feat: chat onboarding and routine advisor (#927)

* feat: port NPA psychographic profiling system into IronClaw Port the complete psychographic profiling system from NPA into IronClaw, including enriched profile schema, conversational onboarding, profile evolution, and three-tier prompt augmentation. Personal onboarding moved from wizard Step 9 to first assistant interaction per maintainer feedback — the First Contact system prompt block now instructs the LLM to conduct a natural onboarding conversation that builds the psychographic profile via memory_write. Changes: - Enrich profile.rs with 5 new structs, 9-dimension analysis framework, custom deserializers for backward compatibility, and rendering methods - Add conversational onboarding engine with one-step-removed questioning technique, personality framework, and confidence-scored profile generation - Add profile evolution with confidence gating, analysis metadata tracking, and weekly update routine - Replace thin interaction style injection with three-tier system gated on confidence > 0.6 and profile recency - Replace wizard Step 9 with First Contact system prompt block that drives conversational onboarding during the user's first interaction - Add autonomy progression to SOUL.md seed and personality framework to AGENTS.md seed Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: replace chat-based onboarding with bootstrap greeting and workspace seeds Remove the interactive onboarding_chat.rs engine in favor of a simpler bootstrap flow: fresh workspaces get a proactive LLM greeting that naturally profiles the user. Identity files are now seeded from src/workspace/seeds/ instead of being hardcoded. Also removes the identity-file write protection (seeds are now managed), adds routine advisor integration, and includes an e2e trace for bootstrap greeting. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(safety): sanitize identity file writes via Sanitizer to prevent prompt injection Identity files (SOUL.md, AGENTS.md, USER.md, IDENTITY.md) are injected into every system prompt. Rather than hard-blocking writes (which broke onboarding), scan content through the existing Sanitizer and reject writes with High/Critical severity injection patterns. Medium/Low warnings are logged but allowed. Also clarifies AGENTS.md identity file roles (USER.md = user info, IDENTITY.md = agent identity) and adds IDENTITY.md setup as an explicit bootstrap step. Co-Authored-By: Claude Opus 4.6 <[email protected]> * docs: update profile_onboarding_completed comment to reflect current wiring The field is now actively used by the agent loop to suppress BOOTSTRAP.md injection — remove the stale "not yet wired" TODO. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(setup): use env_or_override for NEARAI_API_KEY in model fetch config When the user authenticates via NEAR AI Cloud API key (option 4), api_key_login() stores the key via set_runtime_env(). But build_nearai_model_fetch_config() was using std::env::var() which doesn't check the runtime overlay — so model listing fell back to session-token auth and re-triggered the interactive NEAR AI authentication menu. Switch to env_or_override() which checks both real env vars and the runtime overlay. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(agent): correct channel/user_id in bootstrap greeting persist call persist_assistant_response was called with channel="default", user_id="system" but the assistant thread was created via get_or_create_assistant_conversation("default", "gateway") which owns the conversation as user_id="default", channel="gateway". The mismatch caused ensure_writable_conversation to reject the write with: WARN Rejected write for unavailable thread id user=system channel=default [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(web): remove all inline event handlers for CSP compliance The Content-Security-Policy header (added in f48fe95) blocks inline JS via script-src 'self'. All onclick/onchange attributes in index.html are replaced with getElementById().addEventListener() calls. Dynamic inline handlers in app.js (jobs, routines, memory breadcrumb, code blocks, TEE report) are replaced with data-action attributes and a single delegated click handler on document. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(agent): align bootstrap message user/channel and update fixture schema field - Bootstrap IncomingMessage now uses ("default", "gateway") consistently with persist and session registration calls - Update bootstrap_greeting.json fixture: schema_version → version to match current PROFILE_JSON_SCHEMA [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: cargo fmt [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(safety): address PR review — expand injection scanning and harden profile sync - BOOTSTRAP.md: fix target "profile" → "context/profile.json" so the write hits the correct path and triggers profile sync - IDENTITY_FILES: add context/assistant-directives.md to the scanned set since it is also injected into the