Fix MCP timeouts — now uses a single deadline across sync/async paths. Expired queued requests are skipped before dispatch; in-flight coroutines are canceled. Tests added. Remote side effects cannot be rolled back (server idempotency required).
Add custom CA certificate support to WebDAV data source. Users can now connect to private/self-signed WebDAV servers via the verify option.
Fixes#16635
### Summary
Add Xquik as a new data source for X (Twitter) post ingestion. Supports Latest/Top queries, cursor pagination, incremental sync, and maps engagement/media to RAGFlow documents. Stops duplicate requests on repeated cursors. Tests and docs included.
---------
Co-authored-by: kriptoburak <kriptoburak@users.noreply.github.com>
Adds Azure DevOps as a new data source, syncing repository files and pull requests. Supports both hosted and self-hosted. Excludes wikis, work items, and binaries. Includes checkpoint/resume, change detection via commit IDs, and handles Azure's quirky 203 auth response. Tests passed against real deployment.
Fix build_connector_for_source() to honor config["bucket_type"] when constructing blob-storage connectors. Previously, an S3 source with bucket_type: s3_compatible was always built as Amazon S3, causing wrong credential validation. Now uses the configured bucket type and falls back to source type when missing.
Fix WebDAV data-loss bug where transient listing errors (network/timeout) returned [] and triggered deletion of all indexed documents. Removed top-level except so errors propagate to prune collector (which aborts on error). Individual file errors still handled. 3 regression tests added. Ruff clean.
## Summary
- Broaden `update_metadata_to` to keep `bool` / `int` / `float` / `None`
and structured values (e.g. PDF `outline` list[dict]) while retaining
string / list[str] merge+dedupe for LLM metadata.
- Fixes document system fields (`_isCurrent`, `_version`,
`_processStatus`) being dropped when parse persists PDF outline via full
`meta_fields` replace.
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
## Summary
- route REST retrieval metadata conditions through the existing
metadata-index push-down service
- keep full metadata loading lazy and preserve the Python in-memory
filter as an exact fallback
- add focused coverage for successful and empty push-down results and
multi-valued fallback semantics
## Summary
Fix the silent-failure health-check retry loops in
`common/doc_store/{es_conn_pool, ob_conn_pool, infinity_conn_pool,
infinity_conn_base}.py`. These pool initializers run at module import
via `@singleton`; a brief blip during pod start currently crashes the
whole worker process. The fix retries with exponential backoff, logs
each attempt, and re-raises on exhaustion.
## Related
- #17065 / #17066 — S3 storage
- #17069 / #17070 — non-S3 storage backends
- #17123 / #17125 — `rag/utils/{es_conn, opensearch_conn}`
- #17134 / #17135 — `memory/utils/es_conn`
- Fixes#17195
---------
Co-authored-by: Harsh Kashyap <Harsh23Kashyap@users.noreply.github.com>
## Summary
Fixes#18025. Both merge paths deduplicated IDs by scanning a plain list
(`item not in list`) inside a loop while appending — O(n²) per merge.
Replaced with a set-backed `seen` check alongside the existing ordered
list: same order, same dedup result, O(n).
---------
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
## Summary
- allow ISO 8601 normalization callers to provide an explicit fallback
while preserving the existing default behavior
- use the extraction conversation time when `valid_at` is missing or
invalid
- clear an invalid optional `invalid_at` instead of writing an
unparseable value
- include the rejected timestamp value in the error log
This addresses the timestamp write-through portion of #18415. It is
intentionally separate from #18462, which fixes the semantic output
prompt.
Co-authored-by: Loong <184861530+yzl0ng@users.noreply.github.com>
### Summary
GaussDB DocEngine could return no chunks for conversational queries even
when relevant content was available. `Dealer.search()` supplies
`minimum_should_match` (30%, then 10% on retry), but the GaussDB adapter
discarded it and built a single `plainto_tsquery` from every token. This
effectively required all conversational filler terms to match.
