mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-06-15 15:39:01 +03:00
main
4519 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Danny Avila
|
9efe4878e7 |
🅰️ feat: Native Anthropic Provider for Custom Endpoints (#13748)
* 🅰️ feat: Native Anthropic provider for Custom Endpoints Let a custom endpoint declare `provider: anthropic` to use the native Anthropic `/v1/messages` client (the agents SDK's ChatAnthropic) against its own `baseURL`/`apiKey`/`headers`, instead of being forced through the OpenAI-compatible client. Enables Anthropic itself and Anthropic-compatible gateways (AI gateways, OpenCode Zen, etc.) as custom endpoints — including for agents and role-scoped model access. Closes #10655 (Option 1: explicit provider). - Schema: add optional `provider` (currently `anthropic`) to the custom `endpointSchema` in data-provider. - Routing: `getProviderConfig` maps a custom endpoint with `provider: anthropic` to `Providers.ANTHROPIC` (was always `Providers.OPENAI`). - Config: `initializeCustom` builds the native Anthropic config via the Anthropic `getLLMConfig` (custom baseURL/apiKey/headers) and returns `provider: anthropic`; `useLegacyContent` is left unset to match the built-in Anthropic endpoint. The OpenAI-compatible path is unchanged for endpoints without `provider`. - Summarization: `resolveSummarizationProvider` builds an Anthropic config for a cross-endpoint native-Anthropic summarization target (self-summarize already reuses the agent's client options). Title generation already resolves via `agent.endpoint`, and provider-specific handling (tool conflicts, content/PDF validation, token counting, streamUsage) already branches on `Providers.ANTHROPIC`, so it applies automatically. Note: model auto-fetch (`models.fetch`) uses the OpenAI `/models` convention and is not used for this provider — list models explicitly under `models.default`. * 🅰️ fix: Anthropic custom-endpoint param parity (Codex review) Address Codex P2 findings — the native Anthropic path must match the OpenAI-compatible path's parameter handling: - UI param set: `loadCustomEndpointsConfig` now surfaces `provider` as the client `customParams.defaultParamsEndpoint`, so the Agents model panel shows Anthropic fields (`maxOutputTokens`/`thinking`) instead of OpenAI `max_tokens` (which the native initializer ignored). An explicit non-default `defaultParamsEndpoint` still wins. - Provider override: `getProviderConfig` re-applies `provider: anthropic` after all `customEndpointConfig` resolution, so it also wins when the endpoint name collides with a known custom provider (e.g. `openrouter`) — fixing the token/context budget derived from `overrideProvider`. - Default params: the native path (and cross-endpoint Anthropic summarization) now apply `customParams.paramDefinitions` defaults via `extractDefaultParams`, matching what `getOpenAIConfig` does for the OpenAI-compatible path. Adds tests for each. |
||
|
Danny Avila
|
44c253d48a |
🪙 fix: Correct Context Usage Gauge After Summarization (#13744)
* 🪙 fix: Persist Context Snapshot + Summary Marker After Summarization The post-summarization context is correctly compacted by the SDK, but the breakdown wasn't reliably reaching the client, leaving the gauge on the whole-history estimate (stuck at 100% forever once a conversation compacts). Two server changes in buildResponseMetadata: - Snapshot guard: persist the breakdown when a PRIMARY usage event follows the latest snapshot (tracked via contextUsageSink.latestUsageIndex, recorded in the on_context_usage handler) instead of a brittle snapshot-vs-primary count. A summarization detour adds an extra snapshot whose only following usage is tagged 'summarization', which the count guard could miscount and drop. - Summary marker: whenever a turn compacts (summaryTokens > 0), persist a lightweight metadata.summaryUsedTokens (the pre-invoke compacted context size) UNCONDITIONALLY — so even when the full snapshot can't be saved (interrupted final call) or never reaches the client, the per-message estimate has a signal to cap the discarded history. Tests: client.contextMetadata.spec (guard + marker, incl. marker-survives-drop) and a real-pipeline summarization integration test. * 🪙 fix: Cap the Context Estimate at the Summary Marker When the gauge falls back to the per-message estimate (no usable snapshot on the branch), sumBranch summed the ENTIRE branch history — after a summarization that discarded most of it, this over-counts and pins the gauge at 100% in perpetuity. sumBranch now stops at the deepest summarized response (metadata.summaryUsedTokens) and records it as summaryBaseline; the walk counts only post-summary messages, and useTokenUsage adds the baseline. So the estimate reflects the compacted context (summary + recent turns), not the discarded history. USD/default behavior unchanged when no marker is present. Test: sumBranch caps a huge pre-summary history at the compacted baseline. * 🪙 fix: Address Codex Review on the Summarization Marker - Branch cost/usage is no longer truncated at the summary marker — sumBranch caps only the CONTEXT-window count there and keeps accumulating provider usage/cost to the root (cumulative spend isn't discarded by compaction). - findBranchSnapshotAnchor stops at a summarized response with no snapshot of its own, so it can't recover a stale PRE-summary snapshot and show discarded history; the summary-baseline estimate is used instead. - Abort path: buildAbortedResponseMetadata now persists the summaryUsedTokens marker (pre-invoke, no completedOutputTokens ambiguity, so safe on abort) so a STOPPED summarized turn isn't re-summed on reload. - Marker baseline fallback now includes summaryTokens (a separate breakdown field) so it doesn't under-report the compacted size. DRY'd into a shared computeSummaryUsedTokens used by the completion and abort paths. - Estimate popover surfaces the summary baseline as a row so the displayed rows reconcile with the header total. Tests: sumBranch cost-not-truncated + anchor-stops-at-marker (client); computeSummaryUsedTokens fallback + abort marker (packages/api). * 🪙 fix: Attribute Persisted Context Usage to the Snapshot Run Match the post-snapshot primary usage to the latest snapshot's runId before persisting metadata.contextUsage. Parallel/direct runs interleave snapshots and usage (A snapshot → B snapshot → A usage → B no-usage); the prior index-only guard persisted B's snapshot with A's output. finalCallOutputTokens now filters completedOutputTokens to the snapshot's run. Untagged events (older lib/resume) match any run for back-compat. * 🪙 fix: Harden Summary Marker Against Tool-Loops, Stale Anchors, and Emit Races Codex round on the summarization marker: - Avoid double-counting earlier tool-loop outputs in the summary marker: those outputs sit in BOTH the latest snapshot's pre-invoke baseline AND the response message's tokenCount the client estimate adds on top. computeSummaryUsedTokens now subtracts the run's prior primary outputs (priorRunOutputTokens) — the live path bounds them by the snapshot's usage index, the abort path by all primaries (an interrupted final call emits none). Single-call turns subtract 0. - Stop treating pre-summary anchors as active: sumBranch no longer sets containsAnchor once the context is capped at a summary marker, so a stale pre-summary snapshot can't override the summary-baseline estimate. - Capture latestUsageIndex BEFORE awaiting emitEvent: a yield (resumable SSE / Redis) during parallel runs could let this call's own usage advance the index past the event that proves the snapshot completed, dropping a valid breakdown. * 🪙 fix: Subtract Summarization Output from the Summary Marker recordCollectedUsage folds the summarization call's completion into the response message's tokenCount, while the generated summary is also in the snapshot baseline as summaryTokens. The client estimate (summaryBaseline + responseTokenCount) thus counted the summary twice — inflating the gauge after compaction even on a single-call turn whenever the full snapshot is unavailable. priorRunOutputTokens now also counts summarization-tagged output (still excluding subagent/sequential, which recordCollectedUsage keeps out of the reported total), so the marker subtracts it. Updated unit + guard tests. * 🪙 fix: Refine Marker Subtraction for Summarization RunId and Abort Boundary Two Codex follow-ups on the marker-subtraction logic: - Subtract summarization output regardless of runId: the summarize detour is its own model-end call that may carry a distinct runId, but its output still lands in this response's tokenCount AND the snapshot baseline (summaryTokens). It is now counted unconditionally (still within the response's own usageEmitSink), while primaries keep the parallel-run runId filter. - Don't subtract primaries on the abort path: the job stores no snapshot/usage boundary, so a primary that completed AFTER the latest snapshot is NOT in the baseline; subtracting it would cancel real output and under-report. priorRun- OutputTokens gains an includePrimary flag (false for abort) — abort subtracts only the always-pre-snapshot summarization output. * 🪙 fix: Run-Scope Summary Subtraction and Stop Subtracting on Abort Two Codex follow-ups, resolved by reverting the round-4 detour: - Run-scope the summarization subtraction: the summarize detour inherits the graph run id (traceConfig spreads config.metadata.run_id), so its usage shares the answer snapshot's runId — it is NOT a distinct run. priorRunOutputTokens now filters summarization by runId like primaries, so a parallel sibling run's summary (different runId, in the sibling's baseline) is no longer subtracted from this branch's marker. Drops the includePrimary flag added last round. - Stop subtracting on the abort path: abort tokenCount is countTokens(text) (abortMiddleware) or absent (agents route) — it does not fold in summarization or earlier-call output the way recordCollectedUsage does, so the marker must keep the full baseline. buildAbortedResponseMetadata now subtracts nothing. |
||
|
Danny Avila
|
2350ebb24a |
📨 feat: Custom Headers on Built-in Provider Endpoints (#13742)
* 📨 feat: Custom Headers on Built-in Provider Endpoints Add a `headers` config option to the built-in `openAI`, `anthropic`, and `google` endpoints (incl. Anthropic/Google Vertex), mirroring the custom endpoint header mechanism. Values support the same placeholder resolution (env vars, `{{LIBRECHAT_USER_*}}`, `{{LIBRECHAT_BODY_CONVERSATIONID}}`) and are resolved at request time so dynamic values like conversationId resolve against the live request — without losing provider-native request shaping. Closes #13082. Covers #13713: forwarding conversationId to a reverse proxy is now `X-Conversation-Id: '{{LIBRECHAT_BODY_CONVERSATIONID}}'` — an unknown header is ignored by the native Anthropic API, so no 400 and no metadata gating needed. - Schema: `headers` on `baseEndpointSchema` (openAI/google/anthropic/all). - New `mergeHeaders`/`resolveConfigHeaders` utils centralize the per-provider header locations (`configuration.defaultHeaders`, Anthropic `clientOptions.defaultHeaders`, Google `customHeaders`); provider-managed headers (auth, `anthropic-beta`) always win on collision. - Each initializer threads configured headers (endpoint over `all`) into the right place; request-time resolution runs across all locations in the main and title flows. * 🩹 fix: Cast endpoints.all to TEndpoint for headers DeepPartial widening Adding `headers` (a Record) to `baseEndpointSchema` makes `DeepPartial<TCustomConfig>` widen its value type to `string | undefined`, which is not assignable to the concrete `TEndpoint['headers']: Record<string, string>` at the `loadedEndpoints.all` assignment. Cast at the assignment site, mirroring the existing `anthropicConfig as TAnthropicEndpoint` cast in the same function. * 🛡️ fix: Harden built-in endpoint custom headers (Codex review) Address Codex P2 findings on the custom-headers feature: - Anthropic title requests: `omitTitleOptions` strips the `clientOptions` carrier, which dropped its `defaultHeaders`. Preserve just the header carrier so gateway/reverse-proxy metadata still reaches title generation. - mergeHeaders: match header names case-insensitively so an override (e.g. a provider-managed `Authorization`/`anthropic-beta`) replaces/uniones a case-variant from the base instead of emitting two names a client may collapse. - OpenAI: withhold admin-configured headers when the user supplies the base URL (`user_provided`), since values may carry `${SECRET}`/token placeholders that must not reach a user-controlled endpoint — mirrors the custom-endpoint guard. - Azure: honor global `endpoints.all` headers (same OpenAI carrier) while keeping Azure-managed `api-key`/version headers authoritative. Adds tests for each. * 🔐 fix: Resolve-once + provider-managed header safety (Codex review round 2) Address Codex P2 findings: - Azure: