Add session and reasoning controls

2026-08-29 14:22:45 +00:00
parent 1a0f15e210
commit 06b37c2bae
8 changed files with 355 additions and 28 deletions
--- a/docs/api.md
+++ b/docs/api.md
@@ -45,6 +45,7 @@ copyable shape. At the HTTP adapter boundary, the smallest valid shape is:
 | `prompt_id` | yes | Non-blank prompt ID. |
 | `prompt_version` | no | Prompt version filter. |
 | `profile_id` | no | Execution-profile ID; otherwise the prompt must set `default_profile`. |
+| `session_id` | no | Optional direct, non-secret session identifier. |
 | `inputs` | no | Optional object mapping input names to references. Promptkit decides whether the selected definition needs them. |
 | `vars` | no | Object mapping template-variable names to strings. |
 | `model` | no | Runtime model-override object. |
@@ -77,6 +78,12 @@ field cause `400 invalid_json`.
 inherits the selected profile, a non-empty string replaces its value, and an
 empty string explicitly clears it. JSON `null` is treated as omission.

+`session_id` is passed directly to Promptkit. A nonblank value replaces a
+definition-rendered session ID; omission or a blank value lets the definition
+provide one. Promptkit trims direct values and limits them to 256 Unicode code
+points. Session IDs are not credentials and may be included in prepared data,
+results, and provider-facing requests, so use stable non-sensitive identifiers.
+
 ### Strict JSON

 Request decoding rejects malformed JSON, unknown fields at every request level,
@@ -104,6 +111,10 @@ validation contract. The response contains:
 `total_tokens`, `cached_tokens`, and `cache_write_tokens`; unavailable
 cache usage is reported as zero.

+When Promptkit resolves a direct or definition-rendered session ID,
+`metadata.session_id` contains that effective result value. It is omitted when
+no effective session ID exists.
+
 A validation failure has `validation.status: "failed"`, `is_valid: false`,
 and any available diagnostic errors, while still returning the artifact and
 metadata.
--- a/docs/cli.md
+++ b/docs/cli.md
@@ -50,6 +50,7 @@ Optional flags:
 | `--schema-dir <dir>` | Schema base-directory override. |
 | `--prompt-version <version>` | Optional prompt-definition version selector. |
 | `--profile <id>` | Execution-profile override. |
+| `--session-id <id>` | Optional direct session identifier. |
 | `--input name=path` | Optional input file mapping; repeat or use comma-separated mappings. |
 | `--var name=value` | Template-variable mapping; repeat or use comma-separated mappings. |
 | `--out <path>` | Write generated content to this file instead of stdout. |
@@ -59,6 +60,7 @@ Optional flags:
 | `--temperature <float>` | Runtime temperature override. |
 | `--max-tokens <int>` | Runtime maximum-token override. |
 | `--top-p <float>` | Runtime top-p override. |
+| `--reasoning-effort <value>` | Runtime reasoning-effort override. |
 | `--timeout <duration>` | Runtime timeout override using Go duration syntax. |

 Deprecated aliases: `--prompt-id` for `--prompt`, and `--profile-id` for
@@ -79,6 +81,18 @@ selected prompt ID must have exactly one available version. `--input` is
 optional at the CLI boundary: Promptkit decides whether the selected definition
 requires declared inputs or template-referenced values.

+`--session-id` supplies a direct, non-secret session identifier. A nonblank
+value replaces a definition-rendered session ID; an omitted or blank value lets
+the definition supply one. Promptkit trims direct values and limits them to 256
+Unicode code points. Use stable, non-sensitive identifiers because effective
+session IDs may appear in prepared output, run metadata, and provider-facing
+requests.
+
+`--reasoning-effort` is presence-aware: omitting it inherits the selected
+profile value, a nonblank value replaces that value, and
+`--reasoning-effort=` explicitly clears inherited reasoning. Promptkit treats
+nonblank values as provider-specific opaque strings.
