Files
claudecodeui/server/modules/providers/services/provider-models.service.ts
Haile 4cee5e7286 Fix/resolve different bugs (#964)
* fix: don't overlap thinking banner over conversation

* feat: support message queue and add attention indicator

* fix(shell): use c to copy for claude

* fix: strip timestamp tags from cursor

* fix: select project when loading session from direct URL

* feat: support attached images for all providers

* feat(opencode): support permission options

* fix: resolve source control and chat UX bugs

- make staging real in the git panel: new /stage and /unstage endpoints,
  /status now reports the actual index via porcelain -z (handles renames,
  conflicts, and paths with spaces), and Stage/Unstage All run real git
  commands instead of toggling client-side state
- add branch search to the header dropdown and Branches tab
- persist the chosen permission mode per provider so a brand-new chat
  keeps it once the session id arrives, instead of reverting to default
- replace cmdk's fuzzy model search with strict token matching so
  "chatgpt" no longer surfaces unrelated models
- unit tests for the git status parser

* feat(git): commit graph in history view and cross-spawn everywhere

- render a VSCode-style commit graph in the source control history:
  lane-assignment algorithm, SVG strip with colored rails, merge and
  branch curves, commit dots, and branch/tag badges per commit
- /commits returns parents and ref decorations across all branches
  (--branches --remotes --tags --topo-order) using unit-separator
  fields so pipes in commit subjects can't break parsing
- collect stats via a single --shortstat pass instead of one
  `git show --stat` call per commit; raise the history limit to 50
- replace child_process spawn with cross-spawn in all runtimes,
  routes, and services: it resolves .cmd shims and PATHEXT on
  Windows (fixing taskmaster's npx invocations) and delegates to
  native spawn elsewhere, removing the per-file win32 ternaries
- unit tests for the log parser and lane assignment

* fix: remove gemini support since google discontinued it

* fix: address code review findings

- validate chat image attachments server-side: only files inside the
  ~/.cloudcli/assets upload store may reach provider file reads
- harden asset serving with nosniff and attachment disposition for
  SVGs to prevent stored XSS
- show the timestamp on image-only user messages
- serialize git stage/unstage calls and defer the status re-sync so
  rapid toggles can't interleave or flicker
- use a literal hex fallback for commit ref badges (alpha suffix on a
  var() string produced invalid CSS)
- stop binding a URL session to a guening
  project instead
- add the missing attentionRequiredIndicator key to all sidebar locales
- clean up dangling conjunctions left the
  de/ru/tr/ja/zh-CN/zh-TW READMEs

* fix: address code scanning findings

- enforce a second image trust boundary in the provider builders:
  buildClaudeUserContent/buildCodexInputItems only accept files inside
  the upload store or the run's working directory (CodeQL path
  injection)
- drop an always-true selectedProject check in handleSubmit
- remove the unused resume option from spawnCursor

* fix: use CodeQL-recognized containment check for image reads

Replace the path.relative guard in isPathInsideDirectory with the
resolve + startsWith(root + sep) idiom so the path-injection barrier
is visible to code scanning; behavior is unchanged.

* fix(security): canonicalize Claude image attachment reads

Resolve image attachment paths with realpath before reading so symlinks
inside allowed roots cannot escape to arbitrary files. Preserve support for
symlinked project/upload roots and add focused coverage for both cases.

* fix: show agent subtask

* fix(sessions): title app-created sessions from the first user message

App-created sessions (started by sending a message from cloudcli) were
titled with placeholder names — "Untitled Codex Session" from the disk
indexer and, briefly, "New session" from the empty canonical upsert —
before a later sync finally settled on the right text, causing the
sidebar title to flicker.

- Codex/OpenCode synchronizers now title app-created sessions (distinct
  app id mapped to a provider id) from the first user message, while
  sessions found purely by indexing keep their existing setup. Claude
  keeps its AI-generated titles; Cursor already used the first message.
- Decode OpenCode's JSON-string-literal prompts so titles no longer
  surface wrapped in quotes; hoist unwrapJsonStringLiteral into
  shared/utils since it's now used by both the reader and synchronizer.
- Guard the sidebar upsert merge so an empty summary can never blank out
  a title that is already set.
- Add codex/opencode synchronizer tests for the app-created vs indexed
  naming paths.