keep global `endpoints.all` headers unresolved at init and let request-time `resolveConfigHeaders` resolve them once, avoiding a second-order env expansion of already-substituted user values. - Google: `resolveConfigHeaders` no longer template-resolves the provider-managed `Authorization` header (built from a possibly user-provided key), so a user key like `${ENV}` can't leak server environment values. - Model fetches: thread configured headers (endpoint over `all`) + user object through `getOpenAIModels`/`getAnthropicModels` → `fetchModels`, so a gateway-fronted built-in provider receives the header on `/models` too. Fixed `fetchModels` to merge custom headers for Anthropic instead of overwriting them (managed `x-api-key`/version still win). Adds/updates tests for each. * 🧯 fix: Header provenance, memory/title coverage, idempotency (Codex round 3) Address Codex P2 findings, including two regressions from the prior round: - Google auth (findings 6 & 8): move native Google header resolution to init (`initializeGoogle`), resolving admin templates BEFORE the key-derived auth header is built. resolveConfigHeaders no longer touches Google `customHeaders`, so admin `Authorization` templates resolve again (fixes the round-2 regression) while the SDK auth header (possibly a user-provided key) is never env-expanded. - Memory runs: memory extraction now calls `resolveConfigHeaders`, so native Anthropic (and OpenAI) headers resolve for memory requests too. - Vertex titles: restore the ORIGINAL `clientOptions` object reference (not a copy) when preserving headers across `omitTitleOptions`, so the Vertex `createClient` closure and the resolved headers stay on the same object. - Reuse: `resolveConfigHeaders` is now idempotent (resolve-once per header map), preventing a second pass from env-expanding values already substituted with user/body data when an agent object flows through buildAgentInput twice. Adds/updates tests for each. |
||
|
Danny Avila
|
7c071e244b |
🔢 fix: Prevent "approximately" tildes from rendering as markdown subscript (#13743)
* 🔢 fix: Prevent "approximately" tildes from rendering as markdown subscript `remark-supersub` splits text nodes on every `~`; an even number of tildes wraps the in-between text in `<sub>`. "Approximately" usage like `~50% ... ~10%` pairs up and subscripts everything between the two tildes. A backslash escape cannot fix this: micromark resolves `\~` back to a bare `~` before supersub runs. Instead, `preprocessTilde` swaps approximation tildes (a `~` prefixing a number, not attached to a word) for the Unicode tilde operator `∼` (U+223C), which renders as a tilde but is not split by supersub. Mirrors `preprocessLaTeX`: early return, single regex pass, code-region skipping. Genuine subscripts (`H~2~O`, `a ~2~ b`), strikethrough, escaped tildes, and home paths are preserved. * 🔢 fix: Harden tilde preprocessing — escaped tildes, URLs, math, MarkdownLite Addresses Codex review findings: - Convert escaped approximation tildes too (`\~50%`): markdown decodes `\~` to `~` before supersub, so the escape still pairs into a subscript. - Anchor matches to a prose boundary (start / whitespace / open bracket) and exclude `\(`/`\[`/`\{`, so URL path tildes (`/~50`) and math delimiters (`$~10$`, `$$~10$$`, `\(~10\)`) are left untouched. - Apply preprocessTilde in MarkdownLite (user messages + search/subagent/ code-analysis displays), which also enables remark-supersub. * 🔧 refactor: Neutralize approximation tildes via remark plugin, not raw-text Replaces the string-level preprocessTilde with `remarkApproxTilde`, a remark plugin that rewrites "approximately" tildes (`~50%` → `∼`) on parsed text nodes before remark-supersub runs. Because it operates on the AST, code spans, fenced code blocks (backtick *and* ~~~), inline code with any backtick count, link destinations, and math spans are structurally excluded — none are `text` nodes — resolving every raw-text edge case Codex flagged without region-scanning heuristics. Escaped `\~` is covered for free (markdown decodes it before the plugin runs). - New client/src/utils/tilde.ts: `normalizeApproxTildes` (pure, per-text-node) + `remarkApproxTilde` plugin. - Wired into both renderers (markdownConfig + MarkdownLite), before supersub. - latex.ts / Markdown.tsx reverted to original; preprocessTilde removed. - tilde.spec.ts: pure-function cases + a hand-built-tree test proving code, math, and link URLs are untouched while text (incl. link text) is converted. * 🔧 fix: Cover quoted approximations and the markdown error-boundary fallback - Broaden the boundary to any non-word, non-tilde char (`(?<![\w~])`), which now includes quotes — `"~50%" ... "~10%"` was still subscripting because `"` was not a recognized prose boundary. Safe to widen because the plugin runs on text nodes, so code / links / math / URLs are already excluded structurally (the earlier allowlist only existed to dodge URL paths in raw text). - Add remarkApproxTilde to MarkdownErrorBoundary's fallback remark pipeline so the fix holds when a render error falls back to the minimal renderer. * 🔧 fix: Preserve autolink URL labels when normalizing tildes A GFM autolink renders the URL as its own label (a text node equal to the href), so the broadened boundary was rewriting `~50` inside a displayed URL to `∼50` even though the href stayed correct. Skip text nodes that are an autolink's label (value matches the destination, allowing for the implied scheme on www/email links), so the visible URL is preserved verbatim. Regular link labels (prose) are still normalized. Note: a single URL containing two `~<digit>` segments is still subscripted by remark-supersub itself — that's pre-existing behavior (reproduces with no plugin) and out of scope here. * 🔧 refactor: Drop unist-util-visit runtime dep from tilde plugin Replace the `unist-util-visit` import with a small self-contained recursive walk over text nodes (tracking the parent for the autolink-label check). This removes reliance on a transitively-hoisted runtime package — addressing the dependency- hygiene concern without adding a dependency or churning the lockfile. The type-only `unist` import remains (erased at build, no runtime resolution). Behavior is unchanged; verified against nested emphasis and list/paragraph trees. |
||
|
Danny Avila
|
1ae54b39ad |
🔍 fix: Render Web Search Favicons on Raw SERP Results During Streaming (#13741)
The streaming favicon stack was gated on `source.processed === true`, but the agents scrape pipeline marks sources processed only after a `Promise.all` barrier (the slowest page fetch). Raw SERP results — with everything needed to render favicons — arrive in the first attachment well before that, so the UI sat on "Searching the web" with no favicons for the entire scrape window. Render favicons from the raw sources as soon as they land instead of waiting for `processed`, filling the dead window and moving the label to "Processing results" immediately. Completed-state, turn scoping, and finalizing behavior are unchanged. |
||
|
Danny Avila
|
7cf2877b45 |
🪙 feat: Context Gauge UX, Hover Snapshot, Click Breakdown, Currency, Cost-On-By-Default (#13739)
* 🪙 feat: Default Context Cost On + Configurable Display Currency Flip interface.contextCost to default-on (schema default true, resolved per-field in loadDefaultInterface so it applies unless an admin explicitly sets false). Add interface.currency { code, rate }: an ISO-4217 code and a static USD→local multiplier so non-USD communities (EUR, JPY, CNY, BRL, ZAR, …) can show costs in their currency. Inner fields are required (no nested defaults) to keep zod input/output identical; loadDefaultInterface passes it through. Display-only — model prices stay USD server-side. * 🪙 feat: Currency-Aware Context Cost Formatting formatCost(usd, currency?) applies the static rate (usd × rate) and formats via a cached Intl.NumberFormat keyed by currency code — locale-correct symbol and per-currency decimals, falling back to USD on a malformed code. The USD default (code USD, rate 1) is byte-identical to the prior output. * 💄 feat: Gauge Hover Snapshot, Click-to-Open Breakdown, Hide Until Data Replace the hover-only HoverCard with: a compact hover snapshot tooltip ("Context 341.7k / 1.0M (34%)" + cost when enabled) via the existing Tooltip primitive, and a click-opened Ariakit popover for the full breakdown that dismisses on outside-click/Escape/blur. Gate visibility on usedTokens > 0 so a fresh, message-less chat shows nothing, with an animate-in fade as the first tokens land. Thread the display currency into the breakdown + snapshot. * 🧪 test: Gauge Interaction + Visibility E2E Switch the breakdown specs from hover to click, and add a test that the gauge is absent on a new chat, surfaces the snapshot tooltip on hover, opens the breakdown on click, and dismisses on Escape and outside-click. * 🪙 fix: Harden Currency Resolution + Layer Breakdown Above Tooltip Address Codex review on the currency display: - Unsupported currency code now falls back to USD AND rate 1, so a typo like { code: 'EURO', rate: 0.92 } no longer shows a converted amount under a $ symbol (was $9.20 for a $10 cost; now $10.00). - A non-finite/negative rate (e.g. a partial admin override that set code before rate) falls back to rate 1, so a cost never renders as NaN. - Fraction digits derive from the currency's own defaults, so zero-decimal currencies (JPY) render ¥5, not ¥5.00, and extra sub-unit precision applies only to currencies that have minor units. USD output is unchanged. - Raise the click breakdown popover to z-[200] so it always sits above the z-150 hover tooltip when both briefly coexist. * 🪙 fix: Validate ISO-4217 Codes + Derive Tiny Threshold from Minor Unit Address Codex review on currency formatting: - Intl.NumberFormat accepts any well-formed 3-letter code (EUU, RMB) without throwing, so the previous construct-based check missed typos/non-ISO codes and applied the rate under a bogus label. Validate against Intl.supportedValuesOf ('currency') (the ISO-4217 set); unsupported codes fall back to USD + rate 1. Codes are normalized to upper-case; graceful fallback if the runtime lacks supportedValuesOf. - The tiny-amount threshold now derives from the currency's minor unit (10^-fractionDigits): 0.01 for 2-decimal, 0.001 for 3-decimal (KWD/BHD/JOD), 1 for zero-decimal — instead of a hard-coded 0.01. Sub-unit precision trims to each currency's own scale. USD output unchanged. |
||
|
Danny Avila
|
4ee68d5240 |
💸 feat: Per-Agent Endpoint Token Config in Multi-Endpoint Billing (#13738)
* 💸 feat: Per-Agent Endpoint Token Config in Multi-Endpoint Billing
Price each collected/emitted usage item with the producing agent's resolved
endpoint token config, instead of the primary agent's for the whole graph.
Previously AgentClient.recordCollectedUsage and the subagent usage emitter used
a single this.options.endpointTokenConfig (the primary's) for every usage item.
A connected agent or subagent on a different custom endpoint that shares a model
id with an entry in the primary's tokenConfig was therefore mis-priced (a model
absent from it already fell back to the built-in rate map — no regression).
- Tag each usage with its producing agent: ModelEndHandler stamps
usage.agentId = agentContext.agentId; createSubagentUsageSink stamps the
child's subagentAgentId (UsageMetadata gains an optional agentId).
- buildAgentToolContext retains endpointTokenConfig so initialize.js can build
an agentId -> endpointTokenConfig map from agentToolContexts (the one map that
holds every agent, including pure subagents pruned from agentConfigs).
- AgentClient.resolveAgentEndpointTokenConfig(usage) looks up that map by
agentId, falling back to the primary config; used by both the billing path
(new optional resolveEndpointTokenConfig on recordCollectedUsage) and the
subagent cost emitter.
- recordCollectedUsage's resolver is optional and falls back to the batch
endpointTokenConfig, so the shared responses.js/openai.js call sites are
unchanged.
- Tests: two-endpoint graph with a colliding model id prices per-agent; resolver
nullish falls back to batch; subagent sink tags the child agent id.
* fix: Align emit-path cost with per-agent billing; honor known-agent built-in pricing
Addresses Codex review on the per-agent endpoint token config:
- Emit path (callbacks.js) now prices each on_token_usage event with the
producing agent's config (resolved via usageCost.resolveEndpointTokenConfig),
so streamed/persisted metadata.usage.cost matches the per-agent balance
transaction. The agentId tag is resolved server-side and stripped from the
emitted/persisted payload.
- Resolver (resolveAgentTokenConfig) now treats a known agent's config as
authoritative, including undefined → built-in pricing, so a known non-custom
agent in a custom-primary graph is no longer charged the primary's rates.
Only untagged/unknown usage falls back to the primary config.
