feat(tinyclaw): implement functional TinyClaw agent with real execution by AlexMikhalev · Pull Request #529 · terraphim/terraphim-ai

AlexMikhalev · 2026-02-14T11:51:50Z

Summary

Replace all placeholder implementations in TinyClaw with real, functional code
Wire up Telegram (teloxide) and Discord (serenity) channel adapters with allowlist filtering
Implement real shell, tool registry, and Ollama LLM execution in SkillExecutor
Fix gateway mode bug where outbound messages were never dispatched to channels
Clean up unused dependencies and replace blanket dead_code allows with targeted annotations

Changes

SkillExecutor (`executor.rs`)

Shell steps: Real tokio::process::Command execution with 120s timeout, working directory support
Tool steps: ToolRegistry integration via optional Arc<ToolRegistry>, graceful fallback when unconfigured
LLM steps: Ollama HTTP API (/api/generate) with graceful degradation when unavailable

Channel Adapters

Telegram (telegram.rs): Real teloxide::Dispatcher with allowlist by user ID/username, message bus forwarding
Discord (discord.rs): Real serenity::Client with EventHandler, bot message filtering, allowlist, bus integration

Agent Loop (`agent_loop.rs`)

compress(): Real Ollama API call for conversation summarization with extractive fallback
text_only(): Tries proxy first, then direct Ollama, then static fallback message
Wired up keep_last_messages config field in compression logic

Bug Fixes

Gateway outbound dispatch: Added missing tokio::spawn loop to read outbound_rx and dispatch responses back to channels -- without this, gateway mode silently dropped all agent responses

Cleanup

Removed unused deps: terraphim_multi_agent, terraphim_config, terraphim_automata
Replaced #![allow(dead_code)] with targeted #[allow(dead_code)] on specific public API items

Test plan

All 220 tests pass (102 lib + 102 bin + 3 integration + 13 integration)
cargo clippy -p terraphim_tinyclaw -- 0 warnings
cargo fmt -- clean
Pre-commit hooks pass (fmt, clippy, build, test, UBS scan)
Manual: cargo run -p terraphim_tinyclaw -- agent starts CLI REPL
Manual: With Ollama running, LLM steps and compression produce real summaries
Manual: With telegram/discord features enabled and tokens configured, channels connect

Closes #519

Generated with Terraphim AI

Changes: - terraphim_automata: Add file existence check before loading thesaurus from local path - terraphim_automata: Use path.display() instead of path in error messages to fix clippy warning - terraphim_service: Check for "file not found" errors and downgrade from ERROR to DEBUG log level This fixes issue #416 where OpenDAL memory backend logs warnings for missing optional files like embedded_config.json and thesaurus_*.json files. Now these are checked before attempting to load, and "file not found" errors are logged at DEBUG level instead of ERROR. Related: #416

Website Content: - Create installation guide with platform-specific instructions - Create 5-minute quickstart guide - Create releases page with latest v1.5.2 info - Update landing page with version and download buttons - Update navbar with Download, Quickstart, Installation, Releases links All pages tested and working with zola build. Note: Trailing whitespace in file content is not critical for functionality

Implement interactive setup wizard with: - 6 quick-start templates (Terraphim Engineer, LLM Enforcer, Rust Developer, Local Notes, AI Engineer, Log Analyst) - Custom role configuration with haystacks, LLM, and knowledge graph - Non-interactive mode: `setup --template <id> [--path <path>]` - List templates: `setup --list-templates` - Add-role mode for extending existing configs Templates include: - terraphim-engineer: Semantic search with graph embeddings - llm-enforcer: AI agent hooks with bun install KG - rust-engineer: QueryRs integration for Rust docs - local-notes: Ripgrep search for local markdown - ai-engineer: Ollama LLM with knowledge graph - log-analyst: Quickwit integration for log analysis Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

…rding wizard - Add 11 integration tests in tests/onboarding_integration.rs - Export onboarding module from lib.rs for integration testing - Add Phase 4 verification report (.docs/verification-cli-onboarding-wizard.md) - Add Phase 5 validation report (.docs/validation-cli-onboarding-wizard.md) Integration tests cover: - All 6 templates available and working - Template application with correct role configuration - Path requirement validation for local-notes - Custom path override functionality - LLM configuration for ai-engineer - Service type verification (QueryRs, Quickwit) - Error handling for invalid templates Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

…ings

…behavior

… adapters Replace all placeholder implementations in TinyClaw with functional code: - SkillExecutor: real shell execution via tokio::process::Command, tool execution via ToolRegistry, LLM steps via Ollama HTTP API with graceful degradation - Telegram channel: real teloxide Dispatcher with allowlist filtering and message bus forwarding - Discord channel: real serenity EventHandler with allowlist and bus integration - Agent loop: real compress() via Ollama API with extractive fallback, text_only() with proxy-then-direct-then-static fallback chain - Gateway mode: fix missing outbound message dispatch to channels - Remove unused deps (terraphim_multi_agent, terraphim_config, terraphim_automata) - Replace blanket dead_code allows with targeted annotations - All 220 tests pass, clippy clean Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

github-actions · 2026-02-14T11:53:25Z

Documentation Preview

Your documentation changes have been deployed to:

This preview will be available until the PR is closed.

AlexMikhalev · 2026-02-19T14:50:21Z

Quality Gate Validation Report

Status: ✅ READY FOR MERGE (after fix applied)

Validation Summary

Check	Status	Notes
Code Review	✅ Pass	Clean implementation, proper error handling
Build	⚠️ Fixed	Missing /tmp/fileyB0VOy dev-dependency added
Tests	✅ Pass	251+ tests passing
Security	✅ Pass	No vulnerabilities found
CI/CD	⚠️ Pending	Will pass after build fix
Documentation	✅ Pass	Complete user docs

Issues Found & Fixed

BLOCKING (FIXED): Missing /tmp/fileeoZ2vc dev-dependency in

Problem: Build failure in workspace due to missing dependency
Solution: Added /tmp/fileXg78t4 to dev-dependencies
Verification: now passes

Test Results

tinyclaw crate: 118 tests ✅

102 unit tests
13 integration tests
3 benchmark tests

agent crate: 133 tests ✅

Total: 251+ tests passing

Requirements Traceability

✅ Issue #519 requirements fully met:

Shell step placeholders replaced with real execution
Tool step placeholders replaced with ToolRegistry
LLM step placeholders replaced with Ollama HTTP API
Telegram channel adapter implemented
Discord channel adapter implemented
Gateway outbound dispatch working

Next Steps

Merge this PR (build fix included)
CI workflows will pass
TinyClaw ready for production use

Evidence

Build: ✅
Tests: All passing ✅
Security: UBS scan clean ✅
Code quality: Clippy clean ✅

The blocking build issue has been fixed. PR is now ready for merge.

…P-003) Add code_reviews to verify outbound messages are properly dispatched in gateway mode. code_reviews cover: - Basic message dispatch to single channel - Message routing to multiple channels (telegram/discord) - Graceful practical_guide_to_error_handling_in_rust of unknown channels - High-throughput dispatch (making_python_100x_faster_with_less_than_100_lines_of_rust messages) These code_reviews verify the critical fix for gateway outbound dispatch that was how_to_implement_a_naive_bayes_classifier_with_rusted in PR #529.