system prompt - sync_profile_documents(): scan derived USER.md and assistant-directives content through Sanitizer before writing, rejecting High/Critical injection patterns - profile_evolution_prompt(): wrap recent_messages_summary in <user_data> delimiters with untrusted-data instruction to mitigate indirect prompt injection - routine-advisor skill: update cron examples from 6-field to standard 5-field format for consistency with routine_create tool docs [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: cargo fmt [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(setup): detect env-provided LLM keys during quick-mode onboarding Quick-mode wizard now checks LLM_BACKEND, NEARAI_API_KEY, ANTHROPIC_API_KEY, and OPENAI_API_KEY env vars to pre-populate the provider setting, so users aren't re-prompted for credentials they already supplied. Also teaches setup_nearai() to recognize NEARAI_API_KEY from env (previously only checked session tokens). Includes web UI cleanup (remove duplicate event listeners) and e2e test response count adjustment. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(test): update routine_create_list to expect 7-field normalized cron The cron normalizer now always expands to 7-field format, so the stored schedule is "0 0 9 * * * *" not "0 0 9 * * *". [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat(setup): skip LLM provider prompts when NEARAI_API_KEY is present In quick mode, if NEARAI_API_KEY is set in the environment and the backend was auto-detected as nearai, skip the interactive inference provider and model selection steps. The API key is persisted to the secrets store and a default model is set automatically. Also simplify the static fallback model list for nearai to a single default entry. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: unify default model, static bootstrap greeting, and web UI cleanup - Add DEFAULT_MODEL const and default_models() fallback list in llm/nearai_chat.rs; use from config, wizard, and .env.example so the default model is defined in one place - Restore multi-model fallback list in setup wizard (was reduced to 1) - Move BOOTSTRAP_GREETING to module-level const (out of run() body) - Replace LLM-based bootstrap with static greeting (persist to DB before channels start, then broadcast — eliminates startup LLM call and race) - Fix double env::var read for NEARAI_API_KEY in quick setup path - Move thread sidebar buttons into threads-section-header (web UI) - Remove orphaned .thread-sidebar-header CSS and fix double blank line - Update bootstrap e2e test for static greeting (no LLM trace needed) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(safety): move prompt injection scanning into Workspace write/append Addresses PR #927 review comments (#1, #3) — identity file write protection and unsanitized profile fields in system prompt. Instead of scanning at the tool layer (memory.rs) or the sync layer (sync_profile_documents), injection scanning now lives in Workspace::write() and Workspace::append() for all files that are injected into the system prompt. This ensures every code path that writes to these files is protected, including future ones. - Add SYSTEM_PROMPT_FILES const and reject_if_injected() in workspace - Add WorkspaceError::InjectionRejected variant - Add map_write_err() in memory.rs to convert InjectionRejected to ToolError::NotAuthorized - Remove redundant IDENTITY_FILES/Sanitizer from memory.rs - Remove redundant sanitizer calls from sync_profile_documents() - Move sanitization tests to workspace::tests - Existing integration test (test_memory_write_rejects_injection) continues to pass through the new path Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: cargo fmt Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address Copilot review — merge marker order, orphan thread, stale fixture - merge_profile_section: search for END marker after BEGIN position to avoid matching a stray END earlier in the file - Bootstrap phase 2: use get_or_create_session + Thread::with_id instead of resolve_thread(None) to avoid creating an orphan thread - setup_nearai: use env_or_override for NEARAI_API_KEY consistency with runtime overlay - Delete orphaned bootstrap_greeting.json fixture (no test references it) - Add test_merge_end_marker_must_follow_begin regression test Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: cargo fmt Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: fmt agent_loop.rs (CI stable rustfmt) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: lazy-init sanitizer, check profile non-empty before skipping bootstrap Address Copilot review: - Use LazyLock<Sanitizer> to avoid rebuilding Aho-Corasick + regexes on every workspace write - has_profile check now requires non-empty content, not just file existence, to prevent empty profile.json from suppressing onboarding - Add seed_tests integration tests (libsql-backed) verifying: - Empty profile.json does not suppress BOOTSTRAP.md seeding - Non-empty profile.json correctly suppresses