### What problem does this PR solve?
Two bugs in the Agent Categorize component:
1. The backend rejected `message_history_window_size = 0` while frontend
allowed it, causing API errors.
2. When calling the agent API without a `session_id`, a new session was
created but retained history from previous conversations.
### Type of change
- [x] Bug Fix
### How has this been tested?
- Issue 1: `CategorizeParam().check()` now accepts `0` and rejects
negative values.
- Issue 2: `canvas.clear_history()` is called for new sessions (no
`session_id`), ensuring fresh conversation state. Verified via UI and
API that a second call without `session_id` does not remember the first
conversation.
### Related Issue
Closes#15897
Co-authored-by: RAGFlow Dev <dev@ragflow.local>
Co-authored-by: Wang Qi <wangq8@outlook.com>
## Summary
Implements **chunk 1** of #15282 — the four `/api/v1/auth/password/...`
endpoints from the login-page Go port. **Chunk 2 (OAuth/OIDC) is
deferred** to its own subtask, matching the issue author's own
confidence-low recommendation ("multi-provider, stateful redirect flow
with external dependencies; recommend its own subtask").
New endpoints, all registered under `apiNoAuth` (forgot-password users
are unauthenticated by definition):
| Method | Path | Status |
|--------|------|--------|
| `POST` | `/api/v1/auth/password/forgot/captcha` | new |
| `POST` | `/api/v1/auth/password/forgot/otp` | new |
| `POST` | `/api/v1/auth/password/forgot/otp/verify` | new |
| `POST` | `/api/v1/auth/password/reset` | new |
## Wire compatibility with the Python backend
The two backends share state through Redis, so the Go port had to use
identical keys, encodings, and constants. Either backend can now
validate a code the other minted.
- **Redis keys**: `captcha:<email>`, `otp:<email>`,
`otp_attempts:<email>`, `otp_last_sent:<email>`, `otp_lock:<email>`,
`otp:verified:<email>` — same as `api/utils/web_utils.py`.
- **Stored OTP value**: `"<hex_hash>:<hex_salt>"` — same as Python.
- **Hash**: HMAC-SHA256 with a `crypto/rand` 16-byte salt — same as
`hash_code()`.
- **Constants**: `OTP_LENGTH=4`, `OTP_TTL=5min`, `ATTEMPT_LIMIT=5`,
`ATTEMPT_LOCK_SECONDS=30min`, `RESEND_COOLDOWN_SECONDS=60s` — all match
`api/utils/web_utils.py`.
- **Email body**: matches `RESET_CODE_EMAIL_TMPL` byte-for-byte.
## Files
### New
| File | Purpose |
|---|---|
| `internal/utility/otp.go` | OTP/captcha constants, Redis key builders
(`CaptchaRedisKey`, `OTPRedisKeys`, `OTPVerifiedRedisKey`),
`HashOTPCode`, `GenerateOTPCode` / `GenerateCaptchaCode` /
`GenerateOTPSalt` via `crypto/rand`, and `EncodeOTPStorageValue` /
`DecodeOTPStorageValue` matching Python's storage shape. |
| `internal/utility/smtp.go` | Minimal stdlib `net/smtp` sender.
`SendResetCodeEmail(to, otp, ttlMin)` builds an RFC 5322 plain-text
message and dispatches via implicit TLS / STARTTLS / plain — same
selectors as Python `aiosmtplib`. Returns `SMTPNotConfiguredError` if
the config block is empty. |
### Modified
| File | Change |
|---|---|
| `internal/server/config.go` | New `SMTPConfig` struct + `Config.SMTP`
field. Field names mirror the `smtp:` keys in `common/settings.py`
(`mail_server`, `mail_port`, `mail_use_ssl`, `mail_use_tls`,
`mail_username`, `mail_password`, `mail_from_name`, `mail_from_address`,
`mail_frontend_url`) so a single `conf/service_conf.yaml` powers both
backends. |
| `internal/service/user.go` | Four methods — `ForgotIssueCaptcha`,
`ForgotSendOTP`, `ForgotVerifyOTP`, `ForgotResetPassword`. Reuses the
existing `decryptPassword`, `HashPassword`, `userDAO.Update`, and
`utility.GenerateToken` so the reset+auto-login path is identical to
`LoginByEmail`. |
| `internal/handler/user.go` | Four handlers in the same `c.JSON` shape
as `LoginByEmail`. The reset handler rotates the access token and emits
an `Authorization` header for auto-login (matches Python
`construct_response(auth=user.get_id())`). |
| `internal/router/router.go` | Routes registered under `apiNoAuth`,
with an explanatory comment on why they sit outside the auth middleware.