- endpointTokenConfigByAgentId records every known agent (value may be
undefined) so the resolver distinguishes known-no-rates from unknown.
|
||
|
Danny Avila
|
b03b2a0a29 |
💾 feat: Persist Context Breakdown & Branch/Total Usage Cost (#13734)
* 💾 feat: Persist Context Breakdown & Branch/Total Usage Cost Persist the granular context breakdown and per-response usage/cost on the response message metadata, and re-derive branch + total usage/cost from a per-message index so the popover survives reloads and is branch-aware live. - Add aggregateEmittedUsage + buildPersistedContextUsage helpers in packages/api; capture the latest visible snapshot and every emitted on_token_usage payload via contextUsageSink/usageEmitSink. - Attach metadata.contextUsage (Part A) and metadata.usage (Part B) on the agents response message in sendCompletion. - Carry per-message usage on the token index; add sumTotalUsage/setEntryUsage and branch-scoped usage on sumBranch. - Repurpose the session accumulator into a single in-flight pending holder; flush it into the index at finalize; hydrate breakdowns on load. - Render branch cost with a conditional all-branches total in the breakdown. * 🧹 chore: Remove orphaned com_ui_session_cost i18n key * 🩹 fix: Address Codex review — normalize usage server-side, fix reload deltas - Persist per-event-normalized display units in metadata.usage (TResponseUsage) so reloaded mixed-provider turns match the live session; client reads them directly instead of re-normalizing with a single stamped provider (P2). - Persist completedOutputTokens (final call output) on metadata.contextUsage so a reloaded multi-call turn adds the post-snapshot delta, not the full tokenCount the snapshot already counts (P2). - buildIndex preserves a prior entry's immutable usage when a rebuilt cache message lacks metadata.usage, so a mid-session rebuild (regenerate) keeps a sibling branch's flushed cost (fixes the e2e regenerate failure). - Track costKnown so turns saved with contextCost off don't render $0.00 when cost display is later enabled (P3). - Use an epsilon for the all-branches cost comparison to avoid a spurious total row from float summation order (P3). - Update unit/integration/e2e tests for the new shapes; regenerate e2e asserts the all-branches total after reload (deterministic via persisted metadata). * 🩹 fix: Address Codex round 2 — pending leak, cost coverage, reload delta - Clear the in-flight pending usage on terminal abort/error (resetLive), so a stopped generation's tokens no longer merge into the next response (P2). - costKnown now means COMPLETE coverage (ANDed): a branch mixing cost-bearing and cost-less turns is flagged incomplete and the cost row is hidden rather than rendering an under-reported total (P2). - Drop the tokenCount fallback for completedOutputTokens on reload: only the persisted post-snapshot delta is used, so a multi-call turn whose provider emitted no usage_metadata no longer double-counts earlier output (P2). - Update tokens.spec for AND coverage semantics + incomplete-cost case. * 🩹 fix: Address Codex round 3 — no-usage snapshots, total coverage, provider-less cache - Skip persisting metadata.contextUsage when the response emitted no primary usage event: without a known post-snapshot output the granular gauge would undercount the reply on reload, so fall back to the coarse per-message estimate instead (P2). - Gate the all-branches cost row on totalUsage.costKnown so an incomplete total (a sibling saved without cost) never renders an under-reported figure (P2). - aggregateEmittedUsage/finalCallOutputTokens now normalize per-event with the client's magnitude fallback (normalizeEventUnits) instead of billing splitUsage, so provider-less cached events match live on reload (P2). - Add backend test for the provider-less cached case. * 🩹 fix: Address Codex round 4 — abort attribution, complete cost coverage - aggregateEmittedUsage persists cost only when EVERY call was priced; a partial pricing failure now omits cost so the client treats coverage as unknown rather than reading an under-reported sum as authoritative (P2). - finalizeUsage flushes pending into the response entry only when events were folded this session (eventCount > 0), so a late/second resumable subscriber carrying persisted metadata.usage keeps it instead of being overwritten with an empty pending record (P2). - On user stop, attribute the in-flight pending usage to the partial response (new attributePending handler) instead of discarding it in resetLive — the stopped reply's billed tokens are kept and still can't leak into the next response; resetLive's discard remains for the error path (P2). * 🐛 fix: Persist branch cost across branch switches via sticky usage history Branch cost vanished on switching to a sibling branch (until a new turn) — the cost analog of the granularity bug. buildIndex rebuilds the token index from the messages cache; a sibling generated this session whose cache message lacks metadata.usage (and is transiently dropped from the cache during regenerate) lost its live-flushed usage, so sumBranch found none and the cost row hid. Fix: a sticky per-response usage map (conversationId → messageId → usage), written by setEntryUsage and never rebuilt from the cache — the usage counterpart of snapshotsByAnchorFamily for the breakdown. buildIndex/upsertEntries restore an entry's usage from it when the message carries none; cleared on convo switch and migrated with the index. Add unit coverage for the drop-then-readd regression and an e2e assertion that branch cost survives a branch switch. * 🐛 fix: Re-index on branch switch so branch cost survives the switch The sticky usage history alone didn't fix the reported branch-switch cost drop: on a branch switch no cache `updated` event fires, so the index subscriber never re-ran, and the post-regenerate rebuild was skipped while `isSubmitting` was still true — leaving the index stale and missing the now-viewed branch's response entirely (sticky can only restore entries present in a rebuild). Re-index from the messages cache on every tail change (created/finalize AND branch switch), not just while submitting. The cache holds the full message set at switch time, so the viewed branch's response is re-added and its usage restored from metadata.usage or the sticky history → sumBranch finds it and the branch cost renders. Verified locally: the branch-switch e2e now passes (the cost section shows both the branch row and the all-branches total). Also fixed that e2e assertion to target a single cost value (strict-mode safe). * 🩹 fix: Handle stopped-stream usage — reset pending + persist abort metadata Codex round (stop/abort edges): - Resumable explicit-stop (intentional SSE close) reset UI state but never cleared pendingUsageFamily, so usage folded before the stop leaked into the next response in the conversation. Discard pending on intentional close (resetLive); a resume re-folds via backfillUsage, so nothing is lost. - The abort save path (abortMiddleware) persisted the stopped response without metadata.usage/contextUsage, so its cost + breakdown vanished on reload. Rebuild both from the job's persisted tokenUsage (emitted payloads incl. cost) and contextUsage snapshot — parity with the normal sendCompletion path; breakdown gated on a primary usage event like buildResponseMetadata. Deferred (per scope decision): mid-stream branch-switch transiently shows the streaming branch's pending on the viewed sibling (cosmetic, until finalize). * 🩹 fix: Persist abort metadata on the real agents route + tighten snapshot gate Codex round (corrects last round's wrong-path fixes): - Stopped AGENTS responses are saved by routes/agents/index.js (/chat/abort), not abortMiddleware — so last round's metadata fix never ran for them. Moved the rollup/snapshot builder into packages/api as buildAbortedResponseMetadata (shared, unit-tested) and applied it in BOTH abort save paths, so a stopped agent reply keeps its cost + breakdown on reload. - Persist the breakdown only when the FINAL visible call emitted usage: track a per-response snapshot count and require primaryUsageCount >= snapshotCount. Previously any earlier primary usage event passed the gate, so a multi-call turn whose final call emitted no usage_metadata used an earlier call's output as completedOutputTokens (already counted by the latest snapshot) → reload over-reported. Now it falls back to the coarse estimate. Resumable stop pending-reset (prior round, 3cde6fe035) already flows through clearAllSubmissions → SSE close → the intentional-close handler's resetLive. Deferred per scope: mid-stream branch-switch pending attribution (tracked). * 🩹 fix: Abort breakdown over-count + resume re-fold after pending discard Codex round (on the re-applied abort/snapshot work): - buildAbortedResponseMetadata now persists ONLY the usage/cost rollup, not the context breakdown. The abort path can't tell whether the final call emitted usage (the job stores only the latest snapshot, not a count), so persisting the breakdown risked reusing an earlier call's output as completedOutputTokens (already in the snapshot) → reload over-count. Stopped/incomplete responses now fall back to the coarse gauge estimate, which is safe and apt. - resetLive now also forgets the conversation's folded usage-event identities (clearUsageFolded). Discarding pending on a terminal/intentional close left the folded keys set, so a later resume's backfillUsage saw the persisted events as duplicates and never rebuilt pending — leaving the response's usage missing until a full reload. Clearing them lets the resume re-fold. |
||
|
Danny Avila
|
98704f28c1 |
🌐 fix: Centralize Outbound Proxy Handling (#13726)
* fix: centralize outbound proxy handling * chore: sort proxy imports * test: update proxy helper mocks * fix: honor proxy bypasses consistently * fix: support http axios proxy targets |
||
|
Marco Beretta
|
16bbc4b97e |
🎨 fix: Gate message hover-reveal controls on hover capability, not width (#13712)
Apply the MessageTimestamp transform to all remaining hover-reveal controls in the message UI: replace the md: breakpoint proxy with a (hover: hover) media query so action buttons stay visible on touch and other non-hover devices (e.g. tablets wider than md), while still hiding until row hover/focus where a pointer supports it. The group-hover:visible reveal trio keeps no hidden base state, so it only drops the md: prefixes; the actual hide-until-hover mechanism is the opacity variant, which stays focusable and in the accessibility tree while hidden. |
||
|
Marco Beretta
|
fc2ae89aa6 |
⌚ feat: Show Message Timestamps on Hover (#13709)
* ✨ feat: Show Message Timestamps on Hover Reveal a message's time inline next to the author name on hover. Recent messages (under 24h) show a relative time ("10 minutes ago") with the absolute date on hover; older messages show the absolute date directly. A shared MessageTimestamp component is used by both MessageRender and ContentRender, with createdAt added to their memo comparators so the timestamp appears once it's available. Resolves #5199 * 🎨 fix: Gate message timestamp reveal on hover capability, not width Use a (hover: hover) media query instead of the md: breakpoint so the timestamp stays visible on touch and other non-hover devices (e.g. tablets wider than md), while still revealing on hover/focus where a pointer supports it. * 🎨 fix: Show message timestamps across all renderers and keep them live Extend the hover timestamp to the Assistants (MessageParts), shared-link, search, and parallel/multi-response renderers so every prompt and response shows when it was sent. The parent message's createdAt is threaded down to parallel column headers (SiblingHeader). Add a shared, ref-counted minute ticker (useTimeTick) so relative labels like "2 minutes ago" stay current while a conversation is left open instead of freezing at first render. |
||
|
Danny Avila
|
9618be6eb3 |
🌿 fix: Preserve Viewed Branch on Sibling-Tree Churn (#13732)
* 🌿 fix: Preserve Viewed Branch on Sibling-Tree Churn Regenerating a message could snap the view to an unrelated newest branch. MultiMessage reset siblingIdx to 0 (newest) on any messagesTree.length change, but getRegenerateSubmissionMessages slices the flat message array during a regenerate — the streaming handlers render a tree missing unrelated sibling branches, then finalHandler restores the full set. That 2→1→2 child-count swing snapped unrelated forks to their newest sibling, so regenerating the latest response on an older branch jumped to a previously regenerated branch. Replace the indiscriminate reset with per-fork branch memory: a 'seen' set distinguishes a genuinely new sibling (submission/regeneration/edit here — focus it) from one transiently dropped and restored (preserve the user's branch). Decision extracted as the pure, unit-tested resolveSiblingSelection. - client/src/utils/messages.ts: resolveSiblingSelection + tests - MultiMessage: seen/selectedId refs, structural id-signature effect - e2e: regenerate-latest-on-older-branch keeps the viewed branch (fails on the old reset, passes now) * 🧪 test: Long-Thread Branch Preservation E2E Add the user-reported scenario: in a multi-turn thread, regenerate an earlier response (forking a root branch), switch back to the original, then regenerate a later response on it — the original branch must stay intact. Uses labeled prompts so each turn's unique reply is a reliable settle signal. Verified it fails on the original MultiMessage and passes with the fix. * 🎨 style: Fix import order in MultiMessage (react before recoil) * 🌿 fix: Keep Unrelated Branches in Regenerate Optimistic Render Regenerating a message used a flat `messages.slice(0, targetIndex)` for the optimistic render, which also drops unrelated sibling branches that merely sit later in the flat array. Mid-regenerate the thread briefly collapsed to a short branch (visible flash) and the scroll jumped to the shrunken content and didn't recover — the same flat-array root cause as the branch-reset bug. Remove only the regenerated response and its descendants, keeping unrelated branches. The thread (and scroll) stay put through the regenerate. This array is render-only — the server regenerates from parentMessageId and createPayload doesn't include it — so summing by subtree never affects the request. Verified via a small-viewport scroll trace: old collapses 903->295px / 8->2 renders mid-stream; fixed stays 903px / 8 renders, scroll held at bottom. Unit test covers the keep-unrelated-branches behavior (fails on the old slice). * 🌿 fix: Let an Explicit Branch Selection Survive Streaming ID Churn resolveSiblingSelection focused any unseen sibling id before checking the committed selection. When an in-flight response's id is replaced mid-stream (placeholder → server/run id, e.g. useStepHandler re-keys to runId) after the user switched to a different sibling, that swap looked like a brand-new sibling and stole focus back to the streaming branch. Reorder: the committed selection wins while still present; only focus a fresh sibling when the selection is gone (regenerated