diff options
| author | Peter Stone <thepeterstone@gmail.com> | 2026-05-01 22:14:37 -1000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2026-05-01 22:14:37 -1000 |
| commit | 99115d8158137083239c45e5a860b718ff4cefa1 (patch) | |
| tree | 1bf3bd0505eea79375c67af83c7c5fe8c0f274ff /internal/api/elaborate.go | |
| parent | c2aa026f6ce1c9e216b99d74f294fc133d5fcddd (diff) | |
| parent | 50f8fe8c1ff8b82e0bd399e5776e58bda3e57d1c (diff) | |
Merge pull request #1 from thepeterstone/claude/local-oss-model-agents-MEBqj
Local OSS models as a third runner (epic)
Diffstat (limited to 'internal/api/elaborate.go')
| -rw-r--r-- | internal/api/elaborate.go | 60 |
1 files changed, 49 insertions, 11 deletions
diff --git a/internal/api/elaborate.go b/internal/api/elaborate.go index 0c681ae..30095c8 100644 --- a/internal/api/elaborate.go +++ b/internal/api/elaborate.go @@ -12,6 +12,8 @@ import ( "sort" "strings" "time" + + "github.com/thepeterstone/claudomator/internal/llm" ) const elaborateTimeout = 30 * time.Second @@ -245,6 +247,33 @@ func (s *Server) elaborateWithClaude(ctx context.Context, workDir, fullPrompt st return &result, nil } +// elaborateWithLocal runs elaboration through an OpenAI-compatible local LLM. +// It uses the same prompt template as the Claude/Gemini paths and requests +// json_object response format so we can decode directly without the +// markdown-fence cleanup needed for the CLI paths. +func elaborateWithLocal(ctx context.Context, c *llm.Client, workDir, fullPrompt string) (*elaboratedTask, error) { + if c == nil { + return nil, fmt.Errorf("local llm: no client configured") + } + systemPrompt := buildElaboratePrompt(workDir) + resp, err := c.Chat(ctx, llm.ChatRequest{ + Messages: []llm.Message{ + {Role: "system", Content: systemPrompt}, + {Role: "user", Content: fullPrompt}, + }, + ResponseJSON: true, + }) + if err != nil { + return nil, fmt.Errorf("local llm: %w", err) + } + body := strings.TrimSpace(resp.Content) + var result elaboratedTask + if jerr := json.Unmarshal([]byte(extractJSON(body)), &result); jerr != nil { + return nil, fmt.Errorf("local llm: parse JSON: %w (response: %s)", jerr, body) + } + return &result, nil +} + func (s *Server) elaborateWithGemini(ctx context.Context, workDir, fullPrompt string) (*elaboratedTask, error) { combinedPrompt := fmt.Sprintf("%s\n\n%s", buildElaboratePrompt(workDir), fullPrompt) cmd := exec.CommandContext(ctx, s.geminiBinaryPath(), @@ -314,18 +343,27 @@ func (s *Server) handleElaborateTask(w http.ResponseWriter, r *http.Request) { var result *elaboratedTask var err error - // Try Claude first. - result, err = s.elaborateWithClaude(ctx, workDir, fullPrompt) - if err != nil { - s.logger.Warn("elaborate: claude failed, falling back to gemini", "error", err) - // Fallback to Gemini. - result, err = s.elaborateWithGemini(ctx, workDir, fullPrompt) + // Try local LLM first when configured. Falls back to Claude → Gemini on + // hard failure of each prior attempt. + if s.llm != nil { + result, err = elaborateWithLocal(ctx, s.llm, workDir, fullPrompt) + if err != nil { + s.logger.Warn("elaborate: local llm failed, falling back to claude", "error", err) + result = nil + } + } + if result == nil { + result, err = s.elaborateWithClaude(ctx, workDir, fullPrompt) if err != nil { - s.logger.Error("elaborate: fallback gemini also failed", "error", err) - writeJSON(w, http.StatusBadGateway, map[string]string{ - "error": fmt.Sprintf("elaboration failed: %v", err), - }) - return + s.logger.Warn("elaborate: claude failed, falling back to gemini", "error", err) + result, err = s.elaborateWithGemini(ctx, workDir, fullPrompt) + if err != nil { + s.logger.Error("elaborate: gemini also failed", "error", err) + writeJSON(w, http.StatusBadGateway, map[string]string{ + "error": fmt.Sprintf("elaboration failed: %v", err), + }) + return + } } } |