bootstrap for upgrades Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: cargo fmt Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: duplicate language handler, empty LLM_BACKEND, test_rig style Address Copilot review on PR #927: - Remove duplicate language-option click listeners (delegated data-action handler already covers them) - Guard LLM_BACKEND env prefill against empty string to prevent suppressing API-key-based auto-detection - Use destructured local `keep_bootstrap` instead of `self.keep_bootstrap` in test_rig for consistency after destructure Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: update stale BOOTSTRAP.md write-protection comment [skip-regression-check] BOOTSTRAP.md is now in SYSTEM_PROMPT_FILES and gets injection scanning on write. The old comment incorrectly stated it was not write-protected. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: replace debug_assert panics with graceful error returns [skip-regression-check] debug_assert! in execute_tool_with_safety and JobContext::transition_to panicked in test builds before the graceful error path could run. Existing tests (test_cancel_job_completed, test_execute_empty_tool_name_returns_not_found) already cover these paths — they were the ones failing. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address Copilot review — schema label, env var check, path normalization, profile validation 1. Label ANALYSIS_FRAMEWORK and PROFILE_JSON_SCHEMA sections separately in bootstrap prompt so the LLM knows which blob is the target structure. 2. Wizard quick-mode backend auto-detection now rejects empty env vars (std::env::var().is_ok_and(|v| !v.is_empty())) to avoid selecting the wrong backend when e.g. NEARAI_API_KEY="" is set. 3. Normalize the target path before comparing with paths::PROFILE in memory_write so non-canonical variants like "context//profile.json" still trigger profile sync. 4. seed_if_empty now requires valid JSON parse of context/profile.json before treating it as a populated profile. Corrupted content no longer permanently suppresses bootstrap seeding. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: cargo fmt * fix: address Copilot review — append scan, profile validation, env_or_override 1. Workspace::append() now scans the combined content (existing + new) for prompt injection, not just the appended chunk. Prevents split- injection evasion across multiple appends. 2. seed_if_empty() now deserializes into PsychographicProfile instead of serde_json::Value for profile validation. Stray/legacy JSON that doesn't match the expected schema no longer suppresses bootstrap. 3. Wizard quick-mode backend auto-detection now uses env_or_override() to honor runtime overlays and injected secrets. LLM_BACKEND value is trimmed before storage. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * test: add bootstrap_onboarding_clears_bootstrap E2E trace test Exercises the full onboarding flow end-to-end: 1. Bootstrap greeting fires automatically on fresh workspace 2. User converses for 3 turns (name, tools, work style) 3. Agent writes psychographic profile to context/profile.json 4. Profile sync generates USER.md and assistant-directives.md 5. Agent writes IDENTITY.md (chosen persona) 6. Agent clears BOOTSTRAP.md via memory_write(target: "bootstrap") Verifies: - BOOTSTRAP.md is non-empty before onboarding, empty after - bootstrap_completed flag is set - Profile contains expected user data (name, profession, interests) - USER.md contains profile-derived content (name, tone, profession) - Assistant-directives.md references user and communication style - IDENTITY.md contains agent's chosen persona name - All memory_write calls succeed Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address Copilot review — slash collapse, env_or_override, cron trim [skip-regression-check] 1. memory.rs path normalization now uses the same char-by-char loop as Workspace::normalize_path() to fully collapse consecutive slashes (e.g. "context///profile.json" → "context/profile.json"). 2. Quick-mode NEARAI_API_KEY check (line 239) now uses env_or_override() consistently with the backend auto-detection block above it. 3. normalize_cron_expression() trims input before field counting so the passthrough branch (7+ fields) also strips whitespace. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Jay Zalowitz <[email protected]> Co-authored-by: Claude Opus 4.6 <[email protected]>
2026-08-25 14:53:34 +00:00 · 2026-03-19 22:20:34 -07:00
parent 3a523347b0
commit 806d402876
41 changed files with 3132 additions and 283 deletions
@@ -705,4 +705,210 @@ mod advanced {
        mock_server.shutdown().await;
        rig.shutdown();
    }
+
+    // -----------------------------------------------------------------------
+    // 9. Bootstrap greeting fires on fresh workspace
+    // -----------------------------------------------------------------------
+
+    /// Verifies that a fresh workspace triggers a static bootstrap greeting
+    /// before the user sends any message (no LLM call needed).