Follow-up to #17526 ("Refactor: merge dataset scope graph"), which introduced two code paths that touch Infinity columns the deployed schema does not declare. This PR makes the runtime robust against the old schema while also adding the new column to the new schema so freshly created tables are correct.
### Summary
`format_document_soup` tracks "am I inside a table" and "am I inside a
link" with sticky flags that are meant to be reset by `elif e.name ==
"/table"` and `elif e.name == "/a"`. BeautifulSoup's `.descendants` only
yields opening tags — a `Tag` named `/table` or `/a` never exists — so
both branches are dead code and neither flag is ever cleared.
Everything after the first `<table>` on a page is therefore formatted as
if it were still table content: paragraphs lose their newline, list
items lose their `- ` marker, headings lose their break, and the text is
glued onto the last table cell. Under
`HTML_BASED_CONNECTOR_TRANSFORM_LINKS_STRATEGY=markdown` the same bug
leaks a link's `href` into everything that follows it, including whole
subsequent paragraphs. The Confluence connector
(`confluence_connector.py:948`) goes through this path.
Real output for a Confluence-shaped page (heading, intro, spec table,
then the body) via the public `parse_html_page_basic`:
**Before**
```
prod us-east-1 Rollback procedure If the canary fails, run the rollback script immediately. Drain the load balancer Revert the deployment Escalate to the on-call rota if the rollback stalls. Do not skip the post-mortem.
```
**After**
```
prod us-east-1
Rollback procedure
If the canary fails, run the rollback script immediately.
- Drain the load balancer
- Revert the deployment
Escalate to [the on-call rota](http://oncall.example.com) if the rollback stalls.
Do not skip the post-mortem.
```
Every heading, paragraph and list marker after the table is lost, and
the whole body is indexed as one run-on line hanging off a table cell.
### Fix
Derive both scopes from each element's **ancestors** instead of from
flags that nothing can clear, and drop the two dead branches plus the
two that become redundant.
The scopes are resolved in one up-front pass into `id`-keyed maps
(`table_scope`, `href_scope`) and looked up in O(1) per element. Probing
per element with `find_parent` instead is O(depth) each, which measured
12–13× slower on table-heavy pages and up to 103× on deeply nested
markup; the map version costs a depth-independent 1.13–1.35× over
`main`. Numbers and method are in the round-2 comment below.
This also changes one adjacent behaviour worth calling out explicitly: a
link **inside** a table cell now renders as markdown, where before it
rendered as plain text. That previous behaviour was not by design — it
only held when no link preceded the table. With a link before the table,
`main` stamps the stale href onto every cell:
```
main: '[pre](http://STALE.com)\n\t[cellA](http://STALE.com)\t[cellB](http://STALE.com)'
branch: '[pre](http://STALE.com)\n\tcellA\tcellB'
```
Those cells are not links. Both symptoms are the same sticky-state bug,
so they are fixed together rather than left half-done.
### Testing
`test/unit_test/data_source/test_html_utils.py` is new —
`format_document_soup` had no test coverage. 11 tests: 8 fail on `main`
and pass on this branch, 3 are controls that pass on both (the table
itself still separates rows and cells, anchor text is still linkified,
the default `strip` strategy still strips).
Representative failures on `main`:
```
assert '\nAfter' in 'Before\n\tA\tB After'
assert '\n- item1' in 'Before\n\tA\tB item1 item2'
assert 'see [link](http://x.com) [ after](http://x.com)' == 'see [link](http://x.com) after'
assert '[next paragraph]' not in '[link](http://x.com)\n[next paragraph](http://x.com)'
```
Reverting each clause of the fix independently keeps the anchors honest:
reverting only the table clause fails exactly the 4 table tests and
leaves the link tests green; reverting only the link clause fails
exactly the 3 link tests and leaves the table tests green.
(`test_link_inside_a_table_cell_is_linkified` needs both clauses broken
to fail, so it appears in neither single-clause revert — it is covered
by the 8-fail run against `main`.)
