Go: implement provider: LongCat (#14809)
### What problem does this PR solve?
Add a Go driver for LongCat (Meituan, https://longcat.chat), one of the
unchecked providers on the umbrella tracking issue #14736. LongCat
exposes an OpenAI-compatible REST API at
`https://api.longcat.chat/openai/v1` with three public chat models
including `LongCat-Flash-Thinking`, a reasoning model that returns
chain-of-thought in `reasoning_content` (OpenAI o-series shape).
Until this PR, a tenant who configured `longcat` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/longcat.go` with a `LongCatModel`
implementing the `ModelDriver` interface.
- New `conf/models/longcat.json` with the 3 public chat models
(Flash-Chat, Flash-Lite, Flash-Thinking) and `url_suffix` for `chat` and
`models`.
- `factory.go`: route `"longcat"` to `NewLongCatModel`.
Method coverage:
- `ChatWithMessages`: `POST /openai/v1/chat/completions`, non-streaming
- `ChatStreamlyWithSender`: SSE stream against the same endpoint
- `ListModels` / `CheckConnection`: `GET /openai/v1/models`
- **Reasoning extraction**: `message.reasoning_content` (non-stream) and
`delta.reasoning_content` (stream) flow into
`ChatResponse.ReasonContent` / the sender's second arg. Matches the
OpenAI o-series convention also used by kimi-k2.6 and DeepSeek-R1.
- **`reasoning_effort` propagation**: `ChatConfig.Effort` → request body
`reasoning_effort` (LongCat-Flash-Thinking honors it; non-reasoning
models ignore it).
- `Embed` / `Rerank` / `Balance` / `TranscribeAudio` / `AudioSpeech` /
`OCRFile` return `"no such method"` (LongCat does not expose any of
these surfaces).
No interface change. No new dependencies.
### How was this tested?
**21 unit tests** in `internal/entity/models/longcat_test.go` — all
pass:
```
$ go test -vet=off -run TestLongCat -count=1 -v ./internal/entity/models/...
=== RUN TestLongCatName
--- PASS: TestLongCatName (0.00s)
=== RUN TestLongCatChatHappyPath
--- PASS: TestLongCatChatHappyPath (0.00s)
=== RUN TestLongCatChatExtractsReasoningContent
--- PASS: TestLongCatChatExtractsReasoningContent (0.00s)
=== RUN TestLongCatChatPropagatesReasoningEffort
--- PASS: TestLongCatChatPropagatesReasoningEffort (0.00s)
=== RUN TestLongCatChatOmitsReasoningEffortWhenUnset
--- PASS: TestLongCatChatOmitsReasoningEffortWhenUnset (0.00s)
=== RUN TestLongCatChatRequiresAPIKey
--- PASS: TestLongCatChatRequiresAPIKey (0.00s)
=== RUN TestLongCatChatRequiresMessages
--- PASS: TestLongCatChatRequiresMessages (0.00s)
=== RUN TestLongCatChatRejectsHTTPError
--- PASS: TestLongCatChatRejectsHTTPError (0.00s)
=== RUN TestLongCatStreamHappyPath
--- PASS: TestLongCatStreamHappyPath (0.00s)
=== RUN TestLongCatStreamExtractsReasoningContent
--- PASS: TestLongCatStreamExtractsReasoningContent (0.00s)
=== RUN TestLongCatStreamRejectsExplicitFalse
--- PASS: TestLongCatStreamRejectsExplicitFalse (0.00s)
=== RUN TestLongCatStreamRequiresSender
--- PASS: TestLongCatStreamRequiresSender (0.00s)
=== RUN TestLongCatStreamFailsWithoutTerminal
--- PASS: TestLongCatStreamFailsWithoutTerminal (0.00s)
=== RUN TestLongCatListModelsHappyPath
--- PASS: TestLongCatListModelsHappyPath (0.00s)
=== RUN TestLongCatListModelsRequiresAPIKey
--- PASS: TestLongCatListModelsRequiresAPIKey (0.00s)
=== RUN TestLongCatCheckConnectionDelegatesToListModels
--- PASS: TestLongCatCheckConnectionDelegatesToListModels (0.00s)
=== RUN TestLongCatEmbedReturnsNoSuchMethod
--- PASS: TestLongCatEmbedReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatRerankReturnsNoSuchMethod
--- PASS: TestLongCatRerankReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatBalanceReturnsNoSuchMethod
--- PASS: TestLongCatBalanceReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatAudioOCRReturnNoSuchMethod
--- PASS: TestLongCatAudioOCRReturnNoSuchMethod (0.00s)
PASS
ok ragflow/internal/entity/models 0.020s
```
`go build ./internal/entity/models/...` exits 0 on go 1.25.
**Live integration test** against `api.longcat.chat`:
```
=== RUN TestLongCatLiveSmoke
[OK] Name() = "longcat"
[OK] CheckConnection
[OK] ListModels: 5 models -> [LongCat-Flash-Lite LongCat-Flash-Chat LongCat-Flash-Thinking-2601 LongCat-Flash-Omni-2603 LongCat-2.0-Preview]
[OK] Chat (Flash-Chat) answer="Got it! Let me know if you" reason=""
[OK] Chat (Flash-Thinking) answer len=443 head="To find 15 % of 80, follow these steps:\n\n1. **Convert the percentage to a frac..."
ReasonContent len=557 head="The user asks: \"15% of 80?\" They want step by step reasoning and final answer in \\boxed{}. So we need to compute 15% of ..."
[OK] Stream content: 78 chunks, 351 chars
[OK] Stream reasoning: 107 chunks, 537 chars
[OK] Balance returns longcat, no such method
[OK] Embed returns longcat, no such method
[OK] Rerank returns longcat, no such method
LONGCAT LIVE SMOKE PASSED
--- PASS: TestLongCatLiveSmoke (31.01s)
```
What the live run proves on the wire:
- Auth header (`Bearer <key>`) is accepted by `api.longcat.chat`.
- `/openai/v1/models` parser handles the real 5-model response (note:
live API returns versioned aliases `LongCat-Flash-Thinking-2601`,
`LongCat-Flash-Omni-2603`, `LongCat-2.0-Preview` plus the un-versioned
`LongCat-Flash-Chat` and `LongCat-Flash-Lite`).
- Non-stream chat against `LongCat-Flash-Chat`: visible answer parses
correctly, `ReasonContent` correctly empty.
- Non-stream chat against `LongCat-Flash-Thinking`: 443-char answer
flows into `Answer`, 557-char chain-of-thought flows into
`ReasonContent` via the new `message.reasoning_content` extraction.
- Streaming chat against `LongCat-Flash-Thinking`: 107 reasoning chunks
(537 chars) reach the sender's second arg via `delta.reasoning_content`;
78 content chunks (351 chars) reach the first arg. Before this code, the
reasoning chunks would have been silently dropped.
- All sentinel methods (Balance, Embed, Rerank, audio/OCR) return the
documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for LongCat. The diff against `main` is a clean +969 lines
across 4 files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 22:27:56 -10:00
|
|
|
package models
|
|
|
|
|
|
|
|
|
|
import (
|
|
|
|
|
"encoding/json"
|
|
|
|
|
"io"
|
|
|
|
|
"net/http"
|
|
|
|
|
"net/http/httptest"
|
|
|
|
|
"strings"
|
|
|
|
|
"testing"
|
|
|
|
|
)
|
|
|
|
|
|
2026-05-26 04:58:53 -07:00
|
|
|
func newLongCatServer(t *testing.T, expectedPath string, handler func(t *testing.T, r *http.Request, body map[string]interface{}, w http.ResponseWriter)) *httptest.Server {
|
Go: implement provider: LongCat (#14809)
### What problem does this PR solve?
Add a Go driver for LongCat (Meituan, https://longcat.chat), one of the
unchecked providers on the umbrella tracking issue #14736. LongCat
exposes an OpenAI-compatible REST API at
`https://api.longcat.chat/openai/v1` with three public chat models
including `LongCat-Flash-Thinking`, a reasoning model that returns
chain-of-thought in `reasoning_content` (OpenAI o-series shape).
Until this PR, a tenant who configured `longcat` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/longcat.go` with a `LongCatModel`
implementing the `ModelDriver` interface.
- New `conf/models/longcat.json` with the 3 public chat models
(Flash-Chat, Flash-Lite, Flash-Thinking) and `url_suffix` for `chat` and
`models`.
- `factory.go`: route `"longcat"` to `NewLongCatModel`.
Method coverage:
- `ChatWithMessages`: `POST /openai/v1/chat/completions`, non-streaming
- `ChatStreamlyWithSender`: SSE stream against the same endpoint
- `ListModels` / `CheckConnection`: `GET /openai/v1/models`
- **Reasoning extraction**: `message.reasoning_content` (non-stream) and
`delta.reasoning_content` (stream) flow into
`ChatResponse.ReasonContent` / the sender's second arg. Matches the
OpenAI o-series convention also used by kimi-k2.6 and DeepSeek-R1.
- **`reasoning_effort` propagation**: `ChatConfig.Effort` → request body
`reasoning_effort` (LongCat-Flash-Thinking honors it; non-reasoning
models ignore it).
- `Embed` / `Rerank` / `Balance` / `TranscribeAudio` / `AudioSpeech` /
`OCRFile` return `"no such method"` (LongCat does not expose any of
these surfaces).
No interface change. No new dependencies.
### How was this tested?
**21 unit tests** in `internal/entity/models/longcat_test.go` — all
pass:
```
$ go test -vet=off -run TestLongCat -count=1 -v ./internal/entity/models/...
=== RUN TestLongCatName
--- PASS: TestLongCatName (0.00s)
=== RUN TestLongCatChatHappyPath
--- PASS: TestLongCatChatHappyPath (0.00s)
=== RUN TestLongCatChatExtractsReasoningContent
--- PASS: TestLongCatChatExtractsReasoningContent (0.00s)
=== RUN TestLongCatChatPropagatesReasoningEffort
--- PASS: TestLongCatChatPropagatesReasoningEffort (0.00s)
=== RUN TestLongCatChatOmitsReasoningEffortWhenUnset
--- PASS: TestLongCatChatOmitsReasoningEffortWhenUnset (0.00s)
=== RUN TestLongCatChatRequiresAPIKey
--- PASS: TestLongCatChatRequiresAPIKey (0.00s)
=== RUN TestLongCatChatRequiresMessages
--- PASS: TestLongCatChatRequiresMessages (0.00s)
=== RUN TestLongCatChatRejectsHTTPError
--- PASS: TestLongCatChatRejectsHTTPError (0.00s)
=== RUN TestLongCatStreamHappyPath
--- PASS: TestLongCatStreamHappyPath (0.00s)
=== RUN TestLongCatStreamExtractsReasoningContent
--- PASS: TestLongCatStreamExtractsReasoningContent (0.00s)
=== RUN TestLongCatStreamRejectsExplicitFalse
--- PASS: TestLongCatStreamRejectsExplicitFalse (0.00s)
=== RUN TestLongCatStreamRequiresSender
--- PASS: TestLongCatStreamRequiresSender (0.00s)
=== RUN TestLongCatStreamFailsWithoutTerminal
--- PASS: TestLongCatStreamFailsWithoutTerminal (0.00s)
=== RUN TestLongCatListModelsHappyPath
--- PASS: TestLongCatListModelsHappyPath (0.00s)
=== RUN TestLongCatListModelsRequiresAPIKey
--- PASS: TestLongCatListModelsRequiresAPIKey (0.00s)
=== RUN TestLongCatCheckConnectionDelegatesToListModels
--- PASS: TestLongCatCheckConnectionDelegatesToListModels (0.00s)
=== RUN TestLongCatEmbedReturnsNoSuchMethod
--- PASS: TestLongCatEmbedReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatRerankReturnsNoSuchMethod
--- PASS: TestLongCatRerankReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatBalanceReturnsNoSuchMethod
--- PASS: TestLongCatBalanceReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatAudioOCRReturnNoSuchMethod
--- PASS: TestLongCatAudioOCRReturnNoSuchMethod (0.00s)
PASS
ok ragflow/internal/entity/models 0.020s
```
`go build ./internal/entity/models/...` exits 0 on go 1.25.
**Live integration test** against `api.longcat.chat`:
```
=== RUN TestLongCatLiveSmoke
[OK] Name() = "longcat"
[OK] CheckConnection
[OK] ListModels: 5 models -> [LongCat-Flash-Lite LongCat-Flash-Chat LongCat-Flash-Thinking-2601 LongCat-Flash-Omni-2603 LongCat-2.0-Preview]
[OK] Chat (Flash-Chat) answer="Got it! Let me know if you" reason=""
[OK] Chat (Flash-Thinking) answer len=443 head="To find 15 % of 80, follow these steps:\n\n1. **Convert the percentage to a frac..."
ReasonContent len=557 head="The user asks: \"15% of 80?\" They want step by step reasoning and final answer in \\boxed{}. So we need to compute 15% of ..."
[OK] Stream content: 78 chunks, 351 chars
[OK] Stream reasoning: 107 chunks, 537 chars
[OK] Balance returns longcat, no such method
[OK] Embed returns longcat, no such method
[OK] Rerank returns longcat, no such method
LONGCAT LIVE SMOKE PASSED
--- PASS: TestLongCatLiveSmoke (31.01s)
```
What the live run proves on the wire:
- Auth header (`Bearer <key>`) is accepted by `api.longcat.chat`.
- `/openai/v1/models` parser handles the real 5-model response (note:
live API returns versioned aliases `LongCat-Flash-Thinking-2601`,
`LongCat-Flash-Omni-2603`, `LongCat-2.0-Preview` plus the un-versioned
`LongCat-Flash-Chat` and `LongCat-Flash-Lite`).
- Non-stream chat against `LongCat-Flash-Chat`: visible answer parses
correctly, `ReasonContent` correctly empty.
- Non-stream chat against `LongCat-Flash-Thinking`: 443-char answer
flows into `Answer`, 557-char chain-of-thought flows into
`ReasonContent` via the new `message.reasoning_content` extraction.
- Streaming chat against `LongCat-Flash-Thinking`: 107 reasoning chunks
(537 chars) reach the sender's second arg via `delta.reasoning_content`;
78 content chunks (351 chars) reach the first arg. Before this code, the
reasoning chunks would have been silently dropped.
- All sentinel methods (Balance, Embed, Rerank, audio/OCR) return the
documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for LongCat. The diff against `main` is a clean +969 lines
across 4 files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 22:27:56 -10:00
|
|
|
t.Helper()
|
|
|
|
|
return httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
|
|
|
if r.URL.Path != expectedPath {
|
|
|
|
|
t.Errorf("expected path=%s, got %s", expectedPath, r.URL.Path)
|
|
|
|
|
return
|
|
|
|
|
}
|
|
|
|
|
if got := r.Header.Get("Authorization"); got != "Bearer test-key" {
|
|
|
|
|
t.Errorf("expected Authorization=Bearer test-key, got %q", got)
|
|
|
|
|
return
|
|
|
|
|
}
|
|
|
|
|
if r.Method == http.MethodPost {
|
|
|
|
|
// Accept "application/json" with or without a parameter
|
|
|
|
|
// suffix like "; charset=utf-8" — both are valid JSON.
|
|
|
|
|
if got := r.Header.Get("Content-Type"); !strings.HasPrefix(got, "application/json") {
|
|
|
|
|
t.Errorf("expected Content-Type to start with application/json, got %q", got)
|
|
|
|
|
return
|
|
|
|
|
}
|
|
|
|
|
raw, err := io.ReadAll(r.Body)
|
|
|
|
|
if err != nil {
|
|
|
|
|
t.Errorf("read body: %v", err)
|
|
|
|
|
return
|
|
|
|
|
}
|
|
|
|
|
var body map[string]interface{}
|
|
|
|
|
if err := json.Unmarshal(raw, &body); err != nil {
|
|
|
|
|
t.Errorf("unmarshal: %v\nraw=%s", err, string(raw))
|
|
|
|
|
return
|
|
|
|
|
}
|
2026-05-26 04:58:53 -07:00
|
|
|
handler(t, r, body, w)
|
Go: implement provider: LongCat (#14809)
### What problem does this PR solve?
Add a Go driver for LongCat (Meituan, https://longcat.chat), one of the
unchecked providers on the umbrella tracking issue #14736. LongCat
exposes an OpenAI-compatible REST API at
`https://api.longcat.chat/openai/v1` with three public chat models
including `LongCat-Flash-Thinking`, a reasoning model that returns
chain-of-thought in `reasoning_content` (OpenAI o-series shape).
Until this PR, a tenant who configured `longcat` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/longcat.go` with a `LongCatModel`
implementing the `ModelDriver` interface.
