MCP preview after the server lost a session (it expired, or the MCP
process restarted):
- Every server state has an id, made when the state is created. The tab
notices a new id even when the version numbers happen to match, and
every push names the state it was based on, so one based on a lost state
is refused, also when it comes before the tab's first poll (the server
recovers the saved file first).
- The tab keeps the newest canvas XML, saved or not. When the server knows
nothing (no file) or exactly what the tab last saved, the canvas wins and
is saved, so edits made while the server was down are kept. Otherwise
the server's diagram (an AI write the tab missed, a cleared document
that was saved) is shown and the tab's copy goes to History.
- Late answers to an old state's push or poll are dropped; a failed push
says the server is unreachable; Download as .drawio saves the canvas.
Settings and server:
- Saved providers this version does not know stay in storage with their
keys, and sending no longer trips over them.
- The desktop "Ollama (Local)" preset with a key goes to local Ollama
again; a server model's Ollama URL variable is read; the admin panel
writes Ollama Cloud's URL for a key without one.
- Provider error texts show again in the desktop app and for EdgeOne.
- .env: a quoted value followed by a comment ending in a quote is read as
dotenv reads it; unquoted values are unchanged.
- Desktop app: the next launch opens the port where a chat was last
saved; a launch elsewhere that saves nothing does not move it, and a
page with no chats lets the next launch try the other port once.
- The Test button no longer stays busy after another tab changed the key.
- A completed append_diagram is no longer undone by an earlier failed
edit's preview; a file read once in vain is saved again once it is read
or gone.
From the first batch's review:
- The admin panel's Test of an entry without a URL now tests the server's
<P>_BASE_URL, where chat sends the entry's key; chat is unchanged (the
first fix rerouted working setups).
- The model list ends downloads that are too large, accepts answers
without a body, and keeps the "redirects are not allowed" explanation.
- A test covers the preview's History rendering.
- Bedrock: a request's AWS region must be a region name. It becomes part
of the endpoint's host name, so a value such as
"us-east-1.attacker.example/" sent the server's bearer token or signed
request to another host.
- MCP preview server: only the preview page itself (Origin equal to the
Host) or a non-browser client may call it; a page on another localhost
port could replace the diagram with a plain text POST. History builds
its thumbnails element by element and shows only SVG data images, so a
stored value can no longer run script in the preview.
- chat, validate-model, validate-diagram, provider-models and parse-url
take JSON bodies only, so another website cannot make the user's own
server (the desktop app, a local install) run models with their keys;
the desktop app also refuses a foreign Host (DNS rebinding).
- The model list reads at most 2 MB, also through the Gateway SDK, and
answers only with its own error texts: the URL is the caller's and may
be an internal address.
- An admin panel provider with its own key and no URL no longer inherits
the global <P>_BASE_URL, which may be a proxy for another key; OpenAI
then gets the official endpoint, as its Test. Azure keeps the server's
resource.
- Bedrock: a user's AWS keys no longer go to an endpoint the server sets
in AWS_ENDPOINT_URL_BEDROCK_RUNTIME / AWS_ENDPOINT_URL (read by the
upgraded SDK), and admin panel keys win over AWS_BEARER_TOKEN_BEDROCK,
as the Test button checks them. Checked with Bedrock.
- Ollama: a server key without a base URL (admin panel, OLLAMA_API_KEY)
goes to Ollama Cloud, as env.example says, instead of 127.0.0.1.
- Quota: EdgeOne counts whatever key header comes along, keyless Ollama at
a private address counts, and their provider texts stay in the log.
- An EdgeOne server model (admin panel, ai-models.json) works: the route
checked the raw provider header, which holds the name's slug.
- parse-url ends downloads it does not read (too large, PDF, errors).
- Desktop app: the port follows where the chats are (IndexedDB per
origin) instead of a remembered port, which could hide them for good;
a same-port restart tells the page to refetch the server models; a
failed preset switch no longer undoes a newer choice; a presets file
removed after a failed read can be saved again; .env values quoted from
start to end keep their inner quotes, as dotenv reads them.
Found by the second PR review:
- With AWS_BEARER_TOKEN_BEDROCK set on the server, a request with the
user's AWS keys ran on the server's token: the Bedrock SDK prefers it.
Checked with Bedrock: invalid user keys used to get an answer.
- An OpenAI key with the official URL filled in (the settings form does
that) went to the Responses API. Back to main's rule: a configured base
URL uses Chat Completions.
- A user's Ollama key went to the server's OLLAMA_BASE_URL, for chat and
for the model list. Like every other provider, it goes to the user's
base URL or Ollama Cloud.
- The server's keyless Ollama and EdgeOne were not counted in the quota.
- AI_MODEL models on the server's keys ran on any provider with a server
key, not only on AI_PROVIDER.
- A user's Azure key without a base URL used the server's resource name.
- The admin panel's Test button failed whenever access codes were set.
- DeepSeek's errors in the stream (plain text) were shown as they were,
without a hint and also on the server's keys. Bedrock's throttling in
the stream was not recognised as a rate limit.
- The EdgeOne function accepted text/plain; x=application/json, which
other sites can send without a CORS preflight.
- Desktop app: a launch that found the old port taken for a moment (the
previous version still quitting after an update) remembered the new
port for good. The new port is kept only when Windows reserves the old
one. A failed read of the presets file moved it aside as corrupt, and a
save could then replace the presets. Switching presets on the same port
now reloads the page. The dev launcher no longer misses a preset change
made before or during a restart.
Found by the PR review, each with a test that failed first:
- Quota: any key header skipped it, even one the provider never reads
(x-aws-access-key-id with OpenAI), so a request ran on the server's
key without being counted. The check now runs after the model is
resolved and uses usesServerCredentials. On main already.
- usesServerCredentials read the raw base URL; "/" cleans up to none, so
an Ollama request ran on the server's key past the server-model check.
- SGLang's default 127.0.0.1:8000 only fills the settings form. Chat and
the model list used it as a real address, so the server called its own
machine even with private URLs blocked. Now a base URL is required.
- With a user's OpenAI key and no base URL, the SDK read the server's
OPENAI_BASE_URL. The official endpoint is now passed. On main already.
- The Test button refused nothing on the server's keys (Ollama Cloud),
and a 15 s timeout reported "connected, no tool call".