Full `test/unit_test/data_source/` suite: **3 failed, 199 passed**, and
the failure set is byte-identical to clean `main` (**3 failed, 188
passed**) — the 3 are `TestSSRFValidation::*`, which resolve
`api.example.com` against real DNS and are unrelated to this change.
`ruff check` and `ruff format --check` are clean on both touched files.
---
This PR was drafted with AI assistance (Claude). I reviewed the change,
independently reproduced both symptoms against `main`, and take
responsibility for it.
## What
Adds [**SereneDB**](https://serenedb.com) as a selectable doc-store
engine on **both** RAGFlow paths:
- the **Go** `DocEngine` (`internal/engine/serenedb`), alongside
Elasticsearch and Infinity;
- the **Python** `DocStoreConnection` (`rag/utils/serenedb_conn.py`) +
`DOC_ENGINE=serenedb` registration.
SereneDB is a PostgreSQL-wire engine (DuckDB execution) whose single
inverted index carries **both** a scored text column (`@@`, BM25) and an
IVF vector column (`<#>`, inner product), so hybrid search is one SQL
statement. The Go engine connects with `database/sql` + `lib/pq`
(already a dependency, no new module); the Python connector uses
psycopg2 (already a dependency).
## Storage model
One table per tenant with `kb_id` as a filter column - the
**Elasticsearch / OceanBase** model, not Infinity's per-dataset tables.
This keeps BM25 statistics (IDF, avgdl) computed over the whole tenant
corpus (global IDF). Both connectors use this identical layout, so they
are storage- and retrieval-compatible: `hybrid` proxy routing and
Python↔Go switching are safe. On the Python side the connector is wired
as OceanBase's plain-SQL sibling (chunk_data JSON metadata, inline chunk
vectors, verbatim ES field names); the ES tokenizer path is unchanged.
Metadata stays one table per tenant (`ragflow_doc_meta_<tenant>`).
The query shapes mirror the Python connector, including the five
empirically-found landmines: the scored dictionary needs `frequency +
norm` (else `BM25()` silently returns 0.0), the `@@` query is the
tokenized query, the scored lexical branch matches one column, vectors
use an L2-normalized shadow column with `ip`/`sq8`, and the similarity
threshold goes directly in the ANN scan's `WHERE`. **Minimum engine
version: SereneDB 26.07.4.**
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
### What problem does this PR solve?
`common/misc_utils.once` set `executed=True` before invoking the wrapped
function, so an exception on the first call permanently disabled future
calls and returned the cached `None`.
This change marks `executed=True` only after a successful call, allowing
retries after transient failures while preserving once-only behavior
after success. It also adds regression tests for retry-after-exception
and thread-safe single execution.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Harsh Kashyap <harshkashyap@Harshs-MacBook-Pro.local>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### Summary
The **aimlapi.com** provider added in #17311 does not identify itself on
any of its outgoing requests, so its traffic cannot be attributed to the
integration. This PR adds the two headers AIMLAPI expects —
`X-AIMLAPI-Source` and `X-AIMLAPI-Partner-ID` — to every request the
provider makes.
### What problem does this PR solve?
Adds first-class support for **Mistral OCR** (`POST /v1/ocr`) as a
document parser, and fixes the long-standing bug where selecting
`mistral-ocr-latest` fails with `Can't find model for
<tenant>/image2text/mistral-ocr-latest`.
`mistral-ocr-latest` is Mistral's dedicated document-OCR endpoint, not a
vision-chat (`image2text`) model, but the catalog tagged it `image2text`
— so it resolved to the `CvModel` registry, which has no `Mistral`
entry, and there was no `OcrModel` entry either. This PR registers it
correctly and wires it end to end.