- New `conf/models/longcat.json` with the 3 public chat models
(Flash-Chat, Flash-Lite, Flash-Thinking) and `url_suffix` for `chat` and
`models`.
- `factory.go`: route `"longcat"` to `NewLongCatModel`.
Method coverage:
- `ChatWithMessages`: `POST /openai/v1/chat/completions`, non-streaming
- `ChatStreamlyWithSender`: SSE stream against the same endpoint
- `ListModels` / `CheckConnection`: `GET /openai/v1/models`
- **Reasoning extraction**: `message.reasoning_content` (non-stream) and
`delta.reasoning_content` (stream) flow into
`ChatResponse.ReasonContent` / the sender's second arg. Matches the
OpenAI o-series convention also used by kimi-k2.6 and DeepSeek-R1.
- **`reasoning_effort` propagation**: `ChatConfig.Effort` → request body
`reasoning_effort` (LongCat-Flash-Thinking honors it; non-reasoning
models ignore it).
- `Embed` / `Rerank` / `Balance` / `TranscribeAudio` / `AudioSpeech` /
`OCRFile` return `"no such method"` (LongCat does not expose any of
these surfaces).
No interface change. No new dependencies.
### How was this tested?
**21 unit tests** in `internal/entity/models/longcat_test.go` — all
pass:
```
$ go test -vet=off -run TestLongCat -count=1 -v ./internal/entity/models/...
=== RUN TestLongCatName
--- PASS: TestLongCatName (0.00s)
=== RUN TestLongCatChatHappyPath
--- PASS: TestLongCatChatHappyPath (0.00s)
=== RUN TestLongCatChatExtractsReasoningContent
--- PASS: TestLongCatChatExtractsReasoningContent (0.00s)
=== RUN TestLongCatChatPropagatesReasoningEffort
--- PASS: TestLongCatChatPropagatesReasoningEffort (0.00s)
=== RUN TestLongCatChatOmitsReasoningEffortWhenUnset
--- PASS: TestLongCatChatOmitsReasoningEffortWhenUnset (0.00s)
=== RUN TestLongCatChatRequiresAPIKey
--- PASS: TestLongCatChatRequiresAPIKey (0.00s)
=== RUN TestLongCatChatRequiresMessages
--- PASS: TestLongCatChatRequiresMessages (0.00s)
=== RUN TestLongCatChatRejectsHTTPError
--- PASS: TestLongCatChatRejectsHTTPError (0.00s)
=== RUN TestLongCatStreamHappyPath
--- PASS: TestLongCatStreamHappyPath (0.00s)
=== RUN TestLongCatStreamExtractsReasoningContent
--- PASS: TestLongCatStreamExtractsReasoningContent (0.00s)
=== RUN TestLongCatStreamRejectsExplicitFalse
--- PASS: TestLongCatStreamRejectsExplicitFalse (0.00s)
=== RUN TestLongCatStreamRequiresSender
--- PASS: TestLongCatStreamRequiresSender (0.00s)
=== RUN TestLongCatStreamFailsWithoutTerminal
--- PASS: TestLongCatStreamFailsWithoutTerminal (0.00s)
=== RUN TestLongCatListModelsHappyPath
--- PASS: TestLongCatListModelsHappyPath (0.00s)
=== RUN TestLongCatListModelsRequiresAPIKey
--- PASS: TestLongCatListModelsRequiresAPIKey (0.00s)
=== RUN TestLongCatCheckConnectionDelegatesToListModels
--- PASS: TestLongCatCheckConnectionDelegatesToListModels (0.00s)
=== RUN TestLongCatEmbedReturnsNoSuchMethod
--- PASS: TestLongCatEmbedReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatRerankReturnsNoSuchMethod
--- PASS: TestLongCatRerankReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatBalanceReturnsNoSuchMethod
--- PASS: TestLongCatBalanceReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatAudioOCRReturnNoSuchMethod
--- PASS: TestLongCatAudioOCRReturnNoSuchMethod (0.00s)
PASS
ok ragflow/internal/entity/models 0.020s
```
`go build ./internal/entity/models/...` exits 0 on go 1.25.
**Live integration test** against `api.longcat.chat`:
```
=== RUN TestLongCatLiveSmoke
[OK] Name() = "longcat"
[OK] CheckConnection
[OK] ListModels: 5 models -> [LongCat-Flash-Lite LongCat-Flash-Chat LongCat-Flash-Thinking-2601 LongCat-Flash-Omni-2603 LongCat-2.0-Preview]
[OK] Chat (Flash-Chat) answer="Got it! Let me know if you" reason=""
[OK] Chat (Flash-Thinking) answer len=443 head="To find 15 % of 80, follow these steps:\n\n1. **Convert the percentage to a frac..."
ReasonContent len=557 head="The user asks: \"15% of 80?\" They want step by step reasoning and final answer in \\boxed{}. So we need to compute 15% of ..."
[OK] Stream content: 78 chunks, 351 chars
[OK] Stream reasoning: 107 chunks, 537 chars
[OK] Balance returns longcat, no such method
[OK] Embed returns longcat, no such method
[OK] Rerank returns longcat, no such method
LONGCAT LIVE SMOKE PASSED
--- PASS: TestLongCatLiveSmoke (31.01s)
```
What the live run proves on the wire:
- Auth header (`Bearer <key>`) is accepted by `api.longcat.chat`.
- `/openai/v1/models` parser handles the real 5-model response (note:
live API returns versioned aliases `LongCat-Flash-Thinking-2601`,
`LongCat-Flash-Omni-2603`, `LongCat-2.0-Preview` plus the un-versioned
`LongCat-Flash-Chat` and `LongCat-Flash-Lite`).
- Non-stream chat against `LongCat-Flash-Chat`: visible answer parses
correctly, `ReasonContent` correctly empty.
- Non-stream chat against `LongCat-Flash-Thinking`: 443-char answer
flows into `Answer`, 557-char chain-of-thought flows into
`ReasonContent` via the new `message.reasoning_content` extraction.
- Streaming chat against `LongCat-Flash-Thinking`: 107 reasoning chunks
(537 chars) reach the sender's second arg via `delta.reasoning_content`;
78 content chunks (351 chars) reach the first arg. Before this code, the
reasoning chunks would have been silently dropped.
- All sentinel methods (Balance, Embed, Rerank, audio/OCR) return the
documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for LongCat. The diff against `main` is a clean +969 lines
across 4 files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 22:27:56 -10:00
|
|
|
return
|
|
|
|
|
}
|
2026-05-26 04:58:53 -07:00
|
|
|
handler(t, r, nil, w)
|
Go: implement provider: LongCat (#14809)
### What problem does this PR solve?
Add a Go driver for LongCat (Meituan, https://longcat.chat), one of the
unchecked providers on the umbrella tracking issue #14736. LongCat
exposes an OpenAI-compatible REST API at
`https://api.longcat.chat/openai/v1` with three public chat models
including `LongCat-Flash-Thinking`, a reasoning model that returns
chain-of-thought in `reasoning_content` (OpenAI o-series shape).
Until this PR, a tenant who configured `longcat` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/longcat.go` with a `LongCatModel`
implementing the `ModelDriver` interface.
- New `conf/models/longcat.json` with the 3 public chat models
(Flash-Chat, Flash-Lite, Flash-Thinking) and `url_suffix` for `chat` and
`models`.
- `factory.go`: route `"longcat"` to `NewLongCatModel`.
Method coverage:
- `ChatWithMessages`: `POST /openai/v1/chat/completions`, non-streaming
- `ChatStreamlyWithSender`: SSE stream against the same endpoint
- `ListModels` / `CheckConnection`: `GET /openai/v1/models`
- **Reasoning extraction**: `message.reasoning_content` (non-stream) and
`delta.reasoning_content` (stream) flow into
`ChatResponse.ReasonContent` / the sender's second arg. Matches the
OpenAI o-series convention also used by kimi-k2.6 and DeepSeek-R1.
- **`reasoning_effort` propagation**: `ChatConfig.Effort` → request body
`reasoning_effort` (LongCat-Flash-Thinking honors it; non-reasoning
models ignore it).
- `Embed` / `Rerank` / `Balance` / `TranscribeAudio` / `AudioSpeech` /
`OCRFile` return `"no such method"` (LongCat does not expose any of
these surfaces).
No interface change. No new dependencies.
### How was this tested?
**21 unit tests** in `internal/entity/models/longcat_test.go` — all
pass:
```
$ go test -vet=off -run TestLongCat -count=1 -v ./internal/entity/models/...
=== RUN TestLongCatName
--- PASS: TestLongCatName (0.00s)
=== RUN TestLongCatChatHappyPath
--- PASS: TestLongCatChatHappyPath (0.00s)
=== RUN TestLongCatChatExtractsReasoningContent
--- PASS: TestLongCatChatExtractsReasoningContent (0.00s)
=== RUN TestLongCatChatPropagatesReasoningEffort
--- PASS: TestLongCatChatPropagatesReasoningEffort (0.00s)
=== RUN TestLongCatChatOmitsReasoningEffortWhenUnset
--- PASS: TestLongCatChatOmitsReasoningEffortWhenUnset (0.00s)
=== RUN TestLongCatChatRequiresAPIKey
--- PASS: TestLongCatChatRequiresAPIKey (0.00s)
=== RUN TestLongCatChatRequiresMessages
--- PASS: TestLongCatChatRequiresMessages (0.00s)
=== RUN TestLongCatChatRejectsHTTPError
--- PASS: TestLongCatChatRejectsHTTPError (0.00s)
=== RUN TestLongCatStreamHappyPath
--- PASS: TestLongCatStreamHappyPath (0.00s)
=== RUN TestLongCatStreamExtractsReasoningContent
--- PASS: TestLongCatStreamExtractsReasoningContent (0.00s)
=== RUN TestLongCatStreamRejectsExplicitFalse
--- PASS: TestLongCatStreamRejectsExplicitFalse (0.00s)
=== RUN TestLongCatStreamRequiresSender
--- PASS: TestLongCatStreamRequiresSender (0.00s)
=== RUN TestLongCatStreamFailsWithoutTerminal
--- PASS: TestLongCatStreamFailsWithoutTerminal (0.00s)
=== RUN TestLongCatListModelsHappyPath
--- PASS: TestLongCatListModelsHappyPath (0.00s)
=== RUN TestLongCatListModelsRequiresAPIKey
--- PASS: TestLongCatListModelsRequiresAPIKey (0.00s)
=== RUN TestLongCatCheckConnectionDelegatesToListModels
--- PASS: TestLongCatCheckConnectionDelegatesToListModels (0.00s)
=== RUN TestLongCatEmbedReturnsNoSuchMethod
--- PASS: TestLongCatEmbedReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatRerankReturnsNoSuchMethod
--- PASS: TestLongCatRerankReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatBalanceReturnsNoSuchMethod
--- PASS: TestLongCatBalanceReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatAudioOCRReturnNoSuchMethod
--- PASS: TestLongCatAudioOCRReturnNoSuchMethod (0.00s)
PASS
ok ragflow/internal/entity/models 0.020s
```
`go build ./internal/entity/models/...` exits 0 on go 1.25.
**Live integration test** against `api.longcat.chat`:
```
=== RUN TestLongCatLiveSmoke
[OK] Name() = "longcat"
[OK] CheckConnection
[OK] ListModels: 5 models -> [LongCat-Flash-Lite LongCat-Flash-Chat LongCat-Flash-Thinking-2601 LongCat-Flash-Omni-2603 LongCat-2.0-Preview]
[OK] Chat (Flash-Chat) answer="Got it! Let me know if you" reason=""
[OK] Chat (Flash-Thinking) answer len=443 head="To find 15 % of 80, follow these steps:\n\n1. **Convert the percentage to a frac..."
ReasonContent len=557 head="The user asks: \"15% of 80?\" They want step by step reasoning and final answer in \\boxed{}. So we need to compute 15% of ..."
[OK] Stream content: 78 chunks, 351 chars
[OK] Stream reasoning: 107 chunks, 537 chars
[OK] Balance returns longcat, no such method
[OK] Embed returns longcat, no such method
[OK] Rerank returns longcat, no such method
LONGCAT LIVE SMOKE PASSED
--- PASS: TestLongCatLiveSmoke (31.01s)
```
What the live run proves on the wire:
- Auth header (`Bearer <key>`) is accepted by `api.longcat.chat`.
- `/openai/v1/models` parser handles the real 5-model response (note:
live API returns versioned aliases `LongCat-Flash-Thinking-2601`,
`LongCat-Flash-Omni-2603`, `LongCat-2.0-Preview` plus the un-versioned
`LongCat-Flash-Chat` and `LongCat-Flash-Lite`).
- Non-stream chat against `LongCat-Flash-Chat`: visible answer parses
correctly, `ReasonContent` correctly empty.
- Non-stream chat against `LongCat-Flash-Thinking`: 443-char answer
flows into `Answer`, 557-char chain-of-thought flows into
`ReasonContent` via the new `message.reasoning_content` extraction.
- Streaming chat against `LongCat-Flash-Thinking`: 107 reasoning chunks
(537 chars) reach the sender's second arg via `delta.reasoning_content`;
78 content chunks (351 chars) reach the first arg. Before this code, the
reasoning chunks would have been silently dropped.
- All sentinel methods (Balance, Embed, Rerank, audio/OCR) return the
documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for LongCat. The diff against `main` is a clean +969 lines
across 4 files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 22:27:56 -10:00
|
|
|
}))
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func newLongCatForTest(baseURL string) *LongCatModel {
|
|
|
|
|
return NewLongCatModel(
|
|
|
|
|
map[string]string{"default": baseURL},
|
2026-05-26 04:58:53 -07:00
|
|
|
URLSuffix{Chat: "openai/v1/chat/completions", Models: "openai/v1/models"},
|
Go: implement provider: LongCat (#14809)
### What problem does this PR solve?
Add a Go driver for LongCat (Meituan, https://longcat.chat), one of the
unchecked providers on the umbrella tracking issue #14736. LongCat
exposes an OpenAI-compatible REST API at
`https://api.longcat.chat/openai/v1` with three public chat models
including `LongCat-Flash-Thinking`, a reasoning model that returns
chain-of-thought in `reasoning_content` (OpenAI o-series shape).
Until this PR, a tenant who configured `longcat` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/longcat.go` with a `LongCatModel`
implementing the `ModelDriver` interface.
- New `conf/models/longcat.json` with the 3 public chat models
(Flash-Chat, Flash-Lite, Flash-Thinking) and `url_suffix` for `chat` and
`models`.
- `factory.go`: route `"longcat"` to `NewLongCatModel`.
Method coverage:
- `ChatWithMessages`: `POST /openai/v1/chat/completions`, non-streaming
- `ChatStreamlyWithSender`: SSE stream against the same endpoint
- `ListModels` / `CheckConnection`: `GET /openai/v1/models`
- **Reasoning extraction**: `message.reasoning_content` (non-stream) and
`delta.reasoning_content` (stream) flow into
`ChatResponse.ReasonContent` / the sender's second arg. Matches the
OpenAI o-series convention also used by kimi-k2.6 and DeepSeek-R1.
- **`reasoning_effort` propagation**: `ChatConfig.Effort` → request body
`reasoning_effort` (LongCat-Flash-Thinking honors it; non-reasoning
models ignore it).
- `Embed` / `Rerank` / `Balance` / `TranscribeAudio` / `AudioSpeech` /
`OCRFile` return `"no such method"` (LongCat does not expose any of
these surfaces).
No interface change. No new dependencies.
### How was this tested?
**21 unit tests** in `internal/entity/models/longcat_test.go` — all
pass:
```
$ go test -vet=off -run TestLongCat -count=1 -v ./internal/entity/models/...