+
 ## `scriptorium render`

 ```text
@@ -89,11 +103,13 @@ scriptorium render [flags]
 `--config`, `--prompt-dir`, `--profile-dir`, `--prompt-version`, `--profile`,
 `--input`, `--var`, `--out`, `--llm-base-url`,
 `--model`, `--api-key-env`, `--temperature`, `--max-tokens`, `--top-p`,
-`--timeout`, and `--format text|json`. Their meanings match the corresponding
+`--reasoning-effort`, `--session-id`, `--timeout`, and `--format text|json`. Their meanings match the corresponding
 `run` flags; `--format` selects prepared-run output and otherwise uses
 `defaults.render_format`.

 The same deprecated aliases and numeric/timeout behavior as `run` apply.
+The same session and reasoning inheritance, replacement, and clearing behavior
+also applies.
 `render` does not accept `--schema-dir`; configure `schema_dir` through the
 configuration file. It resolves profiles and schemas as part of preparation but
 does not call an LLM.
--- a/docs/roadmap/implementation.md
+++ b/docs/roadmap/implementation.md
@@ -225,6 +225,8 @@ built-in, or endpoint-only execution targets.

 ## Stage 4: Expose Session And Presence-Aware Reasoning Controls

+**Completion: Complete.**
+
 Complete the request mapping for direct session identifiers and the v0.9.0
 reasoning override semantics.

--- a/internal/adapter/cli/run.go
+++ b/internal/adapter/cli/run.go
@@ -32,33 +32,36 @@ const (
 type runConfig struct {
 	configPath string

-	promptDir     string
-	profileDir    string
-	promptID      string
-	promptVersion string
-	profileID     string
-	inputRaw      listFlag
-	varRaw        listFlag
-	outputPath    string
-	llmBaseURL    string
-	apiKeyEnv     string
-	model         string
-	temperature   float64
-	maxTokens     int
-	topP          float64
-	schemaDir     string
-	backends      []appconfig.BackendSettings
-	timeout       time.Duration
+	promptDir       string
+	profileDir      string
+	promptID        string
+	promptVersion   string
+	profileID       string
+	sessionID       string
+	inputRaw        listFlag
+	varRaw          listFlag
+	outputPath      string
+	llmBaseURL      string
+	apiKeyEnv       string
+	model           string
+	temperature     float64
+	maxTokens       int
+	topP            float64
+	reasoningEffort string
+	schemaDir       string
+	backends        []appconfig.BackendSettings
+	timeout         time.Duration

 	defaultRenderFormat renderformat.PreparedRunOutputFormat

-	llmBaseURLSet  bool
-	apiKeyEnvSet   bool
-	modelSet       bool
-	temperatureSet bool
-	maxTokensSet   bool
-	topPSet        bool
-	timeoutSet     bool
+	llmBaseURLSet      bool
+	apiKeyEnvSet       bool
+	modelSet           bool
+	temperatureSet     bool
+	maxTokensSet       bool
+	topPSet            bool
+	reasoningEffortSet bool
+	timeoutSet         bool
 }

 type renderConfig struct {
@@ -352,6 +355,7 @@ func registerExecutionRequestFlags(fs *flag.FlagSet, cfg *runConfig) {
 	fs.StringVar(&cfg.promptID, "prompt", "", "prompt ID to run")
