fleet-memory/hindsight-api-slim/pyproject.toml
Nicolò Boschi db70fdbe5e
feat: add LiteLLM LLM provider for Bedrock and 100+ providers (#679)
* 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).
2026-03-25 14:17:38 +01:00

209 lines
6.3 KiB
TOML

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[project]
name = "hindsight-api-slim"
version = "0.4.20"
description = "Hindsight: Agent Memory That Works Like Human Memory"
readme = "README.md"
requires-python = ">=3.11"
dependencies = [
"asyncpg>=0.29.0",
"python-dotenv>=1.0.0",
"openai>=1.0.0",
"pydantic>=2.0.0",
"rich>=13.0.0",
"langchain-text-splitters>=0.3.0",
"fastapi[standard]>=0.120.3",
"uvicorn>=0.38.0",
"wsproto>=1.0.0",
"sqlalchemy>=2.0.44",
"alembic>=1.17.1",
"pgvector>=0.4.1",
"greenlet>=3.2.4",
"psycopg2-binary>=2.9.11",
"tiktoken>=0.12.0",
"httpx>=0.27.0",
"PyJWT[crypto]>=2.8.0",
"fastmcp>=2.14.0", # CVE-2025-66416
"python-dateutil>=2.8.0",
"opentelemetry-api>=1.20.0",
"opentelemetry-sdk>=1.20.0",
"opentelemetry-instrumentation-fastapi>=0.41b0",
"opentelemetry-exporter-prometheus>=0.41b0",
"opentelemetry-exporter-otlp-proto-http>=1.20.0",
"opentelemetry-semantic-conventions>=0.41b0",
"dateparser>=1.2.2",
"google-genai>=1.0.0",
"google-auth>=2.0.0",
"anthropic>=0.40.0",
"typer>=0.9.0",
"cohere>=5.0.0",
"litellm>=1.0.0,<=1.82.6", # 1.82.7+ contains a supply chain attack (malicious .pth credential stealer)
"markitdown[pdf,docx,pptx,xlsx,xls]>=0.1.4", # File to markdown conversion
"obstore>=0.4.0", # S3/GCS/Azure object storage client (Rust-backed)
"uvloop>=0.22.1",
# Transitive dependency security fixes
"pyasn1>=0.6.3", # DoS vulnerability fix
"urllib3>=2.6.3", # Decompression-bomb safeguards bypass fix
"langchain-core>=1.2.11", # Serialization injection + SSRF vulnerability fix
"langsmith>=0.6.3", # SSRF via tracing header injection fix
"protobuf>=6.33.5", # JSON recursion depth bypass fix
"pillow>=12.1.1", # Out-of-bounds write in PSD image loading fix
"cryptography>=46.0.5", # Subgroup attack vulnerability fix
"filelock>=3.20.1", # TOCTOU race condition fix
"authlib>=1.6.9", # Account takeover/JWS header injection vulnerability fix
"pyjwt>=2.12.0", # Accepts unknown crit header extensions fix
"orjson>=3.11.6", # Unbounded recursion DoS fix
"tornado>=6.5.5", # DoS multipart/incomplete cookie validation fix
"aiohttp>=3.13.3", # Multiple DoS vulnerabilities
"claude-agent-sdk>=0.1.27",
"boto3>=1.42.74",
]
[project.optional-dependencies]
local-ml = [
# Local ML models for embeddings/reranking
"sentence-transformers>=3.3.0",
"transformers>=4.53.0", # Security fixes for ReDoS vulnerabilities
"torch>=2.6.0", # CVE fix for remote code execution
"einops>=0.8.2",
"flashrank>=0.2.0",
# Apple Silicon local inference
"mlx>=0.31.0",
"mlx-lm>=0.31.1",
"safetensors>=0.6.2",
]
embedded-db = [
"pg0-embedded>=0.11.0",
]
all = [
"hindsight-api-slim[local-ml,embedded-db]",
]
test = [
"pytest>=7.0.0",
"pytest-asyncio>=0.21.0",
"pytest-timeout>=2.4.0",
"pytest-xdist>=3.0.0",
"filelock>=3.20.1", # TOCTOU race condition fix
"testcontainers>=4.0.0",
]
[project.scripts]
hindsight-api = "hindsight_api.main:main"