Closes#17056Closes#5782Closes#7075
**What it does**
1. **`MistralParser` + `MistralOcrModel`**
(`deepdoc/parser/mistral_parser.py`, `rag/llm/ocr_model.py`) — a proper
`OcrModel` factory `Mistral OCR`, mirroring the SoMark cloud-OCR
template. Tables stay inline as HTML; the page range maps to Mistral's
native `pages` selector (absolute page indices, billed per selected
page, so multi-task documents do not re-OCR the whole file); documents
over the inline limit go through the `/v1/files` signed-URL flow with
cleanup.
2. **Removes the `image2text` mis-tag** for `mistral-ocr-latest` from
the `Mistral` factory in `conf/llm_factories.json` (it now lives only in
the `Mistral OCR` factory, typed `ocr`). This is what closes the `Can't
find model` path.
3. **`MistralCV`** (`rag/llm/cv_model.py`) — a thin `GptV4` subclass
over Mistral's OpenAI-compatible endpoint, registering a `Mistral` entry
in the `CvModel` registry so Mistral vision models (`pixtral-*`) become
usable as `image2text` at all.
4. **Figure description** — Mistral-OCR-extracted figures are captioned
using the tenant's configured `image2text` model (any provider),
matching MinerU/deepdoc behaviour.
5. **Wires the parser into every chunking method** (`naive`, `paper`,
`book`, `laws`, `manual`, `one`, `presentation`) and the `rag/flow` DAG
path. This also fixes a related latent gap where those chunkers
forwarded only `mineru_llm_name`, so any model-based OCR provider
selected on a non-`naive` method silently fell through.
**Notes on the API contract** (verified against the live Mistral API):
`pages` is a selector (returns absolute `index`, bills only the
requested pages); `include_blocks: true` returns per-block bounding
boxes usable for chunk highlighting and figure cropping; large files use
`POST /v1/files` → signed URL → OCR → `DELETE`.
**Testing**: new unit tests cover the response→sections contract (both
the 2-tuple `naive` path and the typed 3-tuple DAG path), the
position-tag rescale, the HTTP client incl. upload failure/cleanup
paths, `parse_pdf` page-range threading, registry registration, env
config, the suffix normalization, the factory catalog entry, `MistralCV`
registration, and figure-description injection. Verified end to end
against the live Mistral API on real PDFs (table extraction,
page-selector cost avoidance, figure captioning).
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix Infinity compatibility issues in knowledge compilation.
This change:
- Stores compilation source ID lists as JSON arrays in Infinity.
- Parses JSON array fields when reading compiled documents.
- Uses `json_contains` for filtering JSON array fields.
- Adds the missing `name` column to the Infinity mapping.
- Updates dataset navigation KNN search to use the unified
`MatchDenseExpr` interface.
- Handles unavailable embeddings without querying an invalid `q_0_vec`
field.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
The Elasticsearch and Infinity metadata push-down translators are meant
to be
interchangeable pre-filters that both mirror the in-memory `meta_filter`
fallback — the shared test section is even titled
*"is_pushdown_supported
pre-check (same logic for both backends)"*. But the two
`is_pushdown_supported`
implementations diverge:
- `common/metadata_es_filter.py` defines
`MULTIVALUE_UNSAFE_NEGATIVE_OPS = frozenset({"≠", "not in"})` and
refuses
push-down for those operators.
- `common/metadata_infinity_filter.py` has **no such guard** and pushes
them
down.
**Why the guard exists:** `meta_fields.<key>` can hold a JSON array, and
the
in-memory `meta_filter` matches a document when **any** of its values
satisfies
the predicate (per-value-bucket semantics). A document whose `tag` is
`[a, b]`
therefore still matches `tag ≠ a` — bucket `b` satisfies it. The
Infinity
push-down emits `NOT JSON_CONTAINS(meta_fields, '$.tag', '"a"')`, which
means
*"the array contains no `a` at all"*, so it **silently drops** that
document.
Same divergence for `not in`. The result: `tag ≠ a` / `tag not in (...)`
under-counts results for any document that has the excluded value
alongside
others, but only on the Infinity backend.
