Research steps ran each tool call straight through the executor, never
asking check_pause, so approval-gated actions (including a public-link
visitor's wiki edits) and an outside caller's writes on the owner's
accounts ran unchecked. A step can't pause, so it now checks each call
first and answers any pause with a refusal the model reads, journaled
like a headless denial. Headless and research runs share the journaling.
Paused, denied, skipped and client-run tool calls all go through
trace_unexecuted_tool_call. The research synthesis, continuation and
workflow step spans use with-blocks instead of hand-rolled GeneratorExit
handling. Fixes blank lines and adds a missing hint and docstrings.
With TRACES_ENABLED off, LLM calls record no GenAI metrics, and a streamed
answer is joined into a preview only when a span keeps it. Agent runs and
continuations build their invoke_agent span in one place, which now reads
the model from model_id. The trace panel shows a stream's model time next
to how long it was open. Adds missing type hints.
Guardrail evaluations are traced when they call a remote check or fire; a
firing guardrail drops every content preview from the stored trace. Each
workflow node and each research phase is a step span, and the workflow run
id links the trace to its Logs row.
The graph tool records every page read_entity_pages returns in
retrieved_docs, but agents only ever collected internal_search's. A turn
answered from graph pages therefore emitted no sources: on the multi-hop e2e
run, a question answered from two read_entity_pages calls came back with none.
_search_tool_docs gathers both tools' documents the way the executor caches
them, and both the classic/agentic collector and the research agent's
per-step citations use it. Checked against the real executor and a real
graph: a graph-only turn now cites the pages it read.
A one-shot graph ranking diffuses over the whole neighbourhood; a question
whose answer sits two hops away is better served by following the edges. The
graph_search tool gives an agent search_entities, get_relationships and
read_entity_pages over its graph sources. On a multi-hop corpus where the
bridging entity is never named, answers went from 0/10 with classic vector
retrieval to 10/10 with the tool, end to end through /stream.
The tool has no setting of its own. It is offered exactly where the agent can
already search: agentic and research agents always, a classic agent only for
sources exposed as a search tool. A graph source left at prefetch is used for
ranking only.
Tests now pin GRAPHRAG_ENABLED to its shipped default, as CI has: with a dev
.env enabling it, every agent test's graph check read the developer's real
database and left a pool to it behind.
The backend import package is now docsgpt, the name it will carry on PyPI;
application was far too generic to install into anyone's site-packages.
git mv plus a mechanical rewrite of every import, dotted string and path
reference: 734 Python files, the compose files, Dockerfile, workflows, docs,
setup scripts, devcontainer, k8s manifests, vscode config, pytest and coverage
config, .gitignore. Behaviour is unchanged.
Kept for one release:
- A top-level application package whose meta-path finder resolves
application.x.y to the already-imported docsgpt.x.y object, so old imports
and entry points (celery -A application.app.celery,
uvicorn application.asgi:asgi_app) keep working with a FutureWarning.
- Celery registers every application.* task name as an alias of its
docsgpt.* task on start-up, so messages queued by the previous release still
run. The redbeat key prefix moves to redbeat:docsgpt:v2: so schedule entries
the previous release wrote are left unread instead of firing twice.
The backend image builds from the repository root (docker build -f
docsgpt/Dockerfile .) so it can ship the alias package; a root .dockerignore
allow-lists docsgpt/ and application/ and keeps caches, local data, .env
files, the sample index files and the Dockerfile out. Compose and the image
workflows point at the new context.
arc53-machine