+    #[tokio::test]
+    async fn bootstrap_greeting_fires() {
+        let rig = TestRigBuilder::new().with_bootstrap().build().await;
+
+        // The static bootstrap greeting should arrive without us sending any
+        // message and without an LLM call.
+        let responses = rig.wait_for_responses(1, TIMEOUT).await;
+        assert!(
+            !responses.is_empty(),
+            "bootstrap greeting should produce a response"
+        );
+        let greeting = &responses[0].content;
+        assert!(
+            greeting.contains("chief of staff"),
+            "bootstrap greeting should contain the static text, got: {greeting}"
+        );
+
+        // The bootstrap greeting must carry a thread_id so the gateway can
+        // route it to the correct assistant conversation.
+        assert!(
+            responses[0].thread_id.is_some(),
+            "bootstrap greeting response should have a thread_id set"
+        );
+
+        rig.shutdown();
+    }
+
+    // -----------------------------------------------------------------------
+    // 10. Bootstrap onboarding completes and clears BOOTSTRAP.md
+    // -----------------------------------------------------------------------
+
+    /// Exercises the full onboarding flow: bootstrap greeting fires, user
+    /// converses for 3 turns, agent writes profile + memory + identity,
+    /// clears BOOTSTRAP.md, and the workspace reflects all writes.
+    #[tokio::test]
+    async fn bootstrap_onboarding_clears_bootstrap() {
+        use ironclaw::workspace::paths;
+
+        let trace = LlmTrace::from_file(format!("{FIXTURES}/bootstrap_onboarding.json")).unwrap();
+        let rig = TestRigBuilder::new()
+            .with_trace(trace.clone())
+            .with_bootstrap()
+            .build()
+            .await;
+
+        // 1. Wait for the static bootstrap greeting (no user message needed).
+        let greeting_responses = rig.wait_for_responses(1, TIMEOUT).await;
+        assert!(
+            !greeting_responses.is_empty(),
+            "bootstrap greeting should arrive"
+        );
+        assert!(
+            greeting_responses[0].content.contains("chief of staff"),
+            "expected bootstrap greeting, got: {}",
+            greeting_responses[0].content
+        );
+
+        // 2. BOOTSTRAP.md should exist (non-empty) before onboarding completes.
+        let ws = rig.workspace().expect("workspace should exist");
+        let bootstrap_before = ws.read(paths::BOOTSTRAP).await;
+        assert!(
+            bootstrap_before.is_ok_and(|d| !d.content.is_empty()),
+            "BOOTSTRAP.md should be non-empty before onboarding"
+        );
+
+        // 3. Run the 3-turn conversation. The trace has the agent write
+        //    profile, memory, identity, and then clear bootstrap.
+        let mut total = 1; // already have the greeting
+        for turn in &trace.turns {
+            rig.send_message(&turn.user_input).await;
+            total += 1;
+            let _ = rig.wait_for_responses(total, TIMEOUT).await;
+        }
+
+        // 4. Verify all memory_write calls succeeded.