|
## Known divergence — captcha rendering
The Python endpoint returns a rendered `image/JPEG` from the
`python-captcha` library. The Go side has **no image-captcha dependency
vendored** in `go.mod`, and hand-rolling a raster generator was out of
scope for this PR.
This commit returns JSON `{captcha: "<text>"}` instead. Implications:
- **Backend gate is identical** — the OTP step still verifies the
user-submitted captcha string against the Redis value, so the security
model is unchanged.
- **Frontend impact**: the password-reset page rendering needs a small
tweak (text display instead of `<img>`) until a Go captcha library is
wired in.
- The handler comments call this out explicitly so the next PR knows
what to swap.
Possible follow-ups (any one closes the gap):
1. Add `github.com/mojocn/base64Captcha` or `github.com/dchest/captcha`
to `go.mod` and replace the JSON response with an `image/JPEG`.
2. Hand-roll a 5x7 bitmap font + `image/png` writer using only the
stdlib.
3. Render a server-side SVG (cheap, but trivially OCR-able — only useful
as a UI shim).
## Test plan
- [ ] **Captcha**: `POST
/api/v1/auth/password/forgot/captcha?email=<existing>` returns `{code:
0, data: {captcha: "ABCD"}}`. Redis shows `captcha:<email>` with that
value and ~60s TTL. Unknown email returns `code: CodeDataError`.
- [ ] **OTP send**: `POST /api/v1/auth/password/forgot/otp` with the
right captcha mints an OTP, stores `<hash>:<salt>` under `otp:<email>`
for 5 min, sends an email, returns success. With a wrong captcha returns
`CodeAuthenticationError`. Hitting it again within 60s returns "you
still have to wait …" with `CodeNotEffective`.
- [ ] **OTP verify**: correct OTP → `code: 0`, OTP keys cleared,
`otp:verified:<email>` = `"1"`. Wrong OTP → `code:
CodeAuthenticationError`, attempt counter bumped; after 5 wrong tries
`otp_lock:<email>` is set and further attempts hit `CodeNotEffective`.
- [ ] **Reset**: with the verified flag set, supply a new password
(RSA-encrypted+base64, same as `LoginByEmail`). Returns `code: 0`,
`Authorization` header set, verified flag deleted. Without the verified
flag returns `CodeAuthenticationError`.
- [ ] **Wire-compat smoke**: mint an OTP from the Python backend, verify
it via the Go endpoint, and vice versa. Should both succeed.
- [ ] **SMTP misconfigured**: drop `smtp.mail_server` from
`conf/service_conf.yaml`. The OTP-send endpoint should now return
"failed to send email" without panicking; check the log for the
`SMTPNotConfiguredError` warning.
- [ ] **End-to-end FE**: hit the password-reset flow from
`web/src/pages/login-next/`. Confirm the text-captcha shim works after
the FE tweak.
- [ ] `go build ./...` and `go vet ./...` — I could not run these in the
sandbox; please confirm a clean build before merging.
- [ ] `uv run pytest` to confirm no Python regressions (shared Redis
schema).
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
## Summary
- Implemented the Go API endpoint for Memory message forgetting:
- `DELETE /api/v1/messages/{memory_id}:{message_id}`
- Added route registration for the Memory message DELETE endpoint only.
- Added request path validation for `memory_id:message_id`.
- Added service logic to mark a message as forgotten by setting
`forget_at`.
- Preserved Python-compatible response behavior:
- Success returns `code: 0`, `message: true`, `data: null`.
- Added focused unit tests for message path parsing and invalid message
ID handling.
- Fixed Linux cgo linker config to use the installed shared PCRE2
library so Go tests/builds can run in this environment.