- The model list for Ollama without a base URL came from ollama.com while
chat went to the server's Ollama.
- Bedrock's "Too many tokens, please wait" counted as context too long.
- On the server's keys the provider's error text stays in the server log;
it can name the server's AWS account, role or internal hosts.
- Desktop app: the preset keys are the user's own (NEXT_AI_DRAWIO_DESKTOP),
so Max Output Tokens can be raised and keyless models in settings work
again. A launch that found the remembered port taken no longer replaces
it, which hid the user's chats and settings for good.
- Claude Opus 5.5 sent an edit with invalid JSON, then the same edit
again. The first call's streamed preview was never undone: its input
has no operations, and the undo sat behind that check. The second edit
then started from the preview, failed on a duplicate id, and the model
had to try a third time. The undo now runs first, and an edit that
starts in the same render uses the undone diagram.
- The SDK passes an invalid tool call's error as a string, which was
wrapped as a provider error. streamErrorText keeps it as the text the
model reads.
- Bedrock's "on-demand throughput isn't supported" gets the model id hint.
- The thinking header uses the page language ("Thought for 1 second" in
English), from the dictionary entries that were already there.
Measured on Bedrock: Claude Opus 4.7, 4.8 and every Claude 5 model reject
a thinking budget ("thinking.type.enabled") and a temperature, and all of
them accept adaptive thinking. The retry used to drop thinking, so with
a thinking budget set these models did not think at all. It now switches
to adaptive thinking with display "summarized"; without that setting the
models think but send no thinking text to show.
The suggested Bedrock ids had no region prefix, and the newer models only
answer through an inference profile id: "anthropic.claude-sonnet-5-5"
fails with "on-demand throughput isn't supported". Each suggested id was
called once; the Claude ones now start with "global.", Llama, Pixtral and
Nova 2 Lite with "us.". Nova Premier (end of life) and the ids without a
working profile are gone. The docs example had the same problem and a
wrong date.
The suggested models stopped at Claude Opus 4.8 and GPT 5.5. They now
start with Claude Opus 5.5, Sonnet 5.5 and Fable 5.1, and gpt-6.1-sol,
gpt-6-sol, gpt-6-luna and gpt-6-astra (ids checked against the provider
lists). The Bedrock list is unchanged until its ids are checked.
The reasoning summary was only turned on for model ids containing o1,
o3, o4 or gpt-5, so GPT 6 models showed no thinking. It now matches the
o-series and gpt-5 or later by version, like the OpenAI SDK.
- An error object sent inside the stream (OpenRouter's { code, message })
showed as "[object Object]"; its message and status code are read now.
- A problem+json "detail" is added to the message: NVIDIA only said
"Gone" for a retired model. 410 counts as model not found.
- "Cannot connect to API" from the SDK gets the connection hint.
- Text that is only whitespace (Kimi K2.6 sends a space before a tool
call) no longer shows an empty bubble.
- allowSystemInMessages stops the warning on every request. Our system
messages carry cache points; a client's own system messages are already
dropped by the empty-content filter.
The "Fetch models" button asks the provider for its models (OpenAI-style
/models, Anthropic, Google, Ollama, OpenRouter, Vercel Gateway, AIHubMix)
and shows them in a searchable picker. This replaces the route that only
worked for AIHubMix.
A snapshot of models.dev (MIT) says which models support tool calls.
Models without them get a "no tool calls" badge in the picker and a hint
in the model list, since drawing needs tool calls. Refresh the snapshot
with scripts/update-model-catalog.mjs.
- lib/llm-errors.ts sorts an error into about a dozen kinds (key
rejected, no access, unknown model, no credit, rate limited, context
too long, no image input, no tool calls, output cut off, provider down,
cannot connect, timeout): first texts that name the cause precisely,
then the HTTP status code, then general texts. It unwraps RetryError and
hides keys and Bearer tokens in the provider's message
- The chat route uses it for errors before the stream and, through
toUIMessageStreamResponse's onError, for errors in the stream. Errors
of the model's own tool call stay as they are: the same text goes back
to the model so it can fix the call
- The chat shows the hint in the user's language, then the provider's
message; a rejected key, missing access or unknown model adds an "Open
model settings" button. The Test button shows the same hints
- Fixes: our message "API key is required when using a custom base URL"
was replaced by "Authentication failed" because it contains "key"; a
provider's "Rate limit exceeded" opened this site's quota toast; an
error body like {"error": ...} was shown as raw JSON; the Test button
matched "401" in the message, where providers rarely put it
- Remove the string matching fallbacks in the chat panel
- A "Get API key" link next to the API Key field for the 19 providers
that have a key page (from env.example and the providers' docs). 17
answered 200 to curl; OpenAI's is behind a Cloudflare challenge and
DeepSeek's behind a regional block, both checked in Chrome
- Base URLs drop spaces, trailing slashes and a pasted endpoint path
(/chat/completions, /completions, /messages, /responses), which the
SDK would otherwise append a second time and get a 404. getAIModel does
this for the chat and the Test button; the field does it on blur and
shows the URL requests go to
- getAIModel resolves credentials (client key, server env vars, the
existing SSRF rules) and createModel builds the model by SDK. The
provider-by-provider switch shrinks from 24 cases to the few that
differ (lib/ai-providers.ts 1531 -> 1106 lines)
- /api/validate-model calls getAIModel instead of its own 24-case switch
(503 -> 175 lines), which had drifted from the chat: it built Azure
with createOpenAI, Kimi and MiMo with createOpenAI instead of
createDeepSeek, and the official OpenAI endpoint with Chat Completions.