This is on a live production path:
`DocMetadataService._filter_doc_ids_by_metadata_infinity`
(`api/db/services/doc_metadata_service.py:948`) calls this exact
`is_pushdown_supported` as the sole gate before building the Infinity
SQL,
mirroring the ES branch at line 880 which uses the guarded ES version.
Reproduction (both real modules, no services needed):
```python
>>> from common import metadata_es_filter as es, metadata_infinity_filter as inf
>>> f = [{"op": "≠", "key": "tag", "value": "a"}]
>>> es.is_pushdown_supported(f), inf.is_pushdown_supported(f)
(False, True) # ES falls back to in-memory (correct); Infinity pushes down (wrong)
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Fix
Add the same `MULTIVALUE_UNSAFE_NEGATIVE_OPS` set to
`metadata_infinity_filter` and reject those operators in
`is_pushdown_supported`, so a single such filter forces the whole
request to
the in-memory path — the only place the per-bucket semantics are
reproduced.
`not contains` is intentionally still allowed, matching the ES backend
(`all(not contains)` == `not any(contains)`, which the push-down
expresses
correctly on multi-valued fields). The `≠` / `not in` translators
themselves
are unchanged — they remain correct for the in-memory-fallback path;
only the
push-down eligibility gate is fixed.
### Testing
- Confirmed `is_pushdown_supported([{op}])` now returns `False` for `≠`
and
`not in` on **both** backends (previously ES=False, Infinity=True).
- Added `test_pushdown_check_rejects_multivalue_unsafe_negative_ops`,
which
asserts both backends reject these ops. Confirmed red→green: it fails
against
the pre-fix Infinity module, passes after.
- `ruff check` / `ruff format --check` clean.
### Note on overlap
Open PR #16833 also edits
`test/unit_test/common/test_metadata_filter.py`, but
only **appends** at the end of the file (line 640+) and changes
`metadata_es_filter.py` / `metadata_utils.py`, not the Infinity module —
no
overlap with this change.
### Disclosure
AI-assisted (Claude Code): the divergence was surfaced by an AI-assisted
review
pass, but I independently reproduced it against the real modules,
confirmed the
production call path, and verified the fix and test before submitting.
Signed-off-by: Andrew Chen <48723787+chuenchen309@users.noreply.github.com>
Signed-off-by: chuenchen309 <48723787+chuenchen309@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
## What
`meta_filter()`'s in-memory `filter_out()` helper has two related bugs
in how it coerces `input`/`value` for comparison operators (`=`, `≠`,
`>`, `<`, `≥`, `≤`):
**1. Asymmetric commit on partial `literal_eval` failure.** The original
code:
```python
input = ast.literal_eval(input)
value = ast.literal_eval(value)
```
runs as two separate statements inside one `try`. If the first succeeds
and the second raises, the first assignment already committed — `input`
and `value` end up as different types, and the subsequent `.lower()`
case-folding silently no-ops for whichever side didn't get lowered as a
string. Concretely: metadata cell `"None"` is a valid Python literal
(`ast.literal_eval("None")` → `None`), but a query value `"none"`
(lowercase) is not — so `status = "none"` never matches a cell whose
value is `"None"`, even though the intended semantics are
case-insensitive.
**2. `value` mutated in place, reused across dict entries.**
`filter_out(v2docs, operator, value)` loops over every `(input, docids)`
pair in `v2docs` and coerces `value` inside the loop body without
resetting it — so once one entry's `literal_eval(value)` succeeds and
rebinds `value` to a non-string, every later entry in the same call
compares against that already-coerced leftover instead of the original
filter value.
## Fix
- Commit both `literal_eval` results together via tuple assignment
(`input, value = ast.literal_eval(input), ast.literal_eval(value)`), so
a failure on either side leaves both operands in their pre-coercion form
instead of a mismatched mix.
- Save the original `value` before the loop and reset it at the top of
each iteration, so per-entry coercion never leaks into the next entry.