=== RUN TestLongCatName
--- PASS: TestLongCatName (0.00s)
=== RUN TestLongCatChatHappyPath
--- PASS: TestLongCatChatHappyPath (0.00s)
=== RUN TestLongCatChatExtractsReasoningContent
--- PASS: TestLongCatChatExtractsReasoningContent (0.00s)
=== RUN TestLongCatChatPropagatesReasoningEffort
--- PASS: TestLongCatChatPropagatesReasoningEffort (0.00s)
=== RUN TestLongCatChatOmitsReasoningEffortWhenUnset
--- PASS: TestLongCatChatOmitsReasoningEffortWhenUnset (0.00s)
=== RUN TestLongCatChatRequiresAPIKey
--- PASS: TestLongCatChatRequiresAPIKey (0.00s)
=== RUN TestLongCatChatRequiresMessages
--- PASS: TestLongCatChatRequiresMessages (0.00s)
=== RUN TestLongCatChatRejectsHTTPError
--- PASS: TestLongCatChatRejectsHTTPError (0.00s)
=== RUN TestLongCatStreamHappyPath
--- PASS: TestLongCatStreamHappyPath (0.00s)
=== RUN TestLongCatStreamExtractsReasoningContent
--- PASS: TestLongCatStreamExtractsReasoningContent (0.00s)
=== RUN TestLongCatStreamRejectsExplicitFalse
--- PASS: TestLongCatStreamRejectsExplicitFalse (0.00s)
=== RUN TestLongCatStreamRequiresSender
--- PASS: TestLongCatStreamRequiresSender (0.00s)
=== RUN TestLongCatStreamFailsWithoutTerminal
--- PASS: TestLongCatStreamFailsWithoutTerminal (0.00s)
=== RUN TestLongCatListModelsHappyPath
--- PASS: TestLongCatListModelsHappyPath (0.00s)
=== RUN TestLongCatListModelsRequiresAPIKey
--- PASS: TestLongCatListModelsRequiresAPIKey (0.00s)
=== RUN TestLongCatCheckConnectionDelegatesToListModels
--- PASS: TestLongCatCheckConnectionDelegatesToListModels (0.00s)
=== RUN TestLongCatEmbedReturnsNoSuchMethod
--- PASS: TestLongCatEmbedReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatRerankReturnsNoSuchMethod
--- PASS: TestLongCatRerankReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatBalanceReturnsNoSuchMethod
--- PASS: TestLongCatBalanceReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatAudioOCRReturnNoSuchMethod
--- PASS: TestLongCatAudioOCRReturnNoSuchMethod (0.00s)
PASS
ok ragflow/internal/entity/models 0.020s
```
`go build ./internal/entity/models/...` exits 0 on go 1.25.
**Live integration test** against `api.longcat.chat`:
```
=== RUN TestLongCatLiveSmoke
[OK] Name() = "longcat"
[OK] CheckConnection
[OK] ListModels: 5 models -> [LongCat-Flash-Lite LongCat-Flash-Chat LongCat-Flash-Thinking-2601 LongCat-Flash-Omni-2603 LongCat-2.0-Preview]
[OK] Chat (Flash-Chat) answer="Got it! Let me know if you" reason=""
[OK] Chat (Flash-Thinking) answer len=443 head="To find 15 % of 80, follow these steps:\n\n1. **Convert the percentage to a frac..."
ReasonContent len=557 head="The user asks: \"15% of 80?\" They want step by step reasoning and final answer in \\boxed{}. So we need to compute 15% of ..."
[OK] Stream content: 78 chunks, 351 chars
[OK] Stream reasoning: 107 chunks, 537 chars
[OK] Balance returns longcat, no such method
[OK] Embed returns longcat, no such method
[OK] Rerank returns longcat, no such method
LONGCAT LIVE SMOKE PASSED
--- PASS: TestLongCatLiveSmoke (31.01s)
```
What the live run proves on the wire:
- Auth header (`Bearer <key>`) is accepted by `api.longcat.chat`.
- `/openai/v1/models` parser handles the real 5-model response (note:
live API returns versioned aliases `LongCat-Flash-Thinking-2601`,
`LongCat-Flash-Omni-2603`, `LongCat-2.0-Preview` plus the un-versioned
`LongCat-Flash-Chat` and `LongCat-Flash-Lite`).
- Non-stream chat against `LongCat-Flash-Chat`: visible answer parses
correctly, `ReasonContent` correctly empty.
- Non-stream chat against `LongCat-Flash-Thinking`: 443-char answer
flows into `Answer`, 557-char chain-of-thought flows into
`ReasonContent` via the new `message.reasoning_content` extraction.
- Streaming chat against `LongCat-Flash-Thinking`: 107 reasoning chunks
(537 chars) reach the sender's second arg via `delta.reasoning_content`;
78 content chunks (351 chars) reach the first arg. Before this code, the
reasoning chunks would have been silently dropped.
- All sentinel methods (Balance, Embed, Rerank, audio/OCR) return the
documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for LongCat. The diff against `main` is a clean +969 lines
across 4 files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 22:27:56 -10:00
|
|
|
)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// newLongCatSSEServer returns an httptest.Server that asserts the
|
|
|
|
|
// request contract (POST + path + Authorization + Content-Type prefix)
|
|
|
|
|
// before writing the supplied SSE payload. Used by the streaming tests
|
|
|
|
|
// so a regression in the wire shape can't slip through unnoticed.
|
|
|
|
|
func newLongCatSSEServer(t *testing.T, expectedPath, ssePayload string) *httptest.Server {
|
|
|
|
|
t.Helper()
|
|
|
|
|
return httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
|
|
|
if r.Method != http.MethodPost {
|
|
|
|
|
t.Errorf("expected POST, got %s", r.Method)
|
|
|
|
|
return
|
|
|
|
|
}
|
|
|
|
|
if r.URL.Path != expectedPath {
|
|
|
|
|
t.Errorf("expected path=%s, got %s", expectedPath, r.URL.Path)
|
|
|
|
|
return
|
|
|
|
|
}
|
|
|
|
|
if got := r.Header.Get("Authorization"); got != "Bearer test-key" {
|
|
|
|
|
t.Errorf("expected Authorization=Bearer test-key, got %q", got)
|
|
|
|
|
return
|
|
|
|
|
}
|
|
|
|
|
if got := r.Header.Get("Content-Type"); !strings.HasPrefix(got, "application/json") {
|
|
|
|
|
t.Errorf("expected Content-Type to start with application/json, got %q", got)
|
|
|
|
|
return
|
|
|
|
|
}
|
|
|
|
|
w.Header().Set("Content-Type", "text/event-stream")
|
|
|
|
|
_, _ = io.WriteString(w, ssePayload)
|
|
|
|
|
}))
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func TestLongCatName(t *testing.T) {
|
|
|
|
|
if got := newLongCatForTest("http://unused").Name(); got != "longcat" {
|
|
|
|
|
t.Errorf("Name()=%q, want %q", got, "longcat")
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2026-05-28 03:45:59 -05:00
|
|
|
func TestLongCatNewModelWithCustomDefaultTransport(t *testing.T) {
|
|
|
|
|
original := http.DefaultTransport
|
|
|
|
|
http.DefaultTransport = roundTripperFunc(func(*http.Request) (*http.Response, error) {
|
|
|
|
|
return nil, nil
|
|
|
|
|
})
|
|
|
|
|
t.Cleanup(func() {
|
|
|
|
|
http.DefaultTransport = original
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
if model := NewLongCatModel(map[string]string{"default": "http://unused"}, URLSuffix{}); model == nil {
|
|
|
|
|
t.Fatal("NewLongCatModel returned nil")
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
Go: implement provider: LongCat (#14809)
### What problem does this PR solve?
Add a Go driver for LongCat (Meituan, https://longcat.chat), one of the
unchecked providers on the umbrella tracking issue #14736. LongCat
exposes an OpenAI-compatible REST API at
`https://api.longcat.chat/openai/v1` with three public chat models
including `LongCat-Flash-Thinking`, a reasoning model that returns
chain-of-thought in `reasoning_content` (OpenAI o-series shape).
Until this PR, a tenant who configured `longcat` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/longcat.go` with a `LongCatModel`
implementing the `ModelDriver` interface.
- New `conf/models/longcat.json` with the 3 public chat models
(Flash-Chat, Flash-Lite, Flash-Thinking) and `url_suffix` for `chat` and
`models`.
- `factory.go`: route `"longcat"` to `NewLongCatModel`.
Method coverage:
- `ChatWithMessages`: `POST /openai/v1/chat/completions`, non-streaming
- `ChatStreamlyWithSender`: SSE stream against the same endpoint
- `ListModels` / `CheckConnection`: `GET /openai/v1/models`
- **Reasoning extraction**: `message.reasoning_content` (non-stream) and
`delta.reasoning_content` (stream) flow into
`ChatResponse.ReasonContent` / the sender's second arg. Matches the
OpenAI o-series convention also used by kimi-k2.6 and DeepSeek-R1.
- **`reasoning_effort` propagation**: `ChatConfig.Effort` → request body
`reasoning_effort` (LongCat-Flash-Thinking honors it; non-reasoning
models ignore it).
- `Embed` / `Rerank` / `Balance` / `TranscribeAudio` / `AudioSpeech` /
`OCRFile` return `"no such method"` (LongCat does not expose any of
these surfaces).
No interface change. No new dependencies.
### How was this tested?
**21 unit tests** in `internal/entity/models/longcat_test.go` — all
pass:
```
$ go test -vet=off -run TestLongCat -count=1 -v ./internal/entity/models/...
=== RUN TestLongCatName
--- PASS: TestLongCatName (0.00s)
=== RUN TestLongCatChatHappyPath
--- PASS: TestLongCatChatHappyPath (0.00s)
=== RUN TestLongCatChatExtractsReasoningContent
--- PASS: TestLongCatChatExtractsReasoningContent (0.00s)
=== RUN TestLongCatChatPropagatesReasoningEffort
--- PASS: TestLongCatChatPropagatesReasoningEffort (0.00s)
=== RUN TestLongCatChatOmitsReasoningEffortWhenUnset
--- PASS: TestLongCatChatOmitsReasoningEffortWhenUnset (0.00s)
=== RUN TestLongCatChatRequiresAPIKey
--- PASS: TestLongCatChatRequiresAPIKey (0.00s)
=== RUN TestLongCatChatRequiresMessages
--- PASS: TestLongCatChatRequiresMessages (0.00s)
=== RUN TestLongCatChatRejectsHTTPError
--- PASS: TestLongCatChatRejectsHTTPError (0.00s)
=== RUN TestLongCatStreamHappyPath
--- PASS: TestLongCatStreamHappyPath (0.00s)
=== RUN TestLongCatStreamExtractsReasoningContent
--- PASS: TestLongCatStreamExtractsReasoningContent (0.00s)
=== RUN TestLongCatStreamRejectsExplicitFalse
--- PASS: TestLongCatStreamRejectsExplicitFalse (0.00s)
=== RUN TestLongCatStreamRequiresSender
--- PASS: TestLongCatStreamRequiresSender (0.00s)
=== RUN TestLongCatStreamFailsWithoutTerminal
--- PASS: TestLongCatStreamFailsWithoutTerminal (0.00s)
=== RUN TestLongCatListModelsHappyPath
--- PASS: TestLongCatListModelsHappyPath (0.00s)
=== RUN TestLongCatListModelsRequiresAPIKey
--- PASS: TestLongCatListModelsRequiresAPIKey (0.00s)
=== RUN TestLongCatCheckConnectionDelegatesToListModels
--- PASS: TestLongCatCheckConnectionDelegatesToListModels (0.00s)
=== RUN TestLongCatEmbedReturnsNoSuchMethod
--- PASS: TestLongCatEmbedReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatRerankReturnsNoSuchMethod
--- PASS: TestLongCatRerankReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatBalanceReturnsNoSuchMethod
--- PASS: TestLongCatBalanceReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatAudioOCRReturnNoSuchMethod
--- PASS: TestLongCatAudioOCRReturnNoSuchMethod (0.00s)
PASS
ok ragflow/internal/entity/models 0.020s
```
`go build ./internal/entity/models/...` exits 0 on go 1.25.
**Live integration test** against `api.longcat.chat`:
```
=== RUN TestLongCatLiveSmoke
[OK] Name() = "longcat"
[OK] CheckConnection
[OK] ListModels: 5 models -> [LongCat-Flash-Lite LongCat-Flash-Chat LongCat-Flash-Thinking-2601 LongCat-Flash-Omni-2603 LongCat-2.0-Preview]
[OK] Chat (Flash-Chat) answer="Got it! Let me know if you" reason=""
[OK] Chat (Flash-Thinking) answer len=443 head="To find 15 % of 80, follow these steps:\n\n1. **Convert the percentage to a frac..."
ReasonContent len=557 head="The user asks: \"15% of 80?\" They want step by step reasoning and final answer in \\boxed{}. So we need to compute 15% of ..."
[OK] Stream content: 78 chunks, 351 chars
[OK] Stream reasoning: 107 chunks, 537 chars
[OK] Balance returns longcat, no such method
[OK] Embed returns longcat, no such method
[OK] Rerank returns longcat, no such method
LONGCAT LIVE SMOKE PASSED
--- PASS: TestLongCatLiveSmoke (31.01s)
```
What the live run proves on the wire:
- Auth header (`Bearer <key>`) is accepted by `api.longcat.chat`.
- `/openai/v1/models` parser handles the real 5-model response (note:
live API returns versioned aliases `LongCat-Flash-Thinking-2601`,
`LongCat-Flash-Omni-2603`, `LongCat-2.0-Preview` plus the un-versioned
`LongCat-Flash-Chat` and `LongCat-Flash-Lite`).
- Non-stream chat against `LongCat-Flash-Chat`: visible answer parses
correctly, `ReasonContent` correctly empty.
- Non-stream chat against `LongCat-Flash-Thinking`: 443-char answer
flows into `Answer`, 557-char chain-of-thought flows into
`ReasonContent` via the new `message.reasoning_content` extraction.
- Streaming chat against `LongCat-Flash-Thinking`: 107 reasoning chunks
(537 chars) reach the sender's second arg via `delta.reasoning_content`;
78 content chunks (351 chars) reach the first arg. Before this code, the
reasoning chunks would have been silently dropped.
- All sentinel methods (Balance, Embed, Rerank, audio/OCR) return the
documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for LongCat. The diff against `main` is a clean +969 lines
across 4 files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 22:27:56 -10:00
|
|
|
func TestLongCatChatHappyPath(t *testing.T) {
|
2026-05-26 04:58:53 -07:00
|
|
|
srv := newLongCatServer(t, "/openai/v1/chat/completions", func(t *testing.T, _ *http.Request, body map[string]interface{}, w http.ResponseWriter) {
|
Go: implement provider: LongCat (#14809)
### What problem does this PR solve?
Add a Go driver for LongCat (Meituan, https://longcat.chat), one of the
unchecked providers on the umbrella tracking issue #14736. LongCat
exposes an OpenAI-compatible REST API at
`https://api.longcat.chat/openai/v1` with three public chat models
including `LongCat-Flash-Thinking`, a reasoning model that returns
chain-of-thought in `reasoning_content` (OpenAI o-series shape).
Until this PR, a tenant who configured `longcat` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/longcat.go` with a `LongCatModel`
implementing the `ModelDriver` interface.
- New `conf/models/longcat.json` with the 3 public chat models
(Flash-Chat, Flash-Lite, Flash-Thinking) and `url_suffix` for `chat` and
`models`.
- `factory.go`: route `"longcat"` to `NewLongCatModel`.
Method coverage:
- `ChatWithMessages`: `POST /openai/v1/chat/completions`, non-streaming
- `ChatStreamlyWithSender`: SSE stream against the same endpoint
- `ListModels` / `CheckConnection`: `GET /openai/v1/models`
- **Reasoning extraction**: `message.reasoning_content` (non-stream) and
`delta.reasoning_content` (stream) flow into
`ChatResponse.ReasonContent` / the sender's second arg. Matches the
OpenAI o-series convention also used by kimi-k2.6 and DeepSeek-R1.
- **`reasoning_effort` propagation**: `ChatConfig.Effort` → request body
`reasoning_effort` (LongCat-Flash-Thinking honors it; non-reasoning
models ignore it).
- `Embed` / `Rerank` / `Balance` / `TranscribeAudio` / `AudioSpeech` /
`OCRFile` return `"no such method"` (LongCat does not expose any of
these surfaces).
No interface change. No new dependencies.
### How was this tested?
**21 unit tests** in `internal/entity/models/longcat_test.go` — all
pass:
```
$ go test -vet=off -run TestLongCat -count=1 -v ./internal/entity/models/...