A passing test now means the chat works
- Plain OpenAI-compatible providers (SiliconFlow, SGLang, ModelScope,
GLM, Qwen, Qiniu, Novita, Atlas Cloud, EdgeOne, Doubao, MiniMax in
OpenAI mode, AIHubMix on a custom URL) use @ai-sdk/openai-compatible,
which reads reasoning_content, so their reasoning shows, and accepts
SGLang's stream as is (its 95-line stream rewrite is gone).
includeUsage keeps token usage for quotas. <think> tags in their text
become reasoning (extractReasoningMiddleware)
- SGLang without a base URL used OpenAI's endpoint; it now defaults to
http://127.0.0.1:8000/v1 like the Test button did
- Chat requests to a client base URL refuse redirects, as the Test
button already did (redirectGuardedFetch moves to lib/ssrf-protection)
- The Test button streams like the chat (the ModelScope special case is
gone), times out after 15 s, does not retry, asks the model to call a
ping tool and warns when it answers without one, and tests all models
at once. The time each test took shows on its check mark
- Unknown provider names are rejected with Object.hasOwn, and the error
texts list providers from PROVIDER_INFO instead of hand-kept lists
- useChat throttles streamed message updates (experimental_throttle,
150 ms), replacing the two hand-written 150 ms timers of the
display_diagram and edit_diagram previews (94 lines less). The preview
now only runs while the input streams; once it is complete the tool
handler takes over, so a queued preview can no longer redraw an edit
the handler rejected and rolled back. Measured on a streamed 60-cell
diagram: 41 redraws at least 97 ms apart, before 37 with gaps down to
48 ms
- The diagram check endpoint uses streamText with Output.object instead
of the deprecated streamObject, and returns its fixed result as a plain
text response; new route test
- Import createGateway/gateway from ai and drop the direct
@ai-sdk/gateway dependency
- The per-request message structure logs only print with
DEBUG_LLM_PAYLOAD=true
- Remove an empty onFinish callback
- Update ai to 6.0.300 and the @ai-sdk providers to their latest v6-line
versions. @ai-sdk/anthropic 3.0.47 did not know claude-opus-4-7/4-8
and capped their output at 32000 tokens; 3.0.127 allows 128000
- Drop the fine-grained-tool-streaming beta header for the Anthropic API:
the provider now streams tool input per tool (eager_input_streaming)
- Claude 4.7 and later reject a non-default temperature/top_p/top_k and
the extended thinking budget with a 400. A middleware retries once
without them, so TEMPERATURE and *_THINKING_BUDGET_TOKENS no longer
break those models
- Prompt caching also reaches Claude on the Anthropic API and OpenRouter;
before, only Bedrock got a cache marker
- GOOGLE_TOP_K and GOOGLE_TOP_P never reached Gemini: they were sent as
Google provider options, which drops them. They are call settings now.
GOOGLE_CANDIDATE_COUNT and GOOGLE_REASONING_EFFORT, which the provider
does not support, are removed
- Add @ai-sdk/openai-compatible as a direct dependency
- The three XML examples (swimlanes, two edges, waypoints) that the web
system prompt, the display_diagram description and the MCP drawing
guide each had a copy of now live in packages/mcp-server/src/xml-examples.ts
- The shape library group list and reader come from the MCP
shape-library.ts; getShapeLibrary takes the folder, and the web route
passes docs/shape-libraries under the working directory as before.
Only the 30 known library names are read. Error texts differ slightly
- next.config.ts traces docs/shape-libraries/*.md for /api/chat, since
the read now happens in another module
- Every prompt is byte-for-byte unchanged: the web system prompt for five
model ids with and without minimal style, and the MCP drawing guide,
compared before and after; the library list and swimlane example match
the old tool description text exactly
- edit_diagram runs the MCP server's editDiagram: every new_xml is checked
first, one cell per operation, and after the edit only the target page
is checked, rejecting only errors this edit introduced. An unrelated
problem elsewhere in the document no longer blocks every edit. The
error lists each failed operation
- The streaming edit preview uses the MCP applyDiagramOperations
- Delete applyDiagramOperations (292 lines) and wrapWithMxFile from
lib/utils.ts, and the unused hand-copied scripts/test-diagram-operations.mjs
- One blank document (BLANK_MXFILE) for the web app and the MCP preview,
replacing four copies
- Saving a .drawio wraps a bare model with normalizeToMxfile
- The empty-diagram check uses hasCells, which also counts cells wrapped
in a UserObject/object
- DiagramOperation is the MCP type
- The wrapped-cell and empty-diagram tests now run against the MCP code
- New e2e test: edit_diagram changes the canvas, and a failing edit
leaves it as it was
- Delete the web app's own copy of the XML checks and repairs from
lib/utils.ts (1,074 lines). loadDiagram now uses the MCP server's
validateAndFixXml without the strict checks, because the XML may hold
the user's own diagram
- display_diagram and append_diagram prepare the model's XML with the new
shared prepareNewDiagram, also used by the MCP create_new_diagram: wrap,
validate strictly and auto-fix while it is still a bare model (where
duplicate ids are renamed), then turn it into an mxfile
- The streaming preview of display_diagram no longer redraws the model's
raw cells after the tool handler loaded the checked diagram, and drops
a queued preview once the input is complete. That redraw lost
auto-fixes and UserObject/object wrappers, so a linked cell lost its
label; it also showed a second error toast
- The web repair regression tests now run against the MCP functions
- New e2e test checks the canvas content after display_diagram
- Fix the e2e upload tests, whose file input locator also matched the
template import input
- Template dialogs no longer submit the outer chat form
- Sending is blocked while files or URLs are still extracting
- File and URL extraction no longer drop or resurrect entries
- IME composition Enter no longer sends
- Tool call cards show the error text; keyboard handling on cards fixed
- Template import available when empty, edit dialog resets, saved templates refresh
- Only png/jpeg/gif/webp images accepted, SVG sent as text; PDF objects released
- parse-url request sends the access code
- Autosave guard reads refs, so edits after a theme or dark mode switch are kept
- Duplicate-id check and rename run per page; repair loop no longer quadratic
- autoFixXml no longer breaks style values, rich text " or single-line cells
- extractCompleteMxCells keeps the cell after a self-closing cell
- Better truncation detection; object/UserObject wrapped cells are editable
- Exports for thumbnail, PNG and save are routed by tag instead of a shared resolver
- History stores the full document; storage errors are reported, no auto-deletion of chats
- IndexedDB connection reopens after errors; focus refresh throttled
- Keep ?session= on locale redirect, map zh-Hant to zh-tw for draw.io
