TRACES_* settings for the per-request trace timeline and its GenAI OTel
export. opentelemetry-api was only transitive; the tracing package
imports it directly.
`uv lock --upgrade` after the major bumps; every direct dependency is now at
its latest release.
What stays behind is capped upstream, not by this project. The notable one:
huggingface-hub sits at 1.16.1 rather than 1.31.0 because 1.31 wants
click>=8.4.2 and gTTS 2.5.4 — the newest gTTS — caps click below 8.2.
marshmallow is held at 3.x by dataclasses-json, websockets by google-genai,
typer and semchunk by docling-core, portalocker by qdrant-client, and
pydantic-core is pinned exactly by pydantic.
Verified beyond the suite: `docsgpt verify-offline` passes (tiktoken
encoding, both tokenizers, both embedding models, docling PDF conversion),
and the wheel builds and installs into a clean environment resolved from the
declared ranges rather than the lock, with the ASGI app importing there.
Lifts the deliberate `transformers<5.9` cap. The cap existed because 5.9
broke docling's PDF layout model on Apple Silicon; 5.17 does not. Checked by
converting a four-document benchmark (two papers, a 30-page table corpus, a
10-page report) on this machine with both stacks: the Markdown is
byte-identical on three, and the fourth differs only by one dropped
`<!-- image -->` placeholder on a figure. Tables still render as GFM tables
and no text is lost.
With that cap gone tokenizers can move too — transformers 5.8.1 pinned it at
<=0.23.0 and no such release exists, which is what held it at 0.22.2.
torchvision follows torch.
Linux still resolves torch and torchvision from the CPU-only PyTorch index,
so the docling Docker variant does not pick up the CUDA stack.
No code change needed: the server side (`FastMCP`, `@mcp.tool`,
`get_http_headers`, `http_app`) and the client side (`Client`, `BearerAuth`,
the three transports, and the `mcp.client.auth` / `mcp.shared.auth` OAuth
types imported directly) all kept their signatures.
Verified beyond the suite by driving the real `/mcp` mount over a live
uvicorn socket with the fastmcp client: tool discovery, a `search_docs` call
and bearer-token extraction all round-trip, with the token reaching
`search()` intact.
fastmcp 4 and mcp 2.2 also moved to httpx2, so the retry tuple's comment now
places them on that side of the split.
Both SDKs' 1.x/3.x majors run on httpx2 (the maintained fork of httpx by its
original author, published by Pydantic at github.com/pydantic/httpx2, version
line 2.x) instead of httpx, which is what makes these two bumps one change.
httpx2 is now a declared dependency because two modules import it directly.
Everything else in the 0.x -> 1.x / 2.x -> 3.x change lists is absent here:
no Text Completions, no `with_raw_response`, no raw `output_format` dicts, no
Bedrock client, and `requires-python` is already 3.12.
Three code changes, all forced by the bump:
The BYOM DNS-pinning client in `docsgpt/security/safe_url.py` is handed to
`OpenAI(http_client=...)`, and the SDK rejects an old-httpx client at
construction — which would have taken the SSRF guard offline. It is built on
httpx2 now, and its `sni_hostname` extension carries a `str` rather than
ascii bytes: httpcore passes the value straight to
`ssl.SSLContext.wrap_socket`, and the truststore backend httpx2 uses for the
default system trust store encodes it instead of accepting bytes. Bytes
therefore failed every real handshake while passing the existing tests, which
stub the transport out; the test now pins the type and says why.
The stream-retry error tuple in `docsgpt/llm/base.py` named `httpx`
exceptions only. The two libraries' exception classes are unrelated types, so
after the bump the retry silently stopped firing for openai and anthropic
while still working for google-genai and elevenlabs. It now covers both
stacks, with a parametrized test over each.
anthropic 1.x dropped temperature/top_p/top_k from `messages.create`'s
signature (passing one raises TypeError) without dropping them from the API,
so the provider forwards them through `extra_body`. The wire request is
unchanged and a model that rejects them 400s exactly as before.