=== RUN TestLongCatName
--- PASS: TestLongCatName (0.00s)
=== RUN TestLongCatChatHappyPath
--- PASS: TestLongCatChatHappyPath (0.00s)
=== RUN TestLongCatChatExtractsReasoningContent
--- PASS: TestLongCatChatExtractsReasoningContent (0.00s)
=== RUN TestLongCatChatPropagatesReasoningEffort
--- PASS: TestLongCatChatPropagatesReasoningEffort (0.00s)
=== RUN TestLongCatChatOmitsReasoningEffortWhenUnset
--- PASS: TestLongCatChatOmitsReasoningEffortWhenUnset (0.00s)
=== RUN TestLongCatChatRequiresAPIKey
--- PASS: TestLongCatChatRequiresAPIKey (0.00s)
=== RUN TestLongCatChatRequiresMessages
--- PASS: TestLongCatChatRequiresMessages (0.00s)
=== RUN TestLongCatChatRejectsHTTPError
--- PASS: TestLongCatChatRejectsHTTPError (0.00s)
=== RUN TestLongCatStreamHappyPath
--- PASS: TestLongCatStreamHappyPath (0.00s)
=== RUN TestLongCatStreamExtractsReasoningContent
--- PASS: TestLongCatStreamExtractsReasoningContent (0.00s)
=== RUN TestLongCatStreamRejectsExplicitFalse
--- PASS: TestLongCatStreamRejectsExplicitFalse (0.00s)
=== RUN TestLongCatStreamRequiresSender
--- PASS: TestLongCatStreamRequiresSender (0.00s)
=== RUN TestLongCatStreamFailsWithoutTerminal
--- PASS: TestLongCatStreamFailsWithoutTerminal (0.00s)
=== RUN TestLongCatListModelsHappyPath
--- PASS: TestLongCatListModelsHappyPath (0.00s)
=== RUN TestLongCatListModelsRequiresAPIKey
--- PASS: TestLongCatListModelsRequiresAPIKey (0.00s)
=== RUN TestLongCatCheckConnectionDelegatesToListModels
--- PASS: TestLongCatCheckConnectionDelegatesToListModels (0.00s)
=== RUN TestLongCatEmbedReturnsNoSuchMethod
--- PASS: TestLongCatEmbedReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatRerankReturnsNoSuchMethod
--- PASS: TestLongCatRerankReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatBalanceReturnsNoSuchMethod
--- PASS: TestLongCatBalanceReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatAudioOCRReturnNoSuchMethod
--- PASS: TestLongCatAudioOCRReturnNoSuchMethod (0.00s)
PASS
ok ragflow/internal/entity/models 0.020s
```
`go build ./internal/entity/models/...` exits 0 on go 1.25.
**Live integration test** against `api.longcat.chat`:
```
=== RUN TestLongCatLiveSmoke
[OK] Name() = "longcat"
[OK] CheckConnection
[OK] ListModels: 5 models -> [LongCat-Flash-Lite LongCat-Flash-Chat LongCat-Flash-Thinking-2601 LongCat-Flash-Omni-2603 LongCat-2.0-Preview]
[OK] Chat (Flash-Chat) answer="Got it! Let me know if you" reason=""
[OK] Chat (Flash-Thinking) answer len=443 head="To find 15 % of 80, follow these steps:\n\n1. **Convert the percentage to a frac..."
ReasonContent len=557 head="The user asks: \"15% of 80?\" They want step by step reasoning and final answer in \\boxed{}. So we need to compute 15% of ..."
[OK] Stream content: 78 chunks, 351 chars
[OK] Stream reasoning: 107 chunks, 537 chars
[OK] Balance returns longcat, no such method
[OK] Embed returns longcat, no such method
[OK] Rerank returns longcat, no such method
LONGCAT LIVE SMOKE PASSED
--- PASS: TestLongCatLiveSmoke (31.01s)
```
What the live run proves on the wire:
- Auth header (`Bearer <key>`) is accepted by `api.longcat.chat`.
- `/openai/v1/models` parser handles the real 5-model response (note:
live API returns versioned aliases `LongCat-Flash-Thinking-2601`,
`LongCat-Flash-Omni-2603`, `LongCat-2.0-Preview` plus the un-versioned
`LongCat-Flash-Chat` and `LongCat-Flash-Lite`).
- Non-stream chat against `LongCat-Flash-Chat`: visible answer parses
correctly, `ReasonContent` correctly empty.
- Non-stream chat against `LongCat-Flash-Thinking`: 443-char answer
flows into `Answer`, 557-char chain-of-thought flows into
`ReasonContent` via the new `message.reasoning_content` extraction.
- Streaming chat against `LongCat-Flash-Thinking`: 107 reasoning chunks
(537 chars) reach the sender's second arg via `delta.reasoning_content`;
78 content chunks (351 chars) reach the first arg. Before this code, the
reasoning chunks would have been silently dropped.
- All sentinel methods (Balance, Embed, Rerank, audio/OCR) return the
documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for LongCat. The diff against `main` is a clean +969 lines
across 4 files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 22:27:56 -10:00
|
|
|
if body["model"] != "LongCat-Flash-Chat" {
|
|
|
|
|
t.Errorf("model=%v", body["model"])
|
|
|
|
|
}
|
|
|
|
|
if body["stream"] != false {
|
|
|
|
|
t.Errorf("stream=%v want false", body["stream"])
|
|
|
|
|
}
|
|
|
|
|
_ = json.NewEncoder(w).Encode(map[string]interface{}{
|
|
|
|
|
"choices": []map[string]interface{}{{
|
|
|
|
|
"message": map[string]interface{}{"content": "pong"},
|
|
|
|
|
}},
|
|
|
|
|
})
|
|
|
|
|
})
|
|
|
|
|
defer srv.Close()
|
|
|
|
|
|
|
|
|
|
m := newLongCatForTest(srv.URL)
|
|
|
|
|
apiKey := "test-key"
|
|
|
|
|
resp, err := m.ChatWithMessages("LongCat-Flash-Chat",
|
|
|
|
|
[]Message{{Role: "user", Content: "ping"}},
|
|
|
|
|
&APIConfig{ApiKey: &apiKey}, nil)
|
|
|
|
|
if err != nil {
|
|
|
|
|
t.Fatalf("Chat: %v", err)
|
|
|
|
|
}
|
|
|
|
|
if resp.Answer == nil || resp.ReasonContent == nil {
|
|
|
|
|
t.Fatalf("Answer/ReasonContent must be non-nil pointers, got Answer=%v ReasonContent=%v", resp.Answer, resp.ReasonContent)
|
|
|
|
|
}
|
|
|
|
|
if *resp.Answer != "pong" {
|
|
|
|
|
t.Errorf("answer=%q want pong", *resp.Answer)
|
|
|
|
|
}
|
|
|
|
|
if *resp.ReasonContent != "" {
|
|
|
|
|
t.Errorf("ReasonContent=%q want empty", *resp.ReasonContent)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func TestLongCatChatExtractsReasoningContent(t *testing.T) {
|
|
|
|
|
// LongCat-Flash-Thinking returns the chain-of-thought in
|
|
|
|
|
// message.reasoning_content (OpenAI o-series shape). Live-probed
|
|
|
|
|
// against api.longcat.chat; the fixture mimics the actual response
|
|
|
|
|
// shape captured there.
|
2026-05-26 04:58:53 -07:00
|
|
|
srv := newLongCatServer(t, "/openai/v1/chat/completions", func(t *testing.T, _ *http.Request, body map[string]interface{}, w http.ResponseWriter) {
|
Go: implement provider: LongCat (#14809)
### What problem does this PR solve?
Add a Go driver for LongCat (Meituan, https://longcat.chat), one of the
unchecked providers on the umbrella tracking issue #14736. LongCat
exposes an OpenAI-compatible REST API at
`https://api.longcat.chat/openai/v1` with three public chat models
including `LongCat-Flash-Thinking`, a reasoning model that returns
chain-of-thought in `reasoning_content` (OpenAI o-series shape).
Until this PR, a tenant who configured `longcat` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/longcat.go` with a `LongCatModel`
implementing the `ModelDriver` interface.
- New `conf/models/longcat.json` with the 3 public chat models
(Flash-Chat, Flash-Lite, Flash-Thinking) and `url_suffix` for `chat` and
`models`.
- `factory.go`: route `"longcat"` to `NewLongCatModel`.
Method coverage:
- `ChatWithMessages`: `POST /openai/v1/chat/completions`, non-streaming
- `ChatStreamlyWithSender`: SSE stream against the same endpoint
- `ListModels` / `CheckConnection`: `GET /openai/v1/models`
- **Reasoning extraction**: `message.reasoning_content` (non-stream) and
`delta.reasoning_content` (stream) flow into
`ChatResponse.ReasonContent` / the sender's second arg. Matches the
OpenAI o-series convention also used by kimi-k2.6 and DeepSeek-R1.
- **`reasoning_effort` propagation**: `ChatConfig.Effort` → request body
`reasoning_effort` (LongCat-Flash-Thinking honors it; non-reasoning
models ignore it).
- `Embed` / `Rerank` / `Balance` / `TranscribeAudio` / `AudioSpeech` /
`OCRFile` return `"no such method"` (LongCat does not expose any of
these surfaces).
No interface change. No new dependencies.
### How was this tested?
**21 unit tests** in `internal/entity/models/longcat_test.go` — all
pass:
```
$ go test -vet=off -run TestLongCat -count=1 -v ./internal/entity/models/...
=== RUN TestLongCatName
--- PASS: TestLongCatName (0.00s)
=== RUN TestLongCatChatHappyPath
--- PASS: TestLongCatChatHappyPath (0.00s)
=== RUN TestLongCatChatExtractsReasoningContent
--- PASS: TestLongCatChatExtractsReasoningContent (0.00s)
=== RUN TestLongCatChatPropagatesReasoningEffort
--- PASS: TestLongCatChatPropagatesReasoningEffort (0.00s)
=== RUN TestLongCatChatOmitsReasoningEffortWhenUnset
--- PASS: TestLongCatChatOmitsReasoningEffortWhenUnset (0.00s)
=== RUN TestLongCatChatRequiresAPIKey
--- PASS: TestLongCatChatRequiresAPIKey (0.00s)
=== RUN TestLongCatChatRequiresMessages
--- PASS: TestLongCatChatRequiresMessages (0.00s)
=== RUN TestLongCatChatRejectsHTTPError
--- PASS: TestLongCatChatRejectsHTTPError (0.00s)
=== RUN TestLongCatStreamHappyPath
--- PASS: TestLongCatStreamHappyPath (0.00s)
=== RUN TestLongCatStreamExtractsReasoningContent
--- PASS: TestLongCatStreamExtractsReasoningContent (0.00s)
=== RUN TestLongCatStreamRejectsExplicitFalse
--- PASS: TestLongCatStreamRejectsExplicitFalse (0.00s)
=== RUN TestLongCatStreamRequiresSender
--- PASS: TestLongCatStreamRequiresSender (0.00s)
=== RUN TestLongCatStreamFailsWithoutTerminal
--- PASS: TestLongCatStreamFailsWithoutTerminal (0.00s)
=== RUN TestLongCatListModelsHappyPath
--- PASS: TestLongCatListModelsHappyPath (0.00s)
=== RUN TestLongCatListModelsRequiresAPIKey
--- PASS: TestLongCatListModelsRequiresAPIKey (0.00s)
=== RUN TestLongCatCheckConnectionDelegatesToListModels
--- PASS: TestLongCatCheckConnectionDelegatesToListModels (0.00s)
=== RUN TestLongCatEmbedReturnsNoSuchMethod
--- PASS: TestLongCatEmbedReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatRerankReturnsNoSuchMethod
--- PASS: TestLongCatRerankReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatBalanceReturnsNoSuchMethod
--- PASS: TestLongCatBalanceReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatAudioOCRReturnNoSuchMethod
--- PASS: TestLongCatAudioOCRReturnNoSuchMethod (0.00s)
PASS
ok ragflow/internal/entity/models 0.020s
```
`go build ./internal/entity/models/...` exits 0 on go 1.25.
**Live integration test** against `api.longcat.chat`:
```
=== RUN TestLongCatLiveSmoke
[OK] Name() = "longcat"
[OK] CheckConnection
[OK] ListModels: 5 models -> [LongCat-Flash-Lite LongCat-Flash-Chat LongCat-Flash-Thinking-2601 LongCat-Flash-Omni-2603 LongCat-2.0-Preview]
[OK] Chat (Flash-Chat) answer="Got it! Let me know if you" reason=""
[OK] Chat (Flash-Thinking) answer len=443 head="To find 15 % of 80, follow these steps:\n\n1. **Convert the percentage to a frac..."
ReasonContent len=557 head="The user asks: \"15% of 80?\" They want step by step reasoning and final answer in \\boxed{}. So we need to compute 15% of ..."
[OK] Stream content: 78 chunks, 351 chars
[OK] Stream reasoning: 107 chunks, 537 chars
[OK] Balance returns longcat, no such method
[OK] Embed returns longcat, no such method
[OK] Rerank returns longcat, no such method
LONGCAT LIVE SMOKE PASSED
--- PASS: TestLongCatLiveSmoke (31.01s)
```
What the live run proves on the wire:
- Auth header (`Bearer <key>`) is accepted by `api.longcat.chat`.
- `/openai/v1/models` parser handles the real 5-model response (note:
live API returns versioned aliases `LongCat-Flash-Thinking-2601`,
`LongCat-Flash-Omni-2603`, `LongCat-2.0-Preview` plus the un-versioned
`LongCat-Flash-Chat` and `LongCat-Flash-Lite`).
- Non-stream chat against `LongCat-Flash-Chat`: visible answer parses
correctly, `ReasonContent` correctly empty.
- Non-stream chat against `LongCat-Flash-Thinking`: 443-char answer
flows into `Answer`, 557-char chain-of-thought flows into
`ReasonContent` via the new `message.reasoning_content` extraction.
- Streaming chat against `LongCat-Flash-Thinking`: 107 reasoning chunks
(537 chars) reach the sender's second arg via `delta.reasoning_content`;
78 content chunks (351 chars) reach the first arg. Before this code, the
reasoning chunks would have been silently dropped.
- All sentinel methods (Balance, Embed, Rerank, audio/OCR) return the
documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for LongCat. The diff against `main` is a clean +969 lines
across 4 files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 22:27:56 -10:00
|
|
|
if body["model"] != "LongCat-Flash-Thinking" {
|
|
|
|
|
t.Errorf("model=%v", body["model"])
|
|
|
|
|
}
|
|
|
|
|
_ = json.NewEncoder(w).Encode(map[string]interface{}{
|
|
|
|
|
"choices": []map[string]interface{}{{
|
|
|
|
|
"message": map[string]interface{}{
|
|
|
|
|
"role": "assistant",
|
|
|
|
|
"content": "15% of 80 is 12.",
|
|
|
|
|
"reasoning_content": "We need to compute 15% of 80. 0.15 * 80 = 12.",
|
|
|
|
|
},
|
|
|
|
|
}},
|
|
|
|
|
})
|
|
|
|
|
})
|
|
|
|
|
defer srv.Close()
|
|
|
|
|
|
|
|
|
|
m := newLongCatForTest(srv.URL)
|
|
|
|
|
apiKey := "test-key"
|
|
|
|
|
resp, err := m.ChatWithMessages("LongCat-Flash-Thinking",
|
|
|
|
|
[]Message{{Role: "user", Content: "15% of 80?"}},
|
|
|
|
|
&APIConfig{ApiKey: &apiKey}, nil)
|
|
|
|
|
if err != nil {
|
|
|
|
|
t.Fatalf("Chat: %v", err)
|
|
|
|
|
}
|
|
|
|
|
if resp.Answer == nil || resp.ReasonContent == nil {
|
|
|
|
|
t.Fatalf("Answer/ReasonContent must be non-nil pointers, got Answer=%v ReasonContent=%v", resp.Answer, resp.ReasonContent)
|
|
|
|
|
}
|
|
|
|
|
if *resp.Answer != "15% of 80 is 12." {
|
|
|
|
|
t.Errorf("Answer=%q", *resp.Answer)
|
|
|
|
|
}
|
|
|
|
|
if *resp.ReasonContent != "We need to compute 15% of 80. 0.15 * 80 = 12." {
|
|
|
|
|
t.Errorf("ReasonContent=%q", *resp.ReasonContent)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// TestLongCatChatDropsUndocumentedFields guards against re-introducing
|
|
|
|
|
// stop / reasoning_effort / response_format / tools etc. The LongCat
|
|
|
|
|
// docs only list model, messages, stream, max_tokens, temperature,
|
|
|
|
|
// top_p — anything else is undocumented and must not be sent, since
|
|
|
|
|
// the maintainer specifically flagged this on PR #14809.
|
|
|
|
|
func TestLongCatChatDropsUndocumentedFields(t *testing.T) {
|
2026-05-26 04:58:53 -07:00
|
|
|
srv := newLongCatServer(t, "/openai/v1/chat/completions", func(t *testing.T, _ *http.Request, body map[string]interface{}, w http.ResponseWriter) {
|
Go: implement provider: LongCat (#14809)
### What problem does this PR solve?
Add a Go driver for LongCat (Meituan, https://longcat.chat), one of the
unchecked providers on the umbrella tracking issue #14736. LongCat
exposes an OpenAI-compatible REST API at
`https://api.longcat.chat/openai/v1` with three public chat models
including `LongCat-Flash-Thinking`, a reasoning model that returns
chain-of-thought in `reasoning_content` (OpenAI o-series shape).
Until this PR, a tenant who configured `longcat` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/longcat.go` with a `LongCatModel`
implementing the `ModelDriver` interface.
- New `conf/models/longcat.json` with the 3 public chat models
(Flash-Chat, Flash-Lite, Flash-Thinking) and `url_suffix` for `chat` and
`models`.
