Files
Zhichang Yu 98b48a0857 Port agentic RAG to Go, expose it as a chat mode, and add per-dialog failover (#20503)
## 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.
2026-10-02 23:00:16 +08:00

281 lines
5.2 KiB
Plaintext

# Generated by Cargo
# will have compiled files and executables
debug/
target/
__pycache__/
hudet/
cv/
layout_app.py
api/flask_session
venv/
# Remove Cargo.lock from gitignore if creating an executable, leave it for libraries
# More information here https://doc.rust-lang.org/cargo/guide/cargo-toml-vs-cargo-lock.html
Cargo.lock
# These are backup files generated by rustfmt
**/*.rs.bk
# MSVC Windows builds of rustc generate these, which store debugging information
*.pdb
*.trie
.idea/
.vscode/
.cursor/settings.json
.opencode/
# Exclude Mac generated files
.DS_Store
# Exclude the log folder
docker/ragflow-logs/
/flask_session
/logs
internal/rag/res/deepdoc/
# DeepDoc model weights and the HuggingFace download cache, fetched by
# ragflow_deps/download_deps.py. Same artifacts as internal/rag/res/deepdoc/,
# under the legacy Python resource path.
rag/res/
# Exclude sdk generated files
sdk/python/ragflow.egg-info/
sdk/python/build/
sdk/python/dist/
sdk/python/ragflow_sdk.egg-info/
# Exclude dep files
libssl*.deb
tika-server*.jar*
cl100k_base.tiktoken
chrome*
huggingface.co/
nltk_data/
uv-x86_64*.tar.gz
office_oxide*.tar.gz
pdf_oxide*.tar.gz
stagehand-server*
# Exclude hash-like temporary files like 9b5ad71b2ce5302211f9c61530b329a4922fc6a4
*[0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f]*
.lh/
.venv
docker/data
# OceanBase data and conf
docker/oceanbase/conf
docker/oceanbase/data
# SeekDB data and conf
docker/seekdb
#--------------------------------------------------#
# The following was generated with gitignore.nvim: #
#--------------------------------------------------#
# Gitignore for the following technologies: Node
# Logs
logs
*.log
npm-debug.log*
yarn-debug.log*
yarn-error.log*
lerna-debug.log*
.pnpm-debug.log*
# Diagnostic reports (https://nodejs.org/api/report.html)
report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
# Runtime data
pids
*.pid
*.seed
*.pid.lock
# Directory for instrumented libs generated by jscoverage/JSCover
lib-cov
# Coverage directory used by tools like istanbul
coverage
*.lcov
# nyc test coverage
.nyc_output
# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
.grunt
# Bower dependency directory (https://bower.io/)
bower_components
# node-waf configuration
.lock-wscript
# Compiled binary addons (https://nodejs.org/api/addons.html)
build/Release
# Dependency directories
node_modules/
jspm_packages/
# Snowpack dependency directory (https://snowpack.dev/)
web_modules/
# TypeScript cache
*.tsbuildinfo
# Optional npm cache directory
.npm
# Optional eslint cache
.eslintcache
# Optional stylelint cache
.stylelintcache
# Microbundle cache
.rpt2_cache/
.rts2_cache_cjs/
.rts2_cache_es/
.rts2_cache_umd/
# Optional REPL history
.node_repl_history
# Output of 'npm pack'
*.tgz
# Claude Code plans / state — local-only artifacts
.claude/
# Yarn Integrity file
.yarn-integrity
# dotenv environment variable files
.env
.env.development.local
.env.test.local
.env.production.local
.env.local
# parcel-bundler cache (https://parceljs.org/)
.cache
.parcel-cache
# Next.js build output
.next
out
# Nuxt.js build / generate output
.nuxt
dist
ragflow_cli.egg-info
# Gatsby files
.cache/
# Comment in the public line in if your project uses Gatsby and not Next.js
# https://nextjs.org/blog/next-9-1#public-directory-support
# public
# vuepress build output
.vuepress/dist
# vuepress v2.x temp and cache directory
.temp
# Docusaurus cache and generated files
.docusaurus
# Serverless directories
.serverless/
# FuseBox cache
.fusebox/
# DynamoDB Local files
.dynamodb/
# TernJS port file
.tern-port
# Stores VSCode versions used for testing VSCode extensions
.vscode-test
# yarn v2
.yarn/cache
.yarn/unplugged
.yarn/build-state.yml
.yarn/install-state.gz
.pnp.*
# Serverless Webpack directories
.webpack/
# SvelteKit build / generate output
.svelte-kit
# Default backup dir
backup
*huqie.txt
.hypothesis
# Added by cargo
/target
# Do not include in PR (local dev / build artifacts / working notes)
ragflow.egg-info/
uv-aarch64*.tar.gz
uv-aarch64-unknown-linux-gnu.tar.gz
docker/launch_backend_service_windows.sh
# Scratch/working notes (agent task planning & self-review docs; not PR material)
tasks/*.md
# C++ build directories
internal/binding/cpp/build/
internal/binding/cpp/cmake-build-release/
internal/binding/cpp/cmake-build-debug/
# Trae IDE config
.trae/
# Go server build output
bin/*
!bin/.gitkeep
/ragflow_server
.claude/settings.local.json
.run/
# Local agent tooling state (per-developer; not for commit)
.omc/
.marscode/
.omx/
# Parser test fixtures and python tools
internal/deepdoc/parser/pdf/testdata/
internal/deepdoc/parser/pdf/tools-py/
# IDE tooling artifacts
.codebuddy/
# Local build output
build/
internal/deepdoc/parser/docx/testdata/
internal/deepdoc/parser/docx/tool/
# test data compare tool
internal/ingestion/task/tool/generate_dataflow_golden.py
internal/ingestion/task/tool/README.md
internal/cpp/cmake-build-release
# downloaded native static-lib artifacts (fetched by ragflow_deps/download_deps.py)
ragflow_deps/*.zip
# external DeepDoc testdata, fetched on demand via scripts/fetch_deepdoc_testdata.sh
# (symlinked into place from ~/.cache/ragflow-testdata; never committed)
internal/deepdoc/native/testdata