## Testing
Added 3 tests to
`test/unit_test/common/test_metadata_filter_operators.py` covering both
symptoms (case-insensitive match against a metadata cell that's a Python
keyword literal, both `=` and `≠`; a numeric `>` comparison unaffected
by an earlier dict entry having coerced the query value). Confirmed red
on `common/metadata_utils.py` at HEAD (`git stash` the fix, tests fail
with the exact symptom described above), green after. Full existing
`test_metadata_filter_operators.py` suite (22/22, including the 3 new
tests) passes. `ruff check` and `ruff format --check` clean on both
touched files.
Sandbox note: this environment has no network access to install
`pytest`/`pytest-asyncio`, so tests were run by importing the test
module and invoking each `test_*` function directly (same approach as
prior PRs from this account against this repo, e.g. #16949).
`test_apply_semi_auto_meta_data_filter.py` (the other file exercising
`meta_filter` indirectly through `apply_meta_data_filter`) needs
`pytest-asyncio` + heavier mocking and wasn't run, but it exercises
`apply_meta_data_filter`'s async/LLM-filter-generation path, not
`filter_out`'s coercion logic touched here.
Cross-referenced open PR #16833 (also touches
`common/metadata_utils.py`) — confirmed via `gh pr diff` it only touches
`convert_conditions`/operator-alias normalization and
`apply_meta_data_filter`'s `None`-vs-`["-999"]` sentinel logic, not
`filter_out`'s comparison-coercion code path. No overlap.
---
This PR was drafted with AI assistance (Claude); I reviewed the change,
independently reproduced both symptoms, and take responsibility for it.
Signed-off-by: chuenchen309 <48723787+chuenchen309@users.noreply.github.com>
### Summary
- Make `BLOB_STORAGE_SIZE_THRESHOLD` configurable through an environment
variable.
- Preserve the existing 20 MiB default.
- Add tests for the default and configured values.
### Why
Blob storage, Seafile, and WebDAV connectors currently use a hardcoded
20 MiB limit. Self-hosted users
cannot raise this limit without modifying the source code inside the
container.
### Testing
- `test/unit_test/data_source/test_config.py`: 2 passed
- `ruff check common/data_source/config.py
test/unit_test/data_source/test_config.py`
Fixes#16634
### What problem does this PR solve?
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [x] Other (please describe):
## Summary
Agent (Canvas) runs previously did not surface token usage in the SSE
stream, and RAGFlow's own Langfuse generations for agent runs were
missing the prompt/completion split and the session/user correlation.
This made it impossible for an external caller (or Langfuse) to
reconcile an agent turn's cost with the upstream provider (e.g.
OpenRouter), because a single turn can issue several distinct LLM calls
(query rewriting / cross-language translation, multi-round tool
reasoning, nested sub-agents, and the final answer).
This PR introduces a per-run token usage sink so that **every** LLM call
in a run is aggregated and reported once, and enriches Langfuse
generations with the prompt/completion split plus session/user
attributes.
## What changes
### 1. Per-run token usage sink (`common/token_utils.py`)
- Adds two `contextvars`: `token_usage_sink` (a mutable per-run
accumulator) and `langfuse_run_attrs` (session_id/user_id for the run).
- Adds `record_run_token_usage(...)` (thread-safe via a lock, because
`thread_pool_exec` copies the context into worker threads that share the
sink dict) and `usage_from_response(...)` which extracts a
`{prompt_tokens, completion_tokens, total_tokens}` split from
OpenAI/OpenRouter-style responses.
### 2. Provider layer captures the prompt/completion split
(`rag/llm/chat_model.py`)
- `LiteLLMBase` and `Base` now store `self.last_usage`
(prompt/completion/total) for the most recent chat call, in both the
plain and tool-calling paths.
- Streaming requests set `stream_options.include_usage = True` (LiteLLM
path) so the authoritative usage arrives on the final chunk; this is
read even on the usage-only chunk that carries no `choices`.
- Fixes a multi-round accounting bug in `*_with_tools`: token totals
were **overwritten** by each round (`total_tokens = tol`) instead of
accumulated, undercounting multi-round tool conversations. Each round is
now committed to a running aggregate.
