Commit Graph

6 Commits

Author SHA1 Message Date
kami 19bffaf77d fix(herdr): occupancy reads harness session state, not herdr pane id (B1)
CLIAdapter.Occupancy called a.Usage(s.PaneID), but ClaudeUsage/CodexUsage/
OpenCodeUsage all take a filesystem path to session state, not a herdr pane
id. Every call failed with "open <pane-id>: no such file", and
Coordinator.rotate silently `continue`d past every failure, so occupancy
always looked unmeasurable and rotation never fired.

Add herdr.Session.SessionFile and CLIAdapter.resolveSessionFile:
  - claude: ClaudeSessionFile resolves the transcript by newest-mtime under
    Claude Code's own encoded project directory
    (~/.claude/projects/<abs-worktree-with-/-as-minus>/*.jsonl). This is the
    Phase-1 fallback; the Stop hook's transcript_path (Phase 2) is the
    authoritative source once wired.
  - codex: routes through the existing CodexActiveUsage sqlite/rollout
    discovery instead of the pane id.
  - opencode: resolution needs a live session id from the SSE/status API,
    not derivable from the worktree alone — refuses loudly with a pointer
    to AUDIT.md Phase 1 rather than guessing a path, per the spec's "verify
    against a live session before wiring any trigger" (§5.2.1).

A missing/unreadable session file is now a hard error, not a silent
zero-usage Usage{}. SessionHealth gained Occupancy/OccupancyError fields,
populated every refreshSessionHealth tick, so GET /v1/tasks/{id}/health
makes the number rotation decides on observable before trusting it.

Tests: TestClaudeUsageIsLastTurnNotCumulative guards the exact trap named
in §5.2.1 (large early-turn total, small last-turn usage -> low occupancy).
TestClaudeSessionFileNewestByMtime and TestClaudeSessionFileMissingIsHardError
cover the resolver.

AUDIT.md B1. Live verification against a real Claude Code session (the
spec's own acceptance bar for this phase) still needs to happen on a host
with an actual session — not possible from this sandbox.
2026-07-27 18:49:13 +04:00
kami ce6f02f9e6 checkpoint: multi-repo Gitea ingestion, per-project repos, rotation anchor_sha fix
Pre-existing uncommitted work found at session start: rotation now emits
anchor_sha on TaskReleased (previously silently dropped by store.Append
validation), multi-repo Gitea provider support, per-project git worktree
roots, and associated test coverage. Committing as a checkpoint before
starting remediation work tracked in AUDIT.md.
2026-07-27 18:15:02 +04:00
kami 952c061c9d add harness monitoring ingestion and discovery 2026-07-26 20:44:45 +04:00
kami 4364dff9c2 support milestone and thrash rotation signals 2026-07-26 20:36:17 +04:00
kami 26011ed33c coordinate rotation at harness turn boundaries 2026-07-26 20:32:01 +04:00
kami 96e94bc2d0 Implement herdr integration layer 2026-07-26 19:07:03 +04:00