### Summary
The Go Anthropic driver's `ChatStreamlyWithSender`
(internal/entity/models/anthropic.go) was a stub that always returned
`"no such method"`, so any caller requesting a streamed response from a
Claude model via the Go path failed outright — diverging from the Python
`AnthropicCV` driver, which already supports streaming.
This implements the method by opening the Messages API with
`stream=true` and parsing the SSE response via the shared
`ParseSSEStream` helper, forwarding `text_delta`/`thinking_delta`
content through the `sender` callback and treating `message_stop` as the
terminal event — consistent with the other Go drivers in this package
(e.g. Cohere).
Fixes#17333
---------
Co-authored-by: Abhay Yadav <abhayyadav@Abhays-MacBook-Air.local>
### Summary
Add token usage reporting for the LongCat (Meituan) model provider.
Related
to #17284.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
### Summary
Adds a `tenki` sandbox provider that runs each agent code execution in a
disposable Tenki (https://tenki.cloud) microVM (create → exec → destroy,
no volumes or snapshots).
Registration mirrors PR #15039, configure `api_key` and `project_id` in
Admin > Sandbox Settings.
Both runtimes are covered:
- Python: `agent/sandbox/providers/tenki.py` (structured results +
artifact collection).
- Go: `internal/agent/sandbox/tenki.go`, mirroring the e2b provider and
wired into the provider manager.
`tenki-sandbox` is an optional dependency (it requires `protobuf>=6.31`,
which differs from RAGFlow's pinned gRPC stack), lazily imported with a
clear error when missing; installation is documented in the sandbox
quickstart.
Unit tests cover execution, structured results, artifacts
(symlink/size/extension limits), non-zero exit, timeout, error mapping,
and idempotent destroy.
---------
Co-authored-by: yiming.wang <yiming.wang@luxor.com>
## Summary
This PR hardens the Go ingestion **Extractor** and **LLM retry** paths
and closes several Python->Go parity gaps in the keyword/question/tag
extraction flow.
- **Generic retry utility** (`internal/common/retry.go`):
`RetryWithBackoff` with exponential backoff (default 3 retries, 2s
initial delay, capped at 1m), context-aware sleep, and a `maxRetries<=0`
fast path. Covered by `internal/common/retry_test.go`.
- **LLM retry reuse**: `agent/component/llm_retry.go` now delegates to
`common.RetryWithBackoff` instead of an inline loop (behavior preserved:
ctx cancellation short-circuits the backoff).
- **Extractor LLM calls** (`extractor.go`):
- `call()` now retries transient LLM failures via `RetryWithBackoff`
(retry exhaustion fails the chunk instead of silently skipping).
- Sets `temperature = 0.2`, matching Python `generator.py:230,245`.
- Runs keyword and question extraction **concurrently** per chunk when
both are enabled (`task_executor.py:444-448`), with mutex-guarded map
writes to avoid data races.
- Substitutes `{field_name}` placeholders (including `{chunks}` -> chunk
text) in `prompt`/`system_prompt` before the call, mirroring Python
`string_format` (`extractor.py:102-103`); unmatched placeholders are
left as-is.
- Falls back to the **tenant default chat model** when `llm_id` is empty
(`task_executor.py:573-574`).
- Strips `` **greedily** (`strings.LastIndex`) in
`cleanExtractionResult`.
- **Auto-tagging** (`extractor_tag.go`): drops the `in.llmID != ""`
guards so an empty `llm_id` no longer skips tagging (uses the tenant
default model), and strips `` greedily in `parseTaggerResponse`.
- **Docs**: fixes a misleading `PresentationChunker` docstring that
claimed per-slide `image`/`position` output (the PPTX path emits none —
unlike PDF), and removes a stale `docs/migration_python_go_diff.md`
reference in `media_dispatch.go`.
## Test plan
- `bash build.sh --test ./internal/common/...` — passes (new retry
utility + tests).
- `bash build.sh --test ./internal/ingestion/component/...` — passes
(extractor/chunker/schema).
- `gofmt` and lefthook pre-commit checks pass.
Note: the personal `docs/migration_python_go_diff.md` working notebook
in the tree is intentionally **not** part of this PR.
---------
Co-authored-by: CodeBuddy <noreply@codebuddy.ai>
## Summary
GreenPT is a European AI provider with an OpenAI-compatible API,
optimized infrastructure, and datacenters powered by 100% renewable
energy.
This adds native GreenPT support across RAGFlow’s Go-first provider
system and its Python compatibility layer:
- discovers the current catalog from `GET /v1/models`
- features `glm-5.2` and `kimi-k2.7-code` for chat and coding
- supports `green-embedding` through `/v1/embeddings`
- supports `green-rerank` through `/v1/rerank`
- supports `green-s` and `green-s-pro` speech-to-text through
`/v1/listen`
- adds provider configuration, UI icon, and supported-provider
documentation
## Summary
- Return the configured `empty_response` when retrieval has no query or
no chunks.
- Preserve `formalized_content` for downstream Message nodes.
## Testing
- `bash build.sh --go`
- `ok ragflow/internal/agent/tool`
- `ok ragflow/internal/agent/component`
## Summary
Remediates two HIGH severity CVEs in `pdfminer.six` by upgrading its
parent dependency `pdfplumber` from `==0.10.4` to `==0.11.10` in
`pyproject.toml`.
| CVE | Severity | Package | Installed | Fixed in |
|---|---|---|---|---|
| CVE-2025-64512 | HIGH | pdfminer.six | 20221105 | 20251107 |
| CVE-2025-70559 | HIGH | pdfminer.six | 20221105 | 20251230 |
`pdfminer.six` is a transitive dependency exact-pinned by `pdfplumber`.
Version 0.10.4 pins `pdfminer.six==20221105` (vulnerable); version
0.11.10 pins `pdfminer.six==20260107` (patched).
…rphaned clusters
### Summary
**Problem**
When deleting a document from the knowledge base, the parent cluster
could never be located and was therefore never cleaned up, leaving
orphaned clusters in Infinity indefinitely.
**Root Cause**
InfinityConnection.field_keyword() treats all _kwd-suffixed columns as
keyword lists and applies .split("###") to them in get_fields().
parent_kwd was missing from the exclusion list. This caused a parent
cluster name like "Toronto Transit & Authority Control 5e8d5eb6" to
become ['Toronto Transit & Authority Control 5e8d5eb6'] (a
single-element list). When that list was fed into _nav_cluster_id(), it
produced a different hash than the actual cluster's hash (computed from
the plain string), so every deletion-time cluster lookup silently
failed.
**Fix**
Added "parent_kwd" to the exclusion list in field_keyword(), alongside
docnm_kwd, important_kwd, question_kwd, etc.
## Summary
Remediates nine litellm CVEs (3 CRITICAL, 6 HIGH) by upgrading the exact
pin from `==1.82.5` to `==1.84.0` in `pyproject.toml`.
| CVE | Severity | Fixed in |
|---|---|---|
| CVE-2026-35030 | CRITICAL | 1.83.0 |
| CVE-2026-42208 | CRITICAL | 1.83.7 |
| CVE-2026-49468 | CRITICAL | 1.84.0 |
| CVE-2026-35029 | HIGH | 1.83.0 |
| CVE-2026-40217 | HIGH | 1.83.10 |
| CVE-2026-42203 | HIGH | 1.83.7 |
| CVE-2026-42271 | HIGH | 1.83.7 |
| CVE-2026-47101 | HIGH | 1.83.14 |
| CVE-2026-47102 | HIGH | 1.83.10 |
`litellm` was pinned to `==1.82.5` because versions 1.82.6 - 1.82.8 had
a broken `litellm.caching.caching` import chain, and 1.88.0 had a broken
`litellm.integrations.custom_logger` import.
Both issues are resolved in 1.84.0.
The exact pin is retained (rather than a range) due to litellm's history
of introducing regressions on minor bumps.
## Problem
`TestMergeByTokenSizeFromJSON_ClampsOverlappedPct` reused a single
`items` fixture across four calls to `mergeByTokenSizeFromJSON`.
`mergeByTokenSizeFromJSON` mutates its `perItem` argument in place and
returns the same backing array (token.go: `perItem[idx] = merged`). As a
result:
- The 2nd and later calls merged already-merged chunks instead of the
original input.
- Because the returned slice aliases the input, later calls silently
overwrote the earlier results (`at100`, `at0`, ...).
- `reflect.DeepEqual(at100, at150)` was therefore vacuously true — the
test was a **false positive** that never actually exercised the clamp.
It would still pass even if the clamp were broken.
This is exactly the defect flagged in the review comment on PR #17396.
## Fix
Add a `clampOverlapFixture()` factory and build a fresh fixture for
every call, so that 150 / 1e300 / -5 / -1e300 are applied to the
original input.
## Verification
- The test passes after the fix.
- When the clamp logic was temporarily disabled, the test **failed**
(panic at token.go:768 — the negative index produced by an out-of-range
pct), proving the fixed test is no longer a false positive and can catch
a clamp regression.
## Scope
Test file only. No production code change (verified `token.go` is
identical to `upstream/main`).
Refs: review comment on PR #17396.
## Summary
Remediates five nltk CVEs by adding `nltk>=3.10.0` to
`constraint-dependencies` in `pyproject.toml`.
| CVE | Severity | Installed | Fixed in |
|---|---|---|---|
| CVE-2025-14009 | CRITICAL | 3.9.2 | 3.9.3 |
| CVE-2026-0846 | HIGH | 3.9.2 | 3.9.3 |
| CVE-2026-0847 | HIGH | 3.9.2 | — |
| CVE-2026-33231 | HIGH | 3.9.2 | 3.9.4 |
| CVE-2026-33236 | HIGH | 3.9.2 | — |
| CVE-2026-54293 | HIGH | 3.9.2 | 3.10.0 |
| CVE-2026-33230 | MEDIUM | 3.9.2 | 3.9.4 |
CVE-2026-0847 and CVE-2026-33236 have no confirmed fixed version.
`nltk` is a transitive dependency (pulled in by `crawl4ai` and
`infinity-sdk`). No package in the graph caps it below 3.10.0. It was
stuck at 3.9.2 simply because the lockfile had never been re-resolved.