- `factory.go`: route `"longcat"` to `NewLongCatModel`.
Method coverage:
- `ChatWithMessages`: `POST /openai/v1/chat/completions`, non-streaming
- `ChatStreamlyWithSender`: SSE stream against the same endpoint
- `ListModels` / `CheckConnection`: `GET /openai/v1/models`
- **Reasoning extraction**: `message.reasoning_content` (non-stream) and
`delta.reasoning_content` (stream) flow into
`ChatResponse.ReasonContent` / the sender's second arg. Matches the
OpenAI o-series convention also used by kimi-k2.6 and DeepSeek-R1.
- **`reasoning_effort` propagation**: `ChatConfig.Effort` → request body
`reasoning_effort` (LongCat-Flash-Thinking honors it; non-reasoning
models ignore it).
- `Embed` / `Rerank` / `Balance` / `TranscribeAudio` / `AudioSpeech` /
`OCRFile` return `"no such method"` (LongCat does not expose any of
these surfaces).
No interface change. No new dependencies.
### How was this tested?
**21 unit tests** in `internal/entity/models/longcat_test.go` — all
pass:
```
$ go test -vet=off -run TestLongCat -count=1 -v ./internal/entity/models/...
=== RUN TestLongCatName
--- PASS: TestLongCatName (0.00s)
=== RUN TestLongCatChatHappyPath
--- PASS: TestLongCatChatHappyPath (0.00s)
=== RUN TestLongCatChatExtractsReasoningContent
--- PASS: TestLongCatChatExtractsReasoningContent (0.00s)
=== RUN TestLongCatChatPropagatesReasoningEffort
--- PASS: TestLongCatChatPropagatesReasoningEffort (0.00s)
=== RUN TestLongCatChatOmitsReasoningEffortWhenUnset
--- PASS: TestLongCatChatOmitsReasoningEffortWhenUnset (0.00s)
=== RUN TestLongCatChatRequiresAPIKey
--- PASS: TestLongCatChatRequiresAPIKey (0.00s)
=== RUN TestLongCatChatRequiresMessages
--- PASS: TestLongCatChatRequiresMessages (0.00s)
=== RUN TestLongCatChatRejectsHTTPError
--- PASS: TestLongCatChatRejectsHTTPError (0.00s)
=== RUN TestLongCatStreamHappyPath
--- PASS: TestLongCatStreamHappyPath (0.00s)
=== RUN TestLongCatStreamExtractsReasoningContent
--- PASS: TestLongCatStreamExtractsReasoningContent (0.00s)
=== RUN TestLongCatStreamRejectsExplicitFalse
--- PASS: TestLongCatStreamRejectsExplicitFalse (0.00s)
=== RUN TestLongCatStreamRequiresSender
--- PASS: TestLongCatStreamRequiresSender (0.00s)
=== RUN TestLongCatStreamFailsWithoutTerminal
--- PASS: TestLongCatStreamFailsWithoutTerminal (0.00s)
=== RUN TestLongCatListModelsHappyPath
--- PASS: TestLongCatListModelsHappyPath (0.00s)
=== RUN TestLongCatListModelsRequiresAPIKey
--- PASS: TestLongCatListModelsRequiresAPIKey (0.00s)
=== RUN TestLongCatCheckConnectionDelegatesToListModels
--- PASS: TestLongCatCheckConnectionDelegatesToListModels (0.00s)
=== RUN TestLongCatEmbedReturnsNoSuchMethod
--- PASS: TestLongCatEmbedReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatRerankReturnsNoSuchMethod
--- PASS: TestLongCatRerankReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatBalanceReturnsNoSuchMethod
--- PASS: TestLongCatBalanceReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatAudioOCRReturnNoSuchMethod
--- PASS: TestLongCatAudioOCRReturnNoSuchMethod (0.00s)
PASS
ok ragflow/internal/entity/models 0.020s
```
`go build ./internal/entity/models/...` exits 0 on go 1.25.
**Live integration test** against `api.longcat.chat`:
```
=== RUN TestLongCatLiveSmoke
[OK] Name() = "longcat"
[OK] CheckConnection
[OK] ListModels: 5 models -> [LongCat-Flash-Lite LongCat-Flash-Chat LongCat-Flash-Thinking-2601 LongCat-Flash-Omni-2603 LongCat-2.0-Preview]
[OK] Chat (Flash-Chat) answer="Got it! Let me know if you" reason=""
[OK] Chat (Flash-Thinking) answer len=443 head="To find 15 % of 80, follow these steps:\n\n1. **Convert the percentage to a frac..."
ReasonContent len=557 head="The user asks: \"15% of 80?\" They want step by step reasoning and final answer in \\boxed{}. So we need to compute 15% of ..."
[OK] Stream content: 78 chunks, 351 chars
[OK] Stream reasoning: 107 chunks, 537 chars
[OK] Balance returns longcat, no such method
[OK] Embed returns longcat, no such method
[OK] Rerank returns longcat, no such method
LONGCAT LIVE SMOKE PASSED
--- PASS: TestLongCatLiveSmoke (31.01s)
```
What the live run proves on the wire:
- Auth header (`Bearer <key>`) is accepted by `api.longcat.chat`.
- `/openai/v1/models` parser handles the real 5-model response (note:
live API returns versioned aliases `LongCat-Flash-Thinking-2601`,
`LongCat-Flash-Omni-2603`, `LongCat-2.0-Preview` plus the un-versioned
`LongCat-Flash-Chat` and `LongCat-Flash-Lite`).
- Non-stream chat against `LongCat-Flash-Chat`: visible answer parses
correctly, `ReasonContent` correctly empty.
- Non-stream chat against `LongCat-Flash-Thinking`: 443-char answer
flows into `Answer`, 557-char chain-of-thought flows into
`ReasonContent` via the new `message.reasoning_content` extraction.
- Streaming chat against `LongCat-Flash-Thinking`: 107 reasoning chunks
(537 chars) reach the sender's second arg via `delta.reasoning_content`;
78 content chunks (351 chars) reach the first arg. Before this code, the
reasoning chunks would have been silently dropped.
- All sentinel methods (Balance, Embed, Rerank, audio/OCR) return the
documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for LongCat. The diff against `main` is a clean +969 lines
across 4 files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 22:27:56 -10:00
|
|
|
for _, k := range []string{"stop", "reasoning_effort", "response_format", "tools", "tool_choice", "presence_penalty", "frequency_penalty", "n", "logprobs"} {
|
|
|
|
|
if _, present := body[k]; present {
|
|
|
|
|
t.Errorf("undocumented field %q must not be sent: %v", k, body[k])
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
// Documented fields, on the other hand, MUST be forwarded when set.
|
|
|
|
|
for _, k := range []string{"model", "messages", "stream", "max_tokens", "temperature", "top_p"} {
|
|
|
|
|
if _, present := body[k]; !present {
|
|
|
|
|
t.Errorf("documented field %q missing from request body", k)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
_ = json.NewEncoder(w).Encode(map[string]interface{}{
|
|
|
|
|
"choices": []map[string]interface{}{{
|
|
|
|
|
"message": map[string]interface{}{"content": "ok"},
|
|
|
|
|
}},
|
|
|
|
|
})
|
|
|
|
|
})
|
|
|
|
|
defer srv.Close()
|
|
|
|
|
|
|
|
|
|
m := newLongCatForTest(srv.URL)
|
|
|
|
|
apiKey := "test-key"
|
|
|
|
|
mt := 32
|
|
|
|
|
temp := 0.7
|
|
|
|
|
topP := 0.9
|
|
|
|
|
stop := []string{"END"}
|
|
|
|
|
effort := "high"
|
|
|
|
|
_, err := m.ChatWithMessages("LongCat-Flash-Chat",
|
|
|
|
|
[]Message{{Role: "user", Content: "x"}},
|
|
|
|
|
&APIConfig{ApiKey: &apiKey},
|
|
|
|
|
// Deliberately pass Stop/Effort to prove they are filtered out.
|
|
|
|
|
&ChatConfig{MaxTokens: &mt, Temperature: &temp, TopP: &topP, Stop: &stop, Effort: &effort})
|
|
|
|
|
if err != nil {
|
|
|
|
|
t.Fatalf("Chat: %v", err)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func TestLongCatChatRequiresAPIKey(t *testing.T) {
|
|
|
|
|
m := newLongCatForTest("http://unused")
|
|
|
|
|
_, err := m.ChatWithMessages("LongCat-Flash-Chat",
|
|
|
|
|
[]Message{{Role: "user", Content: "x"}},
|
|
|
|
|
&APIConfig{}, nil)
|
|
|
|
|
if err == nil || !strings.Contains(err.Error(), "api key is required") {
|
|
|
|
|
t.Errorf("expected api-key error, got %v", err)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func TestLongCatChatRequiresMessages(t *testing.T) {
|
|
|
|
|
m := newLongCatForTest("http://unused")
|
|
|
|
|
apiKey := "test-key"
|
|
|
|
|
_, err := m.ChatWithMessages("LongCat-Flash-Chat", nil, &APIConfig{ApiKey: &apiKey}, nil)
|
|
|
|
|
if err == nil || !strings.Contains(err.Error(), "messages is empty") {
|
|
|
|
|
t.Errorf("expected messages-empty error, got %v", err)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func TestLongCatChatRejectsHTTPError(t *testing.T) {
|
2026-05-26 04:58:53 -07:00
|
|
|
srv := newLongCatServer(t, "/openai/v1/chat/completions", func(t *testing.T, _ *http.Request, body map[string]interface{}, w http.ResponseWriter) {
|
Go: implement provider: LongCat (#14809)
### What problem does this PR solve?
Add a Go driver for LongCat (Meituan, https://longcat.chat), one of the
unchecked providers on the umbrella tracking issue #14736. LongCat
exposes an OpenAI-compatible REST API at
`https://api.longcat.chat/openai/v1` with three public chat models
including `LongCat-Flash-Thinking`, a reasoning model that returns
chain-of-thought in `reasoning_content` (OpenAI o-series shape).
Until this PR, a tenant who configured `longcat` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/longcat.go` with a `LongCatModel`
implementing the `ModelDriver` interface.
- New `conf/models/longcat.json` with the 3 public chat models
(Flash-Chat, Flash-Lite, Flash-Thinking) and `url_suffix` for `chat` and
`models`.
- `factory.go`: route `"longcat"` to `NewLongCatModel`.
Method coverage:
- `ChatWithMessages`: `POST /openai/v1/chat/completions`, non-streaming
- `ChatStreamlyWithSender`: SSE stream against the same endpoint
- `ListModels` / `CheckConnection`: `GET /openai/v1/models`
- **Reasoning extraction**: `message.reasoning_content` (non-stream) and
`delta.reasoning_content` (stream) flow into
`ChatResponse.ReasonContent` / the sender's second arg. Matches the
OpenAI o-series convention also used by kimi-k2.6 and DeepSeek-R1.
- **`reasoning_effort` propagation**: `ChatConfig.Effort` → request body
`reasoning_effort` (LongCat-Flash-Thinking honors it; non-reasoning
models ignore it).
- `Embed` / `Rerank` / `Balance` / `TranscribeAudio` / `AudioSpeech` /
`OCRFile` return `"no such method"` (LongCat does not expose any of
these surfaces).
No interface change. No new dependencies.
### How was this tested?
**21 unit tests** in `internal/entity/models/longcat_test.go` — all
pass:
```
$ go test -vet=off -run TestLongCat -count=1 -v ./internal/entity/models/...
=== RUN TestLongCatName
--- PASS: TestLongCatName (0.00s)
=== RUN TestLongCatChatHappyPath
--- PASS: TestLongCatChatHappyPath (0.00s)
=== RUN TestLongCatChatExtractsReasoningContent
--- PASS: TestLongCatChatExtractsReasoningContent (0.00s)
=== RUN TestLongCatChatPropagatesReasoningEffort
--- PASS: TestLongCatChatPropagatesReasoningEffort (0.00s)
=== RUN TestLongCatChatOmitsReasoningEffortWhenUnset
--- PASS: TestLongCatChatOmitsReasoningEffortWhenUnset (0.00s)
=== RUN TestLongCatChatRequiresAPIKey
--- PASS: TestLongCatChatRequiresAPIKey (0.00s)
=== RUN TestLongCatChatRequiresMessages
--- PASS: TestLongCatChatRequiresMessages (0.00s)
=== RUN TestLongCatChatRejectsHTTPError
--- PASS: TestLongCatChatRejectsHTTPError (0.00s)
=== RUN TestLongCatStreamHappyPath
--- PASS: TestLongCatStreamHappyPath (0.00s)
=== RUN TestLongCatStreamExtractsReasoningContent
--- PASS: TestLongCatStreamExtractsReasoningContent (0.00s)
=== RUN TestLongCatStreamRejectsExplicitFalse
--- PASS: TestLongCatStreamRejectsExplicitFalse (0.00s)
=== RUN TestLongCatStreamRequiresSender
--- PASS: TestLongCatStreamRequiresSender (0.00s)
=== RUN TestLongCatStreamFailsWithoutTerminal
--- PASS: TestLongCatStreamFailsWithoutTerminal (0.00s)
=== RUN TestLongCatListModelsHappyPath
--- PASS: TestLongCatListModelsHappyPath (0.00s)
=== RUN TestLongCatListModelsRequiresAPIKey
--- PASS: TestLongCatListModelsRequiresAPIKey (0.00s)
=== RUN TestLongCatCheckConnectionDelegatesToListModels
--- PASS: TestLongCatCheckConnectionDelegatesToListModels (0.00s)
=== RUN TestLongCatEmbedReturnsNoSuchMethod
--- PASS: TestLongCatEmbedReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatRerankReturnsNoSuchMethod
--- PASS: TestLongCatRerankReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatBalanceReturnsNoSuchMethod
--- PASS: TestLongCatBalanceReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatAudioOCRReturnNoSuchMethod
--- PASS: TestLongCatAudioOCRReturnNoSuchMethod (0.00s)
PASS
ok ragflow/internal/entity/models 0.020s
```
`go build ./internal/entity/models/...` exits 0 on go 1.25.
**Live integration test** against `api.longcat.chat`:
```
=== RUN TestLongCatLiveSmoke
[OK] Name() = "longcat"
[OK] CheckConnection
[OK] ListModels: 5 models -> [LongCat-Flash-Lite LongCat-Flash-Chat LongCat-Flash-Thinking-2601 LongCat-Flash-Omni-2603 LongCat-2.0-Preview]
[OK] Chat (Flash-Chat) answer="Got it! Let me know if you" reason=""
[OK] Chat (Flash-Thinking) answer len=443 head="To find 15 % of 80, follow these steps:\n\n1. **Convert the percentage to a frac..."
ReasonContent len=557 head="The user asks: \"15% of 80?\" They want step by step reasoning and final answer in \\boxed{}. So we need to compute 15% of ..."
[OK] Stream content: 78 chunks, 351 chars
[OK] Stream reasoning: 107 chunks, 537 chars
[OK] Balance returns longcat, no such method
[OK] Embed returns longcat, no such method
[OK] Rerank returns longcat, no such method
LONGCAT LIVE SMOKE PASSED
--- PASS: TestLongCatLiveSmoke (31.01s)
```
What the live run proves on the wire:
- Auth header (`Bearer <key>`) is accepted by `api.longcat.chat`.
- `/openai/v1/models` parser handles the real 5-model response (note:
live API returns versioned aliases `LongCat-Flash-Thinking-2601`,
`LongCat-Flash-Omni-2603`, `LongCat-2.0-Preview` plus the un-versioned
`LongCat-Flash-Chat` and `LongCat-Flash-Lite`).
- Non-stream chat against `LongCat-Flash-Chat`: visible answer parses
correctly, `ReasonContent` correctly empty.
- Non-stream chat against `LongCat-Flash-Thinking`: 443-char answer
flows into `Answer`, 557-char chain-of-thought flows into
`ReasonContent` via the new `message.reasoning_content` extraction.
- Streaming chat against `LongCat-Flash-Thinking`: 107 reasoning chunks
(537 chars) reach the sender's second arg via `delta.reasoning_content`;
78 content chunks (351 chars) reach the first arg. Before this code, the
reasoning chunks would have been silently dropped.
