Each pipeline phase owns one llama-server slot (steward 0, orchestrator
1, synthesizer 2), carried as id_slot in extra_body through the same
mechanism tool_choice already uses, so the phase's stable prompt prefix
stays in that slot's KV cache and a turn re-prefills only its new
tokens. Off by default; a no-op on the Claude backend and ignored by
Ollama, so the flag is safe on any backend and the cutover itself stays
a pure env swap.
The merge helper preserves existing extra_body keys — mutation-checked
(dropping the merge fails exactly the test written for it).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Three native-API touchpoints converted — steward /api/generate to
/v1/chat/completions, embeddings /api/embeddings to /v1/embeddings,
health /api/tags to /v1/models — so the backend behind OLLAMA_HOST is
swappable by env alone. This makes the serving plan's "tatlock needs
zero changes" claim true for the llama-server cutover and for forge
after it. EMBEDDING_HOST (default: OLLAMA_HOST) lets gen and embed
point at different servers, which the boilerroom stack needs.
The dead OllamaClient goes with it: a native-API client nothing
imported, whose presence would make the post-cutover "no native
endpoints" grep lie.
Contract tests rewritten to mirror the new requests and extended with
the embeddings shape (dim must match the configured Qdrant dimension).
All pass against live Ollama's /v1 — deployable before any cutover.
Both new assertions mutation-checked via env overrides (bogus model,
wrong dim: each fails). The Anthropic contract now skips on 401: the
configured key is deliberately revoked per workspace D-11, which is
"fallback disabled", not a boundary break. Embedding continuity across
backends was measured separately: same nomic bytes, cosine 1.0000.
663 unit tests pass; ruff clean.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Mechanical only, and separated from the judgment calls that follow so the
reviewable changes are not buried in a 98-file whitespace diff.
227 automatic fixes: 60 blank lines carrying whitespace, 60 unsorted import
blocks, 34 Optional[X] to X | None, 28 unused imports, 16 deprecated typing
imports, 12 datetime.timezone.utc to datetime.UTC, and assorted smaller
modernisations. Then `ruff format` over src and tests: 98 files reformatted,
35 already conforming.
No file among the unused-import findings defines __all__ or is an __init__.py,
so nothing here removes a re-export.
`make test`: 658 passed, unchanged from HEAD.
Two things observed while verifying, neither addressed here:
`pytest tests/` cannot collect — tests/e2e/test_orchestration_e2e.py uses an
`e2e` marker that is not registered, and the config is strict about markers.
This fails identically at HEAD, so it predates this change; `make test` passes
because it ignores tests/e2e, tests/integration and tests/contracts.
test_tatlock_tool_call_logging_calculator is flaky. It failed once in a full run
with these changes and passed on the next, passes in isolation with them, and
fails in isolation at HEAD. It is order- or timing-dependent, not a regression
from this commit — established by running the full suite both ways rather than
by reasoning about which change could have caused it.
Co-Authored-By: Claude <noreply@anthropic.com>
The homelab is retiring *.schweitz.internal and will rebind host
ports to loopback; container-to-container traffic must use container
names on docker-dataplane.
- SEARXNG_HOST: http://localhost:8087 -> http://searxng:8080
(SearXNG's internal port is 8080; 8087 was the host-published port)
- LIBRARY_DESK_HOST: http://localhost:8089 -> http://library-desk:8089
- CORE_API_HOST: http://localhost:8090 -> http://core-api:8083
(8090 is the Scheduler's host port; Core-API serves 8083 internally,
confirmed by the housekeeper client and test suite hitting :8083)
- scripts/test_housekeeper.sh: reach Core-API via localhost:8083
instead of the LAN IP, which will refuse after loopback rebinding
Local development against host-published ports keeps working via .env
overrides (.env.example unchanged; localhost stays valid on the host).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The request-level tenant guard compared the raw user string exactly
(user == PRODUCTION_TENANT), but all local namespaces (Qdrant
collections, Redis keys) are derived through sanitize_user_id(), which
lowercases and strips/maps punctuation. Case or punctuation variants
("JPMSchweitzer", "jpmschweitzer.", " jpmschweitzer") therefore passed
the guard yet resolved to the production namespaces, letting a dev
instance on the shared services read/write production tenant data.
- context.py: compare sanitize_user_id(user) against the sanitized
production tenant; expose the guard as public apply_tenant_guard()
- config.py: startup refusal validator uses the same sanitized
comparison, so a colliding DEFAULT_USER refuses startup loudly
instead of relying on the allowlist fallback
- tests: variant matrix at both config and request-context level,
plus a non-colliding passthrough case
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Non-production environments (development/testing) now force the
effective tenant to the reserved test tenant "llm_tester" (or a
test_-prefixed override) regardless of DEFAULT_USER misconfiguration:
- Config.effective_default_user only honors DEFAULT_USER outside
production when it is llm_tester or test_-prefixed; anything else
is forced to llm_tester (tenant_forced flags the override)
- Config refuses startup (validation error) when a non-production
environment is explicitly configured with the production tenant
jpmschweitzer
- get_user() applies the same guard at request-context resolution,
so an explicit request for the production tenant in dev/test is
forced to llm_tester with a warning log
- initialize_application() emits one loud startup log line
(tenant_guard_active / tenant_guard_production) stating the
effective tenant
Unit tests cover the dev/test/prod x default/explicit-user matrix.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- add LIBRARIAN_TIMEOUT config (default 180s) and enforce it with
asyncio.wait_for inside delegate_to_librarian, covering the live
paths (steward direct delegation and SSE streaming) that had no cap
- timeouts fail honestly: success=False with a curated butler sentence,
detail in logs
- set an explicit timeout on TatlockOllamaProvider's AsyncOpenAI client
from OLLAMA_TIMEOUT instead of the SDK default (~600s per LLM call)
- remove the contradictory unused 60s default from
AgentRequest.timeout_seconds; coordination falls back to the
configured budget
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Rolls back the claudification backend preference: PREFER_CLOUD_BACKEND now
defaults to false, resolve_backend() picks Ollama first and uses Claude when
explicitly preferred or when the new Ollama startup health check fails. The
Steward retries mid-request failures on the other backend in both directions.