- Restored sessions no longer replay the last display_diagram over the saved diagram
- Failed or stopped edit_diagram restores the canvas
- Message snapshots keep the full multi-page document
- "Improve with suggestions" uses the normal send path (headers, xml, retry counters)
- Editing a message keeps its file/URL sections; cached example edits work
- New chat's first autosave no longer resets the UI
- Validation retries counted per user turn; validate-diagram sends the access code
- Cached examples only match the example files on an empty canvas
- Template sends keep attachments and wait for extraction
- Shared checkAccessCode for validate-diagram, validate-model, parse-url, verify-access-code
- parse-url: 5 MB streamed body limit; validate-diagram: 5 MB image limit
- validate-model refuses redirects when private URLs are blocked
- Admin settings state shared across module instances via globalThis
- Server model ids: unique slugs (non-ASCII names encoded), duplicates rejected
- Panel Bedrock credentials stored as ADMIN_AWS_* so the DynamoDB client keeps its own
- Locale redirect keeps basePath and query; EdgeOne function drops open CORS and checks the access code
- Providers payload reports whether .env sets a default model
- Vertex: a client-supplied base URL only works with the client's own Vertex key
- Accept only data: URLs for file parts in every message, so the server never downloads them
- Output budget retry accounts for the thinking budget Bedrock/Anthropic add, and reads
Volcengine, DashScope, SGLang and vLLM rejections; falls back to 16000 once
- x-max-output-tokens can only lower the budget on server credentials
- On server credentials only server models or AI_MODEL entries can be used
- Drop tool results together with the invalid tool calls they belong to
- Count quota tokens as input + output (cached tokens were counted twice)
- Private-URL check for custom base URLs, end Langfuse traces on error/abort/early return
- Fix repairToolCall ordering and placeholder, align edit_diagram prompt with operations
- Panel Bedrock keys are read from ADMIN_AWS_*; forward the access code to EdgeOne
- isMinimalDiagram only treats root cells as an empty canvas
* fix: raise the output budget so reasoning models reach the tool call
A reasoning model spends the output budget in order: thinking first, then prose,
then the tool call. With 16000 the thinking alone can consume all of it, so the
turn ends with finishReason "length" before display_diagram is ever called. The
canvas stays empty and nothing surfaces in the UI, because no tool call means no
tool error, and the client never reads finishReason.
Measured on openrouter deepseek/deepseek-v4-flash, the model from the report:
- max_tokens=800 with reasoning on returns reasoning_tokens=800, empty content,
finish_reason length. So reasoning is billed against this budget, not exempt.
- refining an existing diagram (19k chars of XML in the input) produced 49142
chars of reasoning, zero tool calls, finishReason "length" at 16000
- the same request at 40000 finished and called edit_diagram with 12 operations
64000 cannot just be sent to every model: bedrock claude-3-haiku caps at 4096,
nova-lite at 10000, and the openrouter deepseek-r1 endpoint counts input and
output against one 64000 ceiling. All three name the real limit in the 400, so
parse it and retry once. Verified: nova-lite logs "64000 rejected, retrying with
10000" and then completes its tool call.
Also expose the budget in Settings. It is sent as a header rather than read from
env only, so desktop users can raise it themselves without an env file.
vercel.json goes back to the 300s it had before #238 traded it for $2-4/month.
That is now Vercel's own default, and billing pauses while the function waits on
the model, so the saving that motivated 120s no longer applies. edgeone.json is
left alone: its 120 may be that platform's actual ceiling.
* fix: only reinterpret an error as a budget rejection when it says so
Review of the first commit found the retry could fire on errors that have
nothing to do with the budget, which would replace a readable provider error
with a truncated response: exactly the symptom this PR exists to remove.
- Drop the generic "lower than N" pattern. For the Bedrock message it was dead
code, since "model limit of N" matches first with the same number. Left live,
it would read a number out of any message shaped like "must be lower than 2".
- Skip errors whose status is not 400 or 422, so auth and rate-limit failures
are never reinterpreted.
- Require the parsed ceiling to be at least 1024. Below that a diagram cannot
come out whole, so retrying would hide the error behind broken XML.
- Validate MAX_OUTPUT_TOKENS from env the same way as the header, so a stray
"-1" falls back instead of reaching the provider.
Adds tests for the retry wrapper itself, which had none: it retries once with
the named ceiling, leaves a 401 alone, does not retry when the ceiling is not
smaller, propagates a second rejection, and preserves the other call options.
Re-verified against the live APIs: bedrock nova-lite still logs "64000 rejected,
retrying with 10000" and completes its tool call, and deepseek-v4-flash still
finishes normally at 64000.
* feat: add MiMo (Xiaomi) as AI provider
* fix: correct MiMo default base URL, suggested models, and reasoning support
- Default base URL was the China Token Plan endpoint (tp- keys only);
switch to https://api.xiaomimimo.com/v1 which works with standard
pay-as-you-go sk- keys. Token Plan users can override in settings.
- Replace deprecated mimo-v2-flash suggestion with mimo-v2.5
(v2 series was deprecated on 2026-06-30).
- Use createDeepSeek instead of createOpenAI so reasoning_content is
passed back during multi-turn tool calls (MiMo returns 400 without
it), matching the existing Kimi implementation.
- Add mimo to SINGLE_SYSTEM_PROVIDERS so system messages are merged.
- Fold validate-model case into the shared OpenAI-compatible group.
- Drop the Bot icon special case; models.dev serves a real xiaomi logo
via PROVIDER_LOGO_MAP.
- Document MIMO_API_KEY/MIMO_BASE_URL in env.example and
docs/{en,cn,ja}/ai-providers.md.
* feat: show base URL hint for MiMo in provider settings
MiMo has two endpoints tied to key type: pay-as-you-go keys (sk-...)
use the default api.xiaomimimo.com/v1, while Token Plan keys (tp-...)
require token-plan-cn.xiaomimimo.com/v1. Surface this under the Base
URL field like the existing MiniMax hint, in all four locales.
---------
Co-authored-by: mapengfei <[email protected]>
Co-authored-by: dayuan.jiang <[email protected]>
* fix: resolve DNS before SSRF check and block redirects in parse-url
isPrivateUrl() did string-only hostname matching and never resolved DNS,
so a public-looking name that maps to an internal IP (e.g.
127-0-0-1.sslip.io -> 127.0.0.1) passed the check while fetch/extract
later resolved it and reached internal services (GHSA-wqcv-5qvx-vx75).
- isPrivateUrl is now async: it keeps the fast string/literal-IP path,
then resolves the hostname via DNS and rejects if any address is private.
