fix(metis): switch primary model to claude-sonnet-4-6 + correct AGENTS.md inaccuracies

Source code change:
- src/shared/model-requirements.ts: prepend claude-sonnet-4-6 to metis fallback
  chain so Sonnet becomes the default. Opus 4.7 max remains as the immediate
  fallback for callers who want extra reasoning.
- src/shared/model-requirements.test.ts: update assertion to expect Sonnet
  primary + Opus secondary.

AGENTS.md accuracy fixes (verified against source):
- Agent modes: Sisyphus/Hephaestus are 'primary' (not 'all'); Sisyphus-Junior
  is 'subagent' (not 'all'). Confirmed via 'const MODE: AgentMode = ...' in
  each agent file. Also clarified Prometheus has no agentSources factory and
  is built via buildPrometheusAgentConfig.
- Sisyphus fallback chain: corrected order to kimi-k2.6 → k2p5 → kimi-k2.5
  → gpt-5.5 medium → glm-5 → big-pickle (was missing kimi-k2.5).
- Librarian/Explore: added missing minimax-m2.7 step between -highspeed and
  claude-haiku-4-5.
- Metis chain: removed fictitious gemini-3.1-pro entry.
- Sisyphus-Junior chain: spelled out the actual fallback (was 'user-configurable').
- Temperatures: Sisyphus/Hephaestus do not set explicit temperature (model
  default); Sisyphus-Junior is 0.1 via SISYPHUS_JUNIOR_DEFAULTS.
- Quick category default: gpt-5.4-mini (not gpt-5.4-mini-fast).

Team-mode corrections:
- Eligibility registry has 3 verdicts: eligible (sisyphus, atlas, sisyphus-junior),
  conditional (hephaestus — needs D-36 teammate permission), hard-reject
  (oracle, librarian, explore, multimodal-looker, metis, momus, prometheus).
- Schema has 11 fields, not 4: added max_messages_per_run, max_wall_clock_minutes,
  max_member_turns, base_dir, message_payload_max_bytes, recipient_unread_max_bytes,
  mailbox_poll_interval_ms.
- Hooks: 'team-session-events' is 4 sub-handlers in src/plugin/event.ts
  (team-idle-wake-hint, team-lead-orphan-handler, team-member-error-handler,
  team-member-status-handler), not a single Continuation-tier hook.
- Tier counts now show base + team-mode: ToolGuard 14/15, Transform 5/7.
- Total: 52 base hooks, 59 with team-mode.

Doc cascade for the Metis change:
- docs/guide/orchestration.md, agent-model-matching.md, installation.md
- docs/reference/configuration.md, features.md

AGENTS.md

@@ -4,7 +4,7 @@
 
 ## OVERVIEW
 
-OpenCode plugin (npm: `oh-my-opencode`, dual-published as `oh-my-openagent` during the rename transition) extending OpenCode with 11 agents, ~50 lifecycle hooks across 57 dirs, 20–39 tools (gated by config flags including team-mode), 3-tier MCP system (built-in + .mcp.json + skill-embedded), Hashline LINE#ID edit tool, IntentGate keyword detector, Team Mode (parallel multi-agent coordination, OFF by default), and Claude Code compatibility. **1967 TypeScript files (1304 source + 663 test), 278k LOC, 120 barrel `index.ts` files.** Entry: `src/index.ts` → 7-step init.
+OpenCode plugin (npm: `oh-my-opencode`, dual-published as `oh-my-openagent` during the rename transition) extending OpenCode with 11 agents, 52–59 lifecycle hooks (base / +team-mode) across 57 dirs, 20–39 tools (gated by config flags including team-mode), 3-tier MCP system (built-in + .mcp.json + skill-embedded), Hashline LINE#ID edit tool, IntentGate keyword detector, Team Mode (parallel multi-agent coordination, OFF by default), and Claude Code compatibility. **1967 TypeScript files (1304 source + 663 test), 278k LOC, 120 barrel `index.ts` files.** Entry: `src/index.ts` → 7-step init.
 
 ## STRUCTURE
 
@@ -84,20 +84,32 @@ pluginModule.server(input, options)
 
 OFF by default. Parallel multi-agent coordination, modeled after Claude Code Agent Teams. Enable via `team_mode.enabled` in `.opencode/oh-my-opencode.jsonc` or user config; restart OpenCode after change.
 
