Merge remote-tracking branch 'upstream/main' into feat/secret-friendly-names

docs/environment-variables.md

@@ -207,8 +207,8 @@ OAuth host chain: `KIMI_CODE_OAUTH_HOST` → `KIMI_OAUTH_HOST` → `https://auth
 | `PI_CODEX_WEBSOCKET_IDLE_TIMEOUT_MS`       | Positive integer override (default 300000)           |
 | `PI_CODEX_WEBSOCKET_RETRY_BUDGET`          | Non-negative integer override (default 5)            |
 | `PI_CODEX_WEBSOCKET_RETRY_DELAY_MS`        | Positive integer base backoff override (default 500) |
-| `PI_OPENAI_STREAM_FIRST_EVENT_TIMEOUT_MS`  | Positive integer OpenAI first-event timeout override |
-| `PI_OPENAI_STREAM_IDLE_TIMEOUT_MS`         | Positive integer OpenAI stream idle timeout override |
+| `PI_OPENAI_STREAM_FIRST_EVENT_TIMEOUT_MS`  | Positive integer OpenAI first-event timeout override; `0` disables. `omp config set providers.streamFirstEventTimeoutSeconds <seconds>` provides the persisted config equivalent |
+| `PI_OPENAI_STREAM_IDLE_TIMEOUT_MS`         | Positive integer OpenAI stream idle timeout override; `0` disables. `omp config set providers.streamIdleTimeoutSeconds <seconds>` provides the persisted config equivalent |
 
 ### Cursor provider debug
 

docs/local-models.md

@@ -127,7 +127,7 @@ Extraction favors **precision** (do not pollute long-term memory) → **Qwen3-1.
 pick** (its consolidation is good enough). If running a second model for consolidation, **gemma-3-1b**
 wins that task.
 
-**Shipped local options**: `qwen3-1.7b` (recommended), `gemma-3-1b`, `qwen2.5-1.5b`, `lfm2-1.2b`.
+**Shipped local options**: `llama3.2:3b`, `qwen3-1.7b` (recommended), `gemma-3-1b`, `qwen2.5-1.5b`, `lfm2-1.2b`.
 **Default**: `online` (the configured smol model).
 
 ### Known Mnemopi parser bugs (surfaced by these experiments)

docs/session-switching-and-recent-listing.md

@@ -179,7 +179,7 @@ Lifecycle/state transition:
 15. restore model via `getRestorableSessionModels(sessionContext.models, lastModelChangeRole)` — tries the recorded models in fallback order and uses the first one present in the model registry
 16. restore thinking level and service tier:
     - thinking uses persisted `thinking_level_change`, otherwise the configured default clamped to model capability
-    - service tier uses persisted `service_tier_change`, otherwise the configured `serviceTier` setting (`"none"` becomes unset)
+    - service tier uses persisted `service_tier_change`, otherwise the configured per-family `tier.openai`/`tier.anthropic`/`tier.google` settings (`"none"` becomes unset)
 17. reconnect agent listeners, run the registered session-switch reconciler if any (interactive mode re-enters persisted modes; errors logged, not fatal), and return `true`
 