 	fs.StringVar(&cfg.promptVersion, "prompt-version", "", "optional prompt definition version")
 	fs.StringVar(&cfg.profileID, "profile", "", "optional execution profile ID; if omitted, prompt default_profile is used")
+	fs.StringVar(&cfg.sessionID, "session-id", "", "optional session ID")
 	fs.Var(&cfg.inputRaw, "input", "input mapping(s): name=path (repeatable, comma-separated)")
 	fs.Var(&cfg.varRaw, "var", "variable mapping(s): name=value (repeatable, comma-separated)")
 	fs.StringVar(&cfg.outputPath, "out", "", "optional output file path")
@@ -361,6 +365,7 @@ func registerExecutionRequestFlags(fs *flag.FlagSet, cfg *runConfig) {
 	fs.Float64Var(&cfg.temperature, "temperature", 0, "optional temperature override")
 	fs.IntVar(&cfg.maxTokens, "max-tokens", 0, "optional max tokens override")
 	fs.Float64Var(&cfg.topP, "top-p", 0, "optional top_p override")
+	fs.StringVar(&cfg.reasoningEffort, "reasoning-effort", "", "optional reasoning effort override")
 	fs.DurationVar(&cfg.timeout, "timeout", 0, "LLM request timeout")
 	fs.StringVar(&cfg.promptID, "prompt-id", "", "deprecated alias for --prompt")
 	fs.StringVar(&cfg.profileID, "profile-id", "", "deprecated alias for --profile")
@@ -405,6 +410,7 @@ func finalizeExecutionRequestConfig(fs *flag.FlagSet, cfg *runConfig) error {
 	cfg.temperatureSet = flagWasSet(fs, "temperature")
 	cfg.maxTokensSet = flagWasSet(fs, "max-tokens")
 	cfg.topPSet = flagWasSet(fs, "top-p")
+	cfg.reasoningEffortSet = flagWasSet(fs, "reasoning-effort")
 	cfg.timeoutSet = flagWasSet(fs, "timeout")
 	return nil
 }
@@ -605,7 +611,7 @@ func buildRunRequestFromConfig(cfg *runConfig) (promptkit.RunRequest, error) {
 	}

 	var modelOverride *promptkit.ExecutionTargetOverride
-	if cfg.llmBaseURLSet || cfg.modelSet || cfg.temperatureSet || cfg.maxTokensSet || cfg.topPSet || cfg.apiKeyEnvSet || cfg.timeoutSet {
+	if cfg.llmBaseURLSet || cfg.modelSet || cfg.temperatureSet || cfg.maxTokensSet || cfg.topPSet || cfg.reasoningEffortSet || cfg.apiKeyEnvSet || cfg.timeoutSet {
 		modelOverride = &promptkit.ExecutionTargetOverride{
 			Endpoint:  cfg.llmBaseURL,
 			Model:     cfg.model,
@@ -620,6 +626,9 @@ func buildRunRequestFromConfig(cfg *runConfig) (promptkit.RunRequest, error) {
 		if cfg.topPSet {
 			modelOverride.TopP = &cfg.topP
 		}
+		if cfg.reasoningEffortSet {
+			modelOverride.ReasoningEffort = &cfg.reasoningEffort
+		}
 		if cfg.timeoutSet {
 			timeoutSeconds := int(cfg.timeout.Seconds())
 			modelOverride.TimeoutSeconds = &timeoutSeconds
@@ -630,6 +639,7 @@ func buildRunRequestFromConfig(cfg *runConfig) (promptkit.RunRequest, error) {
 		PromptID:      cfg.promptID,
 		PromptVersion: cfg.promptVersion,
 		ProfileID:     cfg.profileID,
+		SessionID:     cfg.sessionID,
 		Inputs:        inputs,
 		Vars:          varMappings,
 		Execution:     modelOverride,
@@ -727,7 +737,7 @@ func printSummary(stderr io.Writer, res *promptkit.RunResult) {

 func printUsage(w io.Writer) {
 	fmt.Fprintln(w, "usage: scriptorium <run|render|serve> ...")
