test(video): reproduce Kiro malformed payload retention

test(auto-combo): tolerate full-suite rotation load

@omniroute/opencode-plugin/package.json

@@ -23,7 +23,7 @@
   "scripts": {
     "build": "tsup",
     "clean": "rm -rf dist",
-    "test": "node --import tsx/esm --test tests/scaffold.test.ts tests/auth.test.ts tests/options-schema.test.ts tests/multi-instance.test.ts tests/fetch-interceptor.test.ts tests/provider.test.ts tests/gemini-sanitize.test.ts tests/combos.test.ts tests/config-shim.test.ts tests/features.test.ts tests/feature-defaults.test.ts tests/usable-combo.test.ts tests/disk-snapshot-perms.test.ts tests/fork-features.test.ts tests/auto-combo-context.test.ts tests/provider-id-routing.test.ts tests/management-read-token.test.ts tests/auto-sync.test.ts tests/model-allowlist.test.ts tests/log-level.test.ts tests/effort-tier-variants.test.ts",
+    "test": "node --import tsx/esm --test tests/scaffold.test.ts tests/auth.test.ts tests/options-schema.test.ts tests/multi-instance.test.ts tests/fetch-interceptor.test.ts tests/provider.test.ts tests/gemini-sanitize.test.ts tests/combos.test.ts tests/config-shim.test.ts tests/features.test.ts tests/feature-defaults.test.ts tests/usable-combo.test.ts tests/disk-snapshot-perms.test.ts tests/fork-features.test.ts tests/auto-combo-context.test.ts tests/provider-id-routing.test.ts tests/management-read-token.test.ts tests/auto-sync.test.ts tests/model-allowlist.test.ts tests/log-level.test.ts tests/effort-tier-variants.test.ts tests/naming.test.ts tests/free-budget-magnitude.test.ts",
     "prepublishOnly": "npm run clean && npm run build && npm test"
   },
   "keywords": [

@omniroute/opencode-plugin/src/naming.ts

@@ -23,27 +23,11 @@ const ALIAS_UPPER_MAX_CHARS = 5;
 
 // ── Auto Combo Types ─────────────────────────────────────────────────────
 
-export type AutoVariant =
-  | "coding"
-  | "fast"
-  | "cheap"
-  | "offline"
-  | "smart"
-  | "lkgp";
+export type AutoVariant = "coding" | "fast" | "cheap" | "offline" | "smart" | "lkgp";
 
-export const AUTO_VARIANTS: AutoVariant[] = [
-  "coding",
-  "fast",
-  "cheap",
-  "offline",
-  "smart",
-  "lkgp",
-];
+export const AUTO_VARIANTS: AutoVariant[] = ["coding", "fast", "cheap", "offline", "smart", "lkgp"];
 
-export const AUTO_VARIANT_DESCRIPTIONS: Record<
-  AutoVariant | "default",
-  string
-> = {
+export const AUTO_VARIANT_DESCRIPTIONS: Record<AutoVariant | "default", string> = {
   default: "Best provider via scoring",
   coding: "Quality-first for code tasks",
   fast: "Latency-optimized routing",
@@ -83,24 +67,15 @@ function titleCaseAlias(alias: string): string {
  *   3. Neither → undefined.
  */
 export function shortProviderLabel(
-  enrichment:
-    | { providerDisplayName?: string; providerAlias?: string }
-    | undefined,
+  enrichment: { providerDisplayName?: string; providerAlias?: string } | undefined
 ): string | undefined {
   if (!enrichment) return undefined;
   const raw =
-    typeof enrichment.providerDisplayName === "string"
-      ? enrichment.providerDisplayName.trim()
-      : "";
+    typeof enrichment.providerDisplayName === "string" ? enrichment.providerDisplayName.trim() : "";
   if (raw.length > 0 && raw.length <= PROVIDER_LABEL_MAX_CHARS) return raw;
-  const alias =
-    typeof enrichment.providerAlias === "string"
-      ? enrichment.providerAlias.trim()
-      : "";
+  const alias = typeof enrichment.providerAlias === "string" ? enrichment.providerAlias.trim() : "";
   if (alias.length > 0) {
-    return alias.length <= ALIAS_UPPER_MAX_CHARS
-      ? alias.toUpperCase()
-      : titleCaseAlias(alias);
+    return alias.length <= ALIAS_UPPER_MAX_CHARS ? alias.toUpperCase() : titleCaseAlias(alias);
   }
   // Long displayName with no alias to fall back on: keep the long label
   // rather than dropping the provider prefix entirely.
@@ -131,10 +106,33 @@ export function normaliseFreeLabel(name: string): string {
 
