A 429 usage_limit_reached response during verify_connection() caused the
server to refuse to start entirely. Quota exhaustion is not a configuration
error — the server should start and serve retain/recall requests normally,
it just can't make LLM calls until the quota resets.
Co-authored-by: Marco Rutsch <marco@rutimka.de>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(claude-code): implement tool_choice support for forced tool calls
The call_with_tools() method now properly handles the tool_choice parameter
to force specific tool calls. Previously, the parameter was accepted but ignored,
causing the reflect agent to fail when trying to force specific tools on each
iteration.
Fixes#732
Changes:
- When tool_choice forces a specific function: filter allowed_tools to only
that tool (with mcp prefix) and add a strong system prompt instruction
- When tool_choice is 'required': add instruction that model must call at
least one tool
- When tool_choice is 'none': clear allowed_tools and mcp_servers to disable
all tools
- When tool_choice is 'auto' (default): no change (existing behavior)
This matches the approach used in the OpenAI provider while adapting to the
Claude Agent SDK's lack of native tool_choice parameter by using allowed_tools
filtering and system prompt instructions.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* style: fix ruff formatting in alembic migration
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Port fixes from #461 (claude_code_llm) to codex_llm:
- Replace json.dumps(result) with result.model_dump_json() for Pydantic models to fix TypeError during consolidation
- Wrap record_llm_call tracing block in try/except so logging failures never propagate to retry handler
Co-authored-by: Marco Rutsch <marco@rutimka.de>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add 'ark' and 'volcano' as valid LLM providers (both are aliases for Volcano Engine)
- Set default model to 'doubao-pro-32k' for both providers
- Add them to OpenAICompatibleLLM provider list
- Exclude from json_object response format support
Co-authored-by: yishun.eason <yishun.eason@bytedance.com>
Adds a proper 'none' provider option so users can run Hindsight as a
chunk store with semantic search but without any LLM dependency, replacing
the hacky workaround of setting provider to 'mock'.
When HINDSIGHT_API_LLM_PROVIDER=none:
- Retain automatically uses chunks mode (no fact extraction)
- Recall works normally (semantic search, BM25, graph retrieval)
- Reflect returns HTTP 400 with clear error message
- Consolidation/observations are disabled
- Mental model refresh returns HTTP 400
- No API key required
* feat: add LiteLLM LLM provider for Bedrock and 100+ providers
Add a new `litellm` LLM provider that uses the LiteLLM SDK for chat
completions and tool calling, enabling AWS Bedrock and 100+ other
providers for Hindsight's core engine (retain, recall, reflect).
- New LiteLLMLLM provider in engine/providers/litellm_llm.py
- Registered in factory, valid providers list, and no-api-key set
- Refactored API key validation to use requires_api_key() helper
- Added boto3 dependency for Bedrock auth
- Updated docs: configuration, models, monitoring, providers grid
* feat: add bedrock as first-class LLM provider alias
Add `bedrock` as a dedicated provider name that auto-prepends the
`bedrock/` prefix to model names and delegates to LiteLLMLLM under
the hood. This makes Bedrock support more discoverable — users set
`HINDSIGHT_API_LLM_PROVIDER=bedrock` with plain Bedrock model IDs.
* test: add Bedrock to CI provider tests
- Add bedrock/us.amazon.nova-lite-v1:0 to MODEL_MATRIX in test_llm_provider.py
- Add AWS credential check in should_skip_provider()
- Pass AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_REGION_NAME secrets to test-api job
- Update default bedrock model to amazon.nova-2-lite-v1:0
* fix: regenerate docs skill files and bump memory test timeout
- Regenerate skills/hindsight-docs references after docs changes
- Bump test_llm_provider_memory_operations timeout to 600s for slower
providers like Bedrock via LiteLLM
* test: skip bedrock lite models in memory operations test
Nova Lite has a 10K output token limit which is too low for fact
extraction (requires 64K). The api_methods test (completion, tools,
structured output) already validates the provider works correctly.
* test: use Nova Pro for bedrock CI tests to cover full memory pipeline
Nova Lite only supports 10K output tokens, too low for fact extraction.
Switch to Nova Pro which supports the full 64K output needed for
retain/reflect operations. This ensures bedrock is tested on all
Hindsight functionalities, not just basic API methods.