- parse-url now fetches the page itself with redirect: "error" and parses
via extractFromHtml(), since article-extractor follows redirects
internally and drops a redirect option, which allowed a public URL to
302 to an internal host.
- Update validate-model call site to await; add regression tests.
* fix: preserve charset detection and block CGNAT range in parse-url SSRF fix
Follow-up to the multi-reviewer review of the SSRF fix:
- Restore charset handling lost when switching from extract() to
response.text(): non-UTF-8 pages (Shift_JIS/GBK/EUC/Big5, common on CJK
sites this project targets) decoded as mojibake. Now read the body as
bytes, detect charset from Content-Type / <meta charset>, and decode
with TextDecoder before extractFromHtml.
- Wrap extractFromHtml in try/catch: it throws (not returns null) on
empty/non-HTML bodies, which previously surfaced as a 500 instead of the
intended 400.
- Add 100.64.0.0/10 (RFC 6598 CGNAT) to isPrivateIp; it is routable inside
some cloud internal networks and was a residual SSRF target.
- Add tests for CGNAT, its boundaries, 0.0.0.0, and DNS-resolved IPv6.
supportsImageInput() guessed multimodal capability from the model id
string. The heuristic misfired on newer models (e.g. kimi-k3.6, qwen36),
either wrongly rejecting images for capable models or letting them through.
The AI SDK does not emit a warning when an OpenAI-compatible endpoint
silently drops an image, so the guess was the only signal — but an
unreliable one. Drop the detection entirely and let the real provider
error surface instead (already translated to a friendly message in
chat-panel.tsx). Validation falls back to "valid" on any model error.
- Remove supportsImageInput() and its pre-send check in chat route
- Drop the vision-capability throw in getValidationModel()
- Remove the corresponding unit tests
Users expected setting AI_MODEL to a comma-separated list to expose
multiple models in the picker, but the value was used verbatim as a
single model id, leaving the picker with only the "Server Default"
fallback.
Add a third-priority fallback in loadEnvServerModelsConfig: when
AI_MODELS_CONFIG and ai-models.json are both absent, AI_MODEL contains
a comma, and AI_PROVIDER is set to a known provider, synthesize an
equivalent ServerModelsConfig with the provider's models trimmed,
deduplicated, and the first marked as default.
Also makes getAIModel and getValidationModel pick the first comma-split
value when falling back to AI_MODEL, so requests started before the
client picker hydrates still resolve to a real model id.
Docs (en/cn/ja) and env.example updated; tests cover the new fallback
plus the no-comma / no-AI_PROVIDER negative cases.
* feat: add file-based admin settings panel at /admin
Settings saved in the panel are written to data/settings.json and
overlaid onto process.env, taking precedence over environment
variables and applying immediately without restart. Enable by setting
ADMIN_PASSWORD; on serverless platforms without persistent disk the
panel degrades to read-only.
* polish: admin panel UI improvements
- Provider logos in credential rows (shared ProviderLogo component,
extracted from model-config-dialog)
- Scroll-spy active state in the sidebar nav
- Green success state in the save bar that clears after a few seconds
- Wider content column (max-w-6xl) for less wasted space on desktop
* polish: admin panel section toggles and reorder
- Move Quota & Rate Limits to the end of the settings page
- Add enable switches to Observability and Quota sections; default off
with fields grayed out, auto-on when any field is already configured
* polish: make section enable switch more visible
Wrap the switch in a labeled pill ('Enabled'/'Disabled') with border
and background so the off state is clearly visible.
* refactor: derive admin registry from PROVIDER_INFO, simplify page state
- Provider options, labels, and base-URL placeholders now come from
PROVIDER_INFO instead of hand-copied lists (fixes SiliconFlow .com/.cn
placeholder drift; panel names now match the model-config dialog)
- Replace free-text subgroup strings + SUBGROUP_PROVIDERS reverse map
with a typed provider field on SettingDef
- Precompute SETTINGS_BY_GROUP and PROVIDER_SUBGROUPS at module level
- Merge justSaved into saveMessage, drop unused mainRef, hoist
fetchSettings out of the component, dedupe savedText logic
- Serialize from SETTINGS_REGISTRY directly; json validators in a map
instead of a hardcoded key check
- Make allowPrivateUrls a function so ALLOW_PRIVATE_URLS edits in the
admin panel apply without restart
* feat: graphical model management in admin panel
Replace the provider credential fields and raw AI_MODELS_CONFIG JSON
textarea with a Models section mirroring the in-app model settings UI:
provider instance list with logos, credential fields per provider type,
model add/remove with suggestions, per-model connectivity test, and a
default-provider star.
On save the server derives everything the runtime needs into
settings.json: credential env vars (with _2 suffixes for multiple
instances of one provider), AI_MODELS_CONFIG, and AI_PROVIDER/AI_MODEL
for the default. Secrets round-trip as masked markers and are never
sent back to the browser. The general settings registry now only
covers non-provider settings (generation, access, features,
observability, quota).
* fix: allow testing unsaved providers in admin panel
The test button previously looked up credentials by providerId in the
saved settings, so testing a newly added (unsaved) provider failed with
'Unknown provider or model'. The test endpoint now accepts the client's
current provider state; newly typed secrets are used as-is and masked
markers are resolved against the stored values, so testing works both
before and after saving.
* fix: merge env AI_MODELS_CONFIG with admin panel providers
Previously, saving in the admin panel wrote a complete AI_MODELS_CONFIG
into settings.json, which (by overlay precedence) replaced any config
from .env or ai-models.json — admins lost their env-configured models.
The panel no longer writes AI_MODELS_CONFIG. Instead its providers are
merged with the env baseline at read time in loadRawServerModelsConfig,
and panel credentials go to ADMIN_-prefixed env vars wired up via
apiKeyEnv/baseUrlEnv so they never shadow standard vars. Env-based
providers now appear read-only in the panel, name clashes are rejected,
and a panel default overrides the env default. data/ is now gitignored.
* fix: block global-credential providers already managed via env
Bedrock, Vertex AI, and Ollama credentials live in fixed env vars with
no apiKeyEnv redirection, so a panel instance of one of these would
silently override the credentials that env-configured models rely on.