Also hardens the fallback itself: Anthropic SDK imports are lazy so a broken
anthropic package degrades to Ollama-only instead of crashing at import time
(root cause of the production outage since April), anthropic is pinned to a
pydantic-ai-1.27-compatible range, ANTHROPIC_MODEL defaults to claude-sonnet-5
(sonnet-4-20250514 retired 2026-06-15), sampling parameters are stripped from
Claude calls (Sonnet 5 rejects them), and the Steward timeout is configurable
(STEWARD_TIMEOUT, default 60s) since gemma4 needs ~35s warm for analysis.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
gemma4:e2b has native function calling with dedicated tool tokens,
achieving 100% tool selection accuracy in benchmarks vs 67% for
mistral-nemo-large, with 5-8x faster response times (2-4s vs 15-20s)
and lower VRAM usage (8GB vs 9.2GB).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
All agents now prefer Claude API when ANTHROPIC_API_KEY is configured,
with automatic fallback to Ollama when offline or unconfigured. New
src/anthropic/ module provides model selection via get_model() factory.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove the Redis-backed performance benchmarking in favor of the new
lightweight file-based tracing system which provides better debugging
capabilities for local development.
- Delete src/core/benchmarks.py
- Remove ENABLE_BENCHMARKS, REDIS_BENCHMARK_DB, redis_url from config
- Update memory_cache comment (now uses DB 1)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements The Housekeeper, a new expert agent for home automation
following the Librarian pattern. Communicates with core-api service
which wraps Home Assistant REST API.
New agent features:
- CoreAPIClient with 13 home automation methods
- 13 tools: list_areas, list_devices, get_device_state, turn_on,
turn_off, toggle, list_scenes, activate_scene, list_scripts,
run_script, list_automations, toggle_automation, get_history
- PydanticAI agent with butler-friendly system prompt
- HouseholdCapability registration for Steward coordination
- delegate_to_housekeeper() wrapper for orchestration
Also includes:
- Dev port changed from 8123 to 8777 (avoids Home Assistant conflict)
- Config: CORE_API_HOST, CORE_API_KEY, CORE_API_TIMEOUT
- 44 unit tests for client and capability
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
### Added
- Environment-aware configuration:
- Auto-selected logging (DEBUG for dev, WARNING for prod)
- Auto-selected default user (llm_tester for dev isolation)
- User context logging at request entry
- Direct delegation bypass:
- Pure memory/librarian requests skip Tatlock LLM
- Reduces latency for memory-only requests
- Text-based delegation fallback:
- Parse [DELEGATE:agent] patterns from LLM output
- Sequential and parallel execution support
- Comprehensive E2E test suite:
- 22 orchestration tests with QdrantVerifier
- assert_llm_behavior() for flexible pattern matching
- Tests for memory, delegation, isolation, scenarios
### Fixed
- Unit test mocks for streaming (async generator)
- Temporal context handling in tests
- LLM non-determinism with pytest.xfail()
- Streaming test timeouts increased
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix Qdrant client to use query_points API (qdrant-client >= 1.10)
- Rename REDIS_DB to REDIS_BENCHMARK_DB for clarity
- Update Redis defaults to match stack allocation (benchmark=6, memory=1)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add _get_version_from_pyproject() function to config.py
- APP_VERSION now uses default_factory to load from pyproject.toml
- Add pyproject.toml to Docker build for version detection
- Add LIBRARY_DESK configuration settings
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add SEARXNG_HOST config with localhost:8087 default
- Add SEARXNG_TIMEOUT setting (30 seconds default)
- Update .env.example with SearXNG configuration
- Supports both local and production SearXNG instances
Version increment to mark basic setup completion milestone.
Changes:
- Updated APP_VERSION to 0.1.1 in src/core/config.py
- Released CHANGELOG.md [Unreleased] section as [0.1.1]
- Updated version links to use git.schweitz.net repository
This version represents the completion of all core infrastructure:
- Agent interface and implementations
- Responses API with full feature set
- Chat Completions wrapper
- Comprehensive test coverage (95 tests, 78.95%)
- Production-ready architecture
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Implement global application configuration and custom Pydantic models
following FastAPI best practices.
Core Configuration (src/core/config.py):
- BaseSettings with environment variable support
- Split configuration by domain (following best practices)
- Ollama connection settings (host, model, timeouts)
- API configuration (host, port, prefix)
- CORS settings
- 20-second streaming timeout per turn
- Cached configuration with @lru_cache
Custom Base Models (src/core/models.py):
- CustomBaseModel for consistent serialization
- ISO datetime formatting
- Alias population support
- Enum value serialization
- Validation on assignment
- serializable_dict() for logging/debugging
Exception Handling (src/core/exceptions.py):
- Base AppException with status codes
- OllamaConnectionError (503)
- OllamaTimeoutError (504)
- ModelNotFoundError (404)
- ValidationError (422)
- OpenAI-compatible error structure
Benefits:
- Consistent configuration across domains
- Type-safe settings with validation
- Easy environment override via .env
- Predictable error responses
- Better debugging with serializable models
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