* fix(chat): make message queuing reliable across sessions and turn boundaries

Queued messages had four related defects:

- A queued message flashed and then vanished at flush time: concurrent
  transcript refreshes (the `complete` handler racing the watcher-triggered
  update) could resolve out of order, letting a stale response overwrite
  newer server messages after the optimistic row was pruned. Session slots
  now carry a monotonic fetch ticket and discard stale fetch/refresh/
  fetchMore responses.

- Switching sessions flushed the previous session's queued draft into the
  newly viewed one (sending it with the wrong provider's settings, e.g. a
  Claude model into a Codex session). The composer flush is now scoped to
  its session, and a draft restored into an idle session sends after a
  short grace period so a live-run ack can cancel it.

- The thinking banner never appeared for a queued turn: the chat handler's
  session-keyed completeRun safety net could fire after a queued message
  had already started the session's next run, emitting a spurious
  `complete` that killed it. The safety net is now scoped to its own run
  via completeRunIfCurrent (with a regression test).

- Queued messages only sent while their session was being viewed. Drafts
  now persist their send options (model, effort, permissions) at queue
  time, and a new app-level useQueuedMessageAutoSend hook dispatches a
  non-viewed session's queued message as soon as its run completes, using
  the storage key as the claim ticket to prevent double sends.
2026-07-08 10:32:32 +02:00