away, or its own placeholder id was just replaced — that's how a regen/edit still takes focus, since the slice removes the old response). Added unit tests for both churn directions. * 🌿 fix: Only Focus a New Sibling When the Fork Actually Grew The previous churn fix (selection-wins-first) was too aggressive: a genuinely new sibling ADDED while the prior selection is still present — e.g. a follow-up re-parented as a sibling after a generation-start failure — was no longer focused, so its reply never rendered (broke message-tree generation-start recovery e2e). Gate new-sibling focus on actual growth: resolveSiblingSelection now takes prevCount and only focuses a never-seen id when ids.length > prevCount. A same-count placeholder→server id swap (churn) or a restored already-seen sibling is not growth, so the committed selection still wins there. Covers follow-up/new-branch focus, churn steal-prevention, and self-churn follow. message-tree + chat e2e: 17 passed (incl. the recovered generation-start test). * 🌿 refactor: Drop MultiMessage Branch-Memory in Favor of the Slice Fix The regenerate-slice fix (keep unrelated branches in the optimistic render) is the true root cause: with no spurious tree collapse, the original setSiblingIdx(0)-on-length-change never misfires, so the branch-reset is fixed without per-fork memory. The earlier MultiMessage rewrite (seen/selectedId/ prevCount + resolveSiblingSelection) was a symptom patch added before the root cause was found, and its per-instance memory generated two edge-case findings (placeholder→server id churn; divergence from external siblingIdx writes like resume restore). Revert MultiMessage to the simple upstream version and remove resolveSiblingSelection (+ its tests). The slice fix + the existing branch e2e (chat.spec: switch-back, regenerate-latest, long-thread) cover the behavior; all 17 chat + message-tree branch specs pass with this version. * 🌿 fix: Focus the Regenerated Response When Its Fork Count Is Unchanged When a parent already has multiple sibling responses and the user switches to a non-latest one and regenerates it, the optimistic slice drops the target but keeps the other siblings, so the child count is unchanged. MultiMessage only resets the (reversed) sibling index on a length change, so the stale index kept pointing at the kept sibling and the regenerating response stayed hidden until the server restored the dropped sibling at finalize (count bump → reset). Explicitly focus the newest sibling (reversed index 0 = the appended response) of the regenerated fork in createdHandler. Position-based, fires only on the regenerate action, so it doesn't reintroduce the placeholder→server id churn or external-write fragility that a per-render selection memory had. E2E: new during-stream test (slow+counted reply marker) asserting the regenerating response is visible before finalize; negatively verified (fails without the focus call, passes with it). * 🌿 fix: Eliminate Pre-Created Flash by Focusing at the Optimistic Render The createdHandler focus removed the until-finalize bug, but a brief flash remained between clicking regenerate and the `created` event: useChatFunctions renders the optimistic placeholder first, and that render has the same unchanged-count problem, so the kept sibling showed until createdHandler fired. Extract the focus into a shared useFocusRegeneratedResponse hook and apply it at the optimistic render too (useChatFunctions) and on `created` (useEventHandlers). The placeholder is now focused from the first frame. E2E: gated pre-created test — holds the SSE stream GET (the chat POST returns a stream id; the stream is a separate GET) so `created` cannot arrive, leaving only the optimistic render, then asserts the kept sibling is already gone. This isolates the optimistic focus (createdHandler cannot mask it); negatively verified (fails without the optimistic focus call). * 🧪 test: Extend Store Mock for the Regenerate Focus Hook useChatFunctions.regenerate.spec.tsx mocks ~/store and recoil partially; the new useFocusRegeneratedResponse calls store.messagesSiblingIdxFamily via a recoil `set`, neither of which the mock provided (TypeError on regenerate). Add messagesSiblingIdxFamily to the store mock and `set` to the useRecoilCallback mock. Test-only; production code unchanged. |
||
|
Danny Avila
|
db7011d567 |
📊 feat: Real-Time Context Window & Token Usage Tracking (#13670)
* 📊 feat: Real-Time Context Window & Token Usage Tracking * 🧪 fix: Align Pricing Spec Dep Signatures with TxDeps * 🩹 fix: Resolve Codex Findings for Context Usage Tracking * 📊 feat: Granular Tool Token Breakdown with Deferred Splits * 🧪 test: Cover Session Cost in Mock E2E and Scope Usage Selectors * 🧪 test: Live Host-Pipeline Usage Verification (Env-Gated) * 🧪 test: Local Real-Provider Multi-Turn E2E Harness * 🪙 fix: Keep Tagged Usage Buckets Out of the Live Context Estimate * 🩹 fix: Scoped Token-Config Fallback and Sequential Visibility for Usage Events * 🩹 fix: Address Usage Review Findings — Cost Timing, Scoped Caches, Finalized Output - carry the post-snapshot output estimate into the context snapshot at finalize so the gauge keeps the last response after live resets - accumulate per-rate billable units and price the session cost at render, so usage events arriving before the token-config load still count once it resolves - pass user-scoped token-config cache keys through loadConfigModels fetches and drop the controller's unscoped fallback to prevent serving another user's resolved config - tag emitted usage events with a per-run seq so resume dedupe never drops a distinct call with an identical payload - admit the static tokenConfig override in the custom endpoint schema so it survives zod parsing into req.config * 🩹 fix: Align Client Usage Accounting with Backend Cost Semantics - classify cache tokens by provider (shared inputTokensIncludesCache from data-provider, consumed by both the backend billing path and the client) instead of a magnitude heuristic, so Anthropic/Bedrock turns where cache is smaller than uncached input no longer under-bill input - mirror resolveCompletionTokens on the client so Vertex-style hidden thinking tokens are reflected in the Output row and session cost - prefer endpoint pricing over adapter-provider pricing so a custom endpoint can price a known model name without built-in rates shadowing it - carry static cacheRead/cacheWrite overrides through the tokenConfig schema and buildTokenConfigMap * 🩹 fix: Honor Static Token Config in Billing; Tighten Usage Freshness - initializeCustom now uses a static endpoint tokenConfig as the agent's endpointTokenConfig (billing + balance checks), not just the advertised UI config — previously the gauge showed admin rates while the agent billed against built-in tables - invalidate the token-config query alongside models on user-key add/ revoke so context windows and pricing refresh without a reload - include maxContextTokens in ChatForm's stabilized conversation memo so the gauge reflects a changed context-window setting immediately - feed the live output estimate from the legacy content path (direct and assistants streams), setting from cumulative part text rather than accumulating deltas * 🩹 fix: Resume Usage Dedup, Agent Pricing, and Partial Override Billing - fold usage events idempotently by (runId, seq) so resume backfill no longer resets the conversation totals — a mid-stream reconnect keeps the usage of prompts already completed earlier in the session - tap replayed pending message/reasoning/content events so output streamed past the resume snapshot reaches the live estimate, not just the message - resolve cost against the agent's backing endpoint (Agents conversations report endpoint `agents` / provider `openAI`, neither of which keys a custom endpoint's tokenConfig) - getMultiplier/getCacheMultiplier fall back to the standard tables for models absent from a partial endpointTokenConfig, so a partial static override no longer bills non-listed models at defaultRate while the UI shows the correct pattern rate * 🩹 fix: Repaired Output in Gauge, Cache-Rate Keys, Config Gate, Usage Cleanup - live/completed gauge counts the repaired completion (normalized output), so under-reporting providers don't drop the response from used context - translate static tokenConfig cacheWrite/cacheRead onto the write/read keys getCacheMultiplier reads, so cache tokens bill at the configured rate instead of the prompt-rate fallback - clear the token index and usage atoms when leaving a conversation, so visited histories don't accumulate in memory for the tab's lifetime - wait for startupConfig before mounting the gauge, so a deployment with contextUsage disabled never briefly mounts it or fires the token-config query on first load * 🩹 fix: Move Token-Config Resolution to TS; Key Live Usage by Created Convo - extract the token-config resolution (override gathering + cache lookup + buildTokenConfigMap) into resolveTokenConfigMap in packages/api, leaving the /api controller a thin request-scoped wrapper (CLAUDE.md TS rule) - getConvoKey prefers the user message's real conversationId once the `created` event stamps it, so a new chat's first-response live gauge and totals land under the id TokenUsage subscribes to instead of NEW_CONVO * 🩹 fix: Clear Stale Redis Job Usage; Live-Tap Legacy Streams; Share Fetched Config - DEL the Redis job hash before re-creating it so a reused streamId can't inherit a prior run's contextUsage/tokenUsage and backfill stale usage - tap the legacy {message,text} stream branch (non-agent OpenAI/Anthropic streams) into the live estimate, not just the content path - copy a deduped fetch's token config to every sibling endpoint sharing the baseURL/key/headers, so /token-config resolves each by its own name * ⏪ revert: Don't DEL Redis job hash in createJob (breaks cross-replica resume) createJob is an idempotent join — a second replica calls it for the same streamId to share an in-flight stream's state. DELeting the hash wiped the prior replica's persisted created/usage state, so a joining replica missed the created event (GenerationJobManager cross-replica integration test). Reverts the F1 change from 2bfce0c34b; the stale-usage concern doesn't arise in practice (streamId is unique per generation). * 🩹 fix: Best-Effort Usage Emit; Tag Hidden Sequential-Agent Usage - wrap the ModelEndHandler usage emit in try/catch so a failed telemetry delivery (closed SSE / Redis publish error) can't abort the handler before thought-signature capture, which would break resumed tool calls - tag hidden sequential-agent usage as 'sequential' (non-primary) so the client folds it into session cost/totals but not the live context gauge, instead of letting an undefined usage_type inflate the visible gauge * 🩹 fix: Refetch Stale Token Config on Mount; Normalize Vertex for Lookup - useTokenConfigQuery refetches on mount when stale, so a user-key change that invalidates tokenConfig while the gauge is unmounted takes effect on return instead of serving the prior key's resolved config - normalize a Vertex-backed agent's provider (vertexai) to the google token-config key, so Gemini context windows and rates resolve instead of showing unknown context / $0 cost * ✨ feat: Server-Side Per-Event Cost (Authoritative Pricing for the Gauge) Move usage-cost pricing to the single source of truth. The backend prices each model call with the same billing functions (premium tiers via getMultiplier(inputTokenCount), cache rates) and emits the USD cost on on_token_usage when interface.contextCost is enabled; the client sums emitted costs instead of re-deriving from base token-config rates. - computeUsageCostUSD reuses prepareTokenSpend/prepareStructuredTokenSpend so the emitted cost matches what is billed (incl. premium thresholds) - getDefaultHandlers gains a usageCost pricing context; initialize.js wires db.getMultiplier/getCacheMultiplier gated on contextCost (agents path) - client UsageTotals carries a summed costUSD; retire the client-side rate lookups (costFromUnits/calcUsageCost) that drifted from backend pricing and produced the provider-keying / cache-key / Vertex / premium findings - keep normalizeUsageUnits for the displayed token counts; token-config is still used for the context-window meter Fixes the premium-tier session-cost under-report (gpt-5.x / gemini-3.1 above their input thresholds). * 🩹 fix: Branch-Accurate Usage Snapshot + Clearer Gauge Track Contrast - re-anchor the context snapshot from the user message to the response message at finalize. Regenerating a response branches off a shared user message, so anchoring on it made the snapshot read as "active" on both branches — switching to the sibling branch showed the wrong (other branch's) context. The response message is branch-unique, so sibling branches now correctly fall back to their own per-branch totals. - raise the gauge ring's track/fill contrast (muted track, prominent fill) so the used portion reads clearly as a fill-level indicator * 🩹 fix: Tag Sequential Usage in Billing; Emit Subagent Cost; Reset Live on Resume Errors - tag hidden sequential-agent usage `usage_type: 'sequential'` on the COLLECTED usage (not just the emit), and treat it as non-primary in recordCollectedUsage (billed, excluded from the reported output total) so hidden intermediate output stops inflating the parent's tokenCount/pruning - emit on_token_usage from the subagent usage sink (tagged `subagent`, with authoritative cost when contextCost is on) so the gauge's session cost/totals include billed subagent usage; it stays out of the live meter - call resetLive on the resumable 404 and max-retry terminal branches so the gauge doesn't keep counting stale in-flight tokens after the stream ends * 🎨 fix: Contrast the Popup Context Bar; Revert Ring Restyle - raise the popup breakdown's context progressbar contrast (muted surface-tertiary track, prominent text-primary fill) — that's the bar the contrast feedback was about - revert the gauge ring restyle (kept its original border-heavy track / text-secondary fill); the ring wasn't the element in question * 🩹 fix: Stop Snapshot Granularity Leaking Across Branches; Revert Tree Memo - a null-anchor context snapshot was treated as active on every branch, leaking one generation's granular breakdown onto sibling branches. Require a non-null (response-message) anchor on the viewed branch instead, so siblings without a matching snapshot fall back to their own totals. - revert the buildTree WeakMap memo in messages.ts. buildTree is pure (builds from shallow copies) so the memo was behaviorally identical, but it was the feature's only change to core branch-navigation selectors — removing it matches upstream and rules it out of branch-navigation debugging. * 🪙 fix: Thread Endpoint Token Config to Agent Billing, Cost, and Context Limits Custom-endpoint agents resolve an endpointTokenConfig during agent init but it never reached the AgentClient, so spending, emitted cost, and runtime max-token resolution all fell back to default rates for those agents. - Surface options.endpointTokenConfig on the returned