Commit Graph
6 Commits
Author SHA1 Message Date
jason.woltje 56cc7b59dd fix(seat,unslop-hook): review round: the linked fixed path test puts the stand-in's real path outside HOME so only its own guard refuses the source; the Stop hook's notes name the late-fallback turn a later Stop can check again and say a second Stop after a blocking hook waits and logs one late entry; the plugins README names the Perl, Ruby, less and resolver hooks and points to REFUSED_NAMES (#1873, lane triage-p3s) 2026-11-18 11:05:35 -06:00
jason.woltje 80ce06851d fix(unslop-hook): the Stop hook records the last prompt it checked per session in <log>.stop.json and waits while the transcript still ends with that turn, so a Stop with no last_assistant_message, or one whose reply has the last turn's text, no longer checks the last turn as this one; the 2 s wait stays (#1873, lane triage-p3s) 2026-11-18 10:52:53 -06:00
jason.woltje b39d5e2ff3 fix(unslop-hook): review round, the Stop fallback logs late: true and the comment names the two stale cases left: an input with no last_assistant_message, and a reply whose text equals the last turn's last reply; cli.mjs notes that the packs-http read is the tested gate for system-only templates (#1873, lane triage-followups) 2026-11-16 16:05:43 -06:00
jason.woltje 0354452971 fix(unslop-hook): the Claude Stop hook waits for the turn to reach the transcript
Claude Code 2.1.319, 2.1.322 and 2.1.325 can run the Stop hook before they
write the turn to the transcript. The hook then read the last turn's reply,
logged it a second time, and missed this turn's reply. That made
claude-session.test.mjs row 66 red in most runs.

The hook now reads the transcript again, for up to 2 s, until its last reply
matches last_assistant_message. If it never does, it checks
last_assistant_message alone with an empty entryId, never the last turn
again. (#1873, lane triage-followups)
2026-11-16 15:45:09 -06:00
jason.woltje 2c38325eca row 66: managed sessions run the unslop check on both harnesses, the operator note on the RESULT, a correction notice on the next turn, and unslop.jsonl counts (#1559)
Lands Sage's sage/row66-r5 at 7ffb640ac, round 4 (r4d 82c830779) rebased onto a36523713 after row 197,
approved by Dewey (comment 30085) and Filbert (30086) on manifest 6cfd812da4ca (23 paths, rev 2905). The
rebase had no conflict. The range-diff is = except one pi-session.test.mjs hunk header. Patch-id without
agents/ is d67275ac4251 on 7b9737953, a36523713 and this commit's parent. Gate (mos-1186): unslop,
harness, cli and every scripts/test-*.sh green on r4d, harness 149/0 again on r5. Landing sessions on a
scratch root from the candidate tree: Claude Code r4ab24630d323 showed the note, the injected notice and
counts checked 2, flagged 1, notices 1. Pi r1dd94171bede is launch only until #383 (Vikunja #454).
2026-10-21 13:51:28 -05:00
jason.woltje 7db4c5c2ed feat(agent): interactive TUI launcher + identity + TOOLS.md (#35)
- scripts/agent.sh <name>: launches interactive pi TUI in the container
  with contracts + optional mission + agent identity + named session +
  optional workspace/tools; the Mosaic alternative to vanilla pi
- pi adapter: MOSAIC_INTERACTIVE branch (clean TUI, no -p, no initial
  prompt); headless exec rebuilt via positional args (no word-splitting
  on the request); MOSAIC_AGENT_NAME optional in headless
- loader: AGENT IDENTITY section when the launcher names the agent
- compose: fixed command removed (request defaults live in run-agent.sh);
  MOSAIC_INTERACTIVE/MOSAIC_AGENT_NAME passthrough
- docs/TOOLS.md: full on-demand tool reference; AGENTS.md routes to it
- RELEASE -> 0.0.8 (container change); build verified

Closes #35
2026-09-03 11:24:56 -05:00