+        let completed = rig.tool_calls_completed();
+        let memory_writes: Vec<_> = completed
+            .iter()
+            .filter(|(name, _)| name == "memory_write")
+            .collect();
+        assert!(
+            memory_writes.len() >= 4,
+            "expected at least 4 memory_write calls (profile, memory, identity, bootstrap), got: {memory_writes:?}"
+        );
+        assert!(
+            memory_writes.iter().all(|(_, ok)| *ok),
+            "all memory_write calls should succeed: {memory_writes:?}"
+        );
+
+        // 5. BOOTSTRAP.md should now be empty (cleared by memory_write target=bootstrap).
+        let bootstrap_after = ws.read(paths::BOOTSTRAP).await.expect("read BOOTSTRAP");
+        assert!(
+            bootstrap_after.content.is_empty(),
+            "BOOTSTRAP.md should be empty after onboarding, got: {:?}",
+            bootstrap_after.content
+        );
+
+        // 6. The bootstrap-completed flag should be set (prevents re-injection).
+        assert!(
+            ws.is_bootstrap_completed(),
+            "bootstrap_completed flag should be set after profile write"
+        );
+
+        // 7. Profile should exist in workspace with expected fields.
+        let profile = ws.read(paths::PROFILE).await.expect("read profile");
+        assert!(
+            !profile.content.is_empty(),
+            "profile.json should not be empty"
+        );
+        assert!(
+            profile.content.contains("Alex"),
+            "profile should contain preferred_name, got: {:?}",
+            &profile.content[..profile.content.len().min(200)]
+        );
+
+        // Try parsing the stored profile to catch deserialization issues early.
+        let stored = ws
+            .read(paths::PROFILE)
+            .await
+            .expect("read profile for deser test");
+        let deser_result =
+            serde_json::from_str::<ironclaw::profile::PsychographicProfile>(&stored.content);
+        assert!(
+            deser_result.is_ok(),
+            "profile should deserialize: {:?}\ncontent: {:?}",
+            deser_result.err(),
+            &stored.content[..stored.content.len().min(300)]
+        );
+        let parsed = deser_result.unwrap();
+        assert!(
+            parsed.is_populated(),
+            "profile should be populated: name={:?}, profession={:?}, goals={:?}",
+            parsed.preferred_name,
+            parsed.context.profession,
+            parsed.assistance.goals
+        );
+
+        // Manually trigger sync.
+        let synced = ws
+            .sync_profile_documents()
+            .await
+            .expect("sync_profile_documents");
+        assert!(
+            synced,
+            "sync_profile_documents should return true for a populated profile"
+        );
+        assert!(
+            profile.content.contains("backend engineer"),
+            "profile should contain profession"
+        );
+        assert!(
+            profile.content.contains("distributed systems"),
+            "profile should contain interests"
+        );
+
+        // 8. USER.md should have been synced from the profile via sync_profile_documents().
+        let user_doc = ws.read(paths::USER).await.expect("read USER.md");
+        assert!(
+            user_doc.content.contains("Alex"),
+            "USER.md should contain user name from profile, got: {:?}",
+            &user_doc.content[..user_doc.content.len().min(300)]
+        );
+        assert!(
+            user_doc.content.contains("direct"),
+            "USER.md should contain communication tone from profile, got: {:?}",
+            &user_doc.content[..user_doc.content.len().min(300)]
+        );
+        assert!(
+            user_doc.content.contains("backend engineer"),
+            "USER.md should contain profession from profile, got: {:?}",
+            &user_doc.content[..user_doc.content.len().min(300)]
+        );
+
+        // 9. Assistant directives should have been synced from the profile.
+        let directives = ws
+            .read(paths::ASSISTANT_DIRECTIVES)
+            .await
+            .expect("read assistant-directives.md");
+        assert!(
+            directives.content.contains("Alex"),
+            "assistant-directives should reference user name, got: {:?}",
+            &directives.content[..directives.content.len().min(300)]
+        );
+        assert!(
+            directives.content.contains("direct"),
+            "assistant-directives should reflect communication style, got: {:?}",
+            &directives.content[..directives.content.len().min(300)]
+        );
+
+        // 10. IDENTITY.md should have been written by the agent.