 // ── Free Budget Formatting ────────────────────────────────────────────────
 
+/** Scales, largest first, so the unit is chosen by descending magnitude. */
+const TOKEN_UNITS = [
+  [1e9, "B"],
+  [1e6, "M"],
+  [1e3, "K"],
+] as const;
+
+/**
+ * Format a token count as a short magnitude string: `25M`, `1.5K`, `999`.
+ *
+ * The unit has to be picked from the value that will actually be *printed*,
+ * not from the raw input. `toFixed(1)` rounds to the nearest tenth, so at the
+ * K scale 999_950 and above render as `1000.0` — and by then the M branch has
+ * already been skipped, producing `1000K` for a number that is `1M`. The same
+ * carry turns just under a billion into `1000M`. When the rounded value reaches
+ * the next scale, re-render at that scale instead.
+ */
 function fmtTokens(n: number): string {
-  if (n >= 1e9) return (n / 1e9).toFixed(1).replace(/\.0$/, "") + "B";
-  if (n >= 1e6) return (n / 1e6).toFixed(1).replace(/\.0$/, "") + "M";
-  if (n >= 1e3) return (n / 1e3).toFixed(1).replace(/\.0$/, "") + "K";
+  for (let i = 0; i < TOKEN_UNITS.length; i++) {
+    const [scale, suffix] = TOKEN_UNITS[i]!;
+    if (n < scale) continue;
+    const value = Number((n / scale).toFixed(1));
+    // `Number()` also drops a trailing `.0`, which the previous regex did.
+    if (value < 1000 || i === 0) return `${value}${suffix}`;
+    const [nextScale, nextSuffix] = TOKEN_UNITS[i - 1]!;
+    return `${Number((n / nextScale).toFixed(1))}${nextSuffix}`;
+  }
   return String(n);
 }
 
@@ -184,15 +182,11 @@ export function formatFreeBudget(params: {
  */
 export function formatAutoComboName(
   variant: AutoVariant | undefined,
-  candidateCount?: number,
+  candidateCount?: number
 ): string {
-  const label = variant
-    ? variant.charAt(0).toUpperCase() + variant.slice(1)
-    : "Default";
+  const label = variant ? variant.charAt(0).toUpperCase() + variant.slice(1) : "Default";
   const count =
-    typeof candidateCount === "number" && candidateCount > 0
-      ? ` (${candidateCount}p)`
-      : "";
+    typeof candidateCount === "number" && candidateCount > 0 ? ` (${candidateCount}p)` : "";
   return `Auto: ${label}${count}`;
 }
 

