5b207425ed
The routing decision is about reasoning capacity, not cost or provider. Fast model (koala/qwen35-9b-fast) handles high-pass-rate calls; thinking model (iguana/gemma4-26b) handles low-pass-rate calls. Removes the implicit Anthropic dependency from the routing pod — both models go through LiteLLM. Renames: HYPERGUILD_LOCAL_MODEL → HYPERGUILD_FAST_MODEL, HYPERGUILD_CLAUDE_MODEL → HYPERGUILD_THINKING_MODEL, Router.LocalModel → FastModel, Router.ClaudeModel → ThinkingModel, log decision "claude_fallback" → "thinking_fallback". Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
80 lines
2.1 KiB
Go
80 lines
2.1 KiB
Go
package routing
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"net/http"
|
|
"time"
|
|
)
|
|
|
|
// LogEntry describes a single routing decision to log via the brain MCP.
|
|
type LogEntry struct {
|
|
SessionID string
|
|
Skill string // the original skill the call routed (e.g., "review")
|
|
Decision string // "local" or "thinking" or "thinking_fallback"
|
|
Message string // free-form, e.g. "model=qwen35, pass_rate=0.94"
|
|
ProjectRoot string
|
|
DurationMs int64
|
|
Failed bool // true → final_status: "fail"; false → "skip"
|
|
}
|
|
|
|
// Logger posts session_log entries to a brain MCP at BrainURL + /mcp.
|
|
type Logger struct {
|
|
BrainURL string
|
|
HTTP *http.Client
|
|
}
|
|
|
|
// NewLogger creates a Logger with a 2-second HTTP timeout.
|
|
func NewLogger(brainURL string) *Logger {
|
|
return &Logger{
|
|
BrainURL: brainURL,
|
|
HTTP: &http.Client{Timeout: 2 * time.Second},
|
|
}
|
|
}
|
|
|
|
// LogDecision posts a session_log MCP call. Errors are returned but the caller
|
|
// MUST NOT block real work on them — logging is best-effort.
|
|
func (l *Logger) LogDecision(ctx context.Context, e LogEntry) error {
|
|
status := "skip"
|
|
if e.Failed {
|
|
status = "fail"
|
|
}
|
|
payload := map[string]any{
|
|
"jsonrpc": "2.0",
|
|
"id": 1,
|
|
"method": "tools/call",
|
|
"params": map[string]any{
|
|
"name": "session_log",
|
|
"arguments": map[string]any{
|
|
"session_id": e.SessionID,
|
|
"skill": "_routing",
|
|
"phase": "decide",
|
|
"final_status": status,
|
|
"message": fmt.Sprintf("%s: %s — %s", e.Skill, e.Decision, e.Message),
|
|
"duration_ms": e.DurationMs,
|
|
"project_root": e.ProjectRoot,
|
|
},
|
|
},
|
|
}
|
|
body, err := json.Marshal(payload)
|
|
if err != nil {
|
|
return fmt.Errorf("log: marshal: %w", err)
|
|
}
|
|
req, err := http.NewRequestWithContext(ctx, http.MethodPost, l.BrainURL+"/mcp", bytes.NewReader(body))
|
|
if err != nil {
|
|
return fmt.Errorf("log: build request: %w", err)
|
|
}
|
|
req.Header.Set("Content-Type", "application/json")
|
|
resp, err := l.HTTP.Do(req)
|
|
if err != nil {
|
|
return fmt.Errorf("log: request: %w", err)
|
|
}
|
|
defer func() { _ = resp.Body.Close() }()
|
|
if resp.StatusCode != http.StatusOK {
|
|
return fmt.Errorf("log: server returned status %d", resp.StatusCode)
|
|
}
|
|
return nil
|
|
}
|