+        let identity = ws.read(paths::IDENTITY).await.expect("read IDENTITY.md");
+        assert!(
+            identity.content.contains("Claw"),
+            "IDENTITY.md should contain the chosen agent name, got: {:?}",
+            identity.content
+        );
+
+        rig.shutdown();
+    }
 }
@@ -0,0 +1,122 @@
+{
+  "model_name": "bootstrap-onboarding-flow",
+  "expects": {
+    "tools_used": ["memory_write"],
+    "all_tools_succeeded": true,
+    "min_responses": 2
+  },
+  "turns": [
+    {
+      "user_input": "Hey! I'm Alex, a backend engineer working on distributed systems. I like direct, concise communication.",
+      "steps": [
+        {
+          "request_hint": { "last_user_message_contains": "Alex" },
+          "response": {
+            "type": "text",
+            "content": "Nice to meet you, Alex. Distributed systems — solid domain. I'll keep things direct.\n\nWhat's on your plate right now that I can help with? And any tools or services you use daily that I should know about?",
+            "input_tokens": 800,
+            "output_tokens": 40
+          }
+        }
+      ]
+    },
+    {
+      "user_input": "I mainly use GitHub and Slack. I need help staying on top of PRs and incident response.",
+      "steps": [
+        {
+          "request_hint": { "last_user_message_contains": "GitHub" },
+          "response": {
+            "type": "text",
+            "content": "Got it — GitHub PRs and incident response are your priorities. I can set up routines for both.\n\nOne more thing: when something goes wrong at work, what's your instinct — jump in and debug, or step back and coordinate?",
+            "input_tokens": 900,
+            "output_tokens": 45
+          }
+        }
+      ]
+    },
+    {
+      "user_input": "I usually jump in and start debugging. I'm pretty hands-on.",
+      "steps": [
+        {
+          "request_hint": { "last_user_message_contains": "debugging" },
+          "response": {
+            "type": "tool_calls",
+            "tool_calls": [
+              {
+                "id": "call_profile_write",
+                "name": "memory_write",
+                "arguments": {
+                  "content": "{\"version\":2,\"preferred_name\":\"Alex\",\"personality\":{\"empathy\":50,\"problem_solving\":50,\"emotional_intelligence\":50,\"adaptability\":50,\"communication\":50},\"communication\":{\"detail_level\":\"concise\",\"formality\":\"casual\",\"tone\":\"direct\",\"learning_style\":\"unknown\",\"social_energy\":\"unknown\",\"decision_making\":\"unknown\",\"pace\":\"fast\",\"response_speed\":\"unknown\"},\"cohort\":{\"cohort\":\"other\",\"confidence\":0,\"indicators\":[]},\"behavior\":{\"frictions\":[],\"desired_outcomes\":[],\"time_wasters\":[],\"pain_points\":[\"staying on top of PRs\",\"incident response\"],\"strengths\":[],\"suggested_support\":[]},\"friendship\":{\"style\":\"unknown\",\"values\":[],\"support_style\":\"unknown\",\"qualities\":{\"user_values\":[],\"friends_appreciate\":[],\"consistency_pattern\":null,\"primary_role\":null,\"secondary_roles\":[],\"challenging_aspects\":[]}},\"assistance\":{\"proactivity\":\"moderate\",\"formality\":\"unknown\",\"focus_areas\":[],\"routines\":[],\"goals\":[\"PR management\",\"incident response\"],\"interaction_style\":\"unknown\",\"notification_preferences\":\"moderate\"},\"context\":{\"profession\":\"backend engineer\",\"interests\":[\"distributed systems\"],\"life_stage\":null,\"challenges\":[]},\"relationship_values\":{\"primary\":[],\"secondary\":[],\"deal_breakers\":[]},\"interaction_preferences\":{\"proactivity_style\":\"reactive\",\"feedback_style\":\"direct\",\"decision_making\":\"guided\"},\"analysis_metadata\":{\"message_count\":0,\"analysis_date\":null,\"time_range\":null,\"model_used\":null,\"confidence_score\":0.0,\"analysis_method\":null,\"update_type\":null},\"confidence\":0.5,\"created_at\":\"2026-03-19T00:00:00Z\",\"updated_at\":\"2026-03-19T00:00:00Z\"}",