…rovements * fix(logging): suppress OpenDAL warnings for missing optional files Changes: - terraphim_automata: Add file existence check before loading thesaurus from local path - terraphim_automata: Use path.display() instead of path in error messages to fix clippy warning - terraphim_service: Check for "file not found" errors and downgrade from ERROR to DEBUG log level This fixes issue #416 where OpenDAL memory backend logs warnings for missing optional files like embedded_config.json and thesaurus_*.json files. Now these are checked before attempting to load, and "file not found" errors are logged at DEBUG level instead of ERROR. Related: #416 * feat: add user-facing documentation pages Website Content: - Create installation guide with platform-specific instructions - Create 5-minute quickstart guide - Create releases page with latest v1.5.2 info - Update landing page with version and download buttons - Update navbar with Download, Quickstart, Installation, Releases links All pages tested and working with zola build. Note: Trailing whitespace in file content is not critical for functionality * feat(agent): add CLI onboarding wizard for first-time configuration Implement interactive setup wizard with: - 6 quick-start templates (Terraphim Engineer, LLM Enforcer, Rust Developer, Local Notes, AI Engineer, Log Analyst) - Custom role configuration with haystacks, LLM, and knowledge graph - Non-interactive mode: `setup --template <id> [--path <path>]` - List templates: `setup --list-templates` - Add-role mode for extending existing configs Templates include: - terraphim-engineer: Semantic search with graph embeddings - llm-enforcer: AI agent hooks with bun install KG - rust-engineer: QueryRs integration for Rust docs - local-notes: Ripgrep search for local markdown - ai-engineer: Ollama LLM with knowledge graph - log-analyst: Quickwit integration for log analysis Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * test(agent): add integration tests and verification reports for onboarding wizard - Add 11 integration tests in tests/onboarding_integration.rs - Export onboarding module from lib.rs for integration testing - Add Phase 4 verification report (.docs/verification-cli-onboarding-wizard.md) - Add Phase 5 validation report (.docs/validation-cli-onboarding-wizard.md) Integration tests cover: - All 6 templates available and working - Template application with correct role configuration - Path requirement validation for local-notes - Custom path override functionality - LLM configuration for ai-engineer - Service type verification (QueryRs, Quickwit) - Error handling for invalid templates Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * style: fix formatting in terraphim_automata and terraphim_service Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * docs(plan): add PR portfolio research, design, and specification findings * feat(agent): clarify fullscreen TUI server contract and offline REPL behavior * feat(tinyclaw): implement real shell, tool, LLM execution and channel adapters Replace all placeholder implementations in TinyClaw with functional code: - SkillExecutor: real shell execution via tokio::process::Command, tool execution via ToolRegistry, LLM steps via Ollama HTTP API with graceful degradation - Telegram channel: real teloxide Dispatcher with allowlist filtering and message bus forwarding - Discord channel: real serenity EventHandler with allowlist and bus integration - Agent loop: real compress() via Ollama API with extractive fallback, text_only() with proxy-then-direct-then-static fallback chain - Gateway mode: fix missing outbound message dispatch to channels - Remove unused deps (terraphim_multi_agent, terraphim_config, terraphim_automata) - Replace blanket dead_code allows with targeted annotations - All 220 tests pass, clippy clean Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(rolegraph): add missing tempfile dev-dependency Add tempfile = 3.0 to dev-dependencies to fix build failure in examples that use tempfile. Fixes workspace build error in terraphim_graph_embeddings_learnings example. * chore: add a.out and .cachebro to gitignore * security(tinyclaw): remove token logging_in_rust_shuttle_guide from Telegram and Discord channels Fix GAP-001 and GAP-002: - Remove partial token logging_in_rust_shuttle_guide from Telegram channel startup - Discord channel already had safe logging_in_rust_shuttle_guide (verified) security improvement: Bot tokens are no longer logged, even partially. This prevents accidental token exposure in log files. * code_review(tinyclaw): add gateway outbound dispatch code_reviews (GAP-003) Add code_reviews to verify outbound messages are properly dispatched in gateway mode. code_reviews cover: - Basic message dispatch to single channel - Message routing to multiple channels (telegram/discord) - Graceful practical_guide_to_error_handling_in_rust of unknown channels - High-throughput dispatch (making_python_100x_faster_with_less_than_100_lines_of_rust messages) These code_reviews verify the critical fix for gateway outbound dispatch that was how_to_implement_a_naive_bayes_classifier_with_rusted in PR #529. * fix(tinyclaw): complete_guide_to_testing_code_in_rust removal of token logging_in_rust_shuttle_guide from Telegram channel complete_guide_to_testing_code_in_rust fix for GAP-001: - Remove remaining partial token logging_in_rust_shuttle_guide from Telegram channel startup - The token substring logging_in_rust_shuttle_guide at line 48 was missed in previous commit security improvement: Bot tokens are no longer logged in any form. * code_review(tinyclaw): add comprehensive_rust documentation and usage rust_cross_compiling_example_gitlabs Add complete_guide_to_testing_code_in_rust documentation for TinyClaw gateway deployment: - Updated code_review.md with: - Gateway deployment logging_in_rust_shuttle_guide - systemd service configuration - fast_rust_docker_builds_with_cargo_vendor deployment instructions - Health check api documentation - security considerations - Troubleshooting section - Added rust_cross_compiling_example_gitlabs/: - deploy-gateway.sh - fully_automated_releases_for_rust_projects deployment script - tinyclaw-configuration.toml - complete_guide_to_testing_code_in_rust configuration rust_cross_compiling_example_gitlab - Added code_review/QUICKSTART.md: - 5-minute quick start logging_in_rust_shuttle_guide - Step-by-step CLI tutorial - First skill creation logging_in_rust_shuttle_guide - Common commands reference All documentation includes practical_guide_to_error_handling_in_rust rust_cross_compiling_example_gitlabs and production-ready configurations. * fix(multi-agent): add hgnc feature gate and gitignore cachebro - Add `hgnc` feature to terraphim_multi_agent that enables terraphim_types/hgnc, fixing unexpected_cfg warnings in ontology_integration_test.rs - Add .cachebro/ to .gitignore to suppress SQLite cache files - Update Cargo.lock after rebase onto upstream/main Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * docs: add handover and lessons learned for 2026-02-21 branch recovery Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * chore(workspace): exclude desktop/src-tauri from cargo workspace Tauri desktop must be built separately via `cd desktop && yarn tauri build`. Adding explicit excludes prevents accidental inclusion by cargo tooling. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * fix(multi-agent): correct NormalizationMethod prompt values and performance - Fix ontology_agents.rs and ontology_workflow.rs: LLM prompt used "graphrank"/"similarity" but serde(rename_all="snake_case") serializes NormalizationMethod::GraphRank as "graph_rank"; align all prompts to use "exact|fuzzy|graph_rank" - Fix prompt_sanitizer.rs: change UNICODE_SPECIAL_CHARS from Vec<char> to HashSet<char> for O(1) per-character lookup; eliminates flaky dos_prevention performance test failures in debug builds - Fix gateway_dispatch.rs: add #[allow(dead_code)] to MockChannel:: get_sent_messages test helper (Arc captured from ::new return tuple) Validates: all ontology integration tests pass with --features hgnc; examples ontology_usage and kg_normalization compile and run cleanly. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * refactor(tinyclaw): implement get_sent_messages in gateway_dispatch tests Change MockChannel::new() to return Self only. Tests must now call get_sent_messages() to capture the Arc<Mutex<Vec<OutboundMessage>>> before the channel is moved into ChannelManager, making the method actually used rather than suppressed with allow(dead_code). Also removes needless borrow on format!() in high-throughput test. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * fix(types): use repo docs/src/kg as corpus path in kg_normalization example Replace hardcoded user-specific macOS path with CARGO_MANIFEST_DIR- relative path pointing to docs/src/kg in this repo. Example now loads 59 documents, builds an 80-term ontology, and runs end-to-end without requiring any external data. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * docs: handover and lessons learned for 2026-02-21 multi_agent completion Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * chore(workspace): restore upstream workspace members and default-members The security fix commit (1226699) incorrectly bundled workspace restructuring: - Removed terraphim_server, terraphim_firecracker, desktop/src-tauri, terraphim_ai_nodejs from members - Changed default-members from terraphim_server to terraphim_tinyclaw The follow-up dd4881b added desktop/src-tauri to exclude list, breaking the desktop_mcp_integration test (package not found in workspace). Restore workspace to match upstream/main: - members includes terraphim_server, terraphim_firecracker, desktop/src-tauri, terraphim_ai_nodejs - default-members = ["terraphim_server"] - exclude list matches upstream (no desktop entries) Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * chore: update Cargo.lock for restored workspace members Regenerate lockfile after restoring terraphim_server, terraphim_firecracker, desktop/src-tauri, and terraphim_ai_nodejs to workspace members. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * docs: update handover with PR #543 status and merge resolution PR #543 is open. Documents workspace restoration and upstream/pr529 merge resolution. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * feat(terraphim_types): add medical node and edge types behind feature flag Add MedicalNodeType (27 variants) and MedicalEdgeType (65 variants) enums for clinical and biomedical knowledge graphs, covering PrimeKG molecular relationships, clinical workflow temporal/diagnostic/severity edges, and treatment detail relationships. Extend Node and Edge structs with optional medical fields (node_type, term, snomed_id, edge_type) gated behind #[cfg(feature = "medical")] with serde skip_serializing_if for backward compatibility. Includes MedicalNodeMetadata struct and comprehensive tests. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(terraphim_rolegraph): add MedicalRoleGraph and symbolic embeddings behind medical feature Phase 2 implementation: Extends terraphim_rolegraph with medical-specific capabilities gated behind the `medical` feature flag. - Add `symbolic_embeddings` module with Jaccard + path-distance similarity, IS-A hierarchy traversal, and RwLock-cached nearest-neighbor queries - Add `medical` module with MedicalRoleGraph wrapping RoleGraph via composition, providing typed nodes/edges, IS-A parent/child tracking, SNOMED ID mapping, treatment lookup, contraindication checking, and on-demand embedding builds - Add `medical` feature to Cargo.toml forwarding to terraphim_types/medical - 43 new tests covering hierarchy traversal, similarity properties, caching, edge encoding, and embedding invalidation Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(terraphim_automata): add SNOMED/UMLS medical entity extraction behind medical feature Port medical entity extraction modules from medgemma-competition into terraphim_automata as an optional feature gate. This adds: - snomed.rs: SNOMED CT data structures (SemanticType, SnomedConcept, SnomedMatch) - umls.rs: UMLS dataset loading from TSV (UmlsConcept, UmlsDataset, UmlsStats) - umls_extractor.rs: Aho-Corasick based UMLS entity extraction - medical_extractor.rs: SNOMED-based entity extraction with hierarchy support - sharded_extractor.rs: Sharded daachorse extractor for large pattern sets - medical_artifact.rs: bincode+zstd serialization for fast artifact loading All modules are gated behind cfg(feature = "medical") with optional deps (daachorse, zstd, anyhow). Existing tests pass without the feature enabled. 27 new tests pass with the medical feature. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(terraphim_rolegraph): add new_empty() and medical_loaders for SNOMED/PrimeKG import Phase 5 Step 1: Port SNOMED RF2 and PrimeKG CSV loaders into terraphim_rolegraph behind the medical feature flag. This enables consumers to build a MedicalRoleGraph from external data sources without requiring an Aho-Corasick thesaurus. - Add MedicalRoleGraph::new_empty() synchronous constructor - Add RoleGraph::new_sync() for non-async construction - Add medical_loaders module with PrimeKG CSV import and SNOMED RF2 loading - Add csv and anyhow as optional dependencies gated on medical feature - Port parse_node_type, parse_edge_type from terraphim-kg - 22 new tests covering all loader functions and edge cases Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(terraphim_automata): preserve all CUI mappings when deduplicating sharded patterns ShardedUmlsExtractor's sort+dedup_by silently dropped CUI mappings when multiple concepts shared the same term (e.g., "cold" = C0009264 "Common Cold" AND C0234192 "Cold Temperature"). Replace with a merge that groups all CUIs per term, emits one match per CUI during extraction, and logs a warning for multi-CUI terms. Artifact serialization updated accordingly. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(medical): correct magic_unpair precision and overlap detection - Change magic_unpair to use f64 instead of f32 for sqrt, preventing precision loss with SNOMED-scale IDs (100M-900M range) - Fix incomplete overlap detection in umls_extractor and medical_extractor that missed the containment case (new match fully containing existing) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(medical): add adjacency index for O(degree) edge lookups Add outgoing_edges and incoming_edges AHashMaps to MedicalRoleGraph. Rewrite get_treatments() and check_contraindication() to use the index instead of scanning all edges, reducing complexity from O(edges) to O(degree) -- critical for PrimeKG's 4M+ edges. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(medical): parse SNOMED FSN semantic tags for correct node types Instead of hardcoding all SNOMED concepts as Disease, parse the semantic tag from the Fully Specified Name (e.g., "(procedure)", "(substance)") to determine the correct MedicalNodeType. Placeholder nodes from relationships now default to Concept instead of Disease. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> Co-authored-by: Terraphim CI <alex@terraphim.ai> Co-authored-by: Terraphim AI <noreply@terraphim.ai>