InitializedAgent. - Pass it to the AgentClient (this.options.endpointTokenConfig) so the spending path bills at configured rates. - Thread it through usageCost to computeUsageCostUSD so emitted per-event cost matches billing. - getModelMaxTokens/getModelMaxOutputTokens fall back to the built-in map for models absent from a partial override (matches buildTokenConfigMap); consolidates the duplicated fallback in pricing.ts. * 🪙 fix: Preserve Granular Breakdown Across Branch Switches The granular context breakdown lives only in the live on_context_usage snapshot — a single per-conversation slot, anchored to the latest response and overwritten by each generation. Switching to a branch generated earlier this session lost its tool/skill/system rows and fell back to coarse totals. Retain each generation's finalized snapshot in a per-conversation map keyed by its branch-unique response id (snapshotsByAnchorFamily). When the live snapshot is off the viewed branch, walk the branch tail for its deepest stored anchor and render that breakdown. Bounded by generation count and cleared on conversation switch; the live/just-generated path is unchanged. * 🪙 fix: Harden Resume Seeding and Subagent Usage Emission - useResumableSSE: skip the trailing-output live seed when the resume carries a context snapshot; the snapshot's messageTokens already counts produced output, so seeding it again inflated usage until the next reset. - AgentClient subagent emitter: await GenerationJobManager.emitChunk like every other caller (it persists before publishing), so a floating promise can't race job cleanup and a Redis/publish failure is caught by the emitter's try/catch instead of surfacing as an unhandled rejection. * 🧪 test: Playwright Coverage for Context Breakdown Granularity Add a test-only data-testid distinguishing the granular snapshot breakdown (context-breakdown) from the coarse message-history estimate (context-estimate), then assert granularity in the mock e2e harness: - renders the granular breakdown from the live on_context_usage snapshot (guards that the snapshot event actually reaches the popover, not just the usage totals). - preserves the granular breakdown after switching branches — regenerate to overwrite the single live snapshot, switch back, and confirm the rows survive via the per-anchor snapshot history map. Branch regenerate/sibling selectors mirror the existing chat.spec branch test. All three usage specs pass against the mock pipeline. * 🪙 fix: Correct Resume Live-Seed, Fallback Re-index, and Subagent Emit Flush Codex round on the prior commit: - countTrailingOutputChars now counts only output at the very END of the aggregated content (0 when the model paused at a tool call), and the resume path always seeds it. The earlier skip-trailing-tool-parts behavior plus the skip-seed-when-snapshot gate together over- or under-counted in-flight output on resume; one rule fixes both — pre-invoke snapshot budget is never double-counted, and genuine in-flight output is no longer dropped. - useTokenUsage re-indexes from the messages cache on tail change while submitting. The cache subscriber is muted during streaming, so without a context snapshot (non-agent streams) sumBranch missed the created tail and dropped history + prompt until finalize. Bounded — tailId only shifts on created/finalize/branch-switch. - AgentClient tracks subagent usage emit promises and flushes them in chatCompletion's finally. The sink fires the emitter without awaiting, and resume reads the usage emitChunk persists (HSET), so cleanup must not race it or resumed clients miss billed subagent usage. |
||
|
Danny Avila
|
3c3837bb7d |
🧾 fix: Bill Subagent Child-Run Model Usage in Parent Transactions (#13683)
* 🧾 fix: Bill Subagent Child-Run Model Usage in Parent Transactions * 🩹 fix: Type Subagent Usage Sink Structurally Until SDK Release * 🔧 chore: Update @librechat/agents dependency to version 3.2.35 in package-lock.json and related package.json files |
||
|
Anubhav Anand
|
65e2838038 |
🔧 fix: Honor NO_PROXY for OpenID requests when PROXY is set (#13716)
* 🔧 fix: Honor NO_PROXY for OpenID requests when PROXY is set openidStrategy routed every OIDC request (issuer discovery, JWKS, token endpoint, Microsoft Graph overage resolution) through undici.ProxyAgent whenever PROXY was set. undici.ProxyAgent does not consult NO_PROXY, so OIDC providers on internal networks that the corporate proxy cannot reach failed at startup with ECONNREFUSED or discovery timeouts, even when the issuer host was listed in NO_PROXY. Replace ProxyAgent with undici.EnvHttpProxyAgent configured to use PROXY for both protocols. EnvHttpProxyAgent applies the standard NO_PROXY/no_proxy exclusion list per request host (suffix matching, leading-dot domains, host:port entries, and *), so excluded hosts are requested directly. The agent is also memoized (keyed on PROXY + NO_PROXY) instead of being constructed per request, so repeated OIDC calls reuse one connection pool. Fixes #13705 * fix: move OpenID proxy helper to api package * chore: import order in openidStrategy.js * chore: import order in openidStrategy.spec.js --------- Co-authored-by: Danny Avila <danny@librechat.ai> |
||
|
Michael Harvey
|
05eb986097 |
💬 feat: Conversation Starters for Model Specs (#13710)
* 💬 feat: Conversation Starters for Model Specs Adds an optional conversation_starters field to model specs in librechat.yaml. When the active conversation uses a spec that defines starters (and no agent/assistant starters apply), the chat landing renders clickable starter prompts between the landing content and the chat input; clicking one submits it as the first message. - data-provider: add conversation_starters to TModelSpec and tModelSpecSchema so the field survives strict config parsing - client: ConversationStarters falls back to the active spec's starters via getModelSpec; entity (agent/assistant) starters take precedence; starter cards are centered, size to content, wrap at word boundaries, stagger their fade-in, and gain a focus-visible ring - sanitizeModelSpecs passes the field through (denylist); covered by a new unit test - e2e: mock spec + tests for rendering, absence, click-to-submit, and the MAX_CONVO_STARTERS cap Closes #3619 Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore: Sort ChatView imports --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> Co-authored-by: Danny Avila <danny@librechat.ai> |
||
|
Danny Avila
|
49859c04a2 |
🗄️ fix: Gate Request-Scoped MCP Servers Out of Persistent Tool Cache (#13672)
* 🗄️ fix: Gate Request-Scoped MCP Servers Out of Persistent Tool Cache PR #13626 established that request-scoped MCP servers (runtime OPENID/GRAPH/BODY placeholders) must not use the persistent 12h tool cache, but only gated three of five touchpoints. The panel endpoint still back-filled the cache and the OAuth callback still wrote to it, while agent loading read those entries ungated — pinning ephemeral model-spec/agent toolsets to stale definitions for up to 12h. Centralize the invariant in createMCPToolCacheService: a getServerConfig resolver dep gates both writers and a new service-owned getMCPServerTools read, so every current and future caller is covered. Callers that already hold the parsed config pass it to skip resolution; the per-call skipCache flag and duplicated call-site gates are removed in favor of the single config-based mechanism. Resolution failures fail open to preserve prior behavior. * 🩹 fix: Address Codex Review on Cache Gating - Repair getCachedTools.spec.js, which destructured the relocated getMCPServerTools directly from the module; its coverage now lives in the service-level tools.spec.ts. - Resolve the merged (Config-tier-aware) server config in the OAuth callback before writing tool definitions, so the cache gate detects request-scoped servers supplied via admin Config overlays that the base registry lookup cannot see. - Discover tools actively for request-scoped servers in the panel endpoint via ephemeral reinitialization: such servers have no stored app/user connections, so the previous getServerToolFunctions fallback returned an empty toolset once the cache read was gated. * 🧵 fix: Address Second Codex Review on Cache Gating - Resolve the merged server config before the OAuth callback reconnects, so the connection itself uses Config-tier overlays rather than only the subsequent cache write. - Pass Config-tier candidates into the panel's request-scoped discovery, matching the reinitialize route: reinitMCPServer forwards configServers (not the provided serverConfig) to its OAuth discovery fallback. - Document the accepted read-path trade-off: the gate resolver sees base configs only, all writers pass merged configs, so a pre-gating or overlay-divergent entry survives at most one cache TTL. * 🚏 chore: Rework Cache Gating for BODY-Only Request Scoping After #13673 narrowed requiresEphemeralUserConnection to BODY placeholders, the central gate follows the predicate unchanged, but the panel's active discovery no longer serves a purpose: the only remaining request-scoped class cannot connect outside a chat turn, so the reinitialization attempt would always fail at the missing-body check. Remove that path; OpenID/Graph servers are persistent user-scoped again and flow through the stored-connection and cache lookups as before. Flip test fixtures that used OPENID placeholders to denote request-scoped configs over to BODY placeholders. * 🪟 fix: Check Config Overlays in Agent-Loading Cache Reads The cache service's registry resolver sees only base YAML/DB configs, so a BODY placeholder introduced by a request-tier Config overlay was invisible to the gate on the agent-loading read path: model-spec and ephemeral-agent expansion could read a leftover persistent entry and pin stale concrete tool names instead of the mcp_all fresh-discovery path. Check the raw overlay candidate inline in loadEphemeralAgent and loadAddedAgent — a pure placeholder scan with no extra IO — and skip the cache read when the overlay makes the server request-scoped. Widen UserScopedConnectionConfig so raw (pre-inspection) configs qualify for the scoping predicates, which only check key presence. * 🧪 test: Guard Run-Scoped MCP Definition Handoff Boundaries The original ClickHouse breaker storm regressed precisely at field pass-through boundaries that unit tests of each end could not see: initializeAgent dropping mcpAvailableTools from its destructure, and the agent tool context losing it on the way into ON_TOOL_EXECUTE. Add direct guards on both hops: the loadTools result must surface on the initialized agent, and the captured toolExecuteOptions closure must forward it to loadToolsForExecution. |
||
|
Danny Avila
|
5ceabad5f3 |
🪢 fix: Prune Dangling Skill IDs from Agent Allowlists (#13702)
* 🧹 fix: Prune Dangling Skill IDs from Agent Allowlists Deleted skills left their ids behind in every agent's `skills` allowlist: nothing removed them on skill deletion, the builder rendered no chip for unresolvable ids (so users could neither see nor remove them), and at runtime the non-empty allowlist intersected with accessible skills to an empty set — silently disabling the entire skills catalog for the agent even though the panel looked like "no skills selected." - deleteSkill / deleteUserSkills now $pull deleted ids from all agent allowlists (no versioning, timestamps untouched) - createAgent / updateAgent prune allowlist ids whose skill doc no longer exists (existence-only check, never ACL), so poisoned agents self-heal on the next save — including duplicates and sync paths - the builder renders unresolvable allowlist entries as removable "Unavailable skill" chips once the catalog query resolves * 🪞 fix: Keep Skill Queries and Authoring Labels Truthful After Chat Edits Skills authored mid-chat via create_file/edit_file never reached the Skills panel or builder without a manual refresh, and a create_file that overwrote an existing file still announced "Created" in the tool card. - invalidate all skill query caches (refetchType: 'all', since the skill hooks opt out of refetchOnMount) when a completed create_file/edit_file call targets a skills/ path - label create_file completions from the host-authored output summary: overwrites now read "Updated <file>" with the edit icon * ♻️ refactor: Inject Skill Authoring Callback Instead of Query Client useStepHandler took useQueryClient directly, forcing a QueryClientProvider wrapper onto all 54 renderHook calls in its spec. Its only consumer, useEventHandlers, already holds the query client and does this exact invalidation pattern for project/MCP keys — so pass an optional onSkillAuthoringComplete callback instead. Detection stays in the completion handler; the side effect lives with the client. Spec diff collapses to pure additions. * 🩹 fix: Resolve Codex Review Findings on Allowlist Pruning - normalize allowlist candidates to lowercase in filterExistingSkillIds: isValidObjectIdString accepts uppercase hex, but _id.toString() is lowercase, so a casing mismatch silently emptied a valid allowlist (widening scope to the full catalog) - prune agent allowlists immediately after the Skill row deletion in deleteSkill: a SkillFile cleanup failure previously skipped the prune forever, since retries exit early on deletedCount === 0 - filter version-snapshot skills through filterExistingSkillIds in revertAgentVersion so reverting to a pre-delete version cannot resurrect dangling ids - resolve allowlist ids missing from the builder's first catalog page individually via getSkill before labeling them unavailable — a cache miss on a >100-skill catalog no longer invites removing a valid skill * 🚪 fix: Fail Closed When Pruning Empties a Skill Allowlist Codex round 2: an automated prune that empties an enabled allowlist would silently widen the agent to the full accessible catalog (empty + enabled = full per the #13526 semantics). Hygiene must only ever narrow. - deleteSkill/deleteUserSkills: agents whose entire allowlist is being deleted get skills disabled instead of an emptied-but-enabled list; ids are lowercased before the $pull so an uppercase-but-valid id cannot leave the dangling entry behind - createAgent/updateAgent/revertAgentVersion: pruning a non-empty allowlist to zero survivors disables skills; an explicit user-sent skills: [] keeps the full-catalog semantics - builder: a per-id skill lookup only renders the removable "Unavailable skill" chip on a confirmed 404/403 — transient and server errors keep the chip hidden rather than inviting removal |
||
|
Lacy
|
dea71c8396 |
🪟 fix: Cross-Platform Absolute-Path Check in tsdown neverBundle Predicates (#13700)
The deps.neverBundle predicates in the four package tsdown configs detect
first-party (resolved) module ids with !id.startsWith('/'). On Windows,
resolved ids are absolute paths like C:\..., which never match, so every
project module is externalized. Builds still exit 0 but emit near-empty
bundles — e.g. packages/client dist/index.mjs drops from ~276 kB to
~2.7 kB and dist/style.css is never produced, breaking the client dev
server with "Failed to resolve import @librechat/client/style.css".