The API now rejects saving such a provider when the env config already
uses that type, and the Add Provider dropdown disables it with a
'managed via env' note.
* fix: address admin panel review findings
- Security: test-model no longer resolves a stored secret when the
request's baseUrl/provider differs from the stored entry, closing a
path where a tampered baseUrl could exfiltrate a saved key
- Save failures are now visible: the save bar shows the error in red
(was masked by the persistent 'Unsaved changes' text), and per-field
validation errors from the settings API are surfaced under each field
- The Observability/Quota enable switch is now real: toggling off stages
deletion of the group's saved values, and the toggle no longer snaps
back to Enabled after saving
- Env provider's default star is hidden when a panel provider is the
active default (no more double star)
- Clearing a credential field reverts to the stored value instead of
silently deleting it; an explicit X button removes a stored secret
- Form inputs are disabled during an in-flight save
* refactor(admin): split 1549-line admin page into focused modules
Extract admin-shared.ts (types + fetch helper), setting-field.tsx
(registry-driven fields), and models-section.tsx (provider/model
manager) from page.tsx. Pure mechanical move, no behavior change.
* feat(admin): share credential fields with user dialog and localize panel
Extract ProviderCredentialsFields (display name + per-provider
credential inputs) used by both the user ModelConfigDialog and the
admin Models panel; secret input passed via renderSecret (plaintext
vs masked), test button via footer slot. Add full i18n for the admin
panel across en/zh/ja/zh-Hant, reusing modelConfig.* for shared parts.
* fix(admin): address Copilot review findings
- Reflect built-in defaults for boolean settings (ALLOW_PRIVATE_URLS
defaults on) and allow clearing a saved boolean back to default,
so the SSRF toggle matches actual runtime behavior.
- Harden JSON loading: filter settings values to strings only, and
schema-validate stored ADMIN_PROVIDERS entries, dropping malformed
ones instead of letting them reach runtime code.
- Set beforeunload returnValue so the unsaved-changes prompt shows in
all browsers; reject non-finite numbers in settings validation.
- Fix README/CN/JA docs that claimed the panel auto-generates
AI_MODELS_CONFIG (providers are merged at read time, not written).
- Add unit tests for corrupted-file value filtering and provider
schema validation.
* docs: move admin panel details to dedicated docs/{en,cn,ja}/admin-panel.md
The READMEs now carry a short blurb + link, matching the existing
per-topic docs (docker.md, ai-providers.md, ...). Removes the ~22-line
inline section and the duplicated data/settings.json mentions.
* fix(admin): address follow-up Copilot findings on the prior fixes
- loadAdminProviders now validates against a stored-shape schema where
secrets are plain strings, so a hand-edited ADMIN_PROVIDERS holding an
{isSet} marker is dropped instead of later crashing maskSecret().
- loadSettings guards against array values (typeof [] === 'object'),
which would otherwise overlay numeric keys onto process.env.
- Admin SecretInput uses the bare id so the shared component's
<Label htmlFor> stays associated (only one ProviderDetail mounts).
- Add tests: marker-secret rejection, array-values guard, bedrock
multi-secret round-trip.
Updates the SUGGESTED_MODELS quick-add list in lib/types/model-config.ts
against each provider's official model docs as of 2026-06-09.
- openai: GPT-5.5 / 5.4 frontier; drop deprecated 5.0-5.2 family
- anthropic: add Opus 4.8/4.7/4.6, Sonnet 4.6, Haiku 4.5 (new dateless
pinned IDs); fix wrong date suffixes on Opus/Sonnet 4.5
- google / vertexai: adopt Gemini 3 family; drop Gemini 2.0 (shut down)
and 1.5
- azure: GPT-5.x line + o3 / o4-mini; drop gpt-4-turbo / gpt-35-turbo
- bedrock: Opus 4.8/4.7/4.6, Sonnet 4.6, Haiku 4.5, Nova Premier /
Nova 2 Lite, Llama 4 Maverick / Scout, Mistral Large 3, Pixtral
- openrouter: refreshed against live /api/v1/models
- deepseek: V4 Pro / Flash
- siliconflow / modelscope: DeepSeek V4, Qwen 3.x, drop bogus
qwen3.5-plus
- gateway: verified against live Vercel AI Gateway endpoint
- doubao: Seed 2.0 / 1.8 / 1.6 in official dash-form IDs
- minimax: + M2.5
- novita: M3, GLM-5.1, Kimi-K2.6, DeepSeek V4
* fix: block private IPv6 URLs
* fix: cover full fe80::/10 link-local range and :: unspecified
- Replace startsWith("fe80:") with a check covering the full fe80::/10
range (fe80 through febf) per RFC 4291.
- Add :: (unspecified) to the localhost block.
- Drop the dead 0:0:0:0:0:0:0:1 branch (URL parser normalizes it to ::1).
- Add tests for fe9f::1, febf::1, and ::.
---------
Co-authored-by: dayuan.jiang <[email protected]>
- Add MiniMax-M3 to the model selection list (set as new default at top)
- Retain MiniMax-M2.7 and MiniMax-M2.7-highspeed
- Remove deprecated MiniMax-M2.5 / M2.5-highspeed
- Update supportsImageInput: M3 supports image input (M2.x stay text-only)
- Update unit tests to reflect new model lineup
- Update example AI_MODEL in CN/EN/JA docs to MiniMax-M3
Co-authored-by: octo-patch <[email protected]>
* fix(anthropic): support ANTHROPIC_AUTH_TOKEN as alternative to ANTHROPIC_API_KEY
Anthropic SDK supports two mutually exclusive auth methods: apiKey (sent as
x-api-key header) and authToken (sent as Authorization: Bearer header). Detect
either env var during provider detection and credential validation, and pass
authToken to createAnthropic when only ANTHROPIC_AUTH_TOKEN is set.
* docs(anthropic): document ANTHROPIC_AUTH_TOKEN and refine error message
- Add ANTHROPIC_AUTH_TOKEN to env.example and the en/cn/ja provider docs
- Reword the missing-credential error to "Either ... or ..." for readability
---------
Co-authored-by: duyunjie <[email protected]>
Co-authored-by: dayuan.jiang <[email protected]>
/api/parse-url accepted any URL the user submitted, fetched it via
@extractus/article-extractor, and returned the body as Markdown. With
ALLOW_PRIVATE_URLS unset (the default after #600) the SSRF guard
short-circuited entirely, so an unauthenticated POST could probe
container ports, read AWS IMDS / GCP metadata, and reach same-VPC
internal services.