- All sentinel methods (Balance, Embed, Rerank, audio/OCR) return the
documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for LongCat. The diff against `main` is a clean +969 lines
across 4 files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 22:27:56 -10:00
|
|
|
w.WriteHeader(http.StatusUnauthorized)
|
|
|
|
|
_, _ = w.Write([]byte(`{"error":"unauthorized"}`))
|
|
|
|
|
})
|
|
|
|
|
defer srv.Close()
|
|
|
|
|
|
|
|
|
|
m := newLongCatForTest(srv.URL)
|
|
|
|
|
apiKey := "test-key"
|
|
|
|
|
_, err := m.ChatWithMessages("LongCat-Flash-Chat",
|
|
|
|
|
[]Message{{Role: "user", Content: "x"}},
|
|
|
|
|
&APIConfig{ApiKey: &apiKey}, nil)
|
|
|
|
|
if err == nil || !strings.Contains(err.Error(), "401") {
|
|
|
|
|
t.Errorf("expected 401 propagated, got %v", err)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func TestLongCatStreamHappyPath(t *testing.T) {
|
|
|
|
|
srv := newLongCatSSEServer(t, "/openai/v1/chat/completions",
|
|
|
|
|
`data: {"choices":[{"index":0,"delta":{"role":"assistant"}}]}`+"\n"+
|
|
|
|
|
`data: {"choices":[{"index":0,"delta":{"content":"Hello"}}]}`+"\n"+
|
|
|
|
|
`data: {"choices":[{"index":0,"delta":{"content":" world"},"finish_reason":"stop"}]}`+"\n"+
|
|
|
|
|
`data: [DONE]`+"\n",
|
|
|
|
|
)
|
|
|
|
|
defer srv.Close()
|
|
|
|
|
|
|
|
|
|
m := newLongCatForTest(srv.URL)
|
|
|
|
|
apiKey := "test-key"
|
|
|
|
|
var chunks []string
|
|
|
|
|
var sawDone bool
|
|
|
|
|
err := m.ChatStreamlyWithSender("LongCat-Flash-Chat",
|
|
|
|
|
[]Message{{Role: "user", Content: "hi"}},
|
|
|
|
|
&APIConfig{ApiKey: &apiKey}, nil,
|
|
|
|
|
func(c *string, _ *string) error {
|
|
|
|
|
if c == nil {
|
|
|
|
|
return nil
|
|
|
|
|
}
|
|
|
|
|
if *c == "[DONE]" {
|
|
|
|
|
sawDone = true
|
|
|
|
|
return nil
|
|
|
|
|
}
|
|
|
|
|
chunks = append(chunks, *c)
|
|
|
|
|
return nil
|
|
|
|
|
})
|
|
|
|
|
if err != nil {
|
|
|
|
|
t.Fatalf("stream: %v", err)
|
|
|
|
|
}
|
|
|
|
|
if strings.Join(chunks, "") != "Hello world" {
|
|
|
|
|
t.Errorf("content=%v", chunks)
|
|
|
|
|
}
|
|
|
|
|
if !sawDone {
|
|
|
|
|
t.Error("expected [DONE] sentinel")
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func TestLongCatStreamExtractsReasoningContent(t *testing.T) {
|
|
|
|
|
// Fixture matches the shape captured live from
|
|
|
|
|
// LongCat-Flash-Thinking against api.longcat.chat: deltas
|
|
|
|
|
// interleave reasoning_content and content within the stream.
|
|
|
|
|
srv := newLongCatSSEServer(t, "/openai/v1/chat/completions",
|
|
|
|
|
`data: {"choices":[{"index":0,"delta":{"role":"assistant"}}]}`+"\n"+
|
|
|
|
|
`data: {"choices":[{"index":0,"delta":{"reasoning_content":"step 1. "}}]}`+"\n"+
|
|
|
|
|
`data: {"choices":[{"index":0,"delta":{"reasoning_content":"step 2."}}]}`+"\n"+
|
|
|
|
|
`data: {"choices":[{"index":0,"delta":{"content":"final answer"},"finish_reason":"stop"}]}`+"\n"+
|
|
|
|
|
`data: [DONE]`+"\n",
|
|
|
|
|
)
|
|
|
|
|
defer srv.Close()
|
|
|
|
|
|
|
|
|
|
m := newLongCatForTest(srv.URL)
|
|
|
|
|
apiKey := "test-key"
|
|
|
|
|
var content, reasoning []string
|
|
|
|
|
err := m.ChatStreamlyWithSender("LongCat-Flash-Thinking",
|
|
|
|
|
[]Message{{Role: "user", Content: "x"}},
|
|
|
|
|
&APIConfig{ApiKey: &apiKey}, nil,
|
|
|
|
|
func(c *string, r *string) error {
|
|
|
|
|
if c != nil && r != nil {
|
|
|
|
|
t.Errorf("sender called with both args non-nil")
|
|
|
|
|
}
|
|
|
|
|
if r != nil && *r != "" {
|
|
|
|
|
reasoning = append(reasoning, *r)
|
|
|
|
|
}
|
|
|
|
|
if c != nil && *c != "" && *c != "[DONE]" {
|
|
|
|
|
content = append(content, *c)
|
|
|
|
|
}
|
|
|
|
|
return nil
|
|
|
|
|
})
|
|
|
|
|
if err != nil {
|
|
|
|
|
t.Fatalf("stream: %v", err)
|
|
|
|
|
}
|
|
|
|
|
if got := strings.Join(reasoning, ""); got != "step 1. step 2." {
|
|
|
|
|
t.Errorf("reasoning=%q", got)
|
|
|
|
|
}
|
|
|
|
|
if got := strings.Join(content, ""); got != "final answer" {
|
|
|
|
|
t.Errorf("content=%q", got)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func TestLongCatStreamRejectsExplicitFalse(t *testing.T) {
|
|
|
|
|
m := newLongCatForTest("http://unused")
|
|
|
|
|
apiKey := "test-key"
|
|
|
|
|
stream := false
|
|
|
|
|
err := m.ChatStreamlyWithSender("LongCat-Flash-Chat",
|
|
|
|
|
[]Message{{Role: "user", Content: "x"}},
|
|
|
|
|
&APIConfig{ApiKey: &apiKey},
|
|
|
|
|
&ChatConfig{Stream: &stream},
|
|
|
|
|
func(*string, *string) error { return nil })
|
|
|
|
|
if err == nil || !strings.Contains(err.Error(), "stream must be true") {
|
|
|
|
|
t.Errorf("expected stream-true guard, got %v", err)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func TestLongCatStreamRequiresSender(t *testing.T) {
|
|
|
|
|
m := newLongCatForTest("http://unused")
|
|
|
|
|
apiKey := "test-key"
|
|
|
|
|
err := m.ChatStreamlyWithSender("LongCat-Flash-Chat",
|
|
|
|
|
[]Message{{Role: "user", Content: "x"}},
|
|
|
|
|
&APIConfig{ApiKey: &apiKey}, nil, nil)
|
|
|
|
|
if err == nil || !strings.Contains(err.Error(), "sender is required") {
|
|
|
|
|
t.Errorf("expected sender-required error, got %v", err)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func TestLongCatStreamFailsWithoutTerminal(t *testing.T) {
|
|
|
|
|
srv := newLongCatSSEServer(t, "/openai/v1/chat/completions",
|
|
|
|
|
`data: {"choices":[{"delta":{"content":"half"}}]}`+"\n",
|
|
|
|
|
)
|
|
|
|
|
defer srv.Close()
|
|
|
|
|
|
|
|
|
|
m := newLongCatForTest(srv.URL)
|
|
|
|
|
apiKey := "test-key"
|
|
|
|
|
err := m.ChatStreamlyWithSender("LongCat-Flash-Chat",
|
|
|
|
|
[]Message{{Role: "user", Content: "x"}},
|
|
|
|
|
&APIConfig{ApiKey: &apiKey}, nil,
|
|
|
|
|
func(*string, *string) error { return nil })
|
|
|
|
|
if err == nil || !strings.Contains(err.Error(), "stream ended before") {
|
|
|
|
|
t.Errorf("expected truncation error, got %v", err)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// A malformed SSE frame (invalid JSON) used to be silently skipped,
|
|
|
|
|
// which masked truncated or corrupted streams. The driver must now
|
|
|
|
|
// fail hard with a "longcat: invalid SSE event" wrapper.
|
|
|
|
|
func TestLongCatStreamRejectsMalformedFrame(t *testing.T) {
|
|
|
|
|
srv := newLongCatSSEServer(t, "/openai/v1/chat/completions",
|
|
|
|
|
`data: {"choices":[{"delta":{"content":"ok"}}]}`+"\n"+
|
|
|
|
|
`data: {this is not valid json}`+"\n",
|
|
|
|
|
)
|
|
|
|
|
defer srv.Close()
|
|
|
|
|
|
|
|
|
|
m := newLongCatForTest(srv.URL)
|
|
|
|
|
apiKey := "test-key"
|
|
|
|
|
err := m.ChatStreamlyWithSender("LongCat-Flash-Chat",
|
|
|
|
|
[]Message{{Role: "user", Content: "x"}},
|
|
|
|
|
&APIConfig{ApiKey: &apiKey}, nil,
|
|
|
|
|
func(*string, *string) error { return nil })
|
|
|
|
|
if err == nil || !strings.Contains(err.Error(), "invalid SSE event") {
|
|
|
|
|
t.Errorf("expected invalid-SSE error, got %v", err)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// An upstream {"error": ...} frame mid-stream used to fall through to
|
|
|
|
|
// the "no choices" continue and leave the caller with a generic
|
|
|
|
|
// truncation error. The driver must surface the upstream error verbatim.
|
|
|
|
|
func TestLongCatStreamSurfacesUpstreamError(t *testing.T) {
|
|
|
|
|
srv := newLongCatSSEServer(t, "/openai/v1/chat/completions",
|
|
|
|
|
`data: {"choices":[{"delta":{"content":"partial "}}]}`+"\n"+
|
|
|
|
|
`data: {"error":{"message":"rate limit exceeded","type":"rate_limit_error"}}`+"\n",
|
|
|
|
|
)
|
|
|
|
|
defer srv.Close()
|
|
|
|
|
|
|
|
|
|
m := newLongCatForTest(srv.URL)
|
|
|
|
|
apiKey := "test-key"
|
|
|
|
|
err := m.ChatStreamlyWithSender("LongCat-Flash-Chat",
|
|
|
|
|
[]Message{{Role: "user", Content: "x"}},
|
|
|
|
|
&APIConfig{ApiKey: &apiKey}, nil,
|
|
|
|
|
func(*string, *string) error { return nil })
|
|
|
|
|
if err == nil || !strings.Contains(err.Error(), "upstream stream error") {
|
|
|
|
|
t.Errorf("expected upstream-error surfacing, got %v", err)
|
|
|
|
|
}
|
|
|
|
|
if err != nil && !strings.Contains(err.Error(), "rate limit") {
|
|
|
|
|
t.Errorf("expected upstream message included, got %v", err)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2026-05-26 04:58:53 -07:00
|
|
|
func TestLongCatListModelsAndCheckConnection(t *testing.T) {
|
|
|
|
|
var requests int
|
|
|
|
|
srv := newLongCatServer(t, "/openai/v1/models", func(t *testing.T, r *http.Request, body map[string]interface{}, w http.ResponseWriter) {
|
|
|
|
|
requests++
|
|
|
|
|
if body != nil {
|
|
|
|
|
t.Errorf("GET /models should not send a JSON body: %v", body)
|
|
|
|
|
}
|
|
|
|
|
if r.ContentLength > 0 {
|
|
|
|
|
t.Errorf("GET /models should not send request body with ContentLength=%d", r.ContentLength)
|
|
|
|
|
}
|
|
|
|
|
raw, err := io.ReadAll(r.Body)
|
|
|
|
|
if err != nil {
|
|
|
|
|
t.Errorf("read GET body: %v", err)
|
|
|
|
|
return
|
|
|
|
|
}
|
|
|
|
|
if len(raw) > 0 {
|
|
|
|
|
t.Errorf("GET /models should not send request body: %q", string(raw))
|
|
|
|
|
}
|
|
|
|
|
if requests == 1 {
|
|
|
|
|
_ = json.NewEncoder(w).Encode(map[string]interface{}{
|
|
|
|
|
"object": "list",
|
|
|
|
|
"data": []map[string]interface{}{
|
|
|
|
|
{"id": "LongCat-Flash-Chat", "object": "model"},
|
|
|
|
|
{"id": "LongCat-Flash-Thinking-2601", "object": "model"},
|
|
|
|
|
{"id": "", "object": "model"},
|
|
|
|
|
},
|
|
|
|
|
})
|
|
|
|
|
return
|
|
|
|
|
}
|
|
|
|
|
_ = json.NewEncoder(w).Encode(map[string]interface{}{
|
|
|
|
|
"object": "list",
|
|
|
|
|
"data": []map[string]interface{}{
|
|
|
|
|
{"id": "LongCat-Flash-Chat", "object": "model"},
|
|
|
|
|
},
|
|
|
|
|
})
|
|
|
|
|
})
|
|
|
|
|
defer srv.Close()
|
|
|
|
|
|
Go: implement provider: LongCat (#14809)
### What problem does this PR solve?
Add a Go driver for LongCat (Meituan, https://longcat.chat), one of the
unchecked providers on the umbrella tracking issue #14736. LongCat
exposes an OpenAI-compatible REST API at
`https://api.longcat.chat/openai/v1` with three public chat models
including `LongCat-Flash-Thinking`, a reasoning model that returns
chain-of-thought in `reasoning_content` (OpenAI o-series shape).
Until this PR, a tenant who configured `longcat` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/longcat.go` with a `LongCatModel`
implementing the `ModelDriver` interface.
- New `conf/models/longcat.json` with the 3 public chat models
(Flash-Chat, Flash-Lite, Flash-Thinking) and `url_suffix` for `chat` and
`models`.
- `factory.go`: route `"longcat"` to `NewLongCatModel`.
Method coverage:
- `ChatWithMessages`: `POST /openai/v1/chat/completions`, non-streaming
- `ChatStreamlyWithSender`: SSE stream against the same endpoint
- `ListModels` / `CheckConnection`: `GET /openai/v1/models`
- **Reasoning extraction**: `message.reasoning_content` (non-stream) and
`delta.reasoning_content` (stream) flow into
`ChatResponse.ReasonContent` / the sender's second arg. Matches the
OpenAI o-series convention also used by kimi-k2.6 and DeepSeek-R1.
- **`reasoning_effort` propagation**: `ChatConfig.Effort` → request body
`reasoning_effort` (LongCat-Flash-Thinking honors it; non-reasoning
models ignore it).
- `Embed` / `Rerank` / `Balance` / `TranscribeAudio` / `AudioSpeech` /
`OCRFile` return `"no such method"` (LongCat does not expose any of
these surfaces).
No interface change. No new dependencies.
### How was this tested?
**21 unit tests** in `internal/entity/models/longcat_test.go` — all
pass:
```
$ go test -vet=off -run TestLongCat -count=1 -v ./internal/entity/models/...
=== RUN TestLongCatName
--- PASS: TestLongCatName (0.00s)
=== RUN TestLongCatChatHappyPath
--- PASS: TestLongCatChatHappyPath (0.00s)
=== RUN TestLongCatChatExtractsReasoningContent
--- PASS: TestLongCatChatExtractsReasoningContent (0.00s)
=== RUN TestLongCatChatPropagatesReasoningEffort
--- PASS: TestLongCatChatPropagatesReasoningEffort (0.00s)
=== RUN TestLongCatChatOmitsReasoningEffortWhenUnset
--- PASS: TestLongCatChatOmitsReasoningEffortWhenUnset (0.00s)
=== RUN TestLongCatChatRequiresAPIKey
--- PASS: TestLongCatChatRequiresAPIKey (0.00s)
=== RUN TestLongCatChatRequiresMessages
--- PASS: TestLongCatChatRequiresMessages (0.00s)
=== RUN TestLongCatChatRejectsHTTPError
--- PASS: TestLongCatChatRejectsHTTPError (0.00s)
=== RUN TestLongCatStreamHappyPath
--- PASS: TestLongCatStreamHappyPath (0.00s)
=== RUN TestLongCatStreamExtractsReasoningContent
--- PASS: TestLongCatStreamExtractsReasoningContent (0.00s)
=== RUN TestLongCatStreamRejectsExplicitFalse
--- PASS: TestLongCatStreamRejectsExplicitFalse (0.00s)
=== RUN TestLongCatStreamRequiresSender
--- PASS: TestLongCatStreamRequiresSender (0.00s)
=== RUN TestLongCatStreamFailsWithoutTerminal
--- PASS: TestLongCatStreamFailsWithoutTerminal (0.00s)
=== RUN TestLongCatListModelsHappyPath
--- PASS: TestLongCatListModelsHappyPath (0.00s)
=== RUN TestLongCatListModelsRequiresAPIKey
--- PASS: TestLongCatListModelsRequiresAPIKey (0.00s)
=== RUN TestLongCatCheckConnectionDelegatesToListModels
--- PASS: TestLongCatCheckConnectionDelegatesToListModels (0.00s)
=== RUN TestLongCatEmbedReturnsNoSuchMethod
--- PASS: TestLongCatEmbedReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatRerankReturnsNoSuchMethod
--- PASS: TestLongCatRerankReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatBalanceReturnsNoSuchMethod
--- PASS: TestLongCatBalanceReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatAudioOCRReturnNoSuchMethod
--- PASS: TestLongCatAudioOCRReturnNoSuchMethod (0.00s)
PASS
ok ragflow/internal/entity/models 0.020s
```
`go build ./internal/entity/models/...` exits 0 on go 1.25.