Replace the startsWith('/') check with path.isAbsolute(id), which is
behavior-identical on POSIX and correct on Windows.
Co-authored-by: phoenixtekk <phoenixtekk@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
||
|
Danny Avila
|
8154a31d2d |
📦 chore: npm audit fix (#13701)
- Bump @grpc/grpc-js versions to 1.9.16 and 1.14.4, updating resolved URLs and integrity hashes. - Add license information for the updated packages. |
||
|
Danny Avila
|
2d6b7df3ce | 🛬 fix: Prevent Viewed Conversations from Re-Arming the Soft Default Spec (#13699) | ||
|
Danny Avila
|
a8a63604b9 |
📬 feat: Report Tool Results Per Call via onResult Channel (#13698)
* 📬 feat: Report Tool Results Per Call via onResult Channel Tool batches already execute in parallel here, but results were only delivered to the agent graph through the single resolve(results[]) call — so a fast tool's completion event waited on the slowest call in the batch. Report each result through the optional onResult channel (agents SDK > 3.2.33) as it settles, letting the graph emit that call's completion immediately. resolve remains the authoritative batch outcome; the callback is optional-chained, so this is a no-op until the SDK release lands and remains backward compatible after. * 🧹 chore: Prettier Formatting in onResult Spec * 🧹 chore: Sort Imports in handlers.ts * 🔧 chore: Update @librechat/agents dependency to version 3.2.34 in package-lock.json and related package.json files |
||
|
Danny Avila
|
b39ec16ff0 |
🔌 fix: Preserve Ephemeral MCP Selections Across Model Switches (#13697)
The no-spec branch of `useApplyModelSpecEffects` (added in #11796) reset `ephemeralAgentByConvoId` to null on every `newConversation` call when model specs are configured. On in-place model/endpoint switches (modular chat, same conversation or new-chat draft), BadgeRowContext never refills from localStorage — its init effect only re-runs when the storage suffix or spec changes — so the MCP selection (and tool toggles) were silently dropped from subsequent request payloads while the MCP badge kept displaying them. Reset now only happens on context transitions (leaving a spec, or moving to a different conversation key), where a BadgeRowContext refill is guaranteed; in-place non-spec switches preserve the ephemeral agent. - Gate the no-spec reset on `prevSpecName` / `prevConvoId`, passed from `newConversation` via a snapshot read of the pre-switch conversation - Add jest coverage for all five branches of the no-spec path - Add e2e spec asserting `ephemeralAgent.mcp` stays in the chat payload after a new-chat model switch and after regenerate on a switched conversation (verified failing before the fix, passing after) - Add non-spec "Mock Provider D" endpoint to the e2e config so tests can switch between two real ephemeral endpoints; widen `MockEndpoint` type |
||
|
Danny Avila
|
731a7c57c1 | 🥇 fix: Send First OpenID Audience on Authorization Requests (#13694) | ||
|
Danny Avila
|
788cc5ac07 |
🛟 fix: Auto-Recover from Stale Service Worker Assets After Deploys (#13686)
* 🛟 fix: Auto-Recover from Stale Service Worker Assets After Deploys - 404 missing static assets in the SPA fallback instead of serving index.html - inline recovery script unregisters stale SWs and reloads once on chunk failure - route vite:preloadError into the same recovery path for stale lazy chunks * 🛟 fix: Address Review — SW-Side Recovery, Scoped Unregister, Shared Fallback - importScripts'd sw-heal.js pings window clients on activation and reloads ones that can't pong: stale pages carry no recovery code of their own - scope SW unregistration to the deployment base for subpath installs - preventDefault vite:preloadError only when a recovery reload was initiated - extract createSpaFallback and apply the asset 404 guard to experimental.js |
||
|
Dustin Healy
|
e0f715bd24 |
🔒 fix: Scan All Message Roles in messageFilter.pii (#13677)
A Codex security finding flagged that findPiiMatchInMessages was gating on msg.role === 'user' and silently skipping every other role. The OpenAI-compatible validator accepts system, assistant, and tool from the caller; the Responses input conversion accepts and converts developer and system. All of those roles flow into formatAgentMessages and then createRun, so an authenticated remote agent caller could place a credential-shaped value in any non-user role and reach the model despite the configured filter. Drops the role gate. The helper now scans every caller-supplied message regardless of role; the loop count is unchanged (one outer over messages, one inner over content parts) and the early-exit on first match still holds. Spec adds explicit cases for system, assistant, and tool roles in place of the now-incorrect skips-non-user assertion. |
||
|
Danny Avila
|
139d61c437 |
🚐 fix: Reuse Request-Scoped MCP Connections per Run (#13673)
* fix(mcp): reuse request-scoped connections per run * test(mcp): update connection factory defaults |
||
|
Danny Avila
|
65bca95023 |
🎒 fix: Carry Request-Scoped MCP Tools into PTC Execution (#13669)
* fix(mcp): preserve request-scoped tools for PTC execution * fix(mcp): preserve run-scoped tools on initialized agents |
||
|
Danny Avila
|
919a46312b |
🧹 ci: Relieve disk pressure on GitNexus deploy (#13666)
The gitnexus droplet is ~8.7GB usable, not the 60GB the disk-cleanup
comment assumed. With /usr (~2.8GB), the in-use docker images (~2.1GB),
and the growing /opt/gitnexus/indexes (~1.2GB), deploys were aborting at
the `AVAIL_MB < 2048` guard ("Disk critically low").
Two fixes:
- Reclaim the previous gitnexus image after force-recreate. The pre-pull
`docker system prune -af` cannot remove it while the old container is
still running, so a stale ~700MB generation accumulated every deploy.
A post-recreate `docker image prune -f` makes the box self-cleaning.
- Lower the abort threshold 2048 -> 1536MB. The image is ~700MB and
shares most layers with the running one, so an incremental pull needs
well under 1GB; the old guard was sized for the 60GB assumption.
Also corrects the stale 60GB comment to reflect the actual disk.
|
||
|
Danny Avila
|
197a1dc4e2 |
🧬 feat: Add GitHub Skill Sync (#13293)
* feat: Add GitHub skill sync
* fix: Address GitHub skill sync CI
* fix: Harden GitHub skill sync review paths
* fix: Prevent overlapping skill sync runs
* fix: Address GitHub skill sync review findings
* fix: Satisfy Git ref lint rule
* fix: Address GitHub sync review follow-ups
* fix: Match skill frontmatter closing fence
* fix: Address GitHub sync review cycle
* fix: Address GitHub sync review follow-ups
* fix: Harden GitHub skill sync worker
* fix: Format GitHub sync rollback log
* fix: Address GitHub sync review feedback
* fix: Format skill import parse handling
* fix: Coerce scalar skill frontmatter and correct scheduler timer clear
- parse: coerce numeric/boolean name and description scalars to strings instead of dropping them to empty (restores pre-refactor behavior; preserves absent-vs-empty distinction for the when-to-use fallback)
- scheduler: clear the setTimeout handle with clearTimeout rather than clearInterval
- test: cover non-string scalar frontmatter coercion
* fix: Tolerate trailing whitespace after SKILL.md opening frontmatter fence
extractFrontmatterBlock required the opening fence to be exactly '---\n', so an opener with trailing spaces/tabs (e.g. '--- \n') silently dropped all frontmatter even though the closing-fence regex already tolerates it. Match the opener with /^---[ \t]*\n/ for symmetry. Addresses Codex P3 (parse.ts:24).
* feat: Run GitHub skill sync under a per-source tenant context
Under TENANT_ISOLATION_STRICT, the sync ran with no async tenant context, so the tenant-isolation mongoose hooks threw on every Skill/SkillFile/AclEntry operation; in non-strict mode synced skills were written tenant-less and never matched tenant-scoped reads. Add an optional per-source tenantId to the skillSync config; when set, each source sync runs inside tenantStorage.run({ tenantId }) so skills, files, and public ACL grants are created and listed within that tenant, and the skill row is stamped with the tenantId for correct dedup. Sources without tenantId keep the prior single-tenant behavior. Avoids runAsSystem. Addresses Codex P2 (sync.js:70).
Lock/status/credential bookkeeping stays outside the tenant context (those collections are intentionally global).
* test: Restore dropped tenant-context coverage for GitHub skill sync
The prior commit shipped the getTenantId import in github.spec.ts without the tenant tests that use it (lost in an interrupted edit), which failed the eslint --max-warnings=0 CI job on an unused import. Restore both github.spec.ts tenant tests (tenant-scoped run stamps tenantId and executes inside the tenant ALS context; no-tenant run stays ambient) and the two config-schemas tenant tests (accepts tenantId, rejects __SYSTEM__).
* test: Restore dropped github.spec tenant-context tests
The previous commit's github.spec.ts edit did not apply (anchor mismatch), so the getTenantId import remained unused and failed eslint --max-warnings=0. Add the two tenant tests that use it: a tenant-scoped run stamps tenantId and executes inside the tenant ALS context, and a no-tenant run stays ambient.
* feat: Scope synced skill author to tenant and harden tenant-context sync
Addresses the latest Codex review on the per-source tenant change:
- makeSourceAuthorId now folds tenantId into the synthetic author hash so the
same source mirrored into different tenants gets distinct author ids (clearer
audits, no cross-tenant author collisions). Single-tenant author ids stay
stable (suffix omitted when tenantId is absent).
- syncSourceInTenantContext uses an async callback per the tenant-context
contract so the ALS store propagates across awaited Mongoose calls.
- Tests: same-source/different-tenant yields distinct authors; mirror cleanup
is scoped to the source and deletes only its absent-upstream skills.