359 lines
11 KiB
TypeScript

import { mkdir, readFile, writeFile } from 'node:fs/promises';
import os from 'node:os';
import path from 'node:path';
import { providerRegistry } from '@/modules/providers/provider.registry.js';
import type { IProvider } from '@/shared/interfaces.js';
import type {
LLMProvider,
ProviderChangeActiveModelInput,
ProviderCurrentActiveModel,
ProviderModelsCacheInfo,
ProviderModelsDefinition,
ProviderModelsResult,
ProviderSessionActiveModelChange,
} from '@/shared/types.js';
import { readProviderSessionActiveModelChange } from '@/shared/utils.js';
export const PROVIDER_MODELS_CACHE_TTL_MS = 3 * 24 * 60 * 60 * 1000;
const PROVIDER_MODELS_CACHE_VERSION = 2;
const UNCACHED_PROVIDERS = new Set<LLMProvider>(['claude']);
type ProviderModelsServiceDependencies = {
resolveProvider?: (provider: LLMProvider) => Pick<IProvider, 'models'>;
cachePath?: string;
activeModelChangesPath?: string;
now?: () => number;
};
type ProviderModelsOptions = {
bypassCache?: boolean;
};
type ProviderModelsCacheEntry = {
updatedAt: number;
expiresAt: number;
models: ProviderModelsDefinition;
};
type ProviderModelsCacheFile = {
version: number;
entries: Record<string, ProviderModelsCacheEntry>;
};
const getProviderModelsCachePath = (): string => path.join(
os.homedir(),
'.cloudcli',
'provider-models-cache.json',
);
const toProviderModelsCacheInfo = (
entry: ProviderModelsCacheEntry,
source: ProviderModelsCacheInfo['source'],
): ProviderModelsCacheInfo => ({
updatedAt: new Date(entry.updatedAt).toISOString(),
expiresAt: new Date(entry.expiresAt).toISOString(),
source,
});
const isProviderModelOption = (
value: unknown,
): value is ProviderModelsDefinition['OPTIONS'][number] => (
Boolean(value)
&& typeof value === 'object'
&& typeof (value as ProviderModelsDefinition['OPTIONS'][number]).value === 'string'
&& typeof (value as ProviderModelsDefinition['OPTIONS'][number]).label === 'string'
&& (
typeof (value as ProviderModelsDefinition['OPTIONS'][number]).description === 'undefined'
|| typeof (value as ProviderModelsDefinition['OPTIONS'][number]).description === 'string'
)
);
const isProviderModelsDefinition = (value: unknown): value is ProviderModelsDefinition => (
Boolean(value)
&& typeof value === 'object'
&& Array.isArray((value as ProviderModelsDefinition).OPTIONS)
&& (value as ProviderModelsDefinition).OPTIONS.every(isProviderModelOption)
&& typeof (value as ProviderModelsDefinition).DEFAULT === 'string'
);
const isProviderModelsCacheEntry = (value: unknown): value is ProviderModelsCacheEntry => (
Boolean(value)
&& typeof value === 'object'
&& typeof (value as ProviderModelsCacheEntry).updatedAt === 'number'
&& typeof (value as ProviderModelsCacheEntry).expiresAt === 'number'
&& isProviderModelsDefinition((value as ProviderModelsCacheEntry).models)
);
const readProviderModelsCacheFile = async (
cachePath: string,
): Promise<ProviderModelsCacheFile | null> => {
try {
const raw = await readFile(cachePath, 'utf8');
const parsed = JSON.parse(raw) as Partial<ProviderModelsCacheFile>;
if (parsed.version !== PROVIDER_MODELS_CACHE_VERSION || !parsed.entries || typeof parsed.entries !== 'object') {
return null;
}
const entries = Object.fromEntries(
Object.entries(parsed.entries).filter((entry): entry is [string, ProviderModelsCacheEntry] =>
isProviderModelsCacheEntry(entry[1]),
),
);
return {
version: PROVIDER_MODELS_CACHE_VERSION,
entries,
};
} catch {
return null;
}
};
const writeProviderModelsCacheFile = async (
cachePath: string,
entries: Map<LLMProvider, ProviderModelsCacheEntry>,
now: number,
): Promise<void> => {
const serializableEntries = Object.fromEntries(
[...entries.entries()].filter(([, entry]) => entry.expiresAt > now),
);
const payload: ProviderModelsCacheFile = {
version: PROVIDER_MODELS_CACHE_VERSION,
entries: serializableEntries,
};
await mkdir(path.dirname(cachePath), { recursive: true });
await writeFile(cachePath, `${JSON.stringify(payload, null, 2)}\n`, 'utf8');
};
/**
* Provider model lookup service.
*
* Routes and other service callers use this layer instead of resolving provider
* classes directly so the provider-registry dependency stays centralized in one
* place.
*/
export const createProviderModelsService = (dependencies: ProviderModelsServiceDependencies = {}) => {
const resolveProvider = dependencies.resolveProvider ?? providerRegistry.resolveProvider;
const cachePath = dependencies.cachePath ?? getProviderModelsCachePath();
const activeModelChangesPath = dependencies.activeModelChangesPath;
const now = dependencies.now ?? (() => Date.now());
const memoryCache = new Map<LLMProvider, ProviderModelsCacheEntry>();
const pendingRequests = new Map<LLMProvider, Promise<ProviderModelsResult>>();
let persistedCacheLoaded = false;
let persistedCacheLoadPromise: Promise<void> | null = null;
const pruneExpiredMemoryEntry = (
provider: LLMProvider,
currentTime: number,
source: ProviderModelsCacheInfo['source'],
