merge: integrate github/main — LocalRunner, real GeminiRunner, llm clientHEADmain

Merges 12 commits from github/main (formerly master) that were developed
independently. Key additions:
- LocalRunner: OpenAI-compatible local LLM execution (Ollama, LM Studio)
- Real GeminiRunner with full sandbox parity to ClaudeRunner
- llm.Client for enriching CI failures and elaboration via local model
- retry.ParseRetryAfter moved to shared package
- tokens_in/tokens_out columns in executions table

Conflict resolutions:
- Kept local main's VAPID/push, stories, projects, agent events schema
- Merged both sets of Config fields (local + LocalModel from github/main)
- Unified activePerAgent accounting (decActiveAgent helper)
- Removed duplicate helpers from claude.go (now in helpers.go)
- Fixed double-decrement bug in handleRunResult vs decActiveAgent

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

1 files changed, 49 insertions, 19 deletions

diff --git a/internal/config/config.go b/internal/config/config.go
index 71258c1..25187cf 100644
--- a/internal/config/config.go
+++ b/internal/config/config.go
@@ -16,28 +16,58 @@ type Project struct {
 	Dir  string `toml:"dir"`
 }
 
+// LocalModel configures an OpenAI-compatible local LLM endpoint used for
+// internal helpers (classifier, elaboration, future summarization) and as
+// the backend for the "local" runner. If Endpoint is empty, the LocalRunner
+// is not registered and the classifier falls back to the Gemini CLI.
+//
+// PreferForElaborate gates whether the API server's elaboration handler
+// uses this client. It defaults to true when Endpoint is set; users with a
+// slow or low-quality local model can disable it.
+type LocalModel struct {
+	Endpoint           string  `toml:"endpoint"`              // e.g. "http://localhost:11434/v1"
+	Model              string  `toml:"model"`                 // e.g. "llama3.1:8b"
+	TimeoutSeconds     int     `toml:"timeout_seconds"`       // default 60
+	DefaultTemperature float64 `toml:"default_temperature"`   // default 0.2
+	APIKey             string  `toml:"api_key"`               // optional bearer token
+	PreferForElaborate *bool   `toml:"prefer_for_elaborate"`  // pointer so default-true survives parse
+}
+
+// UseForElaborate returns true when elaboration should try this local model
+// before falling back to Claude/Gemini. Default is true when Endpoint is set.
+func (m LocalModel) UseForElaborate() bool {
+	if m.Endpoint == "" {
+		return false
+	}
+	if m.PreferForElaborate == nil {
+		return true
+	}
+	return *m.PreferForElaborate
+}
+
 type Config struct {
-	DataDir          string    `toml:"data_dir"`
-	DBPath           string    `toml:"-"`
-	LogDir           string    `toml:"-"`
-	DropsDir         string    `toml:"-"`
-	SSHAuthSock      string    `toml:"ssh_auth_sock"`
-	ClaudeBinaryPath string    `toml:"claude_binary_path"`
-	GeminiBinaryPath string    `toml:"gemini_binary_path"`
-	ClaudeImage      string    `toml:"claude_image"`
-	GeminiImage      string    `toml:"gemini_image"`
+	DataDir          string        `toml:"data_dir"`
+	DBPath           string        `toml:"-"`
+	LogDir           string        `toml:"-"`
+	DropsDir         string        `toml:"-"`
+	SSHAuthSock      string        `toml:"ssh_auth_sock"`
+	ClaudeBinaryPath string        `toml:"claude_binary_path"`
+	GeminiBinaryPath string        `toml:"gemini_binary_path"`
+	ClaudeImage      string        `toml:"claude_image"`
+	GeminiImage      string        `toml:"gemini_image"`
 	MaxConcurrent    int           `toml:"max_concurrent"`
 	ShutdownTimeout  time.Duration `toml:"shutdown_timeout"`
-	DefaultTimeout   string    `toml:"default_timeout"`
-	ServerAddr       string    `toml:"server_addr"`
-	WebhookURL       string    `toml:"webhook_url"`
-	WorkspaceRoot    string    `toml:"workspace_root"`
-	WebhookSecret    string    `toml:"webhook_secret"`
-	Projects         []Project `toml:"projects"`
-	VAPIDPublicKey   string    `toml:"vapid_public_key"`
-	VAPIDPrivateKey  string    `toml:"vapid_private_key"`
-	VAPIDEmail       string    `toml:"vapid_email"`
-	ClaudeConfigDir  string    `toml:"claude_config_dir"`
+	DefaultTimeout   string        `toml:"default_timeout"`
+	ServerAddr       string        `toml:"server_addr"`
+	WebhookURL       string        `toml:"webhook_url"`
+	WorkspaceRoot    string        `toml:"workspace_root"`
+	WebhookSecret    string        `toml:"webhook_secret"`
+	Projects         []Project     `toml:"projects"`
+	VAPIDPublicKey   string        `toml:"vapid_public_key"`
+	VAPIDPrivateKey  string        `toml:"vapid_private_key"`
+	VAPIDEmail       string        `toml:"vapid_email"`
+	ClaudeConfigDir  string        `toml:"claude_config_dir"`
+	LocalModel       LocalModel    `toml:"local_model"`
 }
 
 func Default() (*Config, error) {