* fix: Repair tsc error and guard external edits in github skill sync
- Fix TS2352 in github.spec mirror-cleanup test: build the existing-skill mock via makeSkill with authorName instead of an under-typed 'as CreateSkillInput' cast (this was the failing TypeScript CI check on
|
||
|
Danny Avila
|
470be2395f |
✨ feat: Surface Model Spec Branding on Landing and Selector (#13662)
Adds an opt-in showOnLanding flag to model specs. When set, the chat landing shows the spec's label and description in place of the time-of-day greeting; specs without the flag are unaffected, so existing deployments see no behavior change. HTML-valued descriptions (inline icons + markup) render sanitized via the shared config-HTML sanitizer with a new media tag/attribute allowlist, both on the landing and in model selector items. Excludes e2e specs from the typed client lint block so staged e2e files no longer fail pre-commit with 'file not found in project'. |
||
|
Danny Avila
|
7a8a18f07d |
🗝️ chore: Use Element Access over any-Casts in Registry Cache Spec (#13664)
The as-any casts existed only to reach the protected Keyv cache and private localSnapshotExpiry members. TypeScript's element-access escape hatch provides the same access fully typed, so the casts and their eslint-disable directives are unnecessary. The directives also reported as unused under configs that relax no-explicit-any for test files. |
||
|
Danny Avila
|
a52c82489e | 🚷 fix: Reject Client-Supplied Subagent Configuration (#13660) | ||
|
Danny Avila
|
eebbde777a | 📦 chore: Update Turbo package to v2.9.17 | ||
|
Danny Avila
|
0d24cbd496 |
🚪 fix: Align Mobile Sidebar Toggle Gating with JS Breakpoint Across Views (#13654)
* 🚪 fix: Align Mobile Sidebar Toggle Gating with JS Breakpoint Across Views * 🚪 fix: Sidebar Toggle on Read-Only Prompt Details View |
||
|
Ivan-Apro
|
dffd27f883 |
🎫 fix: Forward User Auth Headers on Model Fetch (#13616)
* 🔐 fix: Resolve template vars and respect custom Authorization on model fetch The custom-endpoint model fetch path in `fetchModels` had two bugs that silently broke per-user authentication on `GET /v1/models`: 1. Template variables in the configured `headers:` block were not substituted on the OpenAI-compatible branch. Only the Ollama branch ran `resolveHeaders`, so placeholders like `{{LIBRECHAT_OPENID_ID_TOKEN}}` were forwarded as literal strings on every other endpoint. 2. After spreading the (unresolved) headers into the request, the code unconditionally executed `options.headers.Authorization = \`Bearer ${apiKey}\`` and clobbered any `Authorization` the operator had set in `headers:`. Combined, these meant a config like ```yaml endpoints: custom: - name: "MyProxy" apiKey: "${MY_API_KEY}" headers: authorization: "Bearer {{LIBRECHAT_OPENID_ID_TOKEN}}" ``` sent `Authorization: Bearer ${MY_API_KEY}` on `/v1/models` instead of the user's resolved JWT — even with `OPENID_REUSE_TOKENS=true` set. Auth-aware proxies (e.g. LiteLLM with team-based JWT auth) therefore could not return a per-user filtered model list. This change runs `headers` through `resolveHeaders` (mirroring the Ollama branch) and only falls back to the apiKey-based default when the resolved headers do not already supply an `Authorization` (case-insensitive). All other endpoints behave unchanged: when no `Authorization` is configured, the existing `Bearer ${apiKey}` default still applies. Tests added: - Template variables in custom headers are resolved on the OpenAI path. - A config-supplied `Authorization` overrides the apiKey default. - The override check is case-insensitive (`authorization` works too). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * 🔐 fix: Address review — import order, P1 token leak guard, P2 token-config path - Fix sort-imports drift in `models.ts` and `custom/initialize.ts`. - P1: in `loadConfigModels` (`config/models.ts`), do not forward `endpointHeaders` to `fetchModels` when `baseURLIsUserProvided`. Configured templates such as `Authorization: Bearer {{LIBRECHAT_OPENID_ID_TOKEN}}` would otherwise resolve and be sent to a destination the user controls — leaking the user's identity token. Header overrides remain in place when only the apiKey is user-provided (admin-trusted base URL). - P2: in `initializeCustom` (`custom/initialize.ts`), the token-config fetch path now forwards `headers` and `userObject` to `fetchModels` (mirroring the auth-aware behaviour), with the same `userProvidesURL` guard. Additionally, when `endpointConfig.headers` is set the model cache is skipped to avoid a per-user filtered response leaking across users; token-config caching was already user-keyed when key/URL are user-provided. Tests added: - `config/models.spec.ts` (new): verifies the P1 guard — headers are dropped when the base URL is user-provided, and forwarded when only the apiKey is user-provided. - `custom/initialize.spec.ts`: three cases for the P2 path covering header forwarding to admin-trusted base URLs, header drop on user-provided base URLs, and absence of `skipCache` when no headers are configured. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * 🔐 fix: Scope model + token-config caches when user-bound headers are forwarded Two follow-up fixes from the second review pass: P1.1 (`fetchModels` / `models.ts`): the MODEL_QUERIES cache is keyed by baseURL+apiKey only. When callers forward headers containing template variables that resolve against the current user (e.g. `Authorization: Bearer {{LIBRECHAT_OPENID_ID_TOKEN}}`), one user's filtered list could be served to the next request that happens to share the same baseURL+apiKey. `shouldCache` now skips the cache whenever both `headers` and `userObject` are supplied — that's the unambiguous signal the response is being resolved against a specific user identity. Existing callers that pass neither (fetchOpenAIModels, fetchAnthropicModels) keep their cache. P1.2 (`initializeCustom` / `custom/initialize.ts`): the surrounding tokenConfigCache uses `tokenKey === endpoint` when key+URL are admin-configured. With user-bound headers forwarded, the first user's token config could be cached for the shared endpoint and served to other users until TTL. `tokenKey` is now also user-scoped when `endpointConfig.headers` will be forwarded (i.e. base URL is admin-trusted, so the security guard leaves headers in place). Also removed the explicit `skipCache: !!endpointConfig.headers` from the fetchModels call in initializeCustom — the new fetchModels-level rule covers it uniformly across both call sites. Tests added: - models.spec.ts: cache skipped on `headers + userObject`; cache used when only one of them is supplied (existing callers unaffected). - initialize.spec.ts: `tokenKey` is `${endpoint}:${userId}` when headers will be forwarded, and `endpoint` (unscoped) when no headers are configured. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * 🔐 fix: Include header fingerprint in in-request model fetch coalescing key `loadConfigModels` coalesces concurrent fetches for endpoints that share the same admin-trusted `${BASE_URL}__${API_KEY}` via `fetchPromisesMap`. With per-endpoint `headers:` overrides — including templates that resolve against the current user — that key is too coarse: two custom endpoints sharing a proxy URL/key but configuring different headers (e.g. distinct `X-Tenant` values, or different static `Authorization` strings) would share a single fetch promise, and the first endpoint's filtered response would be returned for the second endpoint within the same request. Fix: include a stable SHA-256 fingerprint of the configured headers in the coalescing key. Endpoints that genuinely share `baseURL + apiKey + headers` still share one fetch (preserves the existing optimisation); endpoints that differ in headers each get their own fetch. Test added in `config/models.spec.ts`: - Two endpoints sharing baseURL+apiKey but with different headers result in two `fetchModels` calls, each carrying the right headers. - Two endpoints sharing baseURL+apiKey AND identical headers still coalesce into a single `fetchModels` call. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Danny Avila
|
b4fa200e5f |
⏫ ci: Bump GitNexus to 1.6.7 to Fix Embeddings Index Timeout (#13658)
* ⏫ ci: Bump GitNexus to 1.6.7 to Fix Embeddings Index Timeout * ⏲️ ci: Raise GitNexus Index Timeout for 1.6.x Embedding Volume |
||
|
Danny Avila
|
4a9af12082 |
📐 fix: Sidebar Chat List Width Tracking and Stale Row Measurements (#13655)
* 📐 fix: Sidebar Chat List Width Tracking and Stale Row Measurements * ✅ test: Sidebar Chat List Width Tracking e2e Coverage * 🩹 fix: Address Review — Shrinkable List Wrapper, Seeded Measure, Fallback Resize * ✅ test: Scope Sidebar Grid Selector and Cover Height Shrink * 🧪 test: Settle Sidebar Sizes Before Asserting to Deflake CI |
||
|
Danny Avila
|
c27d6b85a4 |
🤫 refactor: Silent MCP OAuth Refresh on Mid-Session 401 (#13369)
* 🤫 fix: Silent MCP OAuth Refresh on Mid-Session 401 Avoids the hourly interactive re-auth prompt when an MCP server (e.g. Azure Entra ID) returns 401 mid-session by attempting a refresh token exchange first, and only falling back to the interactive OAuth flow when no refresh token is stored or the refresh server rejects it. Resolves #13364. * fix: Use distinct flow type for silent token refresh to avoid cache hit Addresses the Codex review on PR #13369: `attemptSilentTokenRefresh` was reusing the `'mcp_get_tokens'` flow type, so `FlowStateManager.createFlowWithHandler` would short-circuit and return the same tokens cached by an earlier `getOAuthTokens` call — the very tokens the server just rejected — without executing the forced-refresh handler. Switch silent refresh to the distinct `'mcp_force_refresh_tokens'` flow type so coalescing still works but stale `mcp_get_tokens` cache entries are not reused. After a successful refresh, invalidate the `mcp_get_tokens` flow cache so the next `getOAuthTokens` call reads the freshly persisted tokens from storage rather than the stale cached value. Add a regression test that simulates the real `FlowStateManager.createFlowWithHandler` cache-hit behavior for `mcp_get_tokens` and verifies the silent refresh handler still runs and returns the freshly refreshed tokens. * fix: Address Codex round-2 review on silent MCP OAuth refresh Three follow-up findings from Codex on PR #13369: 1. The new `mcp_force_refresh_tokens` flow type was itself cached by `FlowStateManager.createFlowWithHandler`, so a subsequent 401 within the refreshed token's `expires_at` could re-serve the just-rejected token without ever re-running the refresh handler. 2. The factory's `oauthRequired` listener was removed immediately after the initial `attemptToConnect` succeeded, so a real mid-session 401 emitted by `MCPConnection.connectClient` during transport recovery had no listener — the OAuth handled-promise would simply time out instead of triggering the silent refresh. 3. Routing the silent refresh through a distinct flow type broke coalescing with the `mcp_get_tokens` lock used by `getOAuthTokens`, letting two paths concurrently redeem the same stored refresh token. For providers that rotate refresh tokens (e.g. Azure Entra) the second redemption is rejected, kicking the user back into interactive OAuth despite a successful refresh elsewhere. Resolution: - Drop `FlowStateManager` from the silent-refresh path entirely. Replace with a process-local `inflightSilentRefreshes` Map keyed by `userId:serverName` that holds only the in-flight Promise (no cached result), so every fresh 401 after settlement triggers a fresh redemption while concurrent 401s for the same user/server still share one redemption. - Stop calling `cleanupOAuthHandlers()` on successful initial connect, keeping the OAuth handler attached for the connection's lifetime so mid-session 401s actually reach `attemptSilentTokenRefresh`. - Add a regression test reproducing the stale-cache scenario by faking the `mcp_get_tokens` cache hit and asserting silent refresh still runs against storage and returns the fresh tokens. - Add a coalescing test asserting two concurrent oauthRequired events for the same user/server result in a single `forceRefreshTokens` call. - Clear `inflightSilentRefreshes` in `beforeEach` to prevent cross-test leakage; switch the silent-refresh test mocks to `mockResolvedValueOnce` / `mockImplementationOnce` so leftover mock state cannot leak into later test cases. Acknowledged remaining gap: the silent refresh still races `getOAuthTokens`'s `mcp_get_tokens` flow when both run concurrently (narrow window when an existing connection's local `expires_at` is still valid but the server invalidated the token, and a new connection is being created in parallel). The race is self-healing on the next 401 and documented inline. * fix: Address Codex round-3 review on silent MCP OAuth refresh Three more findings from Codex on PR #13369: 1. The in-flight silent-refresh promise was unbounded. If `forceRefreshTokens()` ever hung (slow provider, dropped TCP), the `inflightSilentRefreshes` lock stayed occupied forever and every later 401 for the same user/server joined the stuck promise instead of starting a fresh attempt or falling back to interactive OAuth. 