docs: changelog for v2.7.17-orchestrator + orchestration research

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-03 15:25:59 +00:00
parent 1937af8df9
commit edc348baf3
2 changed files with 179 additions and 0 deletions

View File

@@ -2,6 +2,10 @@
All notable changes per release tag. Most recent on top, ordered by tag creation date (which matches the git history). Tag names follow `vMAJOR.MINOR.PATCH-slug` — the slug describes what shipped, so the tag name alone is enough to recall the batch.
## v2.7.17-orchestrator — 2026-06-03
Brings the deterministic multi-agent "conductor" into the app as the **Orchestrator**: launch any read-only Han flow (research, code-review, investigate, architectural-analysis, security-review, …) from BooChat or BooCoder and watch each specialist agent stream live in a Paseo-style run pane, ending with an evidence-disciplined, adversarially-validated report — all on free local Qwen, persisted and resumable. Built and audited end-to-end via `paseo-epic` in an isolated worktree, on top of the prior `/opt/boocode/conductor` standalone CLI: the conductor's 22 flow definitions, Spine factory, and Han evidence/YAGNI contracts were re-homed into `apps/coder/src/conductor`, and a new DB-backed flow-runner (`flow_runs`/`flow_steps`) dispatches each step as a real BooCoder task through the existing dispatcher — reusing its streaming→WS-frame pipeline and worktree-as-read-snapshot, with an `onTaskTerminal` hook that advances the wave and a startup resume that re-dispatches in-flight steps after a coder restart. Read-only is enforced hard: every step is dispatched `qwen --approval-mode plan`, an adversarial-security review caught and closed a bypass where a qwen-unavailable task silently fell through to write-capable native inference (now fails closed), and the ACP path's mode-set was made fail-closed too. The UI adds a fourth `orchestrator` pane kind (collapsed agent roster, expand-one live stream, report on top), a Workflow button + slash flows on the shared `ChatInput` for full BooChat/BooCoder parity, a "New Orchestrator" entry in the + and split menus, a category-grouped launcher dialog, runs history, and export (copy / save-to-file / send-to-chat) — fed by two new `flow_run_*` WS frames on a coder user channel. Qwen-only by design (Claude Code remains the Claude path); the existing model-competition Arena stays a separate feature. Spec/plan in `openspec/changes/orchestrator`; coder 373 tests green (42 new scheduler/resume/read-only decision tests), contracts/coder/server builds + web tsc clean. Built on `v2.7.16-container-git-safedir`; pairs conceptually with the earlier `v2.7.12-audit-cleanup` multi-agent orchestration.
## v2.7.16-container-git-safedir — 2026-06-03
Hotfix that makes the `v2.7.15-git-diff-panel` work in production. The `boocode` container runs as root but bind-mounts host project repos owned by uid 1000, so git rejected them with "detected dubious ownership" and the diff route reported every project as not-a-repo — which hid the Git tab entirely (and had been silently nulling the existing branch indicator too). Adds `git config --system --add safe.directory '*'` to the Dockerfile runtime stage so the container's git trusts the mounted repos; applied live to the running container and baked into the image for future rebuilds. Surfaced by a live smoke immediately after the v2.7.14/v2.7.15 deploy.