feat: per-agent model routing — route different agents to different providers (#238)

* feat: add agentModels and agentRouting to SettingsSchema

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: add agentRouting module for per-agent provider resolution

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: thread providerOverride through OpenAI shim for per-agent routing

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: getAnthropicClient accepts providerOverride for agent routing

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: thread providerOverride through Options and queryModel calls

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: thread providerOverride through query loop and ToolUseContext

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: resolve agent routing in runAgent and inject providerOverride

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs: add Agent Routing configuration guide to README

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* test: add unit tests for resolveAgentProvider + plaintext api_key note

- 15 tests covering priority chain (name > subagentType > default > null)
- normalize() case-insensitive and hyphen/underscore equivalence
- Edge cases: null settings, missing config sections, non-existent model
- README note about api_key stored in plaintext

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* security: address code review — SSRF, credential leak, key collision

- base_url schema now uses z.string().url() for SSRF mitigation
- Strip auth headers (Authorization, x-api-key, api-key) from
  defaultHeaders when providerOverride is active, preventing
  Anthropic credentials from leaking to third-party endpoints
- Warn on duplicate normalized routing keys to prevent silent shadowing
- providerOverride.apiKey is never logged (verified via grep)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: 冯俊辉 <fengjunhui@shiyanjia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

README.md

@@ -139,6 +139,50 @@ For best results, use models with strong tool/function calling support.
 
 ---
 
+## Agent Routing
+
+Route different agents to different AI providers within the same session. Useful for cost optimization (cheap model for code review, powerful model for complex coding) or leveraging model strengths.
+
+### Configuration
+
+Add to `~/.claude/settings.json`:
+
+```json
+{
+  "agentModels": {
+    "deepseek-chat": {
+      "base_url": "https://api.deepseek.com/v1",
+      "api_key": "sk-your-key"
+    },
+    "gpt-4o": {
+      "base_url": "https://api.openai.com/v1",
+      "api_key": "sk-your-key"
+    }
+  },
+  "agentRouting": {
+    "Explore": "deepseek-chat",
+    "Plan": "gpt-4o",
+    "general-purpose": "gpt-4o",
+    "frontend-dev": "deepseek-chat",
+    "default": "gpt-4o"
+  }
+}
+```
+
+### How It Works
+
+- **agentModels**: Maps model names to OpenAI-compatible API endpoints
+- **agentRouting**: Maps agent types or team member names to model names
+- **Priority**: `name` > `subagent_type` > `"default"` > global provider
+- **Matching**: Case-insensitive, hyphen/underscore equivalent (`general-purpose` = `general_purpose`)
+- **Teams**: Team members are routed by their `name` — no extra config needed
+
+When no routing match is found, the global provider (env vars) is used as fallback.
+
+> **Note:** `api_key` values in `settings.json` are stored in plaintext. Keep this file private and do not commit it to version control.
+
+---
+
 ## Web Search and Fetch
 
 `WebFetch` works out of the box.