-	fmt.Fprintln(w, "  run:   scriptorium run [--config PATH] [--prompt-dir DIR] [--profile-dir DIR] --prompt ID [--prompt-version VERSION] [--input name=path] [--profile ID] [--llm-base-url URL] [--model NAME] [--api-key-env ENV] [--temperature N] [--max-tokens N] [--top-p N] [--var k=v] [--out path] [--timeout 10m]")
-	fmt.Fprintln(w, "  render: scriptorium render [--config PATH] [--prompt-dir DIR] [--profile-dir DIR] --prompt ID [--prompt-version VERSION] [--input name=path] [--profile ID] [--llm-base-url URL] [--model NAME] [--api-key-env ENV] [--temperature N] [--max-tokens N] [--top-p N] [--var k=v] [--format text|json] [--out path] [--timeout 10m]")
+	fmt.Fprintln(w, "  run:   scriptorium run [--config PATH] [--prompt-dir DIR] [--profile-dir DIR] --prompt ID [--prompt-version VERSION] [--input name=path] [--profile ID] [--session-id ID] [--llm-base-url URL] [--model NAME] [--api-key-env ENV] [--temperature N] [--max-tokens N] [--top-p N] [--reasoning-effort VALUE] [--var k=v] [--out path] [--timeout 10m]")
+	fmt.Fprintln(w, "  render: scriptorium render [--config PATH] [--prompt-dir DIR] [--profile-dir DIR] --prompt ID [--prompt-version VERSION] [--input name=path] [--profile ID] [--session-id ID] [--llm-base-url URL] [--model NAME] [--api-key-env ENV] [--temperature N] [--max-tokens N] [--top-p N] [--reasoning-effort VALUE] [--var k=v] [--format text|json] [--out path] [--timeout 10m]")
 	fmt.Fprintf(w, "  serve: scriptorium serve [--config PATH] [--addr %s] [--prompt-dir DIR] [--profile-dir DIR] [--schema-dir DIR] [--artifact-root DIR] [--max-request-bytes N] [--max-artifact-bytes N] [--max-response-bytes N]\n", defaults.HTTPAddrDefault)
 }
--- a/internal/adapter/cli/run_test.go
+++ b/internal/adapter/cli/run_test.go
@@ -103,12 +103,14 @@ func TestParseRunArgsFlagMapping(t *testing.T) {
 		"--prompt", "prompt.a",
 		"--prompt-version", "2",
 		"--profile", "profile.a",
+		"--session-id", "session-1",
 		"--input", "a=b",
 		"--llm-base-url", "http://x/v1",
 		"--model", "m",
 		"--temperature", "0.7",
 		"--max-tokens", "111",
 		"--top-p", "0.8",
+		"--reasoning-effort", "medium",
 		"--timeout", "30s",
 		"--api-key-env", "SCRIPTORIUM_API_KEY",
 	})
@@ -121,6 +123,9 @@ func TestParseRunArgsFlagMapping(t *testing.T) {
 	if cfg.promptID != "prompt.a" || cfg.promptVersion != "2" || cfg.profileID != "profile.a" {
 		t.Fatalf("unexpected prompt/version/profile ids: %q %q %q", cfg.promptID, cfg.promptVersion, cfg.profileID)
 	}
+	if cfg.sessionID != "session-1" || cfg.reasoningEffort != "medium" || !cfg.reasoningEffortSet {
+		t.Fatalf("unexpected session or reasoning configuration: %+v", cfg)
+	}
 	if !cfg.llmBaseURLSet || !cfg.modelSet || !cfg.temperatureSet || !cfg.maxTokensSet || !cfg.topPSet || !cfg.timeoutSet || !cfg.apiKeyEnvSet {
 		t.Fatalf("expected override flags set, got %+v", cfg)
 	}
@@ -206,6 +211,8 @@ func TestUsageIncludesExecutionAndServeFlags(t *testing.T) {
 	usage := stderr.String()
 	for _, want := range []string{
 		"--prompt-version VERSION",
