// Package harness runs skills: versioned, typed prompts whose structured // output Go validates. A run renders the skill's layered prompt from its // embedded template (see Render and package prompts), asks the provider // for output matching the skill's schema, decodes and validates the reply, // and on failure sends exactly one repair turn quoting the problems. If the // repair fails too the run fails with llm.ErrBadOutput; there is no silent // fallback (D-007). Every run that reaches the provider is recorded in // ai_runs (see Run and Purge). package harness import ( "bytes" "context" "encoding/json" "errors" "fmt" "io" "strings" "code.cubecraftlabs.com/Maniacs_Mansion/Meal-Quest/internal/ai/llm" "code.cubecraftlabs.com/Maniacs_Mansion/Meal-Quest/internal/store" ) // Skill is one versioned AI task with input In and structured output Out. type Skill[In, Out any] interface { // Name identifies the skill, e.g. "side_quests". Name() string // Version is bumped whenever the prompt, schema or validation changes. // The prompt template is prompts/.v.tmpl. Version() int // PromptInput derives the template data and household context for in. PromptInput(in In) (PromptInput, error) // Schema is the JSON Schema the reply must match; Out decodes from it. Schema() llm.JSONSchema // Validate returns every problem with out, or none when it is usable. // The problems are sent to the model in the repair turn, so each must // say what to fix. Validate(out Out) []string // PostProcess finishes a valid out, e.g. normalising names. Its result // is validated again; problems found then are repaired like any other. // Its error fails the run without a repair turn. PostProcess(out Out) (Out, error) } // Config is what a run needs from the household's AI settings. type Config struct { // Provider answers the requests. Provider llm.Provider // Persona is ai_settings.system_prompt, the first layer of every // system prompt; empty means none. Persona string // Temperature is the household's sampling temperature, sent with // every request. Temperature float64 // ProviderName is ai_settings.provider and Model is ai_settings.model, // both recorded in ai_runs. Neither may be empty. ProviderName string Model string // APIKey is the decrypted API key Provider sends, or "" when it sends // none. It is used only to remove the key from the ai_runs row. APIKey string // Store receives the run's ai_runs row. It must not be nil. Store *store.Store } // validate reports a Config missing what every run needs. func (c Config) validate() error { switch { case c.Provider == nil: return errors.New("config has no provider") case c.ProviderName == "": return errors.New("config has no provider name") case c.Model == "": return errors.New("config has no model") case c.Store == nil: return errors.New("config has no store") } return nil } // BadOutputError is a run whose reply and repair reply were both unusable. // It matches llm.ErrBadOutput. type BadOutputError struct { // Skill and Version identify the skill that ran. Skill string Version int // First lists the problems with the first reply, Repair those with // the reply to the repair turn. First []string Repair []string } func (e *BadOutputError) Error() string { return fmt.Sprintf("harness: skill %s v%d: %s: first reply: %s; repair reply: %s", e.Skill, e.Version, llm.ErrBadOutput, strings.Join(e.First, "; "), strings.Join(e.Repair, "; ")) } func (e *BadOutputError) Unwrap() error { return llm.ErrBadOutput } // Run runs skill s on in with cfg and returns its validated, post-processed // output. A provider error other than llm.ErrBadOutput is returned // unchanged and never repaired. // // Every run that sends a request writes one ai_runs row when it ends, // covering both turns, with its RunStatus and the request and response // bodies redacted (see redact). A Config or render error fails the run // before any request, and writes no row. When the row cannot be written // the run fails with that error too, even if its output was usable. func Run[In, Out any](ctx context.Context, cfg Config, s Skill[In, Out], in In) (Out, error) { var zero Out if err := cfg.validate(); err != nil { return zero, fmt.Errorf("harness: skill %s v%d: %w", s.Name(), s.Version(), err) } prompt, err := Render(cfg.Persona, s, in) if err != nil { return zero, fmt.Errorf("harness: skill %s v%d: render: %w", s.Name(), s.Version(), err) } schema := s.Schema() temperature := cfg.Temperature req := llm.Request{ System: prompt.System, Messages: []llm.Message{{Role: llm.RoleUser, Content: prompt.User}}, Temperature: &temperature, Schema: &schema, } log := &runLog{start: store.Now()} out, status, err := turns(ctx, cfg, s, req, log) if saveErr := log.save(ctx, cfg, s.Name(), s.Version(), status, err); saveErr != nil { return zero, errors.Join(err, fmt.Errorf("harness: skill %s v%d: record ai_runs row: %w", s.Name(), s.Version(), saveErr)) } if err != nil { return zero, err } return out, nil } // turns sends req and, when its reply is unusable, the repair turn, // recording both in log. It returns the run's status alongside its result. func turns[In, Out any](ctx context.Context, cfg Config, s Skill[In, Out], req llm.Request, log *runLog) (Out, RunStatus, error) { var zero Out out, reply, first, status, err := attempt(ctx, cfg, s, req, log) if err != nil { return zero, status, err } if len(first) == 0 { return out, StatusOK, nil } log.problems = first if reply != "" { req.Messages = append(req.Messages, llm.Message{Role: llm.RoleAssistant, Content: reply}) } req.Messages = append(req.Messages, llm.Message{Role: llm.RoleUser, Content: repairMessage(req.Schema.Name, first)}) out, _, second, status, err := attempt(ctx, cfg, s, req, log) if err != nil { return zero, status, err } if len(second) > 0 { return zero, StatusBadOutput, &BadOutputError{Skill: s.Name(), Version: s.Version(), First: first, Repair: second} } return out, StatusRepaired, nil } // attempt sends req once, records the turn in log, then decodes, // validates, post-processes and validates the reply again. It returns the // reply for the repair turn and the problems found; err is set only for a // provider or post-process failure, neither of which is repairable, and // status then says which. func attempt[In, Out any](ctx context.Context, cfg Config, s Skill[In, Out], req llm.Request, log *runLog) (out Out, reply string, problems []string, status RunStatus, err error) { resp, err := cfg.Provider.Generate(ctx, req) log.add(cfg.APIKey, req, resp, err) // The repair turn must quote what failed: the structured output when // there is any, otherwise the text. reply = string(resp.JSON) if reply == "" { reply = resp.Text } if err != nil { if errors.Is(err, llm.ErrBadOutput) { return out, reply, []string{err.Error()}, "", nil } return out, "", nil, StatusProviderError, err } if err := decode(resp.JSON, &out); err != nil { return out, reply, []string{err.Error()}, "", nil } if problems := s.Validate(out); len(problems) > 0 { return out, reply, problems, "", nil } out, err = s.PostProcess(out) if err != nil { return out, "", nil, StatusBadOutput, fmt.Errorf("harness: skill %s v%d: post-process: %w", s.Name(), s.Version(), err) } return out, reply, s.Validate(out), "", nil } // decode strictly decodes data into out: one JSON value, no unknown fields. func decode(data json.RawMessage, out any) error { if len(data) == 0 { return errors.New("reply holds no JSON") } dec := json.NewDecoder(bytes.NewReader(data)) dec.DisallowUnknownFields() if err := dec.Decode(out); err != nil { return fmt.Errorf("reply does not decode: %v", err) } if err := dec.Decode(new(json.RawMessage)); err != io.EOF { return errors.New("reply has data after the JSON value") } return nil } // repairMessage asks the model to fix problems in its last reply. func repairMessage(schemaName string, problems []string) string { var b strings.Builder fmt.Fprintf(&b, "Your previous reply was not usable. Reply again with JSON matching the %s schema, fixing these problems:\n", schemaName) for _, p := range problems { fmt.Fprintf(&b, "- %s\n", p) } return b.String() }