### 3. LLMBundle reports usage once, per call
(`api/db/services/llm_service.py`)
- New `_report_usage(total_tokens)` records the call's usage into the
active run sink and returns the prompt/completion/total split for
Langfuse. The split is only used when it is consistent with the
authoritative total; otherwise only the total is reported.
- All three chat entry points (`async_chat`, `async_chat_streamly`,
`async_chat_streamly_delta`) now emit `usage_details` with
`input`/`output`/`total` instead of total-only.
- `_start_langfuse_observation` now applies `session_id`/`user_id` from
the per-run context (`langfuse_run_attrs`) so agent-run generations are
correctly grouped, even though agent LLMBundles are constructed without
those attributes.
### 4. Canvas installs the sink and emits the aggregate
(`agent/canvas.py`)
- `Canvas.run()` installs a fresh `token_usage_sink` and
`langfuse_run_attrs` (from `user_id`/`session_id`) at the start of every
turn.
- `message_end` now includes an aggregated `usage` object:
`{prompt_tokens, completion_tokens, total_tokens, calls}` covering all
LLM calls in the run.
### 5. Pass session id into the run
(`api/db/services/canvas_service.py`)
- `completion()` forwards `session_id` to `Canvas.run()` for Langfuse
session correlation.
## Why a context variable
LLM calls in an agent run originate from many places that each build
their own `LLMBundle` (e.g. `cross_languages`/`keyword_extraction`
helpers, the Agent component, and nested sub-agents invoked as tools). A
run-scoped context variable is the only non-invasive chokepoint that
captures all of them exactly once, including nested agents (which run in
the same async context) and thread-pool tools (the executor copies the
context).
## Behavior / compatibility
- No public API or wire-format removal: `message_end` gains an
additional optional `usage` field; existing consumers are unaffected.
- When a provider does not return authoritative usage, behavior falls
back to the previous token estimate (total only, no split).
- Non-agent flows (Dataflow `Pipeline`, sync `Graph.run`) are untouched.
## Testing
- [x] Simple agent answer: `message_end.usage.total_tokens` matches
provider usage.
- [x] Agent with cross-language retrieval: aggregate equals the sum of
both provider calls.
- [x] Tool-calling agent (multi-round): total accumulates across rounds.
- [x] Nested agent (agent-as-tool): sub-agent tokens included in the
parent run total.
- [x] Langfuse: agent generations show input/output split and are
grouped by session/user.
---------
Co-authored-by: yzc <yuzhichang@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Recovery PR for #16173 after the fork branch was accidentally reset
during rewrite-cleanup.
Cherry-picked onto current `main`:
- fix(common/time_utils): correct fallback timestamp and ISO-8601
normalization
- fix(common/time_utils): preserve zero timestamps and mark regression
tests
- test(common/time_utils): make fallback assertions deterministic
Supersedes closed#16173 — same branch
`Harsh23Kashyap/fix/time-utils-edgecases`, rebuilt per @yuzhichang
recovery steps in
https://github.com/infiniflow/ragflow/pull/16173#issuecomment-4829663835
---------
Co-authored-by: Harsh Kashyap <harshkashyap@Harshs-MacBook-Pro.local>
Co-authored-by: Cursor <cursoragent@cursor.com>
### What problem does this PR solve?
This PR adds Google BigQuery as a first-class data source connector in
RAGFlow.
It enables users to ingest and sync BigQuery data using the same
row-to-document model used by relational database connectors: selected
content columns become document text, metadata columns become document
metadata, an optional ID column provides stable document IDs, and an
optional timestamp column enables cursor-based incremental sync.
The connector supports service-account JSON credentials, table mode,
custom query mode, GoogleSQL queries, cursor-based incremental sync,
deleted-row pruning support, configurable query limits such as
`maximum_bytes_billed`, dry-run validation, batch loading, stable
document IDs, and BigQuery-aware value serialization.