 ## UI state rebuild after interactive switch

docs/session.md

@@ -177,11 +177,11 @@ Stores an `AgentMessage` directly.
   "id": "c1d2e3f4",
   "parentId": "b1c2d3e4",
   "timestamp": "2026-02-16T10:21:45.000Z",
-  "serviceTier": "flex"
+  "serviceTier": { "openai": "priority", "google": "flex" }
 }
 ```
 
-`serviceTier` can also be `null`.
+`serviceTier` is a per-family map keyed by `openai`/`anthropic`/`google` (each value `auto`/`default`/`flex`/`scale`/`priority`), or `null` when no tier is active. Legacy entries that stored a single string (`"flex"`, `"openai-only"`, `"claude-only"`, …) are normalized to this map on read.
 
 ### `thinking_level_change`
 

docs/settings.md

@@ -366,7 +366,11 @@ A value of `-1` means "use the provider/model default" — `omp` does not send t
 | `minP` | number | `-1` | Minimum-probability cutoff. |
 | `presencePenalty` | number | `-1` | Presence penalty. |
 | `repetitionPenalty` | number | `-1` | Repetition penalty. |
-| `serviceTier` | enum | `none` | `none`, `auto`, `default`, `flex`, `scale`, `priority`, `openai-only`, `claude-only`. |
+| `tier.openai` | enum | `none` | `none`, `auto`, `default`, `flex`, `scale`, `priority`. Sent as `service_tier` for OpenAI / OpenAI-Codex and OpenAI-family OpenRouter models. |
+| `tier.anthropic` | enum | `none` | `none`, `priority`. `priority` realizes fast mode on supported direct Claude models (ignored on Bedrock/Vertex and via OpenRouter). |
+| `tier.google` | enum | `none` | `none`, `flex`, `priority`. Gemini API sends it in the body; Vertex sends `priority` via header (`flex` is a no-op on Vertex). |
+| `tier.subagent` | enum | `inherit` | `inherit`, `none`, `auto`, `default`, `flex`, `scale`, `priority`. Applied to the spawned model's family; `inherit` tracks the main agent. |
+| `tier.advisor` | enum | `none` | `inherit`, `none`, `auto`, `default`, `flex`, `scale`, `priority`. Applied to the advisor model's family. |
 | `personality` | enum | `default` | `default`, `friendly`, `pragmatic`, `none`. |
 
 ### Retry and fallback

docs/task-agent-discovery.md

@@ -44,7 +44,7 @@ Bundled agents are embedded at build time (`src/task/agents.ts`) using text impo
 `EMBEDDED_AGENT_DEFS` defines:
 
 - `explore`, `plan`, `designer`, `reviewer`, `librarian`, `oracle` from prompt files
-- `task` and `quick_task` from shared `task.md` body plus injected frontmatter
+- `task` and `sonic` from shared `task.md` body plus injected frontmatter
 
 Loading path:
 
@@ -130,7 +130,7 @@ Runtime output schema precedence in `TaskTool.#runSpawn`:
 
 (`effectiveOutputSchema = effectiveAgent.output ?? this.session.outputSchema` — the task call itself never carries a schema; ad-hoc structured workflows go through the eval bridge's `agent(prompt, schema)`.)
 
-The model-facing prompt (`src/prompts/tools/task.md`) no longer carries the old structured-output mismatch warning; it tags read-only agents and warns against offloading reasoning to `explore`/`quick_task` instead.
+The model-facing prompt (`src/prompts/tools/task.md`) no longer carries the old structured-output mismatch warning; it tags read-only agents and warns against offloading reasoning to `explore`/`sonic` instead.
 
 ## Command discovery interaction
 

docs/tools/task.md

@@ -106,7 +106,7 @@ Artifacts and side channels:
   - off — single spawn per call; `tasks`/`context` are rejected and removed from the schema.
 - Isolation mode (`task.isolation.mode`): `none`, `auto`, `apfs`, `btrfs`, `zfs`, `reflink`, `overlayfs`, `projfs`, `block-clone`, `rcopy` (legacy `worktree`, `fuse-overlay`, `fuse-projfs` accepted for back-compat); the PAL resolves the actual backend with fallback.
 - Isolation merge strategy: patch mode (capture/apply root patches) or branch mode (commit to `omp/task/<id>`, cherry-pick into parent).
-- Agent source precedence: project custom agents, then user custom agents, then bundled agents (`explore`, `plan`, `designer`, `reviewer`, `task`, `quick_task`, `librarian`, `oracle`).
+- Agent source precedence: project custom agents, then user custom agents, then bundled agents (`explore`, `plan`, `designer`, `reviewer`, `task`, `sonic`, `librarian`, `oracle`).
 
 ## Side Effects
 - Filesystem