Major bumps whose ceilings had to move. redis 8.1.0, tiktoken 0.14.0 and
daytona 0.211.2 needed no code change (the Daytona client, filesystem and
process signatures the sandbox calls are unchanged; redis 8 was checked
against a live server through the app's own sync and async clients).
reportlab 5.0.1 is test-only.
openapi-parser 2.0.0 is a rewrite onto pydantic spec models: `paths` is now
a dict keyed by URL rather than a list of objects carrying their own `url`,
and a path item exposes one field per HTTP method instead of an `operations`
list. `OpenAPI3Parser` reads both accordingly, iterating methods in the
order the spec declares them, and its rendered output is byte-identical to
before. The rewrite also drops prance, openapi-spec-validator and five more
transitive packages.
tokenizers stays at 0.22.2: transformers 5.8.1 caps it at <=0.23.0 and no
such release exists, so it moves with the transformers cap or not at all.
`uv lock --upgrade` plus the two code changes the new versions need.
firecrawl-anydoc 0.2.4 raises a dedicated `NeedsOcrError` where 0.2.3 raised
`UnsupportedError("... OCR is required")`, so the anydoc parser no longer
recognised a scanned PDF: the fallback still ran, but a near-empty result was
stored as an empty document instead of failing with the OCR_ENABLED hint.
`_needs_ocr` now accepts both spellings and looks the class up lazily, so an
older anydoc keeps working. 0.2.4 also refuses the CID-font NDA fixture
outright rather than dropping its Chinese column silently, so the PDF
trust-check tests stub that dropped output against the fixture's real bytes
(the check's own inputs) and a new test pins the refusal path.
ruff 0.16 widened its implicit default rule set, turning the dev-group bump
into 7131 findings across the tree. `.ruff.toml` now states the historical
selection (E4, E7, E9, F) explicitly and the CI pin moves to the locked
0.16.7, so lint no longer drifts with the version.
pip install docsgpt (extras: docling, milvus) installs the backend with a
docsgpt command: api, worker, migrate, prefetch-models, verify-offline,
reembed. Second step of the PyPI work after the package rename.
- hatchling build; the version comes from docsgpt/version.py. The wheel is
the docsgpt package with the data it reads at runtime (prompts, model
catalogs, seed config, alembic.ini and migrations) and without the
Dockerfile, the exported requirements, the sample index and local runtime
data. The application import alias stays checkout-only. uv sync installs
the package editable now that [tool.uv] package = false is gone.
- docsgpt/cli.py: api (gunicorn + BoundedDrainUvicornWorker with the image's
flags, --reload for uvicorn), worker (Celery worker with beat embedded,
--no-beat/-Q/--concurrency/--pool, solo pool on macOS), migrate, and
argument pass-through to the maintenance scripts. --help imports no app.
- docsgpt/core/paths.py: runtime data lives in a data home (DOCSGPT_HOME,
else the checkout, else cwd); DOCSGPT_ENV_FILE overrides the env file.
Settings, the dotenv load, LocalStorage and the internal upload route use
it instead of "three directories above this file", which is site-packages
for an installed package. A checkout and the Docker image behave as before.
- [project] dependencies are compatible ranges so the package installs next
to other packages; uv.lock resolves to the same versions and the exported
requirements files are unchanged.
- package-build.yml builds and checks the wheel on PRs and installs it into
a clean venv; pypi-publish.yml publishes on a published release through
trusted publishing (environment pypi), or to TestPyPI on a manual run.
- Docs: Deploying -> Install with pip. AGENTS.md notes the package.
requirements.txt pinned torch and transformers in core although only docling
needs them, and on Linux torch pulls the CUDA 13 stack: 2.7 GB of the 3.0 GB
wheel download. Direct dependencies now live in pyproject.toml, uv.lock pins
everything, and application/requirements*.txt are exported from the lock by
scripts/export_requirements.sh (each file is the core set plus one extra).
The docling extra pins torch/torchvision/transformers itself and, on Linux,
resolves torch from the CPU-only PyTorch index (no nvidia packages). milvus
(pymilvus + milvus-lite, which pulls pyarrow) is the second extra.
application/core/optional_deps.py is the one place install hints come from;
the milvus store and the docling call sites use it so a missing extra fails
with the exact command to run.
arc53-machine