hindsight-worker = "hindsight_api.worker.main:main"
hindsight-local-mcp = "hindsight_api.mcp_local:main"
hindsight-admin = "hindsight_api.admin.cli:main"
[tool.hatch.build.targets.wheel]
packages = ["hindsight_api"]
[tool.hatch.build.targets.wheel.sources]
"hindsight_api" = "hindsight_api"
[tool.hatch.build.targets.sdist]
include = [
"hindsight_api/**/*",
]
[tool.hatch.build]
include = [
"hindsight_api/**/*.py",
"hindsight_api/alembic/**/*",
]
[tool.pytest.ini_options]
log_cli = true
log_cli_level = "INFO"
log_cli_format = "%(asctime)s - %(levelname)s - %(name)s - %(message)s"
log_cli_date_format = "%Y-%m-%d %H:%M:%S"
addopts = "--timeout 300 -n 8 --dist loadgroup --durations=10 -v"
asyncio_mode = "auto"
asyncio_default_fixture_loop_scope = "function"
log_auto_indent = true
filterwarnings = [
"ignore:The @wait_container_is_ready decorator is deprecated:DeprecationWarning",
"ignore::RuntimeWarning:asyncio",
]
[dependency-groups]
dev = [
"pytest>=9.0.0",
"pytest-asyncio>=1.3.0",
"pytest-timeout>=2.4.0",
"pytest-xdist>=3.8.0",
"python-dotenv>=1.2.1",
"filelock>=3.20.1", # TOCTOU race condition fix
"ruff>=0.8.0",
"ty>=0.0.1",
"testcontainers>=4.0.0",
]
[tool.ruff]
line-length = 120
target-version = "py311"
exclude = [
"tests/",
"**/tests/",
]
[tool.ruff.lint]
select = [
"E", # pycodestyle errors
"W", # pycodestyle warnings
"F", # Pyflakes
"I", # isort
]
ignore = [
"E501", # line too long (handled by formatter)
"E402", # module import not at top of file
"F401", # unused import (too noisy during development)
"F841", # unused variable (too noisy during development)
"F811", # redefined while unused
"F821", # undefined name (forward references in type hints)
]
[tool.ruff.lint.isort]
known-third-party = ["alembic"]
[tool.ruff.format]
quote-style = "double"
indent-style = "space"
[tool.uv]
# Use explicit index for PyTorch to prevent the pytorch index from serving
# non-pytorch packages (e.g. markupsafe) with incompatible wheels
[[tool.uv.index]]
name = "pytorch-cpu"
url = "https://download.pytorch.org/whl/cpu"
explicit = true
[tool.uv.sources]
# Route torch to the CPU-only PyTorch index; everything else uses PyPI
torch = { index = "pytorch-cpu" }
[tool.ty]
# Type checking configuration
# ty is an extremely fast Python type checker from Astral (same team as ruff/uv)
[tool.ty.environment]
python-version = "3.11"
[tool.ty.src]
exclude = [
"tests/",
"hindsight_api/alembic/",
]
[tool.ty.rules]
# Disable noisy rules while keeping important ones
invalid-argument-type = "ignore" # False positives with **kwargs patterns
invalid-return-type = "ignore" # Often intentional in async code
invalid-parameter-default = "ignore" # Optional params with None default
possibly-missing-attribute = "ignore" # Common with Optional types
invalid-raise = "ignore" # False positives with exception tracking
call-non-callable = "ignore" # False positives with Optional types
invalid-key = "ignore" # Pydantic ConfigDict not understood
invalid-method-override = "ignore" # Intentional signature differences
unresolved-reference = "ignore" # Forward references not always resolved