+		"--session-id ID",
+		"--reasoning-effort VALUE",
 		"--artifact-root",
 		"--max-request-bytes",
 		"--max-artifact-bytes",
@@ -694,6 +701,39 @@ func TestBuildRunRequestPreservesNumericOverridePresence(t *testing.T) {
 	}
 }

+func TestBuildRunRequestPreservesReasoningEffortPresenceAndSessionID(t *testing.T) {
+	omitted, err := buildRunRequestFromConfig(&runConfig{promptID: "prompt-1"})
+	if err != nil {
+		t.Fatalf("expected omitted request to build, got %v", err)
+	}
+	if omitted.Execution != nil {
+		t.Fatalf("expected omitted reasoning flag to leave execution nil, got %#v", omitted.Execution)
+	}
+
+	for _, tc := range []struct {
+		name  string
+		value string
+	}{
+		{name: "replacement", value: "high"},
+		{name: "clear", value: ""},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			req, err := buildRunRequestFromConfig(&runConfig{
+				promptID:           "prompt-1",
+				sessionID:          "session-1",
+				reasoningEffort:    tc.value,
+				reasoningEffortSet: true,
+			})
+			if err != nil {
+				t.Fatalf("expected request to build, got %v", err)
+			}
+			if req.SessionID != "session-1" || req.Execution == nil || req.Execution.ReasoningEffort == nil || *req.Execution.ReasoningEffort != tc.value {
+				t.Fatalf("unexpected mapped request: %#v", req)
+			}
+		})
+	}
+}
+
 func TestBuildRunRequestAllowsOmittedInputsAndMapsPromptVersion(t *testing.T) {
 	req, err := buildRunRequestFromConfig(&runConfig{
 		promptID:      "prompt-1",
@@ -1002,6 +1042,118 @@ backends:
 	}
 }

+func TestRenderCommandMapsReasoningEffortAndSessionID(t *testing.T) {
+	lib := newCLITestLibrary(t)
+	writePromptDefinition(t, lib.promptDir, "session.yaml", `id: session
+version: "1"
+default_profile: local
+session_id: definition-session
+messages:
+  - role: user
+    content: "hello"
+output:
+  format: text
+  validation_mode: none
+`)
+	if err := os.WriteFile(filepath.Join(lib.profileDir, "local.yaml"), []byte(`id: local
+endpoint: http://127.0.0.1:1/v1
+model: local-model
+reasoning_effort: low
+`), 0o644); err != nil {
+		t.Fatalf("write profile fixture: %v", err)
+	}
+
+	for _, tc := range []struct {
+		name            string
+		args            []string
+		wantReasoning   string
+		wantSessionID   string
+		absentReasoning bool
+	}{
+		{name: "omitted reasoning inherits profile", wantReasoning: "low", wantSessionID: "definition-session"},
+		{name: "nonblank reasoning replaces profile", args: []string{"--reasoning-effort", "high"}, wantReasoning: "high", wantSessionID: "definition-session"},
+		{name: "empty reasoning clears profile", args: []string{"--reasoning-effort="}, wantSessionID: "definition-session", absentReasoning: true},
+		{name: "direct session replaces definition", args: []string{"--session-id", "direct-session"}, wantReasoning: "low", wantSessionID: "direct-session"},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			args := []string{"--prompt-dir", lib.promptDir, "--profile-dir", lib.profileDir, "--prompt", "session"}
+			args = append(args, tc.args...)