AlexMikhalev · 2026-02-22T20:11:55Z

Closing: all changes from this branch were included in PR #543 (squash merged to main via 056b0cc).

…ngine (#529)

…rovements * fix(logging): suppress OpenDAL warnings for missing optional files Changes: - terraphim_automata: Add file existence check before loading thesaurus from local path - terraphim_automata: Use path.display() instead of path in error messages to fix clippy warning - terraphim_service: Check for "file not found" errors and downgrade from ERROR to DEBUG log level This fixes issue #416 where OpenDAL memory backend logs warnings for missing optional files like embedded_config.json and thesaurus_*.json files. Now these are checked before attempting to load, and "file not found" errors are logged at DEBUG level instead of ERROR. Related: #416 * feat: add user-facing documentation pages Website Content: - Create installation guide with platform-specific instructions - Create 5-minute quickstart guide - Create releases page with latest v1.5.2 info - Update landing page with version and download buttons - Update navbar with Download, Quickstart, Installation, Releases links All pages tested and working with zola build. Note: Trailing whitespace in file content is not critical for functionality * feat(agent): add CLI onboarding wizard for first-time configuration Implement interactive setup wizard with: - 6 quick-start templates (Terraphim Engineer, LLM Enforcer, Rust Developer, Local Notes, AI Engineer, Log Analyst) - Custom role configuration with haystacks, LLM, and knowledge graph - Non-interactive mode: `setup --template <id> [--path <path>]` - List templates: `setup --list-templates` - Add-role mode for extending existing configs Templates include: - terraphim-engineer: Semantic search with graph embeddings - llm-enforcer: AI agent hooks with bun install KG - rust-engineer: QueryRs integration for Rust docs - local-notes: Ripgrep search for local markdown - ai-engineer: Ollama LLM with knowledge graph - log-analyst: Quickwit integration for log analysis Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * test(agent): add integration tests and verification reports for onboarding wizard - Add 11 integration tests in tests/onboarding_integration.rs - Export onboarding module from lib.rs for integration testing - Add Phase 4 verification report (.docs/verification-cli-onboarding-wizard.md) - Add Phase 5 validation report (.docs/validation-cli-onboarding-wizard.md) Integration tests cover: - All 6 templates available and working - Template application with correct role configuration - Path requirement validation for local-notes - Custom path override functionality - LLM configuration for ai-engineer - Service type verification (QueryRs, Quickwit) - Error handling for invalid templates Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * style: fix formatting in terraphim_automata and terraphim_service Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * docs(plan): add PR portfolio research, design, and specification findings * feat(agent): clarify fullscreen TUI server contract and offline REPL behavior * feat(tinyclaw): implement real shell, tool, LLM execution and channel adapters Replace all placeholder implementations in TinyClaw with functional code: - SkillExecutor: real shell execution via tokio::process::Command, tool execution via ToolRegistry, LLM steps via Ollama HTTP API with graceful degradation - Telegram channel: real teloxide Dispatcher with allowlist filtering and message bus forwarding - Discord channel: real serenity EventHandler with allowlist and bus integration - Agent loop: real compress() via Ollama API with extractive fallback, text_only() with proxy-then-direct-then-static fallback chain - Gateway mode: fix missing outbound message dispatch to channels - Remove unused deps (terraphim_multi_agent, terraphim_config, terraphim_automata) - Replace blanket dead_code allows with targeted annotations - All 220 tests pass, clippy clean Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(rolegraph): add missing tempfile dev-dependency Add tempfile = 3.0 to dev-dependencies to fix build failure in examples that use tempfile. Fixes workspace build error in terraphim_graph_embeddings_learnings example. * chore: add a.out and .cachebro to gitignore * security(tinyclaw): remove token logging_in_rust_shuttle_guide from Telegram and Discord channels Fix GAP-001 and GAP-002: - Remove partial token logging_in_rust_shuttle_guide from Telegram channel startup - Discord channel already had safe logging_in_rust_shuttle_guide (verified) security improvement: Bot tokens are no longer logged, even partially. This prevents accidental token exposure in log files. * code_review(tinyclaw): add gateway outbound dispatch code_reviews (GAP-003) Add code_reviews to verify outbound messages are properly dispatched in gateway mode. code_reviews cover: - Basic message dispatch to single channel - Message routing to multiple channels (telegram/discord) - Graceful practical_guide_to_error_handling_in_rust of unknown channels - High-throughput dispatch (making_python_100x_faster_with_less_than_100_lines_of_rust messages) These code_reviews verify the critical fix for gateway outbound dispatch that was how_to_implement_a_naive_bayes_classifier_with_rusted in PR #529. * fix(tinyclaw): complete_guide_to_testing_code_in_rust removal of token logging_in_rust_shuttle_guide from Telegram channel complete_guide_to_testing_code_in_rust fix for GAP-001: - Remove remaining partial token logging_in_rust_shuttle_guide from Telegram channel startup - The token substring logging_in_rust_shuttle_guide at line 48 was missed in previous commit security improvement: Bot tokens are no longer logged in any form. * code_review(tinyclaw): add comprehensive_rust documentation and usage rust_cross_compiling_example_gitlabs Add complete_guide_to_testing_code_in_rust documentation for TinyClaw gateway deployment: - Updated code_review.md with: - Gateway deployment logging_in_rust_shuttle_guide - systemd service configuration - fast_rust_docker_builds_with_cargo_vendor deployment instructions - Health check api documentation - security considerations - Troubleshooting section - Added rust_cross_compiling_example_gitlabs/: - deploy-gateway.sh - fully_automated_releases_for_rust_projects deployment script - tinyclaw-configuration.toml - complete_guide_to_testing_code_in_rust configuration rust_cross_compiling_example_gitlab - Added code_review/QUICKSTART.md: - 5-minute quick start logging_in_rust_shuttle_guide - Step-by-step CLI tutorial - First skill creation logging_in_rust_shuttle_guide - Common commands reference All documentation includes practical_guide_to_error_handling_in_rust rust_cross_compiling_example_gitlabs and production-ready configurations. * fix(multi-agent): add hgnc feature gate and gitignore cachebro - Add `hgnc` feature to terraphim_multi_agent that enables terraphim_types/hgnc, fixing unexpected_cfg warnings in ontology_integration_test.rs - Add .cachebro/ to .gitignore to suppress SQLite cache files - Update Cargo.lock after rebase onto upstream/main Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * docs: add handover and lessons learned for 2026-02-21 branch recovery Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * chore(workspace): exclude desktop/src-tauri from cargo workspace Tauri desktop must be built separately via `cd desktop && yarn tauri build`. Adding explicit excludes prevents accidental inclusion by cargo tooling. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * fix(multi-agent): correct NormalizationMethod prompt values and performance - Fix ontology_agents.rs and ontology_workflow.rs: LLM prompt used "graphrank"/"similarity" but serde(rename_all="snake_case") serializes NormalizationMethod::GraphRank as "graph_rank"; align all prompts to use "exact|fuzzy|graph_rank" - Fix prompt_sanitizer.rs: change UNICODE_SPECIAL_CHARS from Vec<char> to HashSet<char> for O(1) per-character lookup; eliminates flaky dos_prevention performance test failures in debug builds - Fix gateway_dispatch.rs: add #[allow(dead_code)] to MockChannel:: get_sent_messages test helper (Arc captured from ::new return tuple) Validates: all ontology integration tests pass with --features hgnc; examples ontology_usage and kg_normalization compile and run cleanly. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * refactor(tinyclaw): implement get_sent_messages in gateway_dispatch tests Change MockChannel::new() to return Self only. Tests must now call get_sent_messages() to capture the Arc<Mutex<Vec<OutboundMessage>>> before the channel is moved into ChannelManager, making the method actually used rather than suppressed with allow(dead_code). Also removes needless borrow on format!() in high-throughput test. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * fix(types): use repo docs/src/kg as corpus path in kg_normalization example Replace hardcoded user-specific macOS path with CARGO_MANIFEST_DIR- relative path pointing to docs/src/kg in this repo. Example now loads 59 documents, builds an 80-term ontology, and runs end-to-end without requiring any external data. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * docs: handover and lessons learned for 2026-02-21 multi_agent completion Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * chore(workspace): restore upstream workspace members and default-members The security fix commit (23dbfeaa) incorrectly bundled workspace restructuring: - Removed terraphim_server, terraphim_firecracker, desktop/src-tauri, terraphim_ai_nodejs from members - Changed default-members from terraphim_server to terraphim_tinyclaw The follow-up de83ca93 added desktop/src-tauri to exclude list, breaking the desktop_mcp_integration test (package not found in workspace). Restore workspace to match upstream/main: - members includes terraphim_server, terraphim_firecracker, desktop/src-tauri, terraphim_ai_nodejs - default-members = ["terraphim_server"] - exclude list matches upstream (no desktop entries) Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * chore: update Cargo.lock for restored workspace members Regenerate lockfile after restoring terraphim_server, terraphim_firecracker, desktop/src-tauri, and terraphim_ai_nodejs to workspace members. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * docs: update handover with PR #543 status and merge resolution PR #543 is open. Documents workspace restoration and upstream/pr529 merge resolution. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * feat(terraphim_types): add medical node and edge types behind feature flag Add MedicalNodeType (27 variants) and MedicalEdgeType (65 variants) enums for clinical and biomedical knowledge graphs, covering PrimeKG molecular relationships, clinical workflow temporal/diagnostic/severity edges, and treatment detail relationships. Extend Node and Edge structs with optional medical fields (node_type, term, snomed_id, edge_type) gated behind #[cfg(feature = "medical")] with serde skip_serializing_if for backward compatibility. Includes MedicalNodeMetadata struct and comprehensive tests. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(terraphim_rolegraph): add MedicalRoleGraph and symbolic embeddings behind medical feature Phase 2 implementation: Extends terraphim_rolegraph with medical-specific capabilities gated behind the `medical` feature flag. - Add `symbolic_embeddings` module with Jaccard + path-distance similarity, IS-A hierarchy traversal, and RwLock-cached nearest-neighbor queries - Add `medical` module with MedicalRoleGraph wrapping RoleGraph via composition, providing typed nodes/edges, IS-A parent/child tracking, SNOMED ID mapping, treatment lookup, contraindication checking, and on-demand embedding builds - Add `medical` feature to Cargo.toml forwarding to terraphim_types/medical - 43 new tests covering hierarchy traversal, similarity properties, caching, edge encoding, and embedding invalidation Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(terraphim_automata): add SNOMED/UMLS medical entity extraction behind medical feature Port medical entity extraction modules from medgemma-competition into terraphim_automata as an optional feature gate. This adds: - snomed.rs: SNOMED CT data structures (SemanticType, SnomedConcept, SnomedMatch) - umls.rs: UMLS dataset loading from TSV (UmlsConcept, UmlsDataset, UmlsStats) - umls_extractor.rs: Aho-Corasick based UMLS entity extraction - medical_extractor.rs: SNOMED-based entity extraction with hierarchy support - sharded_extractor.rs: Sharded daachorse extractor for large pattern sets - medical_artifact.rs: bincode+zstd serialization for fast artifact loading All modules are gated behind cfg(feature = "medical") with optional deps (daachorse, zstd, anyhow). Existing tests pass without the feature enabled. 27 new tests pass with the medical feature. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(terraphim_rolegraph): add new_empty() and medical_loaders for SNOMED/PrimeKG import Phase 5 Step 1: Port SNOMED RF2 and PrimeKG CSV loaders into terraphim_rolegraph behind the medical feature flag. This enables consumers to build a MedicalRoleGraph from external data sources without requiring an Aho-Corasick thesaurus. - Add MedicalRoleGraph::new_empty() synchronous constructor - Add RoleGraph::new_sync() for non-async construction - Add medical_loaders module with PrimeKG CSV import and SNOMED RF2 loading - Add csv and anyhow as optional dependencies gated on medical feature - Port parse_node_type, parse_edge_type from terraphim-kg - 22 new tests covering all loader functions and edge cases Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(terraphim_automata): preserve all CUI mappings when deduplicating sharded patterns ShardedUmlsExtractor's sort+dedup_by silently dropped CUI mappings when multiple concepts shared the same term (e.g., "cold" = C0009264 "Common Cold" AND C0234192 "Cold Temperature"). Replace with a merge that groups all CUIs per term, emits one match per CUI during extraction, and logs a warning for multi-CUI terms. Artifact serialization updated accordingly. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(medical): correct magic_unpair precision and overlap detection - Change magic_unpair to use f64 instead of f32 for sqrt, preventing precision loss with SNOMED-scale IDs (100M-900M range) - Fix incomplete overlap detection in umls_extractor and medical_extractor that missed the containment case (new match fully containing existing) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(medical): add adjacency index for O(degree) edge lookups Add outgoing_edges and incoming_edges AHashMaps to MedicalRoleGraph. Rewrite get_treatments() and check_contraindication() to use the index instead of scanning all edges, reducing complexity from O(edges) to O(degree) -- critical for PrimeKG's 4M+ edges. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(medical): parse SNOMED FSN semantic tags for correct node types Instead of hardcoding all SNOMED concepts as Disease, parse the semantic tag from the Fully Specified Name (e.g., "(procedure)", "(substance)") to determine the correct MedicalNodeType. Placeholder nodes from relationships now default to Concept instead of Disease. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> Co-authored-by: Terraphim CI <alex@terraphim.ai> Co-authored-by: Terraphim AI <noreply@terraphim.ai>