## Related Issue
Closes: #15240
## Change Type
- [x] Feature
- [x] Test
- [x] Build / CI compatibility
## Implemented API
- `DELETE /api/v1/messages/{memory_id}:{message_id}`
## Real Behavior Proof
Validated with targeted Go tests:
```bash
/tmp/go1.25.0/bin/go test ./internal/handler ./internal/router
```
Result:
```text
ok ragflow/internal/handler
? ragflow/internal/router [no test files]
```
Validated server entrypoint build:
```bash
/tmp/go1.25.0/bin/go build -o /tmp/ragflow-server-main ./cmd/server_main.go
```
Result:
```text
build succeeded
```
Validated patch formatting:
```bash
git diff --check
```
Result:
```text
no whitespace errors
```
## Checklist
- [x] Implemented only `DELETE
/api/v1/messages/{memory_id}:{message_id}`.
- [x] Did not implement unrelated Memory message APIs.
- [x] Added route registration.
- [x] Added handler validation.
- [x] Added service-level memory access check.
- [x] Added tests.
- [x] Ran targeted Go tests.
- [x] Ran server build validation.
- [x] Ran `git diff --check`.
### What problem does this PR solve?
1. Fix go test, some cases still failed.
2. Remove unused code.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
## Summary
- Add official Qwen models to `conf/all_models.json` with `qwen/`
canonical names
- Include verified aliases from official Qwen/Hugging Face model IDs and
common provider naming
- Add metadata for context length, model types, thinking support, and
embedding dimensions
## Details
- Added Qwen model families from the official Hugging Face Qwen
organization
- Normalized canonical model names to the `qwen/...` format
- Preserved official HF IDs and lowercase/common aliases for lookup
compatibility
- Added `dimension` for Qwen embedding models
- Added or corrected `max_tokens` for Qwen model families, including:
- Qwen2.5 Instruct variants
- Qwen3 original, 2507, VL, Coder, Coder-Next, Next, Embedding, and
Reranker models
- Qwen3.5 and Qwen3.6 models
- QwQ models
- Added verified `thinking` metadata where officially supported
- Corrected `model_types` for Qwen Image, Omni, Audio, VL, embedding,
reranker, benchmark, and tokenizer entries
## Summary
- Normalize model alias index keys to lowercase
- Detect lowercase alias collisions during provider manager
initialization
- Fix ListModels metadata mapping for mixed-case provider aliases
### What problem does this PR solve?
Fix: add image2text/speech2text/ocr support
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: add thin scrollbar styling for x-spreadsheet component
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: The dataset retrieval test returned an incorrect total number.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: balibabu <assassin_cike@163.com>
### What problem does this PR solve?
Ensure agent components with image inputs route to `image2text` models
instead of staying on the chat path, so visual requests use the CV
wrapper when supported.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Summary
LocalAI exposes two API surfaces with conflicting naming conventions:
- `GET /api/tags` returns model names with `:latest` suffix (Ollama
format)
- `POST /v1/chat/completions` expects names without `:latest` (OpenAI
format)
RAGFlow discovered models via `/api/tags` and stored the tagged name,
then used it with `/v1/chat/completions`, causing a 404 error because
LocalAI didn't recognize `model:latest`.
## Fix
In `LocalAI.get_model_list()`, strip the tag suffix from model names
using `model["name"].rsplit(":", 1)[0]`, so stored names match what the
OpenAI-compatible endpoints expect.
### What problem does this PR solve?
Set OpenDataLoader and call in parser and naive
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## What does this PR do?
This PR migrates the Agent Temporary File Download endpoint (`GET
/api/v1/agents/download`) from the Python backend to the Go backend,
optimizing the data retrieval flow and maintaining strict functional
parity. It also fixes a persistent parsing error in the Sandbox code
execution node.
## Checklist
- [x] Code logic matches Python implementation
- [x] All local unit tests passed
- [x] No breaking changes to existing router interfaces
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
### What problem does this PR solve?
1. remove unused code
2. fix login issue
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
cohere api call failing because of missing prefix
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Support factory models with multiple model types, so visual chat models
can be exposed as both image2text and chat while preserving the database
model-type-per-record design.