+			code, stdout, stderr := runCLICommand(t, renderCommand, args)
+			if code != ExitOK {
+				t.Fatalf("expected ExitOK, got %d stderr=%q", code, stderr)
+			}
+			if !strings.Contains(stdout, "session_id: "+tc.wantSessionID) {
+				t.Fatalf("expected session ID %q, got:\n%s", tc.wantSessionID, stdout)
+			}
+			hasReasoning := strings.Contains(stdout, "reasoning_effort:")
+			if tc.absentReasoning {
+				if hasReasoning {
+					t.Fatalf("expected cleared reasoning to be omitted, got:\n%s", stdout)
+				}
+				return
+			}
+			if !strings.Contains(stdout, "reasoning_effort: "+tc.wantReasoning) {
+				t.Fatalf("expected reasoning effort %q, got:\n%s", tc.wantReasoning, stdout)
+			}
+		})
+	}
+}
+
+func TestRenderCommandOmitsEmptyEffectiveSessionID(t *testing.T) {
+	lib := newCLITestLibrary(t)
+	writePromptDefinition(t, lib.promptDir, "plain.yaml", `id: plain
+version: "1"
+default_profile: local
+messages:
+  - role: user
+    content: "hello"
+output:
+  format: text
+  validation_mode: none
+`)
+	writeProfileFile(t, lib.profileDir, "local", "http://127.0.0.1:1/v1", "local-model")
+
+	code, stdout, stderr := runCLICommand(t, renderCommand, []string{
+		"--prompt-dir", lib.promptDir,
+		"--profile-dir", lib.profileDir,
+		"--prompt", "plain",
+	})
+	if code != ExitOK {
+		t.Fatalf("expected ExitOK, got %d stderr=%q", code, stderr)
+	}
+	if strings.Contains(stdout, "session_id:") {
+		t.Fatalf("expected no effective session ID, got:\n%s", stdout)
+	}
+}
+
+func TestRenderCommandRejectsOverlongSessionID(t *testing.T) {
+	lib := newCLITestLibrary(t)
+	writePromptDefinition(t, lib.promptDir, "session.yaml", `id: session
+version: "1"
+default_profile: local
+messages:
+  - role: user
+    content: "hello"
+output:
+  format: text
+  validation_mode: none
+`)
+	writeProfileFile(t, lib.profileDir, "local", "http://127.0.0.1:1/v1", "local-model")
+
+	code, _, stderr := runCLICommand(t, renderCommand, []string{
+		"--prompt-dir", lib.promptDir,
+		"--profile-dir", lib.profileDir,
+		"--prompt", "session",
+		"--session-id", strings.Repeat("x", 257),
+	})
+	if code != ExitRuntimeError {
+		t.Fatalf("expected runtime error, got %d stderr=%q", code, stderr)
+	}
+	if !strings.Contains(stderr, "invalid run request") {
+		t.Fatalf("expected invalid-request context, got %q", stderr)
+	}
+}
+
 func TestConfiguredBackendValidationComesFromPromptkit(t *testing.T) {
 	lib := newCLITestLibrary(t)

--- a/internal/adapter/http/dto.go
+++ b/internal/adapter/http/dto.go
@@ -8,6 +8,7 @@ type runRequestDTO struct {
 	PromptID         string                   `json:"prompt_id"`
 	PromptVersion    string                   `json:"prompt_version,omitempty"`
 	ProfileID        string                   `json:"profile_id,omitempty"`
+	SessionID        string                   `json:"session_id,omitempty"`
 	Inputs           map[string]inputRefDTO   `json:"inputs"`
 	Vars             map[string]string        `json:"vars,omitempty"`
 	Model            *modelOverrideRequestDTO `json:"model,omitempty"`
@@ -56,6 +57,7 @@ type metadataDTO struct {
 	PromptHash         string            `json:"prompt_hash"`
 	RenderedPromptHash string            `json:"rendered_prompt_hash"`
 	SelectedProfileID  string            `json:"selected_profile_id"`
+	SessionID          string            `json:"session_id,omitempty"`
 	ModelName          string            `json:"model_name"`
 	Endpoint           string            `json:"endpoint"`