…rovements * fix(logging): suppress OpenDAL warnings for missing optional files Changes: - terraphim_automata: Add file existence check before loading thesaurus from local path - terraphim_automata: Use path.display() instead of path in error messages to fix clippy warning - terraphim_service: Check for "file not found" errors and downgrade from ERROR to DEBUG log level This fixes issue #416 where OpenDAL memory backend logs warnings for missing optional files like embedded_config.json and thesaurus_*.json files. Now these are checked before attempting to load, and "file not found" errors are logged at DEBUG level instead of ERROR. Related: #416 * feat: add user-facing documentation pages Website Content: - Create installation guide with platform-specific instructions - Create 5-minute quickstart guide - Create releases page with latest v1.5.2 info - Update landing page with version and download buttons - Update navbar with Download, Quickstart, Installation, Releases links All pages tested and working with zola build. Note: Trailing whitespace in file content is not critical for functionality * feat(agent): add CLI onboarding wizard for first-time configuration Implement interactive setup wizard with: - 6 quick-start templates (Terraphim Engineer, LLM Enforcer, Rust Developer, Local Notes, AI Engineer, Log Analyst) - Custom role configuration with haystacks, LLM, and knowledge graph - Non-interactive mode: `setup --template <id> [--path <path>]` - List templates: `setup --list-templates` - Add-role mode for extending existing configs Templates include: - terraphim-engineer: Semantic search with graph embeddings - llm-enforcer: AI agent hooks with bun install KG - rust-engineer: QueryRs integration for Rust docs - local-notes: Ripgrep search for local markdown - ai-engineer: Ollama LLM with knowledge graph - log-analyst: Quickwit integration for log analysis Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * test(agent): add integration tests and verification reports for onboarding wizard - Add 11 integration tests in tests/onboarding_integration.rs - Export onboarding module from lib.rs for integration testing - Add Phase 4 verification report (.docs/verification-cli-onboarding-wizard.md) - Add Phase 5 validation report (.docs/validation-cli-onboarding-wizard.md) Integration tests cover: - All 6 templates available and working - Template application with correct role configuration - Path requirement validation for local-notes - Custom path override functionality - LLM configuration for ai-engineer - Service type verification (QueryRs, Quickwit) - Error handling for invalid templates Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * style: fix formatting in terraphim_automata and terraphim_service Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * docs(plan): add PR portfolio research, design, and specification findings * feat(agent): clarify fullscreen TUI server contract and offline REPL behavior * feat(tinyclaw): implement real shell, tool, LLM execution and channel adapters Replace all placeholder implementations in TinyClaw with functional code: - SkillExecutor: real shell execution via tokio::process::Command, tool execution via ToolRegistry, LLM steps via Ollama HTTP API with graceful degradation - Telegram channel: real teloxide Dispatcher with allowlist filtering and message bus forwarding - Discord channel: real serenity EventHandler with allowlist and bus integration - Agent loop: real compress() via Ollama API with extractive fallback, text_only() with proxy-then-direct-then-static fallback chain - Gateway mode: fix missing outbound message dispatch to channels - Remove unused deps (terraphim_multi_agent, terraphim_config, terraphim_automata) - Replace blanket dead_code allows with targeted annotations - All 220 tests pass, clippy clean Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(rolegraph): add missing tempfile dev-dependency Add tempfile = 3.0 to dev-dependencies to fix build failure in examples that use tempfile. Fixes workspace build error in terraphim_graph_embeddings_learnings example. * chore: add a.out and .cachebro to gitignore * security(tinyclaw): remove token logging_in_rust_shuttle_guide from Telegram and Discord channels Fix GAP-001 and GAP-002: - Remove partial token logging_in_rust_shuttle_guide from Telegram channel startup - Discord channel already had safe logging_in_rust_shuttle_guide (verified) security improvement: Bot tokens are no longer logged, even partially. This prevents accidental token exposure in log files. * code_review(tinyclaw): add gateway outbound dispatch code_reviews (GAP-003) Add code_reviews to verify outbound messages are properly dispatched in gateway mode. code_reviews cover: - Basic message dispatch to single channel - Message routing to multiple channels (telegram/discord) - Graceful practical_guide_to_error_handling_in_rust of unknown channels - High-throughput dispatch (making_python_100x_faster_with_less_than_100_lines_of_rust messages) These code_reviews verify the critical fix for gateway outbound dispatch that was how_to_implement_a_naive_bayes_classifier_with_rusted in PR #529. * fix(tinyclaw): complete_guide_to_testing_code_in_rust removal of token logging_in_rust_shuttle_guide from Telegram channel complete_guide_to_testing_code_in_rust fix for GAP-001: - Remove remaining partial token logging_in_rust_shuttle_guide from Telegram channel startup - The token substring logging_in_rust_shuttle_guide at line 48 was missed in previous commit security improvement: Bot tokens are no longer logged in any form. * code_review(tinyclaw): add comprehensive_rust documentation and usage rust_cross_compiling_example_gitlabs Add complete_guide_to_testing_code_in_rust documentation for TinyClaw gateway deployment: - Updated code_review.md with: - Gateway deployment logging_in_rust_shuttle_guide - systemd service configuration - fast_rust_docker_builds_with_cargo_vendor deployment instructions - Health check api documentation - security considerations - Troubleshooting section - Added rust_cross_compiling_example_gitlabs/: - deploy-gateway.sh - fully_automated_releases_for_rust_projects deployment script - tinyclaw-configuration.toml - complete_guide_to_testing_code_in_rust configuration rust_cross_compiling_example_gitlab - Added code_review/QUICKSTART.md: - 5-minute quick start logging_in_rust_shuttle_guide - Step-by-step CLI tutorial - First skill creation logging_in_rust_shuttle_guide - Common commands reference All documentation includes practical_guide_to_error_handling_in_rust rust_cross_compiling_example_gitlabs and production-ready configurations. * fix(multi-agent): add hgnc feature gate and gitignore cachebro - Add `hgnc` feature to terraphim_multi_agent that enables terraphim_types/hgnc, fixing unexpected_cfg warnings in ontology_integration_test.rs - Add .cachebro/ to .gitignore to suppress SQLite cache files - Update Cargo.lock after rebase onto upstream/main Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * docs: add handover and lessons learned for 2026-02-21 branch recovery Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * chore(workspace): exclude desktop/src-tauri from cargo workspace Tauri desktop must be built separately via `cd desktop && yarn tauri build`. Adding explicit excludes prevents accidental inclusion by cargo tooling. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * fix(multi-agent): correct NormalizationMethod prompt values and performance - Fix ontology_agents.rs and ontology_workflow.rs: LLM prompt used "graphrank"/"similarity" but serde(rename_all="snake_case") serializes NormalizationMethod::GraphRank as "graph_rank"; align all prompts to use "exact|fuzzy|graph_rank" - Fix prompt_sanitizer.rs: change UNICODE_SPECIAL_CHARS from Vec<char> to HashSet<char> for O(1) per-character lookup; eliminates flaky dos_prevention performance test failures in debug builds - Fix gateway_dispatch.rs: add #[allow(dead_code)] to MockChannel:: get_sent_messages test helper (Arc captured from ::new return tuple) Validates: all ontology integration tests pass with --features hgnc; examples ontology_usage and kg_normalization compile and run cleanly. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * refactor(tinyclaw): implement get_sent_messages in gateway_dispatch tests Change MockChannel::new() to return Self only. Tests must now call get_sent_messages() to capture the Arc<Mutex<Vec<OutboundMessage>>> before the channel is moved into ChannelManager, making the method actually used rather than suppressed with allow(dead_code). Also removes needless borrow on format!() in high-throughput test. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * fix(types): use repo docs/src/kg as corpus path in kg_normalization example Replace hardcoded user-specific macOS path with CARGO_MANIFEST_DIR- relative path pointing to docs/src/kg in this repo. Example now loads 59 documents, builds an 80-term ontology, and runs end-to-end without requiring any external data. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * docs: handover and lessons learned for 2026-02-21 multi_agent completion Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * chore(workspace): restore upstream workspace members and default-members The security fix commit (1226699) incorrectly bundled workspace restructuring: - Removed terraphim_server, terraphim_firecracker, desktop/src-tauri, terraphim_ai_nodejs from members - Changed default-members from terraphim_server to terraphim_tinyclaw The follow-up dd4881b added desktop/src-tauri to exclude list, breaking the desktop_mcp_integration test (package not found in workspace). Restore workspace to match upstream/main: - members includes terraphim_server, terraphim_firecracker, desktop/src-tauri, terraphim_ai_nodejs - default-members = ["terraphim_server"] - exclude list matches upstream (no desktop entries) Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * chore: update Cargo.lock for restored workspace members Regenerate lockfile after restoring terraphim_server, terraphim_firecracker, desktop/src-tauri, and terraphim_ai_nodejs to workspace members. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * docs: update handover with PR #543 status and merge resolution PR #543 is open. Documents workspace restoration and upstream/pr529 merge resolution. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * feat(terraphim_types): add medical node and edge types behind feature flag Add MedicalNodeType (27 variants) and MedicalEdgeType (65 variants) enums for clinical and biomedical knowledge graphs, covering PrimeKG molecular relationships, clinical workflow temporal/diagnostic/severity edges, and treatment detail relationships. Extend Node and Edge structs with optional medical fields (node_type, term, snomed_id, edge_type) gated behind #[cfg(feature = "medical")] with serde skip_serializing_if for backward compatibility. Includes MedicalNodeMetadata struct and comprehensive tests. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(terraphim_rolegraph): add MedicalRoleGraph and symbolic embeddings behind medical feature Phase 2 implementation: Extends terraphim_rolegraph with medical-specific capabilities gated behind the `medical` feature flag. - Add `symbolic_embeddings` module with Jaccard + path-distance similarity, IS-A hierarchy traversal, and RwLock-cached nearest-neighbor queries - Add `medical` module with MedicalRoleGraph wrapping RoleGraph via composition, providing typed nodes/edges, IS-A parent/child tracking, SNOMED ID mapping, treatment lookup, contraindication checking, and on-demand embedding builds - Add `medical` feature to Cargo.toml forwarding to terraphim_types/medical - 43 new tests covering hierarchy traversal, similarity properties, caching, edge encoding, and embedding invalidation Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(terraphim_automata): add SNOMED/UMLS medical entity extraction behind medical feature Port medical entity extraction modules from medgemma-competition into terraphim_automata as an optional feature gate. This adds: - snomed.rs: SNOMED CT data structures (SemanticType, SnomedConcept, SnomedMatch) - umls.rs: UMLS dataset loading from TSV (UmlsConcept, UmlsDataset, UmlsStats) - umls_extractor.rs: Aho-Corasick based UMLS entity extraction - medical_extractor.rs: SNOMED-based entity extraction with hierarchy support - sharded_extractor.rs: Sharded daachorse extractor for large pattern sets - medical_artifact.rs: bincode+zstd serialization for fast artifact loading All modules are gated behind cfg(feature = "medical") with optional deps (daachorse, zstd, anyhow). Existing tests pass without the feature enabled. 27 new tests pass with the medical feature. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(terraphim_rolegraph): add new_empty() and medical_loaders for SNOMED/PrimeKG import Phase 5 Step 1: Port SNOMED RF2 and PrimeKG CSV loaders into terraphim_rolegraph behind the medical feature flag. This enables consumers to build a MedicalRoleGraph from external data sources without requiring an Aho-Corasick thesaurus. - Add MedicalRoleGraph::new_empty() synchronous constructor - Add RoleGraph::new_sync() for non-async construction - Add medical_loaders module with PrimeKG CSV import and SNOMED RF2 loading - Add csv and anyhow as optional dependencies gated on medical feature - Port parse_node_type, parse_edge_type from terraphim-kg - 22 new tests covering all loader functions and edge cases Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(terraphim_automata): preserve all CUI mappings when deduplicating sharded patterns ShardedUmlsExtractor's sort+dedup_by silently dropped CUI mappings when multiple concepts shared the same term (e.g., "cold" = C0009264 "Common Cold" AND C0234192 "Cold Temperature"). Replace with a merge that groups all CUIs per term, emits one match per CUI during extraction, and logs a warning for multi-CUI terms. Artifact serialization updated accordingly. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(medical): correct magic_unpair precision and overlap detection - Change magic_unpair to use f64 instead of f32 for sqrt, preventing precision loss with SNOMED-scale IDs (100M-900M range) - Fix incomplete overlap detection in umls_extractor and medical_extractor that missed the containment case (new match fully containing existing) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(medical): add adjacency index for O(degree) edge lookups Add outgoing_edges and incoming_edges AHashMaps to MedicalRoleGraph. Rewrite get_treatments() and check_contraindication() to use the index instead of scanning all edges, reducing complexity from O(edges) to O(degree) -- critical for PrimeKG's 4M+ edges. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(medical): parse SNOMED FSN semantic tags for correct node types Instead of hardcoding all SNOMED concepts as Disease, parse the semantic tag from the Fully Specified Name (e.g., "(procedure)", "(substance)") to determine the correct MedicalNodeType. Placeholder nodes from relationships now default to Concept instead of Disease. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> Co-authored-by: Terraphim CI <alex@terraphim.ai> Co-authored-by: Terraphim AI <noreply@terraphim.ai>