* test: switch bedrock CI to Nova 2 Lite (supports 64K output tokens)
Nova v1 models (Pro, Lite) have a 10K output token limit which is
too low for fact extraction. Nova 2 Lite supports 64K+ output tokens,
enabling full memory pipeline testing (retain + reflect).
LLM providers like MiniMax wrap JSON responses in markdown code fences
(```json ... ```), causing JSON parse failures and 5-11 retries per
extraction. The existing fence stripping logic was gated to only
"lmstudio" and "ollama" providers (and for Ollama, unreachable due to
the _call_ollama_native redirect).
Changes:
- Extract _strip_code_fences() helper function
- Apply fence stripping to all providers in call() (not just local)
- Add fence stripping safety net to _call_ollama_native()
- Add 10 tests covering bare JSON, fenced JSON, malformed fences,
and real-world MiniMax response format
Fixesvectorize-io/hindsight#645
Co-authored-by: feniix <feniix@desktop>
* feat: upgrade MiniMax default model from M2.5 to M2.7
MiniMax has released MiniMax-M2.7, their latest model with a 1M context
window (up from 204K). This updates the default model across config,
docs, and examples. M2.5 remains fully compatible for users who prefer it.
- Update PROVIDER_DEFAULT_MODELS to MiniMax-M2.7
- Update .env.example and documentation references
- Add test_minimax_provider.py with M2.7 and backward compat tests
* chore: remove test file per review feedback
---------
Co-authored-by: PR Bot <pr-bot@minimaxi.com>
* fix: prevent silent memory loss on consolidation LLM failure
When all LLM retries are exhausted during consolidation, memories were
being marked consolidated_at unconditionally, permanently excluding them
from future consolidation runs without producing any observations.
Fix with two complementary mechanisms:
- Adaptive batch splitting: on LLM failure, the batch is halved and
retried recursively down to batch_size=1, recovering most transient
failures (rate limits, Pydantic validation on long prompts) without
operator intervention
- consolidation_failed_at column: only single-memory batches that still
fail after all retries are marked here instead of consolidated_at, so
they remain visible and retryable
- New API endpoint POST /v1/default/banks/{bank_id}/consolidation/retry-failed
resets these memories for the next consolidation run
* chore: regenerate OpenAPI spec
* fix: rename consolidation endpoint from /retry-failed to /recover
* fix: add consolidation_failed_at column, adaptive batch splitting, and recovery API
- Migration a3b4c5d6e7f8: add consolidation_failed_at TIMESTAMPTZ column to
memory_units with an index for efficient failure queries; properly chains off
g7h8i9j0k1l2 (backsweep_orphan_observations)
- Consolidator: filter pending memories with consolidation_failed_at IS NULL
so failed memories are not re-fetched in an infinite loop
- Consolidator: adaptive batch splitting — when a batch exhausts all 3 LLM
retries, halve it and retry sub-batches recursively; only single-memory
batches that also exhaust all retries get consolidation_failed_at set
- New tests (9 total) covering: adaptive splitting recovers all memories,
larger batch splitting, single-memory permanent failure, exclusion from
next run, partial batch failure, recover resets columns, recover returns
0 when none failed, recover-then-consolidate succeeds, HTTP endpoint
* chore: regenerate Go, Python, TypeScript clients with recover consolidation endpoint
* feat: add Recover Consolidation action to bank Actions dropdown
* style: apply ruff formatting to http.py and config.py
* fix: handle consolidation scope in large batch test mock LLM
The mock LLM was returning {"facts": ...} for ALL calls including consolidation.
Consolidation doesn't use skip_validation=True so it expects a _ConsolidationBatchResponse
instance, not a raw dict. Before this PR consolidation silently swallowed the AttributeError
(failed=False was returned); now failed=True triggers adaptive splitting and timeouts.
Fix: return _ConsolidationBatchResponse() when scope=="consolidation".
* fix: restrict claude-agent-sdk to macOS platform only (no Linux wheel available)
Also fix pre-existing type errors: use setattr for XLM-RoBERTa monkey-patch
and add missing reranker_local_fp16/bucket_batching/batch_size fields to main.py config constructor.
* fix: add UV_INDEX_STRATEGY=unsafe-best-match to fix markupsafe cp314 wheel conflict
PyTorch CPU index serves markupsafe==3.0.3 with only cp314 wheels.
uv's default first-index strategy stops at the first index with any version
even if no compatible wheel exists. unsafe-best-match searches all indices
for the best compatible wheel, falling back to PyPI for markupsafe.
