5 Commits

Include renames

Author	SHA1	Message	Date
weichenandCursor	8e987bf535	Persist step approvals and guard squad HTTP entry points ... Why: A step confirmation cancelled the whole run, approvals and repair budget vanished on restart, and the HTTP server accepted anonymous and oversized requests. Evidence: GOWORK=off go vet ./... && GOWORK=off go test -count=1 ./... && GOWORK=off go test -race ./squad/... passed. scripts/submodule-consistency.sh ok. Impact: Approve and skip apply to one step; runstate.json and unix flock survive restart; wakeup leaves permission holds pending; serve defaults to loopback and requires a token off-loopback. Refs: Q1 Q2 Q3 Q4 Q5 Q8 Q9 Q14 Q15 Q16 Co-authored-by: Cursor <cursoragent@cursor.com>	2026-10-03 01:48:10 +00:00
weichenandCursor	5cbac00b99	Add a SQLite orchestration platform beside the goal engine ... Why: Squad runs were one file workspace and one JSON file the leader had to emit, so agents, issues, and retries had no durable queue. Evidence: GOWORK=off go test -count=1 -timeout 180s ./... Impact: /v1/runs stays. New routes mount only when the orchestration database opens. SSE for a run id now skips other runs. External CLIs are not a sandbox. Refs: feature/orchestration-platform S1-S7 Co-authored-by: Cursor <cursoragent@cursor.com>	2026-10-01 10:30:01 +00:00
weichen	d4d351913f	Plumb RoleSpec execution config into agent-native requests and fix leader parity ... Why: RoleSpec.Tools/Skills were dead fields, BashPermission only gated an HITL prompt with nothing to enforce, leader turns dropped process events and tool profile, and the HTTP API could not start leader mode. Evidence: go vet ./... clean; go test ./... 6 packages ok. New cases: step requests carry ToolAllowlist/Skills/SessionScope/ExecutionID and a step-wide shared deadline; buildAgentNativeOptions bash gating (deny/unset get no exec tools even when configured, ask/allow do, missing model fails closed); Derive inheriting tool_profile/tools/ skills/bash_permission with request overrides; role-level HitlPolicy making a bash=ask step fail under auto instead of holding; leader requests fully assembled with detail events bridged to the sink; HTTP createRun accepting mode/leader_role/max_leader_turns (engine-driven repro of the plan-validation precondition included). Impact: RegisterAgentNative keeps its signature and delegates to a new RegisterAgentNativeFull(AgentNativeConfig); nested agent-native gitlink pinned to f9ab2ef (full-agent batch); llm planner derive schema gains tool_profile/tools/skills/bash_permission. Refs: Dev task feature/full-agent-r1 batch B9; agent-native PR #3.	2026-10-01 06:02:17 +00:00
weichenandCursor	7ddcb2180d	Move Agent-Native under deps and return stable error envelopes. ... HTTP failures now carry catalog codes and a trace id, and the parent replace directives are the only copies used at build time. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-09-29 14:29:14 +00:00
weichenandCursor	bfec3c8930	Import agent-squad as a standalone repository. ... Pin Agent-Native as a submodule so the module builds without the multi-repo sibling path. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-09-29 12:38:35 +00:00