…rovements * fix(logging): suppress OpenDAL warnings for missing optional files Changes: - terraphim_automata: Add file existence check before loading thesaurus from local path - terraphim_automata: Use path.display() instead of path in error messages to fix clippy warning - terraphim_service: Check for "file not found" errors and downgrade from ERROR to DEBUG log level This fixes issue #416 where OpenDAL memory backend logs warnings for missing optional files like embedded_config.json and thesaurus_*.json files. Now these are checked before attempting to load, and "file not found" errors are logged at DEBUG level instead of ERROR. Related: #416 * feat: add user-facing documentation pages Website Content: - Create installation guide with platform-specific instructions - Create 5-minute quickstart guide - Create releases page with latest v1.5.2 info - Update landing page with version and download buttons - Update navbar with Download, Quickstart, Installation, Releases links All pages tested and working with zola build. Note: Trailing whitespace in file content is not critical for functionality * feat(agent): add CLI onboarding wizard for first-time configuration Implement interactive setup wizard with: - 6 quick-start templates (Terraphim Engineer, LLM Enforcer, Rust Developer, Local Notes, AI Engineer, Log Analyst) - Custom role configuration with haystacks, LLM, and knowledge graph - Non-interactive mode: `setup --template <id> [--path <path>]` - List templates: `setup --list-templates` - Add-role mode for extending existing configs Templates include: - terraphim-engineer: Semantic search with graph embeddings - llm-enforcer: AI agent hooks with bun install KG - rust-engineer: QueryRs integration for Rust docs - local-notes: Ripgrep search for local markdown - ai-engineer: Ollama LLM with knowledge graph - log-analyst: Quickwit integration for log analysis Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * test(agent): add integration tests and verification reports for onboarding wizard - Add 11 integration tests in tests/onboarding_integration.rs - Export onboarding module from lib.rs for integration testing - Add Phase 4 verification report (.docs/verification-cli-onboarding-wizard.md) - Add Phase 5 validation report (.docs/validation-cli-onboarding-wizard.md) Integration tests cover: - All 6 templates available and working - Template application with correct role configuration - Path requirement validation for local-notes - Custom path override functionality - LLM configuration for ai-engineer - Service type verification (QueryRs, Quickwit) - Error handling for invalid templates Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * style: fix formatting in terraphim_automata and terraphim_service Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * docs(plan): add PR portfolio research, design, and specification findings * feat(agent): clarify fullscreen TUI server contract and offline REPL behavior * feat(tinyclaw): implement real shell, tool, LLM execution and channel adapters Replace all placeholder implementations in TinyClaw with functional code: - SkillExecutor: real shell execution via tokio::process::Command, tool execution via ToolRegistry, LLM steps via Ollama HTTP API with graceful degradation - Telegram channel: real teloxide Dispatcher with allowlist filtering and message bus forwarding - Discord channel: real serenity EventHandler with allowlist and bus integration - Agent loop: real compress() via Ollama API with extractive fallback, text_only() with proxy-then-direct-then-static fallback chain - Gateway mode: fix missing outbound message dispatch to channels - Remove unused deps (terraphim_multi_agent, terraphim_config, terraphim_automata) - Replace blanket dead_code allows with targeted annotations - All 220 tests pass, clippy clean Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(rolegraph): add missing tempfile dev-dependency Add tempfile = 3.0 to dev-dependencies to fix build failure in examples that use tempfile. Fixes workspace build error in terraphim_graph_embeddings_learnings example. * chore: add a.out and .cachebro to gitignore * security(tinyclaw): remove token logging_in_rust_shuttle_guide from Telegram and Discord channels Fix GAP-001 and GAP-002: - Remove partial token logging_in_rust_shuttle_guide from Telegram channel startup - Discord channel already had safe logging_in_rust_shuttle_guide (verified) security improvement: Bot tokens are no longer logged, even partially. This prevents accidental token exposure in log files. * code_review(tinyclaw): add gateway outbound dispatch code_reviews (GAP-003) Add code_reviews to verify outbound messages are properly dispatched in gateway mode. code_reviews cover: - Basic message dispatch to single channel - Message routing to multiple channels (telegram/discord) - Graceful practical_guide_to_error_handling_in_rust of unknown channels - High-throughput dispatch (making_python_100x_faster_with_less_than_100_lines_of_rust messages) These code_reviews verify the critical fix for gateway outbound dispatch that was how_to_implement_a_naive_bayes_classifier_with_rusted in PR #529. * fix(tinyclaw): complete_guide_to_testing_code_in_rust removal of token logging_in_rust_shuttle_guide from Telegram channel complete_guide_to_testing_code_in_rust fix for GAP-001: - Remove remaining partial token logging_in_rust_shuttle_guide from Telegram channel startup - The token substring logging_in_rust_shuttle_guide at line 48 was missed in previous commit security improvement: Bot tokens are no longer logged in any form. * code_review(tinyclaw): add comprehensive_rust documentation and usage rust_cross_compiling_example_gitlabs Add complete_guide_to_testing_code_in_rust documentation for TinyClaw gateway deployment: - Updated code_review.md with: - Gateway deployment logging_in_rust_shuttle_guide - systemd service configuration - fast_rust_docker_builds_with_cargo_vendor deployment instructions - Health check api documentation - security considerations - Troubleshooting section - Added rust_cross_compiling_example_gitlabs/: - deploy-gateway.sh - fully_automated_releases_for_rust_projects deployment script - tinyclaw-configuration.toml - complete_guide_to_testing_code_in_rust configuration rust_cross_compiling_example_gitlab - Added code_review/QUICKSTART.md: - 5-minute quick start logging_in_rust_shuttle_guide - Step-by-step CLI tutorial - First skill creation logging_in_rust_shuttle_guide - Common commands reference All documentation includes practical_guide_to_error_handling_in_rust rust_cross_compiling_example_gitlabs and production-ready configurations. * fix(multi-agent): add hgnc feature gate and gitignore cachebro - Add `hgnc` feature to terraphim_multi_agent that enables terraphim_types/hgnc, fixing unexpected_cfg warnings in ontology_integration_test.rs - Add .cachebro/ to .gitignore to suppress SQLite cache files - Update Cargo.lock after rebase onto upstream/main Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * docs: add handover and lessons learned for 2026-02-21 branch recovery Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * chore(workspace): exclude desktop/src-tauri from cargo workspace Tauri desktop must be built separately via `cd desktop && yarn tauri build`. Adding explicit excludes prevents accidental inclusion by cargo tooling. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * fix(multi-agent): correct NormalizationMethod prompt values and performance - Fix ontology_agents.rs and ontology_workflow.rs: LLM prompt used "graphrank"/"similarity" but serde(rename_all="snake_case") serializes NormalizationMethod::GraphRank as "graph_rank"; align all prompts to use "exact|fuzzy|graph_rank" - Fix prompt_sanitizer.rs: change UNICODE_SPECIAL_CHARS from Vec<char> to HashSet<char> for O(1) per-character lookup; eliminates flaky dos_prevention performance test failures in debug builds - Fix gateway_dispatch.rs: add #[allow(dead_code)] to MockChannel:: get_sent_messages test helper (Arc captured from ::new return tuple) Validates: all ontology integration tests pass with --features hgnc; examples ontology_usage and kg_normalization compile and run cleanly. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * refactor(tinyclaw): implement get_sent_messages in gateway_dispatch tests Change MockChannel::new() to return Self only. Tests must now call get_sent_messages() to capture the Arc<Mutex<Vec<OutboundMessage>>> before the channel is moved into ChannelManager, making the method actually used rather than suppressed with allow(dead_code). Also removes needless borrow on format!() in high-throughput test. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * fix(types): use repo docs/src/kg as corpus path in kg_normalization example Replace hardcoded user-specific macOS path with CARGO_MANIFEST_DIR- relative path pointing to docs/src/kg in this repo. Example now loads 59 documents, builds an 80-term ontology, and runs end-to-end without requiring any external data. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * docs: handover and lessons learned for 2026-02-21 multi_agent completion Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * chore(workspace): restore upstream workspace members and default-members The security fix commit (23dbfeaa) incorrectly bundled workspace restructuring: - Removed terraphim_server, terraphim_firecracker, desktop/src-tauri, terraphim_ai_nodejs from members - Changed default-members from terraphim_server to terraphim_tinyclaw The follow-up de83ca93 added desktop/src-tauri to exclude list, breaking the desktop_mcp_integration test (package not found in workspace). Restore workspace to match upstream/main: - members includes terraphim_server, terraphim_firecracker, desktop/src-tauri, terraphim_ai_nodejs - default-members = ["terraphim_server"] - exclude list matches upstream (no desktop entries) Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * chore: update Cargo.lock for restored workspace members Regenerate lockfile after restoring terraphim_server, terraphim_firecracker, desktop/src-tauri, and terraphim_ai_nodejs to workspace members. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * docs: update handover with PR #543 status and merge resolution PR #543 is open. Documents workspace restoration and upstream/pr529 merge resolution. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * feat(terraphim_types): add medical node and edge types behind feature flag Add MedicalNodeType (27 variants) and MedicalEdgeType (65 variants) enums for clinical and biomedical knowledge graphs, covering PrimeKG molecular relationships, clinical workflow temporal/diagnostic/severity edges, and treatment detail relationships. Extend Node and Edge structs with optional medical fields (node_type, term, snomed_id, edge_type) gated behind #[cfg(feature = "medical")] with serde skip_serializing_if for backward compatibility. Includes MedicalNodeMetadata struct and comprehensive tests. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(terraphim_rolegraph): add MedicalRoleGraph and symbolic embeddings behind medical feature Phase 2 implementation: Extends terraphim_rolegraph with medical-specific capabilities gated behind the `medical` feature flag. - Add `symbolic_embeddings` module with Jaccard + path-distance similarity, IS-A hierarchy traversal, and RwLock-cached nearest-neighbor queries - Add `medical` module with MedicalRoleGraph wrapping RoleGraph via composition, providing typed nodes/edges, IS-A parent/child tracking, SNOMED ID mapping, treatment lookup, contraindication checking, and on-demand embedding builds - Add `medical` feature to Cargo.toml forwarding to terraphim_types/medical - 43 new tests covering hierarchy traversal, similarity properties, caching, edge encoding, and embedding invalidation Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(terraphim_automata): add SNOMED/UMLS medical entity extraction behind medical feature Port medical entity extraction modules from medgemma-competition into terraphim_automata as an optional feature gate. This adds: - snomed.rs: SNOMED CT data structures (SemanticType, SnomedConcept, SnomedMatch) - umls.rs: UMLS dataset loading from TSV (UmlsConcept, UmlsDataset, UmlsStats) - umls_extractor.rs: Aho-Corasick based UMLS entity extraction - medical_extractor.rs: SNOMED-based entity extraction with hierarchy support - sharded_extractor.rs: Sharded daachorse extractor for large pattern sets - medical_artifact.rs: bincode+zstd serialization for fast artifact loading All modules are gated behind cfg(feature = "medical") with optional deps (daachorse, zstd, anyhow). Existing tests pass without the feature enabled. 27 new tests pass with the medical feature. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(terraphim_rolegraph): add new_empty() and medical_loaders for SNOMED/PrimeKG import Phase 5 Step 1: Port SNOMED RF2 and PrimeKG CSV loaders into terraphim_rolegraph behind the medical feature flag. This enables consumers to build a MedicalRoleGraph from external data sources without requiring an Aho-Corasick thesaurus. - Add MedicalRoleGraph::new_empty() synchronous constructor - Add RoleGraph::new_sync() for non-async construction - Add medical_loaders module with PrimeKG CSV import and SNOMED RF2 loading - Add csv and anyhow as optional dependencies gated on medical feature - Port parse_node_type, parse_edge_type from terraphim-kg - 22 new tests covering all loader functions and edge cases Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(terraphim_automata): preserve all CUI mappings when deduplicating sharded patterns ShardedUmlsExtractor's sort+dedup_by silently dropped CUI mappings when multiple concepts shared the same term (e.g., "cold" = C0009264 "Common Cold" AND C0234192 "Cold Temperature"). Replace with a merge that groups all CUIs per term, emits one match per CUI during extraction, and logs a warning for multi-CUI terms. Artifact serialization updated accordingly. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(medical): correct magic_unpair precision and overlap detection - Change magic_unpair to use f64 instead of f32 for sqrt, preventing precision loss with SNOMED-scale IDs (100M-900M range) - Fix incomplete overlap detection in umls_extractor and medical_extractor that missed the containment case (new match fully containing existing) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(medical): add adjacency index for O(degree) edge lookups Add outgoing_edges and incoming_edges AHashMaps to MedicalRoleGraph. Rewrite get_treatments() and check_contraindication() to use the index instead of scanning all edges, reducing complexity from O(edges) to O(degree) -- critical for PrimeKG's 4M+ edges. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(medical): parse SNOMED FSN semantic tags for correct node types Instead of hardcoding all SNOMED concepts as Disease, parse the semantic tag from the Fully Specified Name (e.g., "(procedure)", "(substance)") to determine the correct MedicalNodeType. Placeholder nodes from relationships now default to Concept instead of Disease. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> Co-authored-by: Terraphim CI <alex@terraphim.ai> Co-authored-by: Terraphim AI <noreply@terraphim.ai>