@omniroute/opencode-plugin/tests/free-budget-magnitude.test.ts

@@ -0,0 +1,78 @@
+/**
+ * Magnitude-crossover regression for the free-budget suffix
+ * (`formatFreeBudget` -> `fmtTokens` in @omniroute/opencode-plugin/src/naming.ts).
+ *
+ * `fmtTokens` picked its unit from the raw input and then rounded with
+ * `toFixed(1)`. Rounding can carry a value into the next magnitude *after* that
+ * branch has been skipped, so 999_950..999_999 rendered as "1000K" rather than
+ * "1M", and just under a billion rendered as "1000M" rather than "1B".
+ *
+ * These budgets are not always round numbers: `monthlyTokens` is derived from the
+ * remote Radar feed (`tokensPerMonth`) and can be replaced wholesale by a
+ * user-local override, so the crossover band is reachable with real data.
+ *
+ * Kept in its own file rather than added to naming.test.ts so this does not
+ * collide with the coverage being added for `formatFreeBudget` in #11660.
+ */
+
+import { test } from "node:test";
+import assert from "node:assert/strict";
+
+import { formatFreeBudget } from "../src/naming.js";
+
+/** `recurring-daily` is the shortest path from a token count to a rendered suffix. */
+const daily = (monthlyTokens: number) =>
+  formatFreeBudget({ freeType: "recurring-daily", monthlyTokens }).replace(" tokens/day", "");
+
+test("fmtTokens: a rounded K value that reaches 1000 is promoted to M", () => {
+  // 999_950 is the true boundary, not 999_999: toFixed(1) rounds to the nearest
+  // tenth, so 999.95K is the first value that carries to "1000.0".
+  assert.equal(daily(999_950), "1M");
+  assert.equal(daily(999_999), "1M");
+});
+
+test("fmtTokens: a rounded M value that reaches 1000 is promoted to B", () => {
+  assert.equal(daily(999_950_000), "1B");
+  assert.equal(daily(999_999_999), "1B");
+});
+
+test("fmtTokens: values just below the rounding boundary keep their own unit", () => {
+  // The promotion must not fire early — 999.9K still rounds to 999.9, not 1000.
+  assert.equal(daily(999_949), "999.9K");
+  assert.equal(daily(999_499), "999.5K");
+  assert.equal(daily(999_499_999), "999.5M");
+});
+
+test("fmtTokens: ordinary magnitudes are unchanged", () => {
+  assert.equal(daily(0), "0");
+  assert.equal(daily(999), "999");
+  assert.equal(daily(1_000), "1K");
+  assert.equal(daily(1_500), "1.5K");
+  assert.equal(daily(1_000_000), "1M");
+  assert.equal(daily(1_500_000), "1.5M");
+  assert.equal(daily(25_000_000), "25M");
+  assert.equal(daily(1_234_567), "1.2M");
+  assert.equal(daily(1_000_000_000), "1B");
+  assert.equal(daily(2_500_000_000), "2.5B");
+});
+
+test("fmtTokens: B is the top unit, so a carry there has nowhere to go", () => {
+  // Deliberately pinned: promoting past B would need a unit that does not exist,
+  // so "1000B" is the intended output rather than an oversight.
+  assert.equal(daily(999_999_999_999), "1000B");
+});
+
+test("formatFreeBudget: the promotion applies to every token-bearing branch", () => {
+  assert.equal(
+    formatFreeBudget({ freeType: "recurring-monthly", monthlyTokens: 999_999 }),
+    "1M tokens/month"
+  );
+  assert.equal(
+    formatFreeBudget({ freeType: "recurring-credit", creditTokens: 999_999 }),
+    "1M credits"
+  );
+  assert.equal(
+    formatFreeBudget({ freeType: "one-time-initial", creditTokens: 999_999 }),
+    "1M credits (one-time)"
+  );
+});

