Commit Graph
2 Commits
Author SHA1 Message Date
dongarandClaude Opus 5.5 74bc68db1c Runs that go in circles end (M7.8)
CI / checks (push) Skipped
CI / checks (pull_request) Failing after 1m50s
CI / e2e (pull_request) Skipped
Driver.run checks each turn with nisse_core.loop.circles and ends the run
as "circling" when the same calls get much the same back, one harness
correction is given again and again, or the model apologises, for
circle_repeats turns in a row (default 3). Near-identical calls (git add
a.py, b.py) and scattered apologies stay flags on the status page. A
fact in the transcript says why the run ended.

nisse-dev calls in a helper as for a stuck run, then asks the operator;
nisse-review counts a failed run and posts none of its drafts. Tuning:
tuning.driver / tuning.review circle_repeats (0 off) and circle_similar.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
2026-10-26 16:30:07 +00:00
dongarandClaude Opus 5.5 a8e2023183 The status page's walkthrough (M6.6b)
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 2m41s
CI / e2e (pull_request) Successful in 4m25s
A new package, nisse-ui: a read-only page for studying how the agents
work. For each work item it shows the steps (what people and the
orchestrator said, and each run), each run's turns, and each turn's
request read against the log it was made from:
- each message beside the events it came from, tagged unchanged,
  labelled, narrated, shortened (by how much) or a compaction, with what
  fitting dropped;
- what is new since the turn before, and where the request first
  differs (where prompt reuse had to stop), next to the server's count;
- the reply with its reasoning, and the raw JSON.

Runs going in circles are flagged by nisse_core.loop.circles (repeated
near-identical replies, one correction given again and again, repeated
apologies), a pure function M7.8 can reuse in Driver.run.

In nisse-core:
- render.py: message_indexes(), from the same code render() uses, so
  the page's matching can't drift from what was sent.
- calls.py: the record notes when recording began; the reader gains
  calls_for(item) and call(id).
- state/readonly.py: opens an agent's SQLite file without creating its
  -wal/-shm files (mode=ro alone does, once the writer has closed).

The page reads only through read-only connections, escapes everything,
and sends a Content Security Policy that allows no script. It listens on
127.0.0.1; until M6.6d puts it behind Authelia, reach it over an SSH
tunnel. Jinja2 is its one new dependency, for autoescaping.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
2026-10-25 03:36:50 +00:00