This also updates the SILICONFLOW model list and adds a helper script to
refresh SiliconFlow models from the provider API.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
fix: rename ark_api_key to api_key for volcengine provider config
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Fix some model provider-related UI issues
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
This PR expands conf/all_models.json with DeepSeek model entries and
provider aliases.
Changes:
- Added DeepSeek model entries across `V4`, `V3.2`, `V3.1`, `V3`, `R1`,
`Coder`, `Math`, `VL`, `OCR`, `Prover`, `MoE`, and `LLM` series.
- Normalized model name values to lowercase canonical IDs.
- Added alias values for official DeepSeek/Hugging Face names and
provider-specific names from OpenRouter, VolcEngine, SiliconFlow,
HuaweiCloud, and QiniuCloud.
- Preserved model metadata such as max_tokens, model_types, and thinking
where applicable.
- Added Gitee ListModels tests to verify DeepSeek aliases map back to
model metadata from all_models.json.
- Added an optional Gitee integration test gated by
GITEE_LIST_MODELS_INTEGRATION=1.
Test:
/usr/local/go/bin/go clean -cache
/usr/local/go/bin/go test ./internal/entity/models -run
'TestGiteeListModels(MapsAllDeepSeekAliasesToModelMetadata|KeepsOwnedBySuffixAfterAliasMetadataLookup|
Integration)'
### What problem does this PR solve?
Fix QWen rerank error handling so DashScope error responses without a
text attribute do not raise a secondary KeyError and hide the real
provider error.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
The RAGFlow Docker image was 9.06 GB with build-only compiler packages
leaking into the runtime, duplicate frontend source shipped alongside
compiled assets, and no .dockerignore causing ~6 GB of unnecessary
context transfer per build.
### Type of change
- [x] Performance Improvement
## Summary
- Add knowledge-base retrieval support to Go chat completions.
## What changed
- Routes KB-backed chat sessions through the Go retrieval service
instead of falling back to solo chat.
- Resolves embedding and rerank models, validates accessible knowledge
bases, and preserves tenant-aware retrieval.
- Rejects mixed embedding models across selected knowledge bases before
retrieval to avoid incompatible vector dimensions.
- Threads the HTTP request context into streaming retrieval so cancelled
requests can stop downstream retrieval work.
- Applies metadata filters and message-level `doc_ids` before retrieval.
- Expands parent/child chunks before building references and prompt
context.
- Injects retrieved knowledge through a copied dialog prompt config so
the caller's original dialog is not mutated.
- Honors configured empty responses when no chunks are found.
- Names the metadata no-match sentinel and reuses it across
retrieval/handler paths.
- Adds a defensive content cast while appending streamed answers.
- Adds focused unit coverage for retrieval, metadata filtering,
authorization, multimodal messages, references, empty-response behavior,
prompt immutability, and mixed embedding models.
---------
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
### What problem does this PR solve?
```
RAGFlow(api/default)> use admin
SUCCESS
RAGFlow(api/default)> use api 'abc';
SUCCESS
```
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Updated supported model providers and the corresponding URLs.
~~Synced supported model providers and base URLs with
**llm_factories.json**, while keeping the AI Badgr configuration example
via the OpenAI-API-Compatible provider.~~
### Type of change
- [x] Documentation Update
### What problem does this PR solve?
As title
```
/api/v1/datasets/<dataset_id>/documents/<document_id>/metadata/config PUT
```
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
### What problem does this PR solve?
Add two API in go
```
/api/v1/agents/test_db_connection POST
/api/v1/agents/<agent_id>/sessions DELETE
```
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
Implements POST /api/v1/searchbots/ask in Go with streaming SSE,
citations, and think-tag processing. 23 files, 90+ unit tests.
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
## Summary
This PR re-enables the Go test steps in CI that were previously
commented out, and fixes all compilation errors that have accumulated in
`internal/entity/models/` since the `ListModels` return type was changed
from `[]string` to `[]ListModelResponse`.