* fix: use explicit pytorch index to prevent markupsafe wheel conflict
Configure the pytorch CPU index as explicit=true in pyproject.toml so it is
ONLY used for torch (via [tool.uv.sources]). All other packages (including
markupsafe) are resolved exclusively from PyPI, preventing the pytorch index
from serving incompatible cp314-only wheels for non-pytorch packages.
Remove UV_INDEX and UV_INDEX_STRATEGY from CI workflow (no longer needed
since the index is now configured in pyproject.toml).
* ci: trigger CI run
* ci: retry trigger
* ci: trigger after remote URL fix
* ci: add workflow_dispatch to unblock manual trigger
* fix: remove empty env blocks left after UV_INDEX removal
* fix: add type: ignore for optional claude_agent_sdk imports (macOS-only)
* fix: correct type: ignore rules for claude_agent_sdk and fix utcnow deprecation
Gemini 3.1+ thinking models include a thought_signature field in functionCall
parts. When reconstructing conversation history for subsequent turns, this
signature must be preserved or the API returns 400 INVALID_ARGUMENT.
- Add optional thought_signature field to LLMToolCall
- Capture thought_signature from Gemini response parts
- Pass thought_signature back when reconstructing multi-turn history
- Add gemini-3.1-flash-lite-preview to the LLM provider test matrix
* feat: introduce hindsight-api-slim and hindsight-all-slim packages
Closes#552
- Move all source code from hindsight-api/ to new hindsight-api-slim/
- hindsight-api-slim has heavy ML deps (torch, sentence-transformers,
transformers, einops, flashrank, mlx, mlx-lm, safetensors) and
pg0-embedded as optional extras: [local-ml], [embedded-db], [all]
- hindsight-api becomes a zero-code meta-package depending on
hindsight-api-slim[all] for full backward compatibility
- Add hindsight-all-slim meta-package: hindsight-api-slim + client + embed
- hindsight-all updated to depend on hindsight-api-slim[all]
- pg0.py: lazy-import pg0 with clear ImportError pointing to [embedded-db]
- Dockerfile: replace sed hack with proper uv sync --extra flags
- Update release.yml, test.yml, lint.sh, release.sh, CLAUDE.md and
all path references throughout the repo
* refactor: rename hindsight/ directory to hindsight-all/
* docs: document hindsight-api-slim and hindsight-all-slim package variants
Add package variants table and extras explanation to installation.md
* docs: remove emojis from installation.md, use professional tone
* docs: link Docker slim variant to pip package variants section
* docs: consolidate Docker image variants into single table
* ci: fix working-directory paths after package restructure
- Replace all hindsight-api → hindsight-api-slim in test.yml
- Replace hindsight → hindsight-all in test.yml
- Add --extra embedded-db to test-embed API install step
* ci: add local-ml and embedded-db extras to API sync steps
These extras were previously implicit in the old hindsight-api package
(which bundled everything). Now that hindsight-api-slim uses optional
extras, we must explicitly request local-ml and embedded-db in CI.
* ci: add API install step with embedded-db to test-embed smoke test
The smoke test starts hindsight-api as a daemon, which requires pg0-embedded.
Add a dedicated install step for hindsight-api-slim with embedded-db extra
so the daemon can start successfully.
* ci: remove --no-install-project when using optional extras
When --no-install-project is combined with --extra, the optional deps
are not installed because extras require the project to be active.
Remove --no-install-project from steps that need local-ml or embedded-db.
* ci: fix ordering of uv sync steps to preserve optional extras
When uv sync runs for a different workspace member, it removes optional
extras installed for other members. Fix by always running extra-requiring
API sync last, after other workspace member syncs.
Also remove --no-install-project from embedded-db sync in test-embed,
as --no-install-project prevents optional extras from being active.
* ci: add local-ml extra to test-embed API install for smoke test
The smoke test starts the full API server which needs sentence-transformers
for local embeddings (default provider). Add local-ml extra to the install.
* ci: simplify extras with --all-extras and add slim pip smoke test
- Replace explicit --extra local-ml --extra embedded-db with --all-extras
for cleaner, more maintainable sync steps
- Add test-pip-slim job: tests hindsight-api-slim[embedded-db] without
local ML models, using Cohere for embeddings/reranking (mirrors Docker
slim smoke test approach)
* ci: simplify slim smoke test to health check only (mirrors Docker test)