+                  "target": "context/profile.json",
+                  "append": false
+                }
+              }
+            ],
+            "input_tokens": 1000,
+            "output_tokens": 300
+          }
+        },
+        {
+          "response": {
+            "type": "tool_calls",
+            "tool_calls": [
+              {
+                "id": "call_memory_save",
+                "name": "memory_write",
+                "arguments": {
+                  "content": "User: Alex, backend engineer. Uses GitHub and Slack daily. Priorities: PR management, incident response. Communication: direct, concise, casual. Hands-on debugger.",
+                  "target": "daily_log"
+                }
+              }
+            ],
+            "input_tokens": 1100,
+            "output_tokens": 50
+          }
+        },
+        {
+          "response": {
+            "type": "tool_calls",
+            "tool_calls": [
+              {
+                "id": "call_identity_write",
+                "name": "memory_write",
+                "arguments": {
+                  "content": "# Identity\n\nName: Claw\nVibe: Sharp, efficient, no-nonsense\nEmoji: ⚡",
+                  "target": "IDENTITY.md",
+                  "append": false
+                }
+              }
+            ],
+            "input_tokens": 1200,
+            "output_tokens": 30
+          }
+        },
+        {
+          "response": {
+            "type": "tool_calls",
+            "tool_calls": [
+              {
+                "id": "call_bootstrap_clear",
+                "name": "memory_write",
+                "arguments": {
+                  "content": "",
+                  "target": "bootstrap"
+                }
+              }
+            ],
+            "input_tokens": 1300,
+            "output_tokens": 20
+          }
+        },
+        {
+          "response": {
+            "type": "text",
+            "content": "All set, Alex. I'm Claw — I'll keep things fast and direct.\n\nI've saved your profile and preferences. Want me to set up a morning PR review routine for your GitHub repos?",
+            "input_tokens": 1400,
+            "output_tokens": 35
+          }
+        }
+      ]
+    }
+  ]
+}
@@ -25,6 +25,8 @@ use ironclaw::error::ChannelError;
 /// A `Channel` implementation for injecting messages and capturing responses
 /// in integration tests.
 pub struct TestChannel {
+    /// Channel name returned by `Channel::name()`.
+    channel_name: String,
    /// Sender half for injecting `IncomingMessage`s into the stream.
    tx: mpsc::Sender<IncomingMessage>,
    /// Receiver half, wrapped in Option so `start()` can take it exactly once.
@@ -59,6 +61,7 @@ impl TestChannel {
        let (tx, rx) = mpsc::channel(256);
        let (ready_tx, ready_rx) = oneshot::channel();
        Self {
+            channel_name: "test".to_string(),
            tx,
            rx: Mutex::new(Some(rx)),
            responses: Arc::new(Mutex::new(Vec::new())),
@@ -72,6 +75,12 @@ impl TestChannel {
        }
    }

+    /// Override the channel name (default: "test").
