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
This commit is contained in:
YeonGyu-Kim
2026-05-08 13:06:34 +09:00
parent 838b5ae216
commit 2dfa6336f5
29 changed files with 2023 additions and 104 deletions
@@ -0,0 +1,50 @@
import type { TmuxConfig } from "../../config/schema"
import type { TrackedSession } from "./types"
import { log } from "../../shared"
import { queryWindowState } from "./pane-state-querier"
import { decideCloseAction, type SessionMapping } from "./decision-engine"
import { executeAction } from "./action-executor"
export interface SessionDeletedHandlerDeps {
tmuxConfig: TmuxConfig
serverUrl: string
sourcePaneId: string | undefined
sessions: Map<string, TrackedSession>
isEnabled: () => boolean
getSessionMappings: () => SessionMapping[]
stopPolling: () => void
}
export async function handleSessionDeleted(
deps: SessionDeletedHandlerDeps,
event: { sessionID: string },
): Promise<void> {
if (!deps.isEnabled()) return
if (!deps.sourcePaneId) return
const tracked = deps.sessions.get(event.sessionID)
if (!tracked) return
log("[tmux-session-manager] onSessionDeleted", { sessionId: event.sessionID })
const state = await queryWindowState(deps.sourcePaneId)
if (!state) {
deps.sessions.delete(event.sessionID)
return
}
const closeAction = decideCloseAction(state, event.sessionID, deps.getSessionMappings())
if (closeAction) {
await executeAction(closeAction, {
config: deps.tmuxConfig,
serverUrl: deps.serverUrl,
windowState: state,
})
}
deps.sessions.delete(event.sessionID)
if (deps.sessions.size === 0) {
deps.stopPolling()
}
}