- parse-url now always rejects private URLs regardless of
ALLOW_PRIVATE_URLS. The flag's only legitimate use case is local
LLM provider baseUrl overrides (validate-model, chat); article
extraction has no business fetching internal hosts. Local LLM
setups (Ollama, LM Studio, etc.) are unaffected.
- Strip a trailing dot from the hostname before equality checks so
the FQDN form "localhost." (which still resolves to 127.0.0.1) is
caught by the existing string match.
Known follow-ups (not addressed here):
- DNS rebinding: hostnames are matched as strings; a public domain
resolving to 127.0.0.1 (e.g. localtest.me) is not caught.
- HTTP redirects: @extractus/article-extractor uses cross-fetch with
default redirect: "follow" and exposes no hook, so a public URL
302-ing to an internal host still leaks.
PR #840 fixed issue #815 in the Electron main process via
will-prevent-unload + preventDefault. The renderer-side workarounds
introduced by previous fix attempts (#642, #648) are no longer needed
and never had effect for their stated purpose.
Removed:
- configuration={ confirmExit: false } in DrawIoEmbed
confirmExit is not a recognized draw.io config key (zero matches in
jgraph/drawio source). This was always dead code.
- modified=0 / keepmodified=0 URL parameters
Per drawio source (app.min.js:14898), these only suppress the
post-save modified-flag clearing — they do not prevent edits from
setting editor.modified=true. They were ineffective for blocking
beforeunload prompts and actually prevented draw.io from clearing
its modified flag after save.
- canPersist / canPersistChecked state and isIndexedDBUsable() probe
Their only purpose was gating the dead config above. Removing them
also removes a startup delay before the iframe renders.
- handleDrawioAutoSave wrapper
After PR #780 stripped its body, it was a pure passthrough useCallback.
Now passes handleDiagramAutoSave directly to onAutoSave.
- withDB / isClosingError / resetDBPromise / onversionchange / onclose
/ terminated handlers in lib/session-storage.ts and lib/template-storage.ts
PR #648 added these to recover from 'IDBDatabase: connection is closing'
errors that PR #642's first land caused via db.close() on the shared
singleton. That bug was already fixed in c5de1a1 (re-land of #642),
three minutes before PR #648 commits started. The retry handlers
defend against multi-tab / version-change scenarios that cannot occur
in this single-instance Electron app (requestSingleInstanceLock).
template-storage.ts copied the same pattern when introduced by #773.
Verified:
- npx tsc --noEmit passes
- Manual test in dev mode: session save/load works, template create works,
diagram-only persistence works.
* feat: add all Draw.io themes to settings panel
Add all available Draw.io themes (kennedy, atlas, dark, min, sketch, simple)
to the settings panel dropdown. Previously only min and sketch were available
as a toggle button.
Changes:
- Replace the Draw.io style toggle button with a dropdown selector
- Expand theme type from "min" | "sketch" to include all 6 themes
- Update localStorage validation to accept all themes
- Update handler from toggle to direct theme selection
Closes#499
* fix: localize theme labels, tighten DrawioTheme typing, sync dark param
- Move DRAWIO_THEMES + DrawioTheme to lib/drawio-themes.ts; reuse in
page.tsx, chat-panel.tsx and settings-dialog.tsx instead of `string`
- Localize theme dropdown labels (Dark/Minimal/Sketch/Simple) in
en/zh/ja/zh-Hant; keep proper-noun themes (Kennedy/Atlas) as-is
- Drop trailing colon from drawioStyleDescription and remove dead
switchTo/minimal/sketch keys in all 4 dictionaries
- Auto-sync drawio dark URL param when ui="dark" is selected
- Add aria-label to drawio-style SelectTrigger
* fix: use kennedy as default theme and label it "Default"
---------
Co-authored-by: dayuan.jiang <[email protected]>
Kimi thinking models (e.g. kimi-k2.6) return reasoning_content in their
responses. The previous createOpenAI-based implementation silently ignored
this field, so reasoning was never captured or replayed in subsequent turns.
Switching to createDeepSeek (which natively understands reasoning_content)
ensures that reasoning context is preserved across conversation turns,
resolving the "cannot interact a second time" error with Kimi k2.6.
This mirrors the existing doubao provider pattern, which already uses
createDeepSeek for kimi-based models routed through Doubao.
Co-authored-by: octo-patch <[email protected]>
QvQ models (e.g. qvq-72b-preview, qvq-max) are visual reasoning models
from the Qwen family that support image input. When accessed via providers
that prefix model names with 'qwen/' (e.g., OpenRouter), these models
contain 'qwen' in their ID but lack the 'vl' or 'vision' indicator.
This caused supportsImageInput() to incorrectly return false for model
IDs like 'qwen/qvq-72b-preview', blocking image uploads for vision-capable
models.
Add 'qvq' as an explicit exception in the Qwen text-model check so that
QvQ models are correctly allowed to receive image input regardless of the
provider prefix.
Co-authored-by: octo-patch <[email protected]>
Qwen3.5 models deployed via vLLM natively support image input, but the
supportsImageInput() check was incorrectly blocking them. The function
only exempted qwen3.5-plus and qwen3.5-flash variants, missing the base
qwen3.5 model name.
Simplify the exception to cover all qwen3.5 variants with a single
substring check on "qwen3.5", since it is a common prefix of all three.
Co-authored-by: octo-patch <[email protected]>
- Fix zoom resetting when dragging items (#775): removed useEffect that
called load() on every autosave-triggered chartXML change, which reset
the viewport. Moved diagram restore logic to onDrawioLoad where it
only fires on remount.
- Fix IndexedDB VersionError: template-storage.ts shared the same DB
name as session-storage.ts but at version 2, causing session storage
to fail with "requested version (1) < existing version (2)". Give
templates their own DB ("next-ai-drawio-templates").