+Full schema in [`src/config/schema/team-mode.ts`](file:///Users/yeongyu/local-workspaces/omo/src/config/schema/team-mode.ts) (11 fields):
+
 ```jsonc
 {
   "team_mode": {
     "enabled": true,
-    "max_parallel_members": 4,
-    "max_members": 8,
-    "tmux_visualization": false
+    "tmux_visualization": false,
+    "max_parallel_members": 4,            // 1..8
+    "max_members": 8,                     // 1..8 hard cap
+    "max_messages_per_run": 10000,
+    "max_wall_clock_minutes": 120,
+    "max_member_turns": 500,
+    "base_dir": null,                     // override default ~/.omo/teams or <project>/.omo/teams
+    "message_payload_max_bytes": 32768,   // ≥1024
+    "recipient_unread_max_bytes": 262144, // ≥1024
+    "mailbox_poll_interval_ms": 3000      // ≥500
   }
 }
 ```
 
 Teams live as directories under `~/.omo/teams/{name}/config.json` (user) or `<project>/.omo/teams/{name}/config.json` (project; project beats user on collisions). Members declared as `kind: "subagent_type"` (direct agent) or `kind: "category"` (routed through `sisyphus-junior`).
 
-**Eligible members only:** sisyphus, atlas, sisyphus-junior, hephaestus. Read-only / orchestration agents (oracle, librarian, explore, multimodal-looker, metis, momus, prometheus) are rejected at parse time — use `task` (delegate) for those.
+**Member eligibility** (from [`AGENT_ELIGIBILITY_REGISTRY`](file:///Users/yeongyu/local-workspaces/omo/src/features/team-mode/types.ts)):
+- `eligible`: sisyphus, atlas, sisyphus-junior
+- `conditional`: hephaestus (lacks `teammate: "allow"` permission by default — apply D-36 in `tool-config-handler.ts` or use `subagent_type: "sisyphus"` instead)
+- `hard-reject`: oracle, librarian, explore, multimodal-looker, metis, momus, prometheus (rejected at parse — use `task`/delegate-task)
 
 **Storage layout** (`~/.omo/teams/{name}/`): `config.json` (spec), `state.json` (runtime), `mailbox/` (messages), `tasklist.jsonl` (tasks), `worktrees/` (per-member git worktrees).
 
@@ -153,7 +165,7 @@ Schema autocomplete: `"$schema": "https://raw.githubusercontent.com/code-yeongyu
 
 - **Canonical agent order:** Sisyphus → Hephaestus → Prometheus → Atlas. Enforced by `installAgentSortShim()` (patches `Array.prototype.toSorted`/`.sort` narrowly when the array contains ≥2 canonical core agents). See [`src/plugin-handlers/AGENTS.md`](file:///Users/yeongyu/local-workspaces/omo/src/plugin-handlers/AGENTS.md) for the full history of why this exists.
 - **Hashline edit + read pairing:** Every `Read` tool output is tagged with `LINE#ID` content hashes; `hashline_edit` validates the hash before applying. Stale hash → reject.
-- **5-tier hook composition:** Session (24) + ToolGuard (14) + Transform (5) + Continuation (7) + Skill (2). Composed by `createCoreHooks()` + `createContinuationHooks()` + `createSkillHooks()`.
+- **5-tier hook composition:** Session (24) + ToolGuard (14) + Transform (5) + Continuation (7) + Skill (2) = 52 base. With `team_mode.enabled`: +1 ToolGuard (`team-tool-gating`), +2 Transform (`team-mode-status-injector`, `team-mailbox-injector`), +4 direct event handlers in `src/plugin/event.ts` (`team-session-events/*`) = 59 total. Composed by `createCoreHooks()` + `createContinuationHooks()` + `createSkillHooks()`.
 - **Per-session MCP isolation:** Tier-3 MCP clients keyed by `${sessionID}:${skillName}:${serverName}` so the same skill in two sessions does not share state.
 - **Two fallback systems:** `model-fallback` (proactive, chat.params) vs `runtime-fallback` (reactive, session.error). They operate independently — no direct integration.
 - **OpenClaw bidirectional:** Outbound dispatchers fire on session events; inbound daemon polls Discord/Telegram and `send-keys` replies into the tracked tmux pane.