
doesn't use it). A held call that is wrong for another reason by then
(sign_off over drafted comments) is left to the model. With nothing open,
reply and skip say which tool ends the run.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
Before each driver call, over compact_at (0.6) of the prompt budget, the
same model is asked for notes over the very request it was about to get,
plus one message, so the server's cache covers all but the notes. The notes,
with code's list of the calls they replace, become a compaction event that
renders in place of its range, keeping word for word what started the work
and the last few turns. Rare, large steps keep the prompt's start unchanged
between them. A later compaction folds in the earlier; one from an earlier
run's view is hidden.
Failed notes are logged and fitting takes over. Fitting now applies
compactions before it measures, records what it cuts (Trim) and logs each
cut as context.trimmed. Wired into both agents' drivers and the benchmark;
nisse-dev's helper loop is a follow-up.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
Archives were downloaded and unpacked afresh for every run, which doesn't
scale to very large repositories. Each repository is now cloned once, with
its whole history, under scratch/repos/<owner>/<name>/ (head/ the clone,
base/ a worktree when read). A run fetches every branch and the PR's
refs/pull/N/head, checks out the head exactly, and fails if that head is
gone. Only the latest repository is kept for now.
Git runs walled off: none of the host's git configuration, links checked
out as plain files, no hooks, submodules or LFS, only the Gitea URL's
protocol, and the token as an http.extraHeader for that URL in git's
environment only. A stop ends a git command; a cut-short first clone is
removed. The reader never shows .git. GiteaClient.archive is gone.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
SIGTERM used to stop only new rounds: a review in progress ran on until
systemd killed it 90s later. Now the scheduler's stop sets the driver's
cancel flag, so the run ends at its next turn, and a model call in flight
is broken off (Interruptible, raising Stopped from the signal handler, only
ever inside a model call). The item goes back to ready, with nothing
drafted posted and no failure counted; replies already posted carry their
markers and are not repeated.
intake.repo_failed is logged when a repository starts failing or the reason
changes, and intake.repo_ok when it lists again, not every round.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
From nisse-review's review of #156: only a failed listing fell back to
the PR's whole diff; one commit's diff failing (a force-push dropped it)
failed the run. Tests also pin down its other three points, which the
code already handled: a command is taken in once, a second review at the
same head has its own marker, and `review` beside a comment is one fresh
review.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
Back on a PR it reviewed: a new head gets a later review of the commits
since (each one's diff, through the API) and of its earlier points; what
was said since gets replies, answered where it was said or skipped with a
reason. It signs off once and stays quiet while still happy. Past
tuning.review.max_rounds it sums up for the operator and goes quiet,
until a push or someone other than the PR's author joins in. An
operator's `stop` quiets it; `review` asks for a fresh review.
Reviews carry numbered markers and replies their point's key, so
recovery posts nothing twice.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
From its failed review of #156: read_file stopped at 20,000 characters
with no way on, so the reviewer hunted each file's end a definition at a
time and ran out of turns; its retry carried every read before it, and a
model call timed out. Both drafts were lost.
- read_file takes a start line and says where the next part starts.
- Each run's view starts at its brief (Transcript.since); the log keeps
the rest.
- A run out of turns with points drafted posts them as a partial review.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
From nisse-review's own review of #155: a failed run, a posted one and
crash recovery rebuilt the item without seen_at, so a retry skipped the
CI wait. seen_at now carries through, renewed when the head moved during
the review. Also: a test for checks Gitea can't report, and the example
config lists ci_wait_s and ci_grace_s.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
The live review test sets ci_grace_s: 0, which the shared tuning parser
refused (every number had to be positive). A field now opts in to zero
with metadata {"zero": True}; ci_wait_s and ci_grace_s do.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
A review judges the CI result (R1), so a new head's review now waits while
its checks are pending, and starts once they finish, passed or failed. It
also keeps reviews off a GPU that CI is using: #154's first review ran
beside CI's end-to-end job and took about 30 minutes.
- Pending: waits up to tuning.review.ci_wait_s (1 h), then reviews anyway.
- No checks: waits tuning.review.ci_grace_s (2 min) for them to appear,
then reviews.
- A PR waiting on CI holds up no other: the oldest settled one goes first.
- The head's first sighting is kept on the item (seen_at).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
Found at bring-up: an empty private repository's /pulls answered 404, and
intake stopped there, so the whole round failed and nothing was reviewed.
A repository whose PRs can't be listed is now logged (intake.repo_failed)
and skipped for the round; its items stay as they are.
Also, from nisse-review's review of this PR: a two-page test pins the
search listing the patterns rest on.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
At bring-up, `dev/*` failed: listing an organization's repositories
(/orgs/dev/repos) needs the read:organization token scope, which the
reviewer's token doesn't have and shouldn't need. Patterns are now matched
against /repos/search, which needs only the repository scope and already
lists every repository the account can read. A pattern that matches
nothing is logged (access.no_match). owner_repositories goes.
A Gitea error at startup is now reported like a config error, not a
traceback.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
At bring-up, nisse-review read no repositories: Gitea's /user/repos leaves
out a public repository's Read collaborators, so dev/nisse never showed up.
`repositories` now holds patterns (dev/nisse, dev/*, */*) matched against
every repository the account can read, public ones included (an
organization's or user's list, or the instance's search); unset, it is
/user/repos as before. A configured repository it can't read is left out
with an oplog line.
The read-only wall (R3) is checked every round, not only at startup: an
account granted push or admin while running stops (exit 3) rather than
review on.
nisse-core's Gitea client gains GiteaNotFound for 404s, owner_repositories
and visible_repositories.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
A new package over nisse-core: it reviews every ready PR in the
repositories its account can read, and posts one COMMENT review.
- scheduler: each round, open PRs per readable repository (or the
configured repositories); an item per PR, ready unless draft or WIP;
closed with the PR. One review at a time, oldest first.
- reader: the repository at head and base from Gitea archives, unpacked
and read in Python (read_file, list_files, search_code), and its issues;
bound to the item's repository; no git, no shell.
- review: starts from the PR, commits, diff, comments, closed issues, CI;
comment drafts a point on any existing line; post_review posts one
COMMENT review at the head, inline where Gitea takes it, else as links in
the summary. ask_expert; vault and memory (memory/nisse-review).
- L8: posting is an intent; recovery asks Gitea for the marked review and
never posts twice; with Gitea down, the item waits.
- Failures retried, then said on the PR until the next push.
- Startup refuses an account that can push to or administer any repo.
- nisse-core gitea: readable_repositories, open_pull_requests, diff,
commits, archive, issue, search_issues, reviews, post_review; PR fields.
- Bring-up: scripts/review-bringup.sh; nisse-review.example.yaml.
- Tests: unit over a fake Gitea and scripted model; a live test
(NISSE_REVIEW_GITEA_TOKEN) reviews a PR in a fresh test repository.
- Docs: Development Plan M7.3, Tuning Guide (tuning.review.*).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
dongarandClaude Opus 5.5