): ProviderModelsResult | null => {
const cachedEntry = memoryCache.get(provider);
if (!cachedEntry) {
return null;
}
if (cachedEntry.expiresAt > currentTime) {
return {
models: cachedEntry.models,
cache: toProviderModelsCacheInfo(cachedEntry, source),
};
}
memoryCache.delete(provider);
return null;
};
const loadPersistedCache = async (): Promise<void> => {
if (persistedCacheLoaded) {
return;
}
if (!persistedCacheLoadPromise) {
persistedCacheLoadPromise = (async () => {
const cacheFile = await readProviderModelsCacheFile(cachePath);
const currentTime = now();
for (const [provider, entry] of Object.entries(cacheFile?.entries ?? {})) {
if (entry.expiresAt > currentTime) {
memoryCache.set(provider as LLMProvider, entry);
}
}
persistedCacheLoaded = true;
})().finally(() => {
persistedCacheLoadPromise = null;
});
}
await persistedCacheLoadPromise;
};
const persistCache = async (): Promise<void> => {
try {
await writeProviderModelsCacheFile(cachePath, memoryCache, now());
} catch (error) {
console.warn('Unable to persist provider models cache:', error);
}
};
const setCacheEntry = async (
provider: LLMProvider,
models: ProviderModelsDefinition,
): Promise<ProviderModelsCacheEntry> => {
const currentTime = now();
const entry: ProviderModelsCacheEntry = {
updatedAt: currentTime,
expiresAt: currentTime + PROVIDER_MODELS_CACHE_TTL_MS,
models,
};
memoryCache.set(provider, entry);
await persistCache();
return entry;
};
const loadAndCacheModels = (
provider: LLMProvider,
): Promise<ProviderModelsResult> => {
const request = resolveProvider(provider).models.getSupportedModels()
.then(async (models) => {
const entry = await setCacheEntry(provider, models);
return {
models,
cache: toProviderModelsCacheInfo(entry, 'fresh'),
};
})
.finally(() => {
pendingRequests.delete(provider);
});
pendingRequests.set(provider, request);
return request;
};
const loadDirectModels = (
provider: LLMProvider,
): Promise<ProviderModelsResult> => {
const request = resolveProvider(provider).models.getSupportedModels()
.then((models) => {
const currentTime = now();
return {
models,
cache: {
updatedAt: new Date(currentTime).toISOString(),
expiresAt: new Date(currentTime).toISOString(),
source: 'fresh' as const,
},
};
})
.finally(() => {
pendingRequests.delete(provider);
});
pendingRequests.set(provider, request);
return request;
};
const getProviderModels = async (
provider: LLMProvider,
options: ProviderModelsOptions = {},
): Promise<ProviderModelsResult> => {
if (UNCACHED_PROVIDERS.has(provider)) {
const pendingRequest = pendingRequests.get(provider);
if (pendingRequest) {
return pendingRequest;
}
return loadDirectModels(provider);
}
if (options.bypassCache) {
const pendingRequest = pendingRequests.get(provider);
if (pendingRequest) {
return pendingRequest;
}
return loadAndCacheModels(provider);
}
const cachedModels = pruneExpiredMemoryEntry(provider, now(), 'memory');
if (cachedModels) {
return cachedModels;
}
const pendingRequest = pendingRequests.get(provider);
if (pendingRequest) {
return pendingRequest;
}
await loadPersistedCache();
const persistedModels = pruneExpiredMemoryEntry(provider, now(), 'disk');
if (persistedModels) {
return persistedModels;
}
const postLoadPendingRequest = pendingRequests.get(provider);
if (postLoadPendingRequest) {
return postLoadPendingRequest;
}
return loadAndCacheModels(provider);
};
const getCurrentActiveModel = async (
provider: LLMProvider,
sessionId?: string,
): Promise<ProviderCurrentActiveModel> => resolveProvider(provider).models.getCurrentActiveModel(sessionId);
const changeActiveModel = async (
provider: LLMProvider,
input: ProviderChangeActiveModelInput,
): Promise<ProviderSessionActiveModelChange> => resolveProvider(provider).models.changeActiveModel(input);
const getChangedActiveModel = async (
provider: LLMProvider,
sessionId: string,
): Promise<ProviderSessionActiveModelChange> => readProviderSessionActiveModelChange(provider, sessionId, {
filePath: activeModelChangesPath,
});
const resolveResumeModel = async (
provider: LLMProvider,
sessionId: string | undefined,
requestedModel?: string | null,
): Promise<string | undefined> => {
const normalizedRequestedModel = typeof requestedModel === 'string' ? requestedModel.trim() : '';
if (!sessionId?.trim()) {
return normalizedRequestedModel || undefined;
}
const changedModel = await getChangedActiveModel(provider, sessionId);
if (changedModel.supported && changedModel.changed && changedModel.model?.trim()) {
return changedModel.model.trim();
}
return normalizedRequestedModel || undefined;
};
const clearCache = (): void => {
memoryCache.clear();
pendingRequests.clear();
persistedCacheLoaded = false;
persistedCacheLoadPromise = null;
};
return {
getProviderModels,
getCurrentActiveModel,
getChangedActiveModel,
changeActiveModel,
resolveResumeModel,
clearCache,
};
};
export const providerModelsService = createProviderModelsService();