 	ModelParams        modelParamsDTO    `json:"model_params"`
--- a/internal/adapter/http/handler.go
+++ b/internal/adapter/http/handler.go
@@ -97,6 +97,7 @@ func (h *Handler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 		PromptID:      req.PromptID,
 		PromptVersion: req.PromptVersion,
 		ProfileID:     req.ProfileID,
+		SessionID:     req.SessionID,
 		Inputs:        mappedInputs,
 		Vars:          req.Vars,
 		Execution:     model,
@@ -124,6 +125,7 @@ func (h *Handler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 			PromptHash:         res.PromptHash,
 			RenderedPromptHash: res.RenderedPromptHash,
 			SelectedProfileID:  res.SelectedProfileID,
+			SessionID:          res.SessionID,
 			ModelName:          res.ModelName,
 			Endpoint:           res.Endpoint,
 			ModelParams:        modelParamsDTOFromExecutionTarget(res.EffectiveModelParams),
--- a/internal/adapter/http/handler_test.go
+++ b/internal/adapter/http/handler_test.go
@@ -514,7 +514,9 @@ func TestHandlerModelOverridePreservesReasoningEffortPresence(t *testing.T) {
 		wantValue   string
 	}{
 		{name: "omitted", model: `{}`},
+		{name: "nonblank", model: `{"reasoning_effort":"high"}`, wantPresent: true, wantValue: "high"},
 		{name: "explicit empty", model: `{"reasoning_effort":""}`, wantPresent: true},
+		{name: "null", model: `{"reasoning_effort":null}`},
 	}

 	for _, tc := range tests {
@@ -546,6 +548,136 @@ func TestHandlerModelOverridePreservesReasoningEffortPresence(t *testing.T) {
 	}
 }

+func TestHandlerMapsSessionIDAndReportsEffectiveResultSessionID(t *testing.T) {
+	r := &fakeRunner{result: &promptkit.RunResult{
+		Artifact:             promptkit.Artifact{Body: []byte("ok")},
+		Validation:           promptkit.ValidationResult{Status: promptkit.ValidationPassed, Mode: promptkit.ValidationBasic, IsValid: true},
+		EffectiveModelParams: promptkit.ExecutionTarget{Endpoint: "http://llm/v1", Model: "m1"},
+		SessionID:            "effective-session",
+	}}
+	h := NewHandler(r)
+	req := httptest.NewRequest(http.MethodPost, "/v1/runs", bytes.NewBufferString(`{"prompt_id":"prompt-1","session_id":"request-session"}`))
+	w := httptest.NewRecorder()
+
+	h.ServeHTTP(w, req)
+
+	if w.Code != http.StatusOK {
+		t.Fatalf("expected 200, got %d body=%s", w.Code, w.Body.String())
+	}
+	if r.last.SessionID != "request-session" {
+		t.Fatalf("expected session ID in run request, got %q", r.last.SessionID)
+	}
+	var resp map[string]any
+	if err := json.Unmarshal(w.Body.Bytes(), &resp); err != nil {
+		t.Fatalf("invalid JSON response: %v", err)
+	}
+	metadata := resp["metadata"].(map[string]any)
+	if metadata["session_id"] != "effective-session" {
+		t.Fatalf("expected effective session ID in response, got %#v", metadata["session_id"])
+	}
+}
+
+func TestHandlerOmitsEmptyEffectiveSessionID(t *testing.T) {
+	r := &fakeRunner{result: &promptkit.RunResult{
+		Artifact:             promptkit.Artifact{Body: []byte("ok")},
+		Validation:           promptkit.ValidationResult{Status: promptkit.ValidationPassed, Mode: promptkit.ValidationBasic, IsValid: true},
+		EffectiveModelParams: promptkit.ExecutionTarget{Endpoint: "http://llm/v1", Model: "m1"},
+	}}
+	h := NewHandler(r)
+	req := httptest.NewRequest(http.MethodPost, "/v1/runs", bytes.NewBufferString(`{"prompt_id":"prompt-1"}`))
+	w := httptest.NewRecorder()
+
+	h.ServeHTTP(w, req)
+
+	if w.Code != http.StatusOK {
+		t.Fatalf("expected 200, got %d body=%s", w.Code, w.Body.String())
+	}
+	var resp map[string]any