+    pub fn with_name(mut self, name: impl Into<String>) -> Self {
+        self.channel_name = name.into();
+        self
+    }
+
    /// Signal the channel (and any listening agent) to shut down.
    pub fn signal_shutdown(&self) {
        self.shutdown.store(true, Ordering::SeqCst);
@@ -87,7 +96,7 @@ impl TestChannel {

    /// Inject a user message into the channel stream.
    pub async fn send_message(&self, content: &str) {
-        let msg = IncomingMessage::new("test", &self.user_id, content);
+        let msg = IncomingMessage::new(&self.channel_name, &self.user_id, content);
        self.tx.send(msg).await.expect("TestChannel tx closed");
    }

@@ -98,7 +107,8 @@ impl TestChannel {

    /// Inject a user message with a specific thread ID.
    pub async fn send_message_in_thread(&self, content: &str, thread_id: &str) {
-        let msg = IncomingMessage::new("test", &self.user_id, content).with_thread(thread_id);
+        let msg =
+            IncomingMessage::new(&self.channel_name, &self.user_id, content).with_thread(thread_id);
        self.tx.send(msg).await.expect("TestChannel tx closed");
    }

@@ -281,7 +291,7 @@ impl Channel for TestChannelHandle {
 #[async_trait]
 impl Channel for TestChannel {
    fn name(&self) -> &str {
-        "test"
+        &self.channel_name
    }

    async fn start(&self) -> Result<MessageStream, ChannelError> {
@@ -291,7 +301,7 @@ impl Channel for TestChannel {
            .await
            .take()
            .ok_or_else(|| ChannelError::StartupFailed {
-                name: "test".to_string(),
+                name: self.channel_name.clone(),
                reason: "start() already called".to_string(),
            })?;

@@ -354,6 +354,7 @@ pub struct TestRigBuilder {
    enable_routines: bool,
    http_exchanges: Vec<HttpExchange>,
    extra_tools: Vec<Arc<dyn Tool>>,
+    keep_bootstrap: bool,
 }

 impl TestRigBuilder {
@@ -369,6 +370,7 @@ impl TestRigBuilder {
            enable_routines: false,
            http_exchanges: Vec::new(),
            extra_tools: Vec::new(),
+            keep_bootstrap: false,
        }
    }

@@ -426,6 +428,12 @@ impl TestRigBuilder {
        self
    }

+    /// Keep `bootstrap_pending` so the proactive greeting fires on startup.
+    pub fn with_bootstrap(mut self) -> Self {
+        self.keep_bootstrap = true;
+        self
+    }
+
    /// Add pre-recorded HTTP exchanges for the `ReplayingHttpInterceptor`.
    ///
    /// When set, all `http` tool calls will return these responses in order
@@ -457,6 +465,7 @@ impl TestRigBuilder {
            enable_routines,
            http_exchanges: explicit_http_exchanges,
            extra_tools,
+            keep_bootstrap,
        } = self;

        // 1. Create temp dir + libSQL database + run migrations.
@@ -537,6 +546,12 @@ impl TestRigBuilder {
            .await
            .expect("AppBuilder::build_all() failed in test rig");

+        // Clear bootstrap flag so tests don't get an unexpected proactive greeting
+        // (unless the test explicitly wants to test the bootstrap flow).
+        if !keep_bootstrap && let Some(ref ws) = components.workspace {
+            ws.take_bootstrap_pending();
+        }
+
        // AppBuilder may re-resolve config from env/TOML and override test defaults.
        // Force test-rig agent flags to the requested deterministic values.
        components.config.agent.auto_approve_tools = auto_approve_tools.unwrap_or(true);
@@ -648,7 +663,13 @@ impl TestRigBuilder {
        };

        // 7. Create TestChannel and ChannelManager.
-        let test_channel = Arc::new(TestChannel::new());
+        // When testing bootstrap, the channel must be named "gateway" because
+        // the bootstrap greeting targets only the gateway channel.
+        let test_channel = if keep_bootstrap {
+            Arc::new(TestChannel::new().with_name("gateway"))
+        } else {
+            Arc::new(TestChannel::new())
+        };
        let handle = TestChannelHandle::new(Arc::clone(&test_channel));
        let channel_manager = ChannelManager::new();
        channel_manager.add(Box::new(handle)).await;