## Changes
### CI (`.github/workflows/tests.yml`)
- Re-enable **Prepare test resources** step (clones resource repo with
WordNet data)
- Re-enable **Test Go packages** step (runs `go test ./internal/...`)
- Fix resource path race condition by using
`/tmp/resource-${GITHUB_RUN_ID}` instead of `/tmp/resource`
- Exclude `/cli` package from Go tests (contains `main` redeclarations)
### Test fixes (16 model provider test files)
All errors were caused by the upstream change from `[]string` to
`[]ListModelResponse` in the `ListModels` interface:
- Add `joinModelNames` test helper to extract `.Name` from
`[]ListModelResponse` slices
- `strings.Join(models, ",")` → `joinModelNames(models, ",")` (11 files)
- `ids[i] != "..."` → `ids[i].Name != "..."` (cometapi, mistral)
- `got[i] != want[i]` → `got[i].Name != want[i]` (bedrock)
- `[]string` return types → `[]ListModelResponse` (google)
### Pre-existing bugs in model_test.go
Bugs introduced by the upstream `entity/` → `entity/models/` directory
rename:
- Add missing `pm := GetProviderManager()` calls in 3 test functions
- Fix `InitProviderManager` signature (`_, err :=` → `err :=`)
- Fix `MaxTokens` `*int` dereference (6 comparisons)
- Fix `readProviderConfig` relative path (3 levels up instead of 2)
### model.go
- Add `findRepoRoot()` to make `conf/all_models.json` resolution work
from any CWD, fixing `TestSiliconFlowProviderConfigLoadsLatestProModels`
### Test validation
```bash
go build ./internal/... # ✅
go test ./internal/entity/models/... -count=1 # ✅ all pass
```
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
### Summary
Closes#15795
Knowledge-graph queries rank entities by `pagerank * sim` in `KGSearch`,
but the entity chunks written at index time stopped carrying the values
that ranking depends on. `graph_node_to_chunk` only stored
`entity_type`, `description`, and `source_id`, dropping the node
`pagerank` and the n-hop neighbour paths, while `search.py` still read
them back as `rank_flt` and `n_hop_with_weight`.
The producer of these fields, `update_nodes_pagerank_nhop_neighbour`,
was removed in #6513, but the read side in `KGSearch` was never updated.
The result is that on every knowledge-graph query:
- `pagerank` resolves to `0`, so the `pagerank * sim` sort key is `0`
for every entity and selection falls back to arbitrary order.
- Every displayed entity score is `0.00`.
- The n-hop relation-enrichment block is dead code because `n_hop_ents`
is always empty, leaving `merge_tuples` and `is_continuous_subsequence`
orphaned.
This PR restores the missing index-time fields so the documented `P(E|Q)
= pagerank * sim` ranking and the n-hop enrichment work again.
What changed:
- `graph_node_to_chunk` now writes `rank_flt` from the node pagerank and
`n_hop_with_weight` from the recomputed n-hop neighbour paths.
- Reintroduced the n-hop path computation (`n_neighbor`) in
`rag/graphrag/utils.py`, reusing the previously orphaned `merge_tuples`
/ `is_continuous_subsequence` helpers, with a direction-agnostic
edge-weight lookup for undirected graphs. `set_graph` computes the paths
per added or updated node and passes them through.
- `KGSearch` now selects `n_hop_with_weight` in the entity keyword
search so Infinity and OceanBase return it (Elasticsearch and OpenSearch
already read it from `_source`), and the read is hardened against
missing keys or empty strings before `json.loads`.
- Added the `n_hop_with_weight` column to OceanBase, including the
`EXTRA_COLUMNS` migration entry so existing tables get it. The other
engines already map both fields via dynamic templates or the Infinity
mapping.
Scope note: pagerank and n-hop are re-indexed for the added or updated
nodes in each pass, consistent with the existing incremental indexing
design.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Testing
Added unit tests in
`test/unit_test/rag/graphrag/test_graphrag_utils.py`:
- `n_neighbor`: path and weight shape, one-hop vs two-hop, isolated
nodes, missing weights, and direction-agnostic lookup.
- `graph_node_to_chunk`: `rank_flt` populated from pagerank and
defaulting to `0`, `n_hop_with_weight` serialized and defaulting to an
empty list.
```
uv run pytest test/unit_test/rag/graphrag/ # 106 passed
uv run ruff check rag/graphrag/ rag/utils/ob_conn.py
```
## Summary
- Complete the Go Elasticsearch result functions that remained stubbed
after #15160.