2. The interactive-OAuth fallback didn't invalidate the `mcp_get_tokens` flow cache after persisting fresh tokens. For providers that don't issue refresh tokens (so silent refresh returns null), the old cache could still feed stale access tokens to the next `getOAuthTokens` call until its TTL expired — causing an immediate reconnect with the same just-rejected token. 3. When silent refresh failed, the handler fell through to `handleOAuthRequired()` whose recent-completion fast path can reuse a COMPLETED `mcp_oauth` flow within `PENDING_STALE_MS`. Those cached tokens are exactly the ones the server just rejected, so the connection would keep adopting them and looping on 401s until the cache aged out. Resolution: - Wrap `runSilentRefresh()` with a 60-second `withTimeout` (well under `connectClient`'s 120s OAuth timeout). On timeout the `.catch` resolves to null and the `finally` clears the in-flight entry, so the next 401 starts fresh and falls through to interactive OAuth. - Extract two helpers — `invalidateGetTokensFlow` and `invalidateCompletedOAuthFlow` — and call them from the right branches: clear `mcp_get_tokens` after silent-refresh success AND after interactive-OAuth `storeTokens`; clear the COMPLETED `mcp_oauth` state (plus its CSRF mapping) before falling through to interactive OAuth so the fast-reuse path can't re-serve the rejected tokens. - Add three regression tests: hung refresh release-the-lock under fake timers, completed-OAuth cache invalidation pre-fallback, and `mcp_get_tokens` invalidation after interactive token store. * fix: Address Codex round-4 review on silent MCP OAuth refresh Three more findings from Codex on PR #13369: 1. (P1) The silent-refresh in-flight lock keyed only by `userId:serverName`. In multi-tenant setups where two tenants share a userId (e.g. username-based IDs) and the same MCP server name, a concurrent mid-session 401 from tenant B would join tenant A's in-flight refresh and adopt tenant A's freshly minted tokens onto a tenant-B connection — a cross-tenant credential leak. 2. (P2) `invalidateGetTokensFlow` deleted the `mcp_get_tokens` flow state regardless of its status. When another connection was currently in `getOAuthTokens()` (PENDING flow) and joiners were monitoring it, the unconditional delete made those waiters see "Flow state not found" and unnecessarily fall back to interactive OAuth — even though fresh tokens were already being written. 3. (P2) The 60s `withTimeout` wrapping `runSilentRefresh()` only races the promise; it does not cancel the underlying `forceRefreshTokens` / refresh-token HTTP request. If the request returned after a subsequent interactive OAuth had stored newer tokens, the late completion would `storeTokens` over the newer state. This requires a provider that doesn't rotate refresh tokens AND a refresh slower than 60s AND a successful interactive OAuth in that window — narrow but real. Resolution: - Capture `getTenantId()` into a new `factory.tenantId` field at factory construction time (before the OAuth handler closes over it outside the original request's async context) and include it in the silent-refresh lock key as `tenantId:userId:serverName`. - `invalidateGetTokensFlow` now calls `getFlowState` first and only deletes when `status === 'COMPLETED'`. PENDING lookups are left alone so concurrent `getOAuthTokens` waiters via `monitorFlow` can still settle. - For (3), document the race as a known limitation inline. Fully closing it requires threading an `AbortSignal` through `MCPTokenStorage.forceRefreshTokens` and the OAuth refresh handler to skip the late `storeTokens` after timeout — out of scope for this PR's surgical change. - Add `getTenantId` to the `MCPOAuthConnectionEvents` test's `@librechat/data-schemas` mock so the factory constructor doesn't blow up under that suite. - Add three regression tests: per-tenant lock isolation, PENDING-state preservation under `invalidateGetTokensFlow`, and (reused) the existing interactive-store invalidation test now driven through `getFlowState` returning the COMPLETED state. * fix: Address silent MCP OAuth refresh review Restore captured tenant context around token storage and OAuth fallback paths so mid-session callbacks do not lose tenant scope. Thread AbortSignal through forced refresh and OAuth token requests, cap silent refresh by the connection OAuth timeout, and prevent timed-out refreshes from writing stale credentials after fallback. Complete pending mcp_get_tokens flows with fresh tokens, add missing FlowState createdAt test fixtures, and cover the new tenant/abort/cache behaviors. * fix: Tighten tenant-scoped MCP token refresh Cap silent refresh by both the factory connect timeout and the connection OAuth wait timeout so fallback OAuth wins before the outer connect attempt expires. Tenant-scope mcp_get_tokens flow ids for both token lookup and refresh invalidation, preventing cross-tenant flow completion or cache deletion when tenants share user ids and server names. Add regression tests for the omitted initTimeout budget and tenant-prefixed token flow locks. * fix: Reserve MCP OAuth fallback budget * fix: Harden MCP OAuth refresh races * fix: Keep MCP OAuth fallback route-compatible * test: Add SDK MCP OAuth refresh repro * fix: Address MCP OAuth refresh review findings * fix: Address MCP OAuth tenant review findings * fix: Close MCP OAuth route tenant gaps * fix: Preserve MCP OAuth refresh flow guards * fix: Avoid reprocessing MCP OAuth reauth config * fix: Release timed-out MCP refresh locks * fix: Release MCP OAuth request callbacks * fix: Tenant-scope remaining MCP OAuth flow lookups * ci: Sort imports in MCP OAuth test suites |
||
|
Ravi Kumar L
|
865e1da857 |
⚙️ refactor: lazy-load React Query Devtools (#13639)
* perf(client): lazy-load query devtools * fix: keep query devtools deps lazy * fix: address query devtools review findings * fix: exclude query devtools from pwa precache --------- Co-authored-by: Danny Avila <danny@librechat.ai> |
||
|
Danny Avila
|
d91cec2101 | 🤗 ci: Cache and Authenticate HF Model Downloads in GitNexus Index (#13653) | ||
|
Danny Avila
|
fe7bf39d9f |
🗜️ ci: Cache Dependencies and Builds in Cache Integration Tests (#13652)
* 🗜️ ci: Cache Dependencies and Builds in Cache Integration Tests Port the node_modules and package-dist caching pattern from backend-review.yml to cache-integration-tests.yml, which ran a full npm ci (~72s) and rebuilt data-provider, data-schemas, and api on every run. Cache keys are identical to backend-review.yml so the two workflows share entries. Drops setup-node's npm tarball cache, superseded by the node_modules restore, matching backend-review.yml. * 🗜️ ci: Exercise Warm-Cache Path |
||
|
Danny Avila
|
87cdd37932 |
🧭 fix: Mobile Sidebar Navigation on Projects View (#13647)
* 🧭 fix: Mobile Sidebar Navigation on Projects View * 🧭 fix: Align Sidebar Toggle with JS Mobile Breakpoint at 768px |
||
|
Teresa Blanco
|
9628930958 |
✅ ci: Add mock e2e coverage for agents, prompts, MCP, and chat flows (#13589)
* ✅ Add mock e2e coverage for agents, prompts, MCP, and chat flows * 🎯 fix: Change enforce modelSpecs to false --------- Co-authored-by: Danny Avila <danny@librechat.ai> |
||
|
Dustin Healy
|
5867f1a065 |
🛡️ feat: Configurable Message PII Filter (#13602)
* 🛡️ feat: Reject chat messages matching configured credential patterns
Adds an opt-in `messagePiiFilter` middleware mounted on the agent
chat route ahead of `moderateText`. When the configured patterns
match the user's input the request is refused with 400, so the
credential never reaches OpenAI moderation, the model, or MongoDB.
Three starter patterns ship by default and operators can subset
them or add their own regex via `customPatterns` in librechat.yaml.
* 🧪 test: Memoize compiled patterns + add middleware spec
Memoize the compiled pattern array via a WeakMap keyed by the
messagePiiFilter config object so repeat requests against the same
config skip the per-request RegExp construction. Cache entries are
released automatically when the config object itself rotates.
Adds packages/api/src/middleware/messagePiiFilter.spec.ts covering
the default-starter rejections, the starterPatterns subset and
empty-array semantics, customPatterns matching layered on top of and
in place of the starters, the no-config and empty-text pass-through
paths, and a memoization regression check.
* 🛡️ fix: Skip invalid customPattern regexes instead of crashing the request
Admin DB overrides for `messagePiiFilter.customPatterns` reach
`req.config` via `mergeConfigOverrides`, which deep-merges raw
override values without re-running `configSchema`. A typo'd regex
like `(` would slip past the YAML-load validation and throw inside
`new RegExp(...)` during `compile()`, returning 500 for every chat
request until the operator rolled the override back.
Wrapped the per-pattern compile in a try/catch that logs the
invalid pattern id + reason and skips it, so other valid patterns
(starters and other custom entries) keep filtering. Added a
regression test alongside the existing spec.
* 🛡️ feat: Extend PII filter to OpenAI-compatible and Responses agent APIs
The chat-route middleware operates on `req.body.text`, but the remote
agent API endpoints (`/api/agents/v1/chat/completions`,
`/api/agents/v1/responses`) accept the same prompt content as a
`messages` array or an `input` field. A caller using their API key
could send a credential-shaped value through either route and bypass
the configured PII filter even though they share the same agent and
model backbone the middleware is meant to guard.
Factored out `findPiiMatchInMessages`, a tolerant walker that handles
both `content: string` and `content: ContentPart[]` user-message
shapes against the same compiled, cached pattern list. Wired it into
the OpenAI-compat controller after agent lookup and into the
Responses controller right after `convertToInternalMessages`. Each
returns the endpoint's native 400 error shape
(`sendErrorResponse` / `sendResponsesErrorResponse`) with the
`message_pii_filter_block` code when a user message matches.
* 🩹 test: Add findPiiMatchInMessages to OpenAI + Responses controller mocks
The OpenAI-compat and Responses controller specs mock `@librechat/api`
with a hand-listed object. The new `findPiiMatchInMessages` export
wired into both controllers in
|
||
|
Danny Avila
|
70f7450bab |
🪟 ci: Shard Windows Frontend Unit Tests (#13651)
* 🪟 ci: Shard Windows Frontend Unit Tests Mirror the 4-way jest sharding the Ubuntu frontend test job already uses onto the Windows job, which currently runs the whole client suite in a single 20-minute job. Also drops the `--verbose` flag, which npm consumed itself (it preceded `--`) and only raised npm's own log level. * 🪟 ci: Trigger Frontend Tests on Workflow Changes |
||
|
Danny Avila
|
56281ece30 |
🚰 ci: Close Leaked Redis Clients in Cache Integration Tests (#13649)
* 🧹 fix: Close Leaked Redis Clients in Cache Integration Tests Importing `redisClients` constructs and connects BOTH `ioredisClient` and `keyvRedisClient` as module side effects, but most cache/mcp integration specs disconnected at most one of them — and specs that re-import the module per test via `jest.resetModules()` leaked a fresh pair of connected clients (sockets + ping timers) for every test. On runners where jest resolves to a single worker (2-core machines with `maxWorkers: '50%'`), the suite runs in-band and the leaked handles keep the main process alive after all tests pass — the run hangs until the CI job timeout. On larger runners jest recovers only by force-exiting the leaked worker ("A worker process has failed to exit gracefully..."). - add a `closeRedisClients()` test helper that settles the connect promise and closes both clients of a `redisClients` module instance - call it from every cache/mcp integration spec that creates clients, mirroring what LeaderElection.cache_integration.spec.ts already does - remove the rethrow in the `keyvRedisClientReady.catch(...)` logging handler — rethrowing inside `.catch` creates a new, never-observed rejected promise, turning any failed initial connect into a guaranteed unhandled rejection; callers awaiting `keyvRedisClientReady` still observe the original rejection All four `test:cache-integration` stages now pass AND exit cleanly with `--maxWorkers=1` against both single-node and cluster Redis, with no force-exit warning in worker mode. * 🧹 chore: Treat testRedisOperations as Assertion in expect-expect Rule * 🗂️ chore: Sort Imports per Repo Convention |
||
|
Danny Avila
|
da6b74e8eb |
🪶 fix: Prevent Soft Default Model Spec from Overriding User Selections (#13642)
* 🎯 fix: Soft Default Model Spec Overriding User Selections * 🎯 fix: Detect Agents-Only Allow-List Before Endpoints Config Loads * 🎯 fix: Preserve Explicit Soft Default Selections over Older History * 🎯 fix: Limit Soft Default Residue to Spec-Named State, Disable E2E Enforcement |
||
|
Ravi Kumar L
|
346ebea2d9 | ⚙️ refactor: brotli asset serving behind a feature toggle (#13641) | ||
|
Ravi Kumar L
|
db863e75e3 | ⚙️ refactor: Lazy load locale resources (#13640) |