**Live integration test** against `api.longcat.chat`:
```
=== RUN TestLongCatLiveSmoke
[OK] Name() = "longcat"
[OK] CheckConnection
[OK] ListModels: 5 models -> [LongCat-Flash-Lite LongCat-Flash-Chat LongCat-Flash-Thinking-2601 LongCat-Flash-Omni-2603 LongCat-2.0-Preview]
[OK] Chat (Flash-Chat) answer="Got it! Let me know if you" reason=""
[OK] Chat (Flash-Thinking) answer len=443 head="To find 15 % of 80, follow these steps:\n\n1. **Convert the percentage to a frac..."
ReasonContent len=557 head="The user asks: \"15% of 80?\" They want step by step reasoning and final answer in \\boxed{}. So we need to compute 15% of ..."
[OK] Stream content: 78 chunks, 351 chars
[OK] Stream reasoning: 107 chunks, 537 chars
[OK] Balance returns longcat, no such method
[OK] Embed returns longcat, no such method
[OK] Rerank returns longcat, no such method
LONGCAT LIVE SMOKE PASSED
--- PASS: TestLongCatLiveSmoke (31.01s)
```
What the live run proves on the wire:
- Auth header (`Bearer <key>`) is accepted by `api.longcat.chat`.
- `/openai/v1/models` parser handles the real 5-model response (note:
live API returns versioned aliases `LongCat-Flash-Thinking-2601`,
`LongCat-Flash-Omni-2603`, `LongCat-2.0-Preview` plus the un-versioned
`LongCat-Flash-Chat` and `LongCat-Flash-Lite`).
- Non-stream chat against `LongCat-Flash-Chat`: visible answer parses
correctly, `ReasonContent` correctly empty.
- Non-stream chat against `LongCat-Flash-Thinking`: 443-char answer
flows into `Answer`, 557-char chain-of-thought flows into
`ReasonContent` via the new `message.reasoning_content` extraction.
- Streaming chat against `LongCat-Flash-Thinking`: 107 reasoning chunks
(537 chars) reach the sender's second arg via `delta.reasoning_content`;
78 content chunks (351 chars) reach the first arg. Before this code, the
reasoning chunks would have been silently dropped.
- All sentinel methods (Balance, Embed, Rerank, audio/OCR) return the
documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for LongCat. The diff against `main` is a clean +969 lines
across 4 files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 22:27:56 -10:00
|
|
|
apiKey := "test-key"
|
2026-05-26 04:58:53 -07:00
|
|
|
models, err := newLongCatForTest(srv.URL).ListModels(&APIConfig{ApiKey: &apiKey})
|
|
|
|
|
if err != nil {
|
|
|
|
|
t.Fatalf("ListModels: %v", err)
|
|
|
|
|
}
|
|
|
|
|
if got := strings.Join(models, ","); got != "LongCat-Flash-Chat,LongCat-Flash-Thinking-2601" {
|
|
|
|
|
t.Errorf("models=%q", got)
|
|
|
|
|
}
|
|
|
|
|
if err := newLongCatForTest(srv.URL).CheckConnection(&APIConfig{ApiKey: &apiKey}); err != nil {
|
|
|
|
|
t.Fatalf("CheckConnection: %v", err)
|
Go: implement provider: LongCat (#14809)
### What problem does this PR solve?
Add a Go driver for LongCat (Meituan, https://longcat.chat), one of the
unchecked providers on the umbrella tracking issue #14736. LongCat
exposes an OpenAI-compatible REST API at
`https://api.longcat.chat/openai/v1` with three public chat models
including `LongCat-Flash-Thinking`, a reasoning model that returns
chain-of-thought in `reasoning_content` (OpenAI o-series shape).
Until this PR, a tenant who configured `longcat` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/longcat.go` with a `LongCatModel`
implementing the `ModelDriver` interface.
- New `conf/models/longcat.json` with the 3 public chat models
(Flash-Chat, Flash-Lite, Flash-Thinking) and `url_suffix` for `chat` and
`models`.
- `factory.go`: route `"longcat"` to `NewLongCatModel`.
Method coverage:
- `ChatWithMessages`: `POST /openai/v1/chat/completions`, non-streaming
- `ChatStreamlyWithSender`: SSE stream against the same endpoint
- `ListModels` / `CheckConnection`: `GET /openai/v1/models`
- **Reasoning extraction**: `message.reasoning_content` (non-stream) and
`delta.reasoning_content` (stream) flow into
`ChatResponse.ReasonContent` / the sender's second arg. Matches the
OpenAI o-series convention also used by kimi-k2.6 and DeepSeek-R1.
- **`reasoning_effort` propagation**: `ChatConfig.Effort` → request body
`reasoning_effort` (LongCat-Flash-Thinking honors it; non-reasoning
models ignore it).
- `Embed` / `Rerank` / `Balance` / `TranscribeAudio` / `AudioSpeech` /
`OCRFile` return `"no such method"` (LongCat does not expose any of
these surfaces).
No interface change. No new dependencies.
### How was this tested?
**21 unit tests** in `internal/entity/models/longcat_test.go` — all
pass:
```
$ go test -vet=off -run TestLongCat -count=1 -v ./internal/entity/models/...
=== RUN TestLongCatName
--- PASS: TestLongCatName (0.00s)
=== RUN TestLongCatChatHappyPath
--- PASS: TestLongCatChatHappyPath (0.00s)
=== RUN TestLongCatChatExtractsReasoningContent
--- PASS: TestLongCatChatExtractsReasoningContent (0.00s)
=== RUN TestLongCatChatPropagatesReasoningEffort
--- PASS: TestLongCatChatPropagatesReasoningEffort (0.00s)
=== RUN TestLongCatChatOmitsReasoningEffortWhenUnset
--- PASS: TestLongCatChatOmitsReasoningEffortWhenUnset (0.00s)
=== RUN TestLongCatChatRequiresAPIKey
--- PASS: TestLongCatChatRequiresAPIKey (0.00s)
=== RUN TestLongCatChatRequiresMessages
--- PASS: TestLongCatChatRequiresMessages (0.00s)
=== RUN TestLongCatChatRejectsHTTPError
--- PASS: TestLongCatChatRejectsHTTPError (0.00s)
=== RUN TestLongCatStreamHappyPath
--- PASS: TestLongCatStreamHappyPath (0.00s)
=== RUN TestLongCatStreamExtractsReasoningContent
--- PASS: TestLongCatStreamExtractsReasoningContent (0.00s)
=== RUN TestLongCatStreamRejectsExplicitFalse
--- PASS: TestLongCatStreamRejectsExplicitFalse (0.00s)
=== RUN TestLongCatStreamRequiresSender
--- PASS: TestLongCatStreamRequiresSender (0.00s)
=== RUN TestLongCatStreamFailsWithoutTerminal
--- PASS: TestLongCatStreamFailsWithoutTerminal (0.00s)
=== RUN TestLongCatListModelsHappyPath
--- PASS: TestLongCatListModelsHappyPath (0.00s)
=== RUN TestLongCatListModelsRequiresAPIKey
--- PASS: TestLongCatListModelsRequiresAPIKey (0.00s)
=== RUN TestLongCatCheckConnectionDelegatesToListModels
--- PASS: TestLongCatCheckConnectionDelegatesToListModels (0.00s)
=== RUN TestLongCatEmbedReturnsNoSuchMethod
--- PASS: TestLongCatEmbedReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatRerankReturnsNoSuchMethod
--- PASS: TestLongCatRerankReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatBalanceReturnsNoSuchMethod
--- PASS: TestLongCatBalanceReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatAudioOCRReturnNoSuchMethod
--- PASS: TestLongCatAudioOCRReturnNoSuchMethod (0.00s)
PASS
ok ragflow/internal/entity/models 0.020s
```
`go build ./internal/entity/models/...` exits 0 on go 1.25.
**Live integration test** against `api.longcat.chat`:
```
=== RUN TestLongCatLiveSmoke
[OK] Name() = "longcat"
[OK] CheckConnection
[OK] ListModels: 5 models -> [LongCat-Flash-Lite LongCat-Flash-Chat LongCat-Flash-Thinking-2601 LongCat-Flash-Omni-2603 LongCat-2.0-Preview]
[OK] Chat (Flash-Chat) answer="Got it! Let me know if you" reason=""
[OK] Chat (Flash-Thinking) answer len=443 head="To find 15 % of 80, follow these steps:\n\n1. **Convert the percentage to a frac..."
ReasonContent len=557 head="The user asks: \"15% of 80?\" They want step by step reasoning and final answer in \\boxed{}. So we need to compute 15% of ..."
[OK] Stream content: 78 chunks, 351 chars
[OK] Stream reasoning: 107 chunks, 537 chars
[OK] Balance returns longcat, no such method
[OK] Embed returns longcat, no such method
[OK] Rerank returns longcat, no such method
LONGCAT LIVE SMOKE PASSED
--- PASS: TestLongCatLiveSmoke (31.01s)
```
What the live run proves on the wire:
- Auth header (`Bearer <key>`) is accepted by `api.longcat.chat`.
- `/openai/v1/models` parser handles the real 5-model response (note:
live API returns versioned aliases `LongCat-Flash-Thinking-2601`,
`LongCat-Flash-Omni-2603`, `LongCat-2.0-Preview` plus the un-versioned
`LongCat-Flash-Chat` and `LongCat-Flash-Lite`).
- Non-stream chat against `LongCat-Flash-Chat`: visible answer parses
correctly, `ReasonContent` correctly empty.
- Non-stream chat against `LongCat-Flash-Thinking`: 443-char answer
flows into `Answer`, 557-char chain-of-thought flows into
`ReasonContent` via the new `message.reasoning_content` extraction.
- Streaming chat against `LongCat-Flash-Thinking`: 107 reasoning chunks
(537 chars) reach the sender's second arg via `delta.reasoning_content`;
78 content chunks (351 chars) reach the first arg. Before this code, the
reasoning chunks would have been silently dropped.
- All sentinel methods (Balance, Embed, Rerank, audio/OCR) return the
documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for LongCat. The diff against `main` is a clean +969 lines
across 4 files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 22:27:56 -10:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2026-05-26 04:58:53 -07:00
|
|
|
func TestLongCatListModelsRejectsInvalidResponses(t *testing.T) {
|
|
|
|
|
for name, response := range map[string]string{
|
|
|
|
|
"missing data": `{}`,
|
|
|
|
|
"null data": `{"data":null}`,
|
|
|
|
|
"too large": strings.Repeat(" ", longCatMaxListModelsResponseBytes+1),
|
|
|
|
|
} {
|
|
|
|
|
t.Run(name, func(t *testing.T) {
|
|
|
|
|
srv := newLongCatServer(t, "/openai/v1/models", func(t *testing.T, _ *http.Request, body map[string]interface{}, w http.ResponseWriter) {
|
|
|
|
|
_, _ = io.WriteString(w, response)
|
|
|
|
|
})
|
|
|
|
|
defer srv.Close()
|
|
|
|
|
|
|
|
|
|
apiKey := "test-key"
|
|
|
|
|
_, err := newLongCatForTest(srv.URL).ListModels(&APIConfig{ApiKey: &apiKey})
|
|
|
|
|
if err == nil {
|
|
|
|
|
t.Fatalf("expected error")
|
|
|
|
|
}
|
|
|
|
|
})
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func TestLongCatListModelsRequiresAPIKey(t *testing.T) {
|
|
|
|
|
for name, cfg := range map[string]*APIConfig{
|
|
|
|
|
"nil config": nil,
|
|
|
|
|
"nil key": {},
|
|
|
|
|
"empty key": {ApiKey: new(string)},
|
|
|
|
|
} {
|
|
|
|
|
t.Run(name, func(t *testing.T) {
|
|
|
|
|
_, err := newLongCatForTest("http://unused").ListModels(cfg)
|
|
|
|
|
if err == nil || !strings.Contains(err.Error(), "api key is required") {
|
|
|
|
|
t.Errorf("expected api-key error, got %v", err)
|
|
|
|
|
}
|
|
|
|
|
err = newLongCatForTest("http://unused").CheckConnection(cfg)
|
|
|
|
|
if err == nil || !strings.Contains(err.Error(), "api key is required") {
|
|
|
|
|
t.Errorf("CheckConnection expected api-key error, got %v", err)
|
|
|
|
|
}
|
|
|
|
|
})
|
Go: implement provider: LongCat (#14809)
### What problem does this PR solve?
Add a Go driver for LongCat (Meituan, https://longcat.chat), one of the
unchecked providers on the umbrella tracking issue #14736. LongCat
exposes an OpenAI-compatible REST API at
`https://api.longcat.chat/openai/v1` with three public chat models
including `LongCat-Flash-Thinking`, a reasoning model that returns
chain-of-thought in `reasoning_content` (OpenAI o-series shape).
Until this PR, a tenant who configured `longcat` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/longcat.go` with a `LongCatModel`
implementing the `ModelDriver` interface.
- New `conf/models/longcat.json` with the 3 public chat models
(Flash-Chat, Flash-Lite, Flash-Thinking) and `url_suffix` for `chat` and
`models`.
- `factory.go`: route `"longcat"` to `NewLongCatModel`.
Method coverage:
- `ChatWithMessages`: `POST /openai/v1/chat/completions`, non-streaming
- `ChatStreamlyWithSender`: SSE stream against the same endpoint
- `ListModels` / `CheckConnection`: `GET /openai/v1/models`
- **Reasoning extraction**: `message.reasoning_content` (non-stream) and
`delta.reasoning_content` (stream) flow into
`ChatResponse.ReasonContent` / the sender's second arg. Matches the
OpenAI o-series convention also used by kimi-k2.6 and DeepSeek-R1.
- **`reasoning_effort` propagation**: `ChatConfig.Effort` → request body
`reasoning_effort` (LongCat-Flash-Thinking honors it; non-reasoning
models ignore it).
- `Embed` / `Rerank` / `Balance` / `TranscribeAudio` / `AudioSpeech` /
`OCRFile` return `"no such method"` (LongCat does not expose any of
these surfaces).
No interface change. No new dependencies.
### How was this tested?
**21 unit tests** in `internal/entity/models/longcat_test.go` — all
pass:
```
$ go test -vet=off -run TestLongCat -count=1 -v ./internal/entity/models/...
=== RUN TestLongCatName
--- PASS: TestLongCatName (0.00s)
=== RUN TestLongCatChatHappyPath
--- PASS: TestLongCatChatHappyPath (0.00s)
=== RUN TestLongCatChatExtractsReasoningContent
--- PASS: TestLongCatChatExtractsReasoningContent (0.00s)
=== RUN TestLongCatChatPropagatesReasoningEffort
--- PASS: TestLongCatChatPropagatesReasoningEffort (0.00s)
=== RUN TestLongCatChatOmitsReasoningEffortWhenUnset
--- PASS: TestLongCatChatOmitsReasoningEffortWhenUnset (0.00s)
=== RUN TestLongCatChatRequiresAPIKey
--- PASS: TestLongCatChatRequiresAPIKey (0.00s)
=== RUN TestLongCatChatRequiresMessages
--- PASS: TestLongCatChatRequiresMessages (0.00s)
=== RUN TestLongCatChatRejectsHTTPError
--- PASS: TestLongCatChatRejectsHTTPError (0.00s)
=== RUN TestLongCatStreamHappyPath
--- PASS: TestLongCatStreamHappyPath (0.00s)
=== RUN TestLongCatStreamExtractsReasoningContent
--- PASS: TestLongCatStreamExtractsReasoningContent (0.00s)
=== RUN TestLongCatStreamRejectsExplicitFalse
--- PASS: TestLongCatStreamRejectsExplicitFalse (0.00s)
=== RUN TestLongCatStreamRequiresSender
--- PASS: TestLongCatStreamRequiresSender (0.00s)
=== RUN TestLongCatStreamFailsWithoutTerminal
--- PASS: TestLongCatStreamFailsWithoutTerminal (0.00s)
=== RUN TestLongCatListModelsHappyPath
--- PASS: TestLongCatListModelsHappyPath (0.00s)
=== RUN TestLongCatListModelsRequiresAPIKey
--- PASS: TestLongCatListModelsRequiresAPIKey (0.00s)
=== RUN TestLongCatCheckConnectionDelegatesToListModels
--- PASS: TestLongCatCheckConnectionDelegatesToListModels (0.00s)
=== RUN TestLongCatEmbedReturnsNoSuchMethod
--- PASS: TestLongCatEmbedReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatRerankReturnsNoSuchMethod
--- PASS: TestLongCatRerankReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatBalanceReturnsNoSuchMethod
--- PASS: TestLongCatBalanceReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatAudioOCRReturnNoSuchMethod
--- PASS: TestLongCatAudioOCRReturnNoSuchMethod (0.00s)
PASS
ok ragflow/internal/entity/models 0.020s
```
`go build ./internal/entity/models/...` exits 0 on go 1.25.