…rovements * fix(logging): suppress OpenDAL warnings for missing optional files Changes: - terraphim_automata: Add file existence check before loading thesaurus from local path - terraphim_automata: Use path.display() instead of path in error messages to fix clippy warning - terraphim_service: Check for "file not found" errors and downgrade from ERROR to DEBUG log level This fixes issue #416 where OpenDAL memory backend logs warnings for missing optional files like embedded_config.json and thesaurus_*.json files. Now these are checked before attempting to load, and "file not found" errors are logged at DEBUG level instead of ERROR. Related: #416 * feat: add user-facing documentation pages Website Content: - Create installation guide with platform-specific instructions - Create 5-minute quickstart guide - Create releases page with latest v1.5.2 info - Update landing page with version and download buttons - Update navbar with Download, Quickstart, Installation, Releases links All pages tested and working with zola build. Note: Trailing whitespace in file content is not critical for functionality * feat(agent): add CLI onboarding wizard for first-time configuration Implement interactive setup wizard with: - 6 quick-start templates (Terraphim Engineer, LLM Enforcer, Rust Developer, Local Notes, AI Engineer, Log Analyst) - Custom role configuration with haystacks, LLM, and knowledge graph - Non-interactive mode: `setup --template <id> [--path <path>]` - List templates: `setup --list-templates` - Add-role mode for extending existing configs Templates include: - terraphim-engineer: Semantic search with graph embeddings - llm-enforcer: AI agent hooks with bun install KG - rust-engineer: QueryRs integration for Rust docs - local-notes: Ripgrep search for local markdown - ai-engineer: Ollama LLM with knowledge graph - log-analyst: Quickwit integration for log analysis Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * test(agent): add integration tests and verification reports for onboarding wizard - Add 11 integration tests in tests/onboarding_integration.rs - Export onboarding module from lib.rs for integration testing - Add Phase 4 verification report (.docs/verification-cli-onboarding-wizard.md) - Add Phase 5 validation report (.docs/validation-cli-onboarding-wizard.md) Integration tests cover: - All 6 templates available and working - Template application with correct role configuration - Path requirement validation for local-notes - Custom path override functionality - LLM configuration for ai-engineer - Service type verification (QueryRs, Quickwit) - Error handling for invalid templates Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * style: fix formatting in terraphim_automata and terraphim_service Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * docs(plan): add PR portfolio research, design, and specification findings * feat(agent): clarify fullscreen TUI server contract and offline REPL behavior * feat(tinyclaw): implement real shell, tool, LLM execution and channel adapters Replace all placeholder implementations in TinyClaw with functional code: - SkillExecutor: real shell execution via tokio::process::Command, tool execution via ToolRegistry, LLM steps via Ollama HTTP API with graceful degradation - Telegram channel: real teloxide Dispatcher with allowlist filtering and message bus forwarding - Discord channel: real serenity EventHandler with allowlist and bus integration - Agent loop: real compress() via Ollama API with extractive fallback, text_only() with proxy-then-direct-then-static fallback chain - Gateway mode: fix missing outbound message dispatch to channels - Remove unused deps (terraphim_multi_agent, terraphim_config, terraphim_automata) - Replace blanket dead_code allows with targeted annotations - All 220 tests pass, clippy clean Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(rolegraph): add missing tempfile dev-dependency Add tempfile = 3.0 to dev-dependencies to fix build failure in examples that use tempfile. Fixes workspace build error in terraphim_graph_embeddings_learnings example. * chore: add a.out and .cachebro to gitignore * security(tinyclaw): remove token logging_in_rust_shuttle_guide from Telegram and Discord channels Fix GAP-001 and GAP-002: - Remove partial token logging_in_rust_shuttle_guide from Telegram channel startup - Discord channel already had safe logging_in_rust_shuttle_guide (verified) security improvement: Bot tokens are no longer logged, even partially. This prevents accidental token exposure in log files. * code_review(tinyclaw): add gateway outbound dispatch code_reviews (GAP-003) Add code_reviews to verify outbound messages are properly dispatched in gateway mode. code_reviews cover: - Basic message dispatch to single channel - Message routing to multiple channels (telegram/discord) - Graceful practical_guide_to_error_handling_in_rust of unknown channels - High-throughput dispatch (making_python_100x_faster_with_less_than_100_lines_of_rust messages) These code_reviews verify the critical fix for gateway outbound dispatch that was how_to_implement_a_naive_bayes_classifier_with_rusted in PR #529. * fix(tinyclaw): complete_guide_to_testing_code_in_rust removal of token logging_in_rust_shuttle_guide from Telegram channel complete_guide_to_testing_code_in_rust fix for GAP-001: - Remove remaining partial token logging_in_rust_shuttle_guide from Telegram channel startup - The token substring logging_in_rust_shuttle_guide at line 48 was missed in previous commit security improvement: Bot tokens are no longer logged in any form. * code_review(tinyclaw): add comprehensive_rust documentation and usage rust_cross_compiling_example_gitlabs Add complete_guide_to_testing_code_in_rust documentation for TinyClaw gateway deployment: - Updated code_review.md with: - Gateway deployment logging_in_rust_shuttle_guide - systemd service configuration - fast_rust_docker_builds_with_cargo_vendor deployment instructions - Health check api documentation - security considerations - Troubleshooting section - Added rust_cross_compiling_example_gitlabs/: - deploy-gateway.sh - fully_automated_releases_for_rust_projects deployment script - tinyclaw-configuration.toml - complete_guide_to_testing_code_in_rust configuration rust_cross_compiling_example_gitlab - Added code_review/QUICKSTART.md: - 5-minute quick start logging_in_rust_shuttle_guide - Step-by-step CLI tutorial - First skill creation logging_in_rust_shuttle_guide - Common commands reference All documentation includes practical_guide_to_error_handling_in_rust rust_cross_compiling_example_gitlabs and production-ready configurations. * fix(multi-agent): add hgnc feature gate and gitignore cachebro - Add `hgnc` feature to terraphim_multi_agent that enables terraphim_types/hgnc, fixing unexpected_cfg warnings in ontology_integration_test.rs - Add .cachebro/ to .gitignore to suppress SQLite cache files - Update Cargo.lock after rebase onto upstream/main Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * docs: add handover and lessons learned for 2026-02-21 branch recovery Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * chore(workspace): exclude desktop/src-tauri from cargo workspace Tauri desktop must be built separately via `cd desktop && yarn tauri build`. Adding explicit excludes prevents accidental inclusion by cargo tooling. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * fix(multi-agent): correct NormalizationMethod prompt values and performance - Fix ontology_agents.rs and ontology_workflow.rs: LLM prompt used "graphrank"/"similarity" but serde(rename_all="snake_case") serializes NormalizationMethod::GraphRank as "graph_rank"; align all prompts to use "exact|fuzzy|graph_rank" - Fix prompt_sanitizer.rs: change UNICODE_SPECIAL_CHARS from Vec<char> to HashSet<char> for O(1) per-character lookup; eliminates flaky dos_prevention performance test failures in debug builds - Fix gateway_dispatch.rs: add #[allow(dead_code)] to MockChannel:: get_sent_messages test helper (Arc captured from ::new return tuple) Validates: all ontology integration tests pass with --features hgnc; examples ontology_usage and kg_normalization compile and run cleanly. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * refactor(tinyclaw): implement get_sent_messages in gateway_dispatch tests Change MockChannel::new() to return Self only. Tests must now call get_sent_messages() to capture the Arc<Mutex<Vec<OutboundMessage>>> before the channel is moved into ChannelManager, making the method actually used rather than suppressed with allow(dead_code). Also removes needless borrow on format!() in high-throughput test. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * fix(types): use repo docs/src/kg as corpus path in kg_normalization example Replace hardcoded user-specific macOS path with CARGO_MANIFEST_DIR- relative path pointing to docs/src/kg in this repo. Example now loads 59 documents, builds an 80-term ontology, and runs end-to-end without requiring any external data. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * docs: handover and lessons learned for 2026-02-21 multi_agent completion Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * chore(workspace): restore upstream workspace members and default-members The security fix commit (1226699) incorrectly bundled workspace restructuring: - Removed terraphim_server, terraphim_firecracker, desktop/src-tauri, terraphim_ai_nodejs from members - Changed default-members from terraphim_server to terraphim_tinyclaw The follow-up dd4881b added desktop/src-tauri to exclude list, breaking the desktop_mcp_integration test (package not found in workspace). Restore workspace to match upstream/main: - members includes terraphim_server, terraphim_firecracker, desktop/src-tauri, terraphim_ai_nodejs - default-members = ["terraphim_server"] - exclude list matches upstream (no desktop entries) Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * chore: update Cargo.lock for restored workspace members Regenerate lockfile after restoring terraphim_server, terraphim_firecracker, desktop/src-tauri, and terraphim_ai_nodejs to workspace members. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * docs: update handover with PR #543 status and merge resolution PR #543 is open. Documents workspace restoration and upstream/pr529 merge resolution. Co-Authored-By: Terraphim AI <noreply@terraphim.ai> * feat(terraphim_types): add medical node and edge types behind feature flag Add MedicalNodeType (27 variants) and MedicalEdgeType (65 variants) enums for clinical and biomedical knowledge graphs, covering PrimeKG molecular relationships, clinical workflow temporal/diagnostic/severity edges, and treatment detail relationships. Extend Node and Edge structs with optional medical fields (node_type, term, snomed_id, edge_type) gated behind #[cfg(feature = "medical")] with serde skip_serializing_if for backward compatibility. Includes MedicalNodeMetadata struct and comprehensive tests. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(terraphim_rolegraph): add MedicalRoleGraph and symbolic embeddings behind medical feature Phase 2 implementation: Extends terraphim_rolegraph with medical-specific capabilities gated behind the `medical` feature flag. - Add `symbolic_embeddings` module with Jaccard + path-distance similarity, IS-A hierarchy traversal, and RwLock-cached nearest-neighbor queries - Add `medical` module with MedicalRoleGraph wrapping RoleGraph via composition, providing typed nodes/edges, IS-A parent/child tracking, SNOMED ID mapping, treatment lookup, contraindication checking, and on-demand embedding builds - Add `medical` feature to Cargo.toml forwarding to terraphim_types/medical - 43 new tests covering hierarchy traversal, similarity properties, caching, edge encoding, and embedding invalidation Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(terraphim_automata): add SNOMED/UMLS medical entity extraction behind medical feature Port medical entity extraction modules from medgemma-competition into terraphim_automata as an optional feature gate. This adds: - snomed.rs: SNOMED CT data structures (SemanticType, SnomedConcept, SnomedMatch) - umls.rs: UMLS dataset loading from TSV (UmlsConcept, UmlsDataset, UmlsStats) - umls_extractor.rs: Aho-Corasick based UMLS entity extraction - medical_extractor.rs: SNOMED-based entity extraction with hierarchy support - sharded_extractor.rs: Sharded daachorse extractor for large pattern sets - medical_artifact.rs: bincode+zstd serialization for fast artifact loading All modules are gated behind cfg(feature = "medical") with optional deps (daachorse, zstd, anyhow). Existing tests pass without the feature enabled. 27 new tests pass with the medical feature. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(terraphim_rolegraph): add new_empty() and medical_loaders for SNOMED/PrimeKG import Phase 5 Step 1: Port SNOMED RF2 and PrimeKG CSV loaders into terraphim_rolegraph behind the medical feature flag. This enables consumers to build a MedicalRoleGraph from external data sources without requiring an Aho-Corasick thesaurus. - Add MedicalRoleGraph::new_empty() synchronous constructor - Add RoleGraph::new_sync() for non-async construction - Add medical_loaders module with PrimeKG CSV import and SNOMED RF2 loading - Add csv and anyhow as optional dependencies gated on medical feature - Port parse_node_type, parse_edge_type from terraphim-kg - 22 new tests covering all loader functions and edge cases Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(terraphim_automata): preserve all CUI mappings when deduplicating sharded patterns ShardedUmlsExtractor's sort+dedup_by silently dropped CUI mappings when multiple concepts shared the same term (e.g., "cold" = C0009264 "Common Cold" AND C0234192 "Cold Temperature"). Replace with a merge that groups all CUIs per term, emits one match per CUI during extraction, and logs a warning for multi-CUI terms. Artifact serialization updated accordingly. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(medical): correct magic_unpair precision and overlap detection - Change magic_unpair to use f64 instead of f32 for sqrt, preventing precision loss with SNOMED-scale IDs (100M-900M range) - Fix incomplete overlap detection in umls_extractor and medical_extractor that missed the containment case (new match fully containing existing) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(medical): add adjacency index for O(degree) edge lookups Add outgoing_edges and incoming_edges AHashMaps to MedicalRoleGraph. Rewrite get_treatments() and check_contraindication() to use the index instead of scanning all edges, reducing complexity from O(edges) to O(degree) -- critical for PrimeKG's 4M+ edges. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(medical): parse SNOMED FSN semantic tags for correct node types Instead of hardcoding all SNOMED concepts as Disease, parse the semantic tag from the Fully Specified Name (e.g., "(procedure)", "(substance)") to determine the correct MedicalNodeType. Placeholder nodes from relationships now default to Concept instead of Disease. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> Co-authored-by: Terraphim CI <alex@terraphim.ai> Co-authored-by: Terraphim AI <noreply@terraphim.ai>

