feat(routing): complete #3018 — RouterCandidates + provider_router_candidates; candidate-aware heuristics, router prompts and recommendation parsing; skip the network router when no cheap tier exists; validate spawn-time model against the active provider; tests + SUBAGENTS.md per-role models docs

Co-Authored-By: Claude <noreply@anthropic.com> https://claude.ai/code/session_018zaP8vUfTAsrE38L6h6fw5
2026-06-11 03:03:08 +00:00
parent a004cfbee6
commit fc10d10189
5 changed files with 513 additions and 55 deletions
@@ -124,6 +124,50 @@ cancelled records persist for inspection but don't occupy a slot.
 Agents that lost their `task_handle` (e.g. across a process
 restart) also don't count against the cap.

+## Per-role models (#3018)
+
+Children can run on a different model than the parent. Two config surfaces
+feed the same override map (`[subagents.models]` keys win on conflict, keys
+are case-insensitive):
+
+```toml
+[subagents]
+default_model  = "deepseek-v4-flash"   # fallback for every role
+worker_model   = "deepseek-v4-pro"     # worker / general
+explorer_model = "deepseek-v4-flash"   # explorer / explore
+awaiter_model  = "deepseek-v4-flash"   # awaiter / plan
+review_model   = "deepseek-v4-pro"     # review
+custom_model   = "deepseek-v4-pro"     # custom
+
+[subagents.models]
+# Free-form role → model map; any role alias accepted by agent_open works.
+implementation = "deepseek-v4-pro"
+```
+
+Model ids may be **any model the active provider accepts** — validation is
+provider-aware and happens at spawn time, not load time. On the official
+DeepSeek API only DeepSeek ids are accepted; every other provider passes the
+id through to the provider API, which is the authority. A non-DeepSeek
+example:
+
+```toml
+provider = "moonshot"
+model = "kimi-k2.6"
+
+[subagents]
+worker_model = "kimi-k2.5"
+```
+
+Spawn-time `model` arguments on `agent_open` are validated the same way; an
+invalid id on the official DeepSeek API fails the spawn with the accepted-id
+list instead of an opaque provider 400.
+
+With `/model auto`, sub-agent routing is provider-aware too: providers with a
+known big/cheap pair (DeepSeek, and the hosted DeepSeek routes on NVIDIA NIM,
+OpenRouter, Novita, SiliconFlow, SGLang, vLLM) route between that pair;
+providers without a known cheap tier (e.g. Ollama, Moonshot) skip the
+network router and keep children on the session model.
+
 ## Per-step API timeout (#1806, #1808)

 Each sub-agent step wraps its DeepSeek `create_message` call in a