**Live integration test** against `api.longcat.chat`:
```
=== RUN TestLongCatLiveSmoke
[OK] Name() = "longcat"
[OK] CheckConnection
[OK] ListModels: 5 models -> [LongCat-Flash-Lite LongCat-Flash-Chat LongCat-Flash-Thinking-2601 LongCat-Flash-Omni-2603 LongCat-2.0-Preview]
[OK] Chat (Flash-Chat) answer="Got it! Let me know if you" reason=""
[OK] Chat (Flash-Thinking) answer len=443 head="To find 15 % of 80, follow these steps:\n\n1. **Convert the percentage to a frac..."
ReasonContent len=557 head="The user asks: \"15% of 80?\" They want step by step reasoning and final answer in \\boxed{}. So we need to compute 15% of ..."
[OK] Stream content: 78 chunks, 351 chars
[OK] Stream reasoning: 107 chunks, 537 chars
[OK] Balance returns longcat, no such method
[OK] Embed returns longcat, no such method
[OK] Rerank returns longcat, no such method
LONGCAT LIVE SMOKE PASSED
--- PASS: TestLongCatLiveSmoke (31.01s)
```
What the live run proves on the wire:
- Auth header (`Bearer <key>`) is accepted by `api.longcat.chat`.
- `/openai/v1/models` parser handles the real 5-model response (note:
live API returns versioned aliases `LongCat-Flash-Thinking-2601`,
`LongCat-Flash-Omni-2603`, `LongCat-2.0-Preview` plus the un-versioned
`LongCat-Flash-Chat` and `LongCat-Flash-Lite`).
- Non-stream chat against `LongCat-Flash-Chat`: visible answer parses
correctly, `ReasonContent` correctly empty.
- Non-stream chat against `LongCat-Flash-Thinking`: 443-char answer
flows into `Answer`, 557-char chain-of-thought flows into
`ReasonContent` via the new `message.reasoning_content` extraction.
- Streaming chat against `LongCat-Flash-Thinking`: 107 reasoning chunks
(537 chars) reach the sender's second arg via `delta.reasoning_content`;
78 content chunks (351 chars) reach the first arg. Before this code, the
reasoning chunks would have been silently dropped.
- All sentinel methods (Balance, Embed, Rerank, audio/OCR) return the
documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for LongCat. The diff against `main` is a clean +969 lines
across 4 files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 22:27:56 -10:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func TestLongCatEmbedReturnsNoSuchMethod(t *testing.T) {
|
|
|
|
|
m := newLongCatForTest("http://unused")
|
|
|
|
|
model := "x"
|
|
|
|
|
_, err := m.Embed(&model, []string{"a"}, &APIConfig{}, nil)
|
|
|
|
|
if err == nil || !strings.Contains(err.Error(), "no such method") {
|
|
|
|
|
t.Errorf("Embed: want 'no such method', got %v", err)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func TestLongCatRerankReturnsNoSuchMethod(t *testing.T) {
|
|
|
|
|
m := newLongCatForTest("http://unused")
|
|
|
|
|
model := "x"
|
|
|
|
|
_, err := m.Rerank(&model, "q", []string{"a"}, &APIConfig{}, &RerankConfig{TopN: 1})
|
|
|
|
|
if err == nil || !strings.Contains(err.Error(), "no such method") {
|
|
|
|
|
t.Errorf("Rerank: want 'no such method', got %v", err)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func TestLongCatBalanceReturnsNoSuchMethod(t *testing.T) {
|
|
|
|
|
m := newLongCatForTest("http://unused")
|
|
|
|
|
_, err := m.Balance(&APIConfig{})
|
|
|
|
|
if err == nil || !strings.Contains(err.Error(), "no such method") {
|
|
|
|
|
t.Errorf("Balance: want 'no such method', got %v", err)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
func TestLongCatAudioOCRReturnNoSuchMethod(t *testing.T) {
|
|
|
|
|
m := newLongCatForTest("http://unused")
|
|
|
|
|
model := "x"
|
|
|
|
|
if _, err := m.TranscribeAudio(&model, &model, &APIConfig{}, nil); err == nil || !strings.Contains(err.Error(), "no such method") {
|
|
|
|
|
t.Errorf("TranscribeAudio: want 'no such method', got %v", err)
|
|
|
|
|
}
|
|
|
|
|
if _, err := m.AudioSpeech(&model, &model, &APIConfig{}, nil); err == nil || !strings.Contains(err.Error(), "no such method") {
|
|
|
|
|
t.Errorf("AudioSpeech: want 'no such method', got %v", err)
|
|
|
|
|
}
|
Go: implement provider: Voyage AI (#14811)
### What problem does this PR solve?
Add a Go driver for Voyage AI (https://voyageai.com), one of the
unchecked providers on the umbrella tracking issue #14736. Voyage AI is
**embed + rerank only** — no chat, no streaming, no `/v1/models`
endpoint. It's the first provider in the Go layer of this shape.
Until this PR, a tenant who configured `voyage` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/voyage.go` with a `VoyageModel`
implementing the `ModelDriver` interface.
- New `conf/models/voyage.json` with 6 embedding models (`voyage-3.5`,
`voyage-3.5-lite`, `voyage-3-large`, `voyage-code-3`, `voyage-law-2`,
`voyage-finance-2`) and 2 rerank models (`rerank-2`, `rerank-2-lite`).
- `factory.go`: route `"voyage"` to `NewVoyageModel`.
- `internal/entity/models/voyage_test.go`: 19 unit tests.
### How the driver works
- **Embed**: `POST /v1/embeddings`. Response is OpenAI-shaped (`{data:
[{embedding, index, object, text}], model, usage}`). Driver reorders by
`index`, rejects duplicate / out-of-range / missing slots, and
short-circuits empty input without an HTTP call.
- **Rerank**: `POST /v1/rerank`. Voyage uses **`top_k`** as the request
param name (not `top_n` like Aliyun/SiliconFlow); the driver translates
`RerankConfig.TopN` → `top_k`. Response is Cohere-shaped (`{data:
[{relevance_score, index}], model}`), so the existing
`RerankResponse{Data: []RerankResult{Index, RelevanceScore}}` shape fits
cleanly.
- **`ListModels`**: returns a hardcoded list of `voyageKnownModels`.
Voyage does **not** expose `/v1/models` (probed live, returns 404), so
the driver synthesizes the list from the same set the config ships. New
upstream models are added by extending one slice.
- **`CheckConnection`**: pings a 1-input embed call against
`voyage-3.5`. Without `/v1/models`, this is the cheapest way to verify
the API key + network path before a tenant tries a real workload.
- **`ChatWithMessages` / `ChatStreamlyWithSender` / `Balance` /
`TranscribeAudio` / `AudioSpeech` / `OCRFile`**: all return `"no such
method"`. Voyage does not host any of these surfaces.
No interface change. No new dependencies.
### How was this tested?
**19 unit tests** in `internal/entity/models/voyage_test.go` — all pass
on go 1.25:
```
$ go test -vet=off -run TestVoyage -count=1 ./internal/entity/models/...
ok ragflow/internal/entity/models 0.036s
```
Coverage: Name; Embed (happy path, reorder, empty-input, missing
key/model, duplicate index, out-of-range index, missing slot); Rerank
(happy path with `top_k` assertion, default-to-len-documents, empty
documents, out-of-range index); ListModels (static list, missing key);
CheckConnection (happy, 401); chat methods sentinels; Balance sentinel;
audio/OCR sentinels.
`go build ./internal/entity/models/...` exits 0.
**Live integration test** against `api.voyageai.com`:
```
=== RUN TestVoyageLiveSmoke
[OK] Name() = "voyage"
[OK] ListModels (static): 8 models -> [voyage-3.5 voyage-3.5-lite voyage-3-large voyage-code-3 voyage-law-2 voyage-finance-2 rerank-2 rerank-2-lite]
[OK] CheckConnection
[OK] Embed vectors=3 dim=1024 indices=[0 1 2]
[OK] Embed(empty) -> 0 vectors
[OK] Rerank results=3 scores=[0.8125 0.59765625 0.39453125]
[OK] ChatWithMessages returns voyage, no such method
[OK] Balance returns voyage, no such method
VOYAGE LIVE SMOKE PASSED
--- PASS: TestVoyageLiveSmoke (0.81s)
```
What the live run proves on the wire:
- Auth (`Bearer <key>`) accepted by `api.voyageai.com`.
- Embed `voyage-3.5` on 3 inputs returns 3 vectors at dim 1024 with
`index` field preserved as `[0, 1, 2]` — the reorder-by-index code is
exercised on real data.
- Empty input short-circuits without an HTTP call (mock server would
have been hit if it did).
- Rerank `rerank-2` on 3 docs returns 3 real `relevance_score` floats
`[0.8125, 0.598, 0.395]`. The `top_k` translation works on the live
wire.
- All sentinel methods return the documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI Embed work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for Voyage. Diff against `main` is a clean +838 lines across 4
files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-13 15:46:54 -10:00
|
|
|
if _, err := m.OCRFile(&model, nil, &model, &APIConfig{}, nil); err == nil || !strings.Contains(err.Error(), "no such method") {
|
Go: implement provider: LongCat (#14809)
### What problem does this PR solve?
Add a Go driver for LongCat (Meituan, https://longcat.chat), one of the
unchecked providers on the umbrella tracking issue #14736. LongCat
exposes an OpenAI-compatible REST API at
`https://api.longcat.chat/openai/v1` with three public chat models
including `LongCat-Flash-Thinking`, a reasoning model that returns
chain-of-thought in `reasoning_content` (OpenAI o-series shape).
Until this PR, a tenant who configured `longcat` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/longcat.go` with a `LongCatModel`
implementing the `ModelDriver` interface.
- New `conf/models/longcat.json` with the 3 public chat models
(Flash-Chat, Flash-Lite, Flash-Thinking) and `url_suffix` for `chat` and
`models`.
- `factory.go`: route `"longcat"` to `NewLongCatModel`.
Method coverage:
- `ChatWithMessages`: `POST /openai/v1/chat/completions`, non-streaming
- `ChatStreamlyWithSender`: SSE stream against the same endpoint
- `ListModels` / `CheckConnection`: `GET /openai/v1/models`
- **Reasoning extraction**: `message.reasoning_content` (non-stream) and
`delta.reasoning_content` (stream) flow into
`ChatResponse.ReasonContent` / the sender's second arg. Matches the
OpenAI o-series convention also used by kimi-k2.6 and DeepSeek-R1.
- **`reasoning_effort` propagation**: `ChatConfig.Effort` → request body
`reasoning_effort` (LongCat-Flash-Thinking honors it; non-reasoning
models ignore it).
- `Embed` / `Rerank` / `Balance` / `TranscribeAudio` / `AudioSpeech` /
`OCRFile` return `"no such method"` (LongCat does not expose any of
these surfaces).
No interface change. No new dependencies.
### How was this tested?
**21 unit tests** in `internal/entity/models/longcat_test.go` — all
pass:
```
$ go test -vet=off -run TestLongCat -count=1 -v ./internal/entity/models/...
=== RUN TestLongCatName
--- PASS: TestLongCatName (0.00s)
=== RUN TestLongCatChatHappyPath
--- PASS: TestLongCatChatHappyPath (0.00s)
=== RUN TestLongCatChatExtractsReasoningContent
--- PASS: TestLongCatChatExtractsReasoningContent (0.00s)
=== RUN TestLongCatChatPropagatesReasoningEffort
--- PASS: TestLongCatChatPropagatesReasoningEffort (0.00s)
=== RUN TestLongCatChatOmitsReasoningEffortWhenUnset
--- PASS: TestLongCatChatOmitsReasoningEffortWhenUnset (0.00s)
=== RUN TestLongCatChatRequiresAPIKey
--- PASS: TestLongCatChatRequiresAPIKey (0.00s)
=== RUN TestLongCatChatRequiresMessages
--- PASS: TestLongCatChatRequiresMessages (0.00s)
=== RUN TestLongCatChatRejectsHTTPError
--- PASS: TestLongCatChatRejectsHTTPError (0.00s)
=== RUN TestLongCatStreamHappyPath
--- PASS: TestLongCatStreamHappyPath (0.00s)
=== RUN TestLongCatStreamExtractsReasoningContent
--- PASS: TestLongCatStreamExtractsReasoningContent (0.00s)
=== RUN TestLongCatStreamRejectsExplicitFalse
--- PASS: TestLongCatStreamRejectsExplicitFalse (0.00s)
=== RUN TestLongCatStreamRequiresSender
--- PASS: TestLongCatStreamRequiresSender (0.00s)
=== RUN TestLongCatStreamFailsWithoutTerminal
--- PASS: TestLongCatStreamFailsWithoutTerminal (0.00s)
=== RUN TestLongCatListModelsHappyPath
--- PASS: TestLongCatListModelsHappyPath (0.00s)
=== RUN TestLongCatListModelsRequiresAPIKey
--- PASS: TestLongCatListModelsRequiresAPIKey (0.00s)
=== RUN TestLongCatCheckConnectionDelegatesToListModels
--- PASS: TestLongCatCheckConnectionDelegatesToListModels (0.00s)
=== RUN TestLongCatEmbedReturnsNoSuchMethod
--- PASS: TestLongCatEmbedReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatRerankReturnsNoSuchMethod
--- PASS: TestLongCatRerankReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatBalanceReturnsNoSuchMethod
--- PASS: TestLongCatBalanceReturnsNoSuchMethod (0.00s)
=== RUN TestLongCatAudioOCRReturnNoSuchMethod
--- PASS: TestLongCatAudioOCRReturnNoSuchMethod (0.00s)
PASS
ok ragflow/internal/entity/models 0.020s
```
`go build ./internal/entity/models/...` exits 0 on go 1.25.
**Live integration test** against `api.longcat.chat`:
```
=== RUN TestLongCatLiveSmoke
[OK] Name() = "longcat"
[OK] CheckConnection
[OK] ListModels: 5 models -> [LongCat-Flash-Lite LongCat-Flash-Chat LongCat-Flash-Thinking-2601 LongCat-Flash-Omni-2603 LongCat-2.0-Preview]
[OK] Chat (Flash-Chat) answer="Got it! Let me know if you" reason=""
[OK] Chat (Flash-Thinking) answer len=443 head="To find 15 % of 80, follow these steps:\n\n1. **Convert the percentage to a frac..."
ReasonContent len=557 head="The user asks: \"15% of 80?\" They want step by step reasoning and final answer in \\boxed{}. So we need to compute 15% of ..."
[OK] Stream content: 78 chunks, 351 chars
[OK] Stream reasoning: 107 chunks, 537 chars
[OK] Balance returns longcat, no such method
[OK] Embed returns longcat, no such method
[OK] Rerank returns longcat, no such method
LONGCAT LIVE SMOKE PASSED
--- PASS: TestLongCatLiveSmoke (31.01s)
```
What the live run proves on the wire:
- Auth header (`Bearer <key>`) is accepted by `api.longcat.chat`.
- `/openai/v1/models` parser handles the real 5-model response (note:
live API returns versioned aliases `LongCat-Flash-Thinking-2601`,
`LongCat-Flash-Omni-2603`, `LongCat-2.0-Preview` plus the un-versioned
`LongCat-Flash-Chat` and `LongCat-Flash-Lite`).
- Non-stream chat against `LongCat-Flash-Chat`: visible answer parses
correctly, `ReasonContent` correctly empty.
- Non-stream chat against `LongCat-Flash-Thinking`: 443-char answer
flows into `Answer`, 557-char chain-of-thought flows into
`ReasonContent` via the new `message.reasoning_content` extraction.
- Streaming chat against `LongCat-Flash-Thinking`: 107 reasoning chunks
(537 chars) reach the sender's second arg via `delta.reasoning_content`;
78 content chunks (351 chars) reach the first arg. Before this code, the
reasoning chunks would have been silently dropped.
- All sentinel methods (Balance, Embed, Rerank, audio/OCR) return the
documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for LongCat. The diff against `main` is a clean +969 lines
across 4 files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 22:27:56 -10:00
|
|
|
t.Errorf("OCRFile: want 'no such method', got %v", err)
|
|
|
|
|
}
|
|
|
|
|
}
|