jpmschweitzer/tatlock
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 5 Wiki Activity
128 Commits 1 Branch 52 Tags
f853db8cccd5ae96b63463c7a5f35cd85b7939a0
Commit Graph
5 Commits
Author SHA1 Message Date
jpmschweitzerandClaude Fable 5 f853db8ccc fix(agents): make librarian failures structured and user-safe 
- run_librarian / run_librarian_stream raise AgentError instead of
  returning/yielding error text as normal output; detail stays in logs
- delegate_to_* wrappers now put a curated butler-toned sentence in
  DelegationResult.output on failure and never expose str(e), so
  streaming's error branch is reachable and honest
- _execute_single_delegation propagates success; direct delegation only
  records delegate_to_* as called when the expert actually succeeded
- librarian tools return user-safe messages instead of
  'Error searching: {e}' strings that leaked internal URLs into
  synthesis; coordination stream errors are curated as well
- ruff cleanups (TYPE_CHECKING forward refs, B904, unused locals) in
  the touched files to keep them lint-clean

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-07-14 10:12:30 +02:00
jpmschweitzerandClaude Fable 5 59f5b54ac9 fix(librarian): map live HybridRAG response fields correctly 
The client parsed field names the live library-desk service never
returns, so every result rendered as "unknown (score: 0.00)":

- source_type/sources -> source + sources (icons key off sources values)
- rrf_score -> score
- context -> formatted_context
- related_dossiers are per-result; top level aggregates unique titles
- synonyms live inside the keywords dict as a {term: [synonyms]} map

Also stop sending zero limits (service 422s on limit < 1); disabled
legs now rely on the enable_* flags with limits clamped to >= 1.

Adds a recorded live response as a fixture plus contract tests that
pin the mapping (non-unknown sources, non-zero scores, icon coverage).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-07-14 10:00:10 +02:00
jpmschweitzerandClaude Opus 4.5 100ebeae52 feat: migrate web search from tatlock_core to Librarian 
Move web search functionality to The Librarian agent, integrating with
the library-desk /rag/search endpoint for enhanced search capabilities.

Changes:
- Add search_web, read_url, read_urls_batch tools to Librarian
- Add WebSearchResult, ContentExtractionResult models to client
- Add search_web, extract_content, extract_content_batch client methods
- Update Librarian capability with web/url/internet domains
- Remove search_web from tatlock_core tools and toolset
- Update Tatlock system prompt to delegate web search to Librarian
- Add comprehensive unit tests for new Librarian tools
- Clean up legacy src/agents/tools.py

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-15 18:30:16 +01:00
jpmschweitzerandClaude Opus 4.5 4efa717796 fix: improve Steward delegation instructions for Librarian
Build and Push / build (release) Successful in 10s
Details 
- Update Librarian capability description to highlight CREATE/UPDATE/SEARCH
- Add specific Steward guidelines for wiki creation, updates, and research
- Add dynamic time injection to user prompts for temporal awareness
- Expand domains to include 'create', 'write', 'update'
- Update test to match new capability description

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-11 21:55:17 +01:00
jpmschweitzerandClaude Opus 4.5 22d44b3071 test(phase3): add comprehensive tests for multi-agent coordination 
Protocol tests (16):
- AgentRequest/AgentResponse serialization
- DelegationIntent and DelegationReason validation
- CoordinationResult aggregation
- Error type tests

Coordination tests (14):
- Engine initialization and agent availability
- Delegation execution (success, error, timeout)
- Multi-intent coordination
- Streaming delegation

Librarian tests (42):
- Library-desk client (all endpoints)
- Wiki operations (search, get, create, update)
- Smart-create with HybridRAG
- Capability registration
- Response model validation

Total: 72 new tests, all passing

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-11 21:30:43 +01:00