- Add focused unit coverage for field mapping, aggregation, IDs, and
highlighting behavior.
- Update a stale query-builder test type import discovered during
validation.
## What changed
- Keep the Elasticsearch Go implementation merged in #15160 and fill in
`GetFields`, `GetAggregation`, `GetHighlight`, and `GetDocIDs` in
`internal/engine/elasticsearch/chunk.go`.
- Add regression and invariant coverage in
`internal/engine/elasticsearch/chunk_helpers_test.go`.
- Update `internal/service/nlp/query_builder_test.go` to use the current
`types.MatchTextExpr` type.
## Why
- #15160 implemented the main Go Elasticsearch surface, but
retrieval/tag flows still call result functions that returned stubs.
- Completing these functions keeps Elasticsearch result processing
aligned with the expected document-engine behavior for field extraction,
tag aggregation, doc ID extraction, and snippet highlighting.
## Validation
- `go test ./internal/engine/elasticsearch`
- `GOARCH=arm64 CGO_ENABLED=1 go test ./internal/service/nlp -run
TestQueryBuilder`
- `git diff --check`
- CodeRabbit review reported 0 issues after follow-up fixes.
- Codex Security diff scan found no reportable issues.
## Notes
- This PR is now a follow-up to #15160 rather than a competing
implementation.
- A full local `go test ./internal/service/nlp` run is blocked by local
WordNet resource prerequisites; the query-builder tests touched by this
PR pass with the arm64 CGO path.
### What problem does this PR solve?
Fix: The variables in the Visual Input File of the agent operator are
not displayed.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fixes four Go paths that dereference a pointer with no prior nil check,
each
causing a **runtime panic**. Closes#15814.
| # | File | Bug | Fix |
|---|------|-----|-----|
| 1 | `internal/entity/models/deepseek.go` | streaming path runs `switch
*chatModelConfig.Effort` inside `if *Thinking`; panics when
`Thinking=true` and `Effort==nil` | nil-check with default `"high"`,
matching the non-streaming path in the same file |
| 2 | `internal/entity/models/volcengine.go` | identical oversight:
`switch *modelConfig.Effort` with no guard | nil-check with default
`"medium"`, matching its non-streaming path |
| 3 | `internal/handler/auth.go` | `AuthMiddleware` does `if
*user.IsSuperuser`; panics on every authenticated request when the DB
column is `NULL` | guard with `user.IsSuperuser != nil &&`, matching
every other call site (`admin/handler.go`, `admin/service.go`,
`user.go`) |
| 4 | `internal/service/heartbeat_sender.go` |
`responseBody["code"].(float64)` panics on any non-200 response lacking
a numeric `code`; the upstream `recover()` calls `Fatal()` →
`os.Exit(1)`, taking down the whole server | comma-ok assertion (`code,
ok := ...`); return an error instead of panicking |
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fixes four panic / spurious-error paths in the Go model layer. Closes
#15818.
| # | File | Bug | Fix |
|---|------|-----|-----|
| 1 | | Thinking-mode streaming path: accessed unconditionally; Gemini
emits usage-only chunks with an empty slice, causing a runtime panic |
Guard each step: , , before indexing |
| 2 | | is a plain for ordinary requests; the cast to silently returns ,
then panics immediately | Switch on concrete type; handle both and |
| 3 | | Identical panic on the streaming path | Same switch-on-type fix
|
| 4 | | The field is optional (absent for non-thinking models) but the
code returned an error when it was missing, breaking every ordinary
Ollama completion | Change to a silent comma-ok assertion; is empty
string when the field is absent |
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
### What problem does this PR solve?
feat: support custom editing for model list
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
## Problem
When users configure auto-metadata for a dataset, parsing crashes with:
```
KeyError: 'properties' in gen_metadata → schema["properties"]
```
## Root Cause
Pydantic `AutoMetadataField` defaults `enum` and `description` to `None`
when the frontend omits these fields:
```python
class AutoMetadataField(Base):
enum: Annotated[list[str] | None, Field(default=None)]
description: Annotated[str | None, Field(default=None)]
```
These `None` values propagate through the call chain and cause two
crashes:
