## Background
This branch started as a focused fix to agentic RAG regexp retrieval
semantics (`f80556585`) and grew into the full agentic RAG path. The
title no longer describes the contents, so it has been rewritten.
The PR now covers three largely independent lines of work:
### 1. The agentic RAG is reachable from the UI
`internal/agentic_rag` (the eino-ADK ReAct explorer) was already built
and wired, but only reachable by hand-crafting an `agent_mode` kwarg. It
is now the sixth option in the chat mode selector (`reasoning` level 5).
One subtlety worth stating plainly: **levels 1-4 and level 5 are not the
same agent.** Levels 1-4 go through `internal/rag/agentic-rag` (the
harness graph) with a depth chosen by `harnessModeForLevel`; level 5
switches engines outright to `internal/agentic_rag`. That is why level 5
must never reach `harnessModeForLevel` — its `level >= 4` case would
silently answer "ultra" for a level outside its domain.
### 2. Per-dialog failover chain
`agenticModelChain` resolved exactly one model and the caller then used
`chain[0]`, so a "chain" was never more than a single element. A dialog
can now configure an ordered list of fallback models in Chat Settings,
handed to `NewFailoverEinoChatModel` (sticky cursor plus a 30s
full-chain cooldown).
The list lives in the dialog's own `llm_setting.failover_llm_ids`, so no
new table is involved. A member that no longer resolves is skipped with
a warning rather than failing the turn.
Also removed: `tenant_model_group` / `tenant_model_group_mapping`, which
nothing ever read (the DAOs were constructed but never called, and no
frontend or Python code referenced the concept). Their removal takes an
explicit drop migration with it, plus the account-deletion cascade that
queried them.
### 3. A hung MiniMax stream (independent of the agentic work)
With any mode selected, a chat rendered its whole answer and then sat on
"thinking" forever. Root cause is `minimax.go:256`: MiniMax sends `data:
[DONE]` but leaves the HTTP connection open, and the code waited for the
scanner goroutine's EOF *after* `HandleStreamingResponse` had already
returned. That receive can only end when `streamCallTimeout` (20
minutes) expires.
Diagnosed by capturing a real SSE stream (the complete answer arrives,
the terminal `final: true` never does) and a goroutine dump (6 requests
parked in `chan receive`).
## Two review findings fixed on the way through
- **KB-scope authorization**: the agentic branch bypassed quote
resolution, and an empty KB scope made `buildBoolQueryFromCondition`
drop the `kb_id` filter — so a citation could resolve a chunk belonging
to a different KB in the same tenant. The agentic branch now requires a
non-empty scope and otherwise falls through to the regular path.
- **Stale documentation**: `agentic-rag-failover-groups.md` described
the "automatically include every tenant model" strategy that upstream
had already removed. It was rewritten for the per-dialog scope and then
dropped entirely, since the design now lives in the code it describes.
## Verification
- `bash build.sh --test`: `admin`, `dao`, `service`, `service/dataset`
and `entity/models` all pass
- The MiniMax fix was verified end-to-end against a live server: before,
the turn hung indefinitely; after, it completes in **1.9s** with `final:
true` present
- Frontend: 9 tests added; type-check and lint clean on the touched
files
## Not included
- **Attachment support in agentic mode.** Text attachments could be
appended safely, but images have no safe fix: the agent's toolset is
built around corpus retrieval and has no image input channel. Fixing
only the text path would leave the feature half-supported and harder to
diagnose than now. Planned as a follow-up PR, with the design synced
here first.
- Tool-calling is not enforced as a group constraint. `is_tools` is a
provider-declared flag rather than a measured capability (187 of 659
chat models do not declare it), so gating on it would reject working
configurations while admitting broken ones.
Bumps [google.golang.org/grpc](https://github.com/grpc/grpc-go) from
1.82.1 to 1.83.1.
Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Jin Hai <[email protected]>
Ports the smart-reasoning (agentic RAG) conversation mode to the eino ADK, with Go retrieval tools (grep_chunks, search_chunks, list_chunks), deep-read XML output, and frontend agent-mode wiring.
- Add Go `EmailParser` support for Outlook `.msg` (OLE2/CFB) files via
the `gomsg` library, in addition to the existing `.eml` (RFC 5322)
support. The `.msg` hard-error is gone; emails with `.msg` attachments
are now ingested end-to-end.
- Re-chunk email attachments into retrievable text (user-oriented). Each
attachment is re-parsed by its file extension through the shared parser
registry and folded back into the same document, so attachment content
becomes searchable. This mirrors Python's legacy `rag/app/email.py`.
Binary attachments (images/audio/video/folders) are skipped by design.
- Restore a corrupted `sample.msg` test fixture and add guards so binary
fixtures are never mangled again (`.gitattributes` marks `*.msg` binary;
`check_files.py` skips NUL-byte files). Also made `check_files.py`
ruff-clean.
### Summary
Brings both halves of the Tenki sandbox provider onto current SDKs and
removes `project_id`, which Tenki deleted from its API.
**Go:** `github.com/LuxorLabs/tenki-sdk-go/sandbox` `v0.5.2` → `v0.7.0`
(current latest).
**Python:** the provider's SDK was renamed on PyPI — `tenki-sandbox` is
frozen at 0.4.0 and everything from 0.5 ships as
[`tenki`](https://pypi.org/project/tenki/). The docs told operators to
`pip install tenki-sandbox`, which installs a stale SDK that no longer
matches this provider's expectations.
**`project_id` is gone.** Tenki removed project scoping from the sandbox
API in 0.5.x: `Client.create()` no longer accepts `project_id`, so the
current code path would raise `TypeError` against a current SDK. It was
also marked `required: True` in the config schema, so the Admin >
Sandbox Settings form asked for a value that no longer exists.
Golden-parity test infrastructure for the **Go `TokenChunker` ↔ Python alignment**.
It runs the Go chunker over a committed case set (`testdata/parity/cases/`) and diffs each output against a captured Python golden (`testdata/parity/golden/`), honoring a `known_diffs.json` ratchet (`extra_fields` / `chunk_count` / `chunk_text`) so accepted divergences are tracked rather than silently widening.
Port dataset-level wiki incremental compile and refactor splitByTokens
token budgeting. Includes replace-only wiki merge, KNN dedup routing,
and template/config wiring.
Re-materialize wiki page graph from merged wiki_page rows after each
batch merge. Adds ProjectWikiGraph/DropWikiGraph, full page_type/slug
identity, delete-then-insert, tests.
Ports doc-level auto-metadata extraction to Go and adds the
knowledge_compiler component with scheduler/routing. Fixes Extractor
metadata injection type assertion and enable_metadata default-on.
### 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 <[email protected]>
### Summary
**Issue**
When calling Infinity under concurrent load, one shared connection was
reused across concurrent operations, it just hangs.
**Solution**
Avoid hangs with pooled connections and bounded timeouts
Ricardo-M-L