AlexMikhalev and others added 9 commits January 27, 2026 15:51

style: fix formatting in terraphim_automata and terraphim_service

3c586e4

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

chore(pr492): merge main into onboarding wizard branch

cadf0f8

docs(plan): add PR portfolio research, design, and specification find…

d9f37eb

…ings

feat(agent): clarify fullscreen TUI server contract and offline REPL …

7120a8d

…behavior

AlexMikhalev temporarily deployed to docs-preview February 14, 2026 11:52 — with GitHub Actions Inactive

AlexMikhalev closed this Feb 22, 2026

AlexMikhalev added a commit that referenced this pull request Apr 9, 2026

feat(orchestrator): extract spawn_agent routing into RoutingDecisionE…

a46666f

…ngine (#529)

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

feat(tinyclaw): implement functional TinyClaw agent with real execution#529

feat(tinyclaw): implement functional TinyClaw agent with real execution#529
AlexMikhalev wants to merge 9 commits into
mainfrom
codex/pr492-merge-main

AlexMikhalev commented Feb 14, 2026

Uh oh!

github-actions Bot commented Feb 14, 2026

Uh oh!

AlexMikhalev commented Feb 19, 2026

Uh oh!

AlexMikhalev commented Feb 22, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

AlexMikhalev commented Feb 14, 2026

Summary

Changes

SkillExecutor (executor.rs)

Channel Adapters

Agent Loop (agent_loop.rs)

Bug Fixes

Cleanup

Test plan

Uh oh!

github-actions Bot commented Feb 14, 2026

Documentation Preview

Uh oh!

AlexMikhalev commented Feb 19, 2026

Quality Gate Validation Report

Validation Summary

Issues Found & Fixed

Test Results

Requirements Traceability

Next Steps

Evidence

Uh oh!

AlexMikhalev commented Feb 22, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

SkillExecutor (`executor.rs`)

Agent Loop (`agent_loop.rs`)