+	if err := json.Unmarshal(w.Body.Bytes(), &resp); err != nil {
+		t.Fatalf("invalid JSON response: %v", err)
+	}
+	metadata := resp["metadata"].(map[string]any)
+	if _, ok := metadata["session_id"]; ok {
+		t.Fatalf("expected empty effective session ID to be omitted, got %#v", metadata)
+	}
+}
+
+func TestHandlerSessionIDUsesPromptkitResolution(t *testing.T) {
+	for _, tc := range []struct {
+		name              string
+		definitionSession string
+		requestSession    string
+		wantSession       string
+	}{
+		{name: "definition session", definitionSession: "definition-session", wantSession: "definition-session"},
+		{name: "direct session", definitionSession: "definition-session", requestSession: "direct-session", wantSession: "direct-session"},
+		{name: "no effective session"},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			promptDir := t.TempDir()
+			profileDir := t.TempDir()
+			sessionLine := ""
+			if tc.definitionSession != "" {
+				sessionLine = "session_id: " + tc.definitionSession + "\n"
+			}
+			if err := os.WriteFile(filepath.Join(promptDir, "prompt.yaml"), []byte("id: p\nversion: \"1\"\ndefault_profile: exec\n"+sessionLine+`messages:
+  - role: user
+    content: "hi"
+output:
+  format: text
+  validation_mode: none
+`), 0o644); err != nil {
+				t.Fatalf("write prompt fixture: %v", err)
+			}
+			if err := os.WriteFile(filepath.Join(profileDir, "profile.yaml"), []byte("id: exec\nendpoint: http://127.0.0.1:1/v1\nmodel: test\n"), 0o644); err != nil {
+				t.Fatalf("write profile fixture: %v", err)
+			}
+			engine, err := promptkit.NewEngine(promptkit.Config{PromptDir: promptDir, ProfileDir: profileDir}, promptkit.WithLLMClient(handlerLLMClient{}))
+			if err != nil {
+				t.Fatalf("new engine: %v", err)
+			}
+
+			body := `{"prompt_id":"p"}`
+			if tc.requestSession != "" {
+				body = `{"prompt_id":"p","session_id":"` + tc.requestSession + `"}`
+			}
+			w := httptest.NewRecorder()
+			NewHandler(engine).ServeHTTP(w, httptest.NewRequest(http.MethodPost, "/v1/runs", bytes.NewBufferString(body)))
+			if w.Code != http.StatusOK {
+				t.Fatalf("expected 200, got %d body=%s", w.Code, w.Body.String())
+			}
+			var resp map[string]any
+			if err := json.Unmarshal(w.Body.Bytes(), &resp); err != nil {
+				t.Fatalf("invalid JSON response: %v", err)
+			}
+			metadata := resp["metadata"].(map[string]any)
+			if tc.wantSession == "" {
+				if _, ok := metadata["session_id"]; ok {
+					t.Fatalf("expected session_id to be omitted, got %#v", metadata)
+				}
+				return
+			}
+			if metadata["session_id"] != tc.wantSession {
+				t.Fatalf("expected effective session ID %q, got %#v", tc.wantSession, metadata["session_id"])
+			}
+		})
+	}
+}
+
+func TestHandlerRejectsOverlongSessionIDAndNonStringReasoningEffort(t *testing.T) {
+	engine := newHandlerEngine(t)
+	for _, body := range []string{
+		`{"prompt_id":"p","session_id":"` + strings.Repeat("x", 257) + `"}`,
+		`{"prompt_id":"p","model":{"reasoning_effort":1}}`,
+	} {
+		w := httptest.NewRecorder()
+		NewHandler(engine).ServeHTTP(w, httptest.NewRequest(http.MethodPost, "/v1/runs", bytes.NewBufferString(body)))
+		if w.Code != http.StatusBadRequest {
+			t.Fatalf("expected 400, got %d body=%s", w.Code, w.Body.String())
+		}
+	}
+}
+
 func TestHandlerModelOverrideAcceptsJSONCompatibleExtraParams(t *testing.T) {
 	r := &fakeRunner{result: &promptkit.RunResult{
 		Artifact:             promptkit.Artifact{Body: []byte("ok")},