@bojackduy/opencode-loopd 1.11.2 → 1.12.2

package/CHANGELOG.md

@@ -6,7 +6,8 @@
 
 ### Added
 
-- **Agent model discovery and same-goal recovery** — `loopd_list_models` exposes safe provider/model metadata, host capabilities, and owner-scoped goal identities; `switch_goal_model` validates ownership/availability, defers busy workers, and preserves the existing worker session and budgets. Optional `fallbackModels` prepares ordered, one-shot alternatives only for observed provider quota/rate-limit errors; interactive goals never auto-wake. Explicit `resume:true` applies only to provider-limit-blocked goals. Remaining quota/reset information is **unknown/unsupported** in the inspected host APIs, never inferred from connected accounts or API keys. Covered by automated host/service/tool tests; no live provider-exhaustion or TUI proof claimed.
+- **Unified same-goal identity switching** — `switch_goal_identity` replaces the separate model/agent owner tools and control operations. Optional `model` and `agent` fields support one-field changes or a combined transaction; at least one is required. Combined assignments persist atomically, busy pairs defer together, and successful host changes roll back on partial failure. Dashboard `:model`/`:agent` dispatch the unified operation. The existing goal, worker session, transcript, progress, checks and budgets are preserved; there is no implicit interactive wake. Explicit resume requires a blocked goal (model-only still requires a provider-limit blocker).
+- **Agent model discovery and same-goal recovery** — `loopd_list_models` exposes safe provider/model metadata, host capabilities, and owner-scoped goal identities; `switch_goal_identity` validates ownership/availability, defers busy workers, and preserves the existing worker session and budgets. Optional `fallbackModels` prepares ordered, one-shot alternatives only for observed provider quota/rate-limit errors; interactive goals never auto-wake. Remaining quota/reset information is **unknown/unsupported** in the inspected host APIs, never inferred from connected accounts or API keys. Covered by automated host/service/tool tests; no live provider-exhaustion or TUI proof claimed.
 - **M1 pty parity** — `env` (values to host, names-only persistence), `timeout_seconds` (in-memory deadline → terminate path, `endReason=timeout`, always notifies), `shell:true` (`/bin/sh -c`), `pattern`+`ignore_case` log read (ANSI-stripped match, ReDoS guard), `terminate remove:true`, `endReason` (`exit|terminate|timeout|until|missing`) on every terminal transition.
 - **M2 sentinel watcher engine** — `watch_filter`/`watch_until`/`watch_ignore_case`/`watch_until_action (stop|keep)` at start, `loopd_command_watch` on running commands; 2s coalescing (20 lines/4KB), 100-lines/sec flood-suspend (process keeps running), 30-push budget; `until:stop` terminates with `endReason=until` and exactly one owner message; `loopd_command_await until:` wakes a goal once on match without stopping.
 - **M3 surface** — watch badges + endReason in Commands tab, watch counters in detail panel, SKILL.md watching guide with pty + sentinel migration tables, de-polled `loopd_command_get` docs.

package/README.md

@@ -22,7 +22,7 @@
 - **Scheduled intervals** — `scheduleEveryMs`/`scheduleMaxRuns` auto-requeues the same goal every N ms (e.g., `10s` monitor, `1h` report) without manual `/goal` spam — `5s` poll, `skip-if-running`, `workspaceWrite` serialization, inbox `Scheduled tick N/M`.
 - **Modal TUI dashboard** — `<leader>o` or `/loop` opens a focused dialog (no leak to chat prompt). Vim-style navigation, live running indicator, per-status borders.
 - **Command sessions, not blocked shells** — run installs, builds, dev servers, and REPLs as background OS processes with a fullscreen terminal, owner exit notifications, line-level `filter`/`until` watches, and timeouts — instead of freezing the agent turn in `bash`.
-- **Switch models mid-run** — `loopd_list_models` discovers providers/models and quota status; `switch_goal_model` moves a goal to another model on the *same* worker/session when a provider hits quota. Optional ordered `fallbackModels` switch automatically on 429s. Dashboard: `:model`/`:models`.
+- **Switch identity mid-run** — `loopd_list_models` discovers models and agents; `switch_goal_identity` changes a goal's model, agent, or both on the *same* worker/session. Combined changes persist atomically and roll back on partial failure. Optional ordered `fallbackModels` switch automatically on 429s. Dashboard: `:model`/`:agent` and `:models`/`:agents`.
 - **Manual mode for interactive work** — `interactive: true` (or `:interactive`) stops the engine from starting turns on its own; every turn comes from your `:send`/nudge. For tasks where the worker waits for input.
 
 Keywords: `opencode` `opencode-plugin` `background-agent` `autonomous` `subagent` `loop` `goal` `tui` `codex` `claude-code` `worker`
@@ -180,7 +180,7 @@ read_goal_transcript()           — last N worker messages (what it's doing)
 send_goal_input(goalID, msg)     — steer: "skip appendix PDFs"
 pause_goal(goalID) / resume / clear
 loopd_list_models()              — providers/models, quota status (unknown where hosts can't report it)
-switch_goal_model(goalID, model) — same goal, new model (same worker/session)
+switch_goal_identity({goal_id, model?, agent?}) — same goal, new identity (same worker/session; at least one field required)
 loopd_command_start(...)         — installs/builds/servers as background processes (never block the turn in bash)
 ```
 
@@ -309,7 +309,7 @@ When a provider hits quota or rate limits mid-run:
 
 ```
 loopd_list_models()                                   — what's connected, quota status (or honestly unknown)
-switch_goal_model(goalID, "other-provider/good-model") — same goal, same worker/session, transcript kept
+switch_goal_identity({goal_id, model:"other-provider/good-model"}) — same goal, same worker/session, transcript kept
 ```
 
 - Busy workers defer the switch to the next turn (`→ pending … applies next turn`); idle ones switch immediately. On v1 the new model takes effect from the next prompt (no mid-stream session switch API); v2 switches the live session where supported, else reports `unsupported` without touching anything.