* 增加了ralph自动化编程梳理
* feat: US-001 - 为模板库建立独立的 IndexedDB 存储层
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* feat: US-002 - 在空聊天状态用我的模板库替换官方示例
- 将 ChatLobby 中的 Quick Examples 替换为 TemplatePanel
- 当没有历史会话时，展示完整的模板库面板
- 当有历史会话时，展示可折叠的 "My Templates" 区域
- 使用 TemplatePanel 组件展示用户的个人模板库
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* feat: US-004 - Provide template creation flow
- Create TemplateCreateDialog component with form fields for prompt, title, description, tags, and pinned
- Add i18n translations for template creation UI in en, zh, zh-Hant, ja
- Update TemplatePanel to integrate the create dialog
- Support initialPrompt prop for pre-filling from current input
- Validate required prompt field (empty prompt not allowed)
- Auto-generate default title from first 20 chars of Pin templates appear at top of list
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* feat: US-005 - 为模板卡片提供编辑、删除和复制操作
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* feat: US-006 - Send template directly on click and record usage statistics
- Implement click-to-send template functionality with confirmation dialog
- Add clickCount and runCount increment logic
- Display runCount and lastUsedAt on template card
- Add i18n translations for confirmation dialog (en, zh, zh-Hant, ja)
- Pass onSendTemplate and currentInput props through component hierarchy
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* feat: US-007 - Support template search, pin and default sorting
- Add search bar to TemplatePanel with real-time filtering by title, description, and tags
- Add pin/unpin toggle button on template cards (uses Bookmark icon with fill indicator)
- Search uses existing searchTemplates function from template-storage
- Sort uses existing sortTemplates function (pinned desc, runCount desc, lastUsedAt desc, updatedAt desc)
- Show empty state with Search icon when search returns no results
- List re-sorts immediately after pin/unpin toggle
- Add i18n keys: searchPlaceholder, searchNoResults, pin, unpin for all 4 languages
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* feat: US-008 - Support saving current input as template
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* feat: US-009 - Support saving historical user message as template
- Add "Save as Template" button to user messages
- Pre-fill prompt with original user message text
- Only show on user messages,- Dialog opens TemplateCreateDialog on click
- Template appears in list immediately after saving
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* feat: US-010 - Support template import and export
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* chore: remove local-only dirs from git tracking (.agents, .cursor, scripts, screenshots)
These directories contain local IDE configs, agent scripts, and
dev tooling that should not be part of the upstream repository.
Added them to .gitignore to prevent future accidental commits.
* chore: remove AGENTS.md from git tracking
* fix: add missing i18n keys for template export/import (en/zh/zh-Hant/ja)
* fix: review fixes for my-templates PR
- Fix fragile querySelector("form") with id-based lookup
- Add objectStoreNames.contains guards for IndexedDB upgrades
- Remove duplicate TemplateSchema, import from template-storage
- Revert contributor-specific .gitignore additions
- Fix broken i18n placeholders and missing translations (zh/ja/zh-Hant)
- Remove unused setFiles prop from ChatLobby
- Remove tags feature (unnecessary complexity)
- Improve template card layout: overlay icons on hover, align stats
- Add break-all and overflow-hidden for long prompt text in dialogs
- Move incrementClickCount into sendTemplate for accurate tracking
- Use Intl.RelativeTimeFormat for locale-aware relative time
* feat: restore Quick Examples panel and add lobby panel visibility settings
Bring back the ExamplePanel as a third collapsible section in ChatLobby
alongside Recent Chats and My Templates. Add toggle switches in Settings
to show/hide each lobby panel, persisted via localStorage.
* fix: template send race condition, import defaults, and empty title bug
- Use flushSync instead of setTimeout(0) in handleSendTemplate to
ensure React state is flushed before form submission
- Explicitly validate and default all fields in importTemplates to
prevent undefined counters from malformed import JSON
- Fall back to existing title in edit dialog instead of writing undefined
* fix: address Copilot review comments and remove PRD file
- Fix fallback formatLastUsed returning "Not used yet" for recent usage
- Remove dead mounted flag in TemplatePanel useEffect
- Respect panel visibility settings in no-history lobby state
- Reject empty/whitespace titles in import validation
- Trim title/prompt in importTemplates with default title fallback
- Remove tasks/prd-template-library-replaces-examples.md from repo
* fix: remove double sort, dead code, redundant stats, and break-all CSS
- Remove redundant sortTemplates call in loadTemplates (already sorted by getAllTemplates)
- Remove unused createEmptyTemplateInput and sortTemplates import
- Show "Not used yet" only once for unused templates instead of twice
- Use break-words instead of break-all on prompt textareas
---------
Co-authored-by: 杜雷 <[email protected]>
Co-authored-by: Claude Opus 4.6 <[email protected]>
Co-authored-by: dayuan.jiang <[email protected]>
Add Novita AI as a new LLM provider with OpenAI-compatible API support.
Users can now select Novita from all entry points (CLI, config, UI).
- Add 'novita' to ProviderName type
- Add Novita AI entry to PROVIDER_INFO with default base URL
- Add Novita suggested models (kimi-k2.5, glm-5, minimax-m2.5)
- Add 'novita' to ALLOWED_CLIENT_PROVIDERS
- Add NOVITA_API_KEY environment variable mapping
- Add novita case to getAIModel() switch using OpenAI-compatible API
- Add novita to SINGLE_SYSTEM_PROVIDERS for proper message handling
* Implement GLM model identification logic
Add checks for GLM text and visual model naming conventions.
* fix: simplify GLM vision detection and add tests
- Remove redundant includes("v-") check that could cause false positives
on model names containing "dev-", "csv-", etc.
- Remove unnecessary includes("v") pre-check
- Update comments with real GLM model names
- Add unit tests for GLM text and vision models
* feat: add vision detection for MiniMax, Moonshot, and fix Qwen
- Add MiniMax text model detection (M2.x series are text-only)
- Add Moonshot v1 text model detection (moonshot-v1-* are text-only)
- Add qwen3.5-flash to Qwen vision model exceptions
- Add unit tests for all new model checks
---------
Co-authored-by: dayuan.jiang <[email protected]>
- Add MiniMax-M2.7 and MiniMax-M2.7-highspeed to model list
- Set MiniMax-M2.7 as default model
- Keep all previous models as alternatives
- Update docs in EN/CN/JA
Co-authored-by: PR Bot <[email protected]>
dayuan.jiang