@omniroute/opencode-plugin/tests/naming.test.ts

@@ -0,0 +1,81 @@
+/**
+ * Tests for `formatFreeBudget` (@omniroute/opencode-plugin/src/naming.ts):
+ * formats a free-tier model's budget info into a short human-readable
+ * suffix, branching on `freeType`.
+ */
+
+import { test } from "node:test";
+import assert from "node:assert/strict";
+
+import { formatFreeBudget, type FreeModelFreeType } from "../src/naming.js";
+
+test("formatFreeBudget: recurring-daily formats tokens/day", () => {
+  assert.equal(
+    formatFreeBudget({ freeType: "recurring-daily", monthlyTokens: 25_000_000 }),
+    "25M tokens/day"
+  );
+});
+
+test("formatFreeBudget: recurring-monthly formats tokens/month", () => {
+  assert.equal(
+    formatFreeBudget({ freeType: "recurring-monthly", monthlyTokens: 1_000_000 }),
+    "1M tokens/month"
+  );
+});
+
+test("formatFreeBudget: recurring-credit formats credits", () => {
+  assert.equal(
+    formatFreeBudget({ freeType: "recurring-credit", creditTokens: 10_000_000 }),
+    "10M credits"
+  );
+});
+
+test("formatFreeBudget: one-time-initial formats credits with (one-time) suffix", () => {
+  assert.equal(
+    formatFreeBudget({ freeType: "one-time-initial", creditTokens: 1_000_000 }),
+    "1M credits (one-time)"
+  );
+});
+
+test("formatFreeBudget: keyless has no token/credit args", () => {
+  assert.equal(formatFreeBudget({ freeType: "keyless" }), "(keyless)");
+});
+
+test("formatFreeBudget: discontinued has no token/credit args", () => {
+  assert.equal(formatFreeBudget({ freeType: "discontinued" }), "(discontinued)");
+});
+
+test("formatFreeBudget: missing token/credit counts default to 0", () => {
+  assert.equal(
+    formatFreeBudget({ freeType: "recurring-daily" }),
+    "0 tokens/day"
+  );
+});
+
+test("formatFreeBudget: unrecognised freeType falls through to the default branch", () => {
+  // `freeType` is populated from catalog data at runtime, so a value the
+  // build doesn't know about is reachable even though TypeScript treats the
+  // `default:` arm as dead code for a well-typed caller.
+  assert.equal(
+    formatFreeBudget({ freeType: "some-future-type" as FreeModelFreeType }),
+    ""
+  );
+});
+
+test("formatFreeBudget: sub-1K token count is not abbreviated", () => {
+  assert.equal(
+    formatFreeBudget({ freeType: "recurring-daily", monthlyTokens: 500 }),
+    "500 tokens/day"
+  );
+});
+
+test("formatFreeBudget: the 999_999 rounding wart is fixed — promotes to 1M", () => {
+  // `toFixed(1)` rounds 999999/1e3 up to "1000.0" before the `>= 1e6` threshold
+  // check has a chance to apply. fmtTokens now promotes a rounded-up "1000" in
+  // any unit to the next unit up, so this correctly reads "1M" instead of the
+  // old "1000K" wart.
+  assert.equal(
+    formatFreeBudget({ freeType: "recurring-daily", monthlyTokens: 999_999 }),
+    "1M tokens/day"
+  );
+});

AGENTS.md

@@ -46,7 +46,7 @@ Repository map and Reference Documentation sections below.
 
 ## Project at a Glance
 
-**OmniRoute** — unified AI proxy/router. One endpoint, 354 LLM providers, auto-fallback.
+**OmniRoute** — unified AI proxy/router. One endpoint, 357 LLM providers, auto-fallback.
 
 | Layer         | Location                | Purpose                                                                                                                                                                   |
 | ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

Dockerfile

@@ -184,19 +184,29 @@ ENV NODE_OPTIONS="--max-old-space-size=${OMNIROUTE_BUILD_MEMORY_MB}"
 # silently leaving no standalone bundle. Next derives the worker count from
 # CIRCLE_NODE_TOTAL (workers = N-1). (#10060)
 #
-# Lowered 8 → 3 (7 workers → 2). Every page-data worker inherits NODE_OPTIONS
-# above, so the ceiling is per PROCESS, not per build: 7 workers on a 16 GB
-# GitHub runner (ubuntu-24.04 / ubuntu-24.04-arm, 4 vCPU) exhausted the host and
-# buildkit failed the whole step with `ResourceExhausted: ... cannot allocate
-# memory`. The compile phase always finished ("✓ Compiled successfully in
-# 4.2min"); the kernel killed the build right after "Collecting page data using
-# 7 workers". It was intermittent for a while and went 100% on 2026-08-22, which
-# is what a threshold being crossed by ordinary codebase growth looks like.
-# tests/unit/docker-build-memory-budget.test.ts does the arithmetic and fails if
-# either knob is raised past what a 16 GB runner holds. 2 workers also stops
-# oversubscribing the runner's 4 vCPU, which 7 did. Override for a big builder:
-# `--build-arg OMNIROUTE_BUILD_WORKERS=8`.
-ARG OMNIROUTE_BUILD_WORKERS=3
+# Lowered 8 → 3 (7 workers → 2) in #11419, then 3 → 2 (2 workers → 1) in #7518.
+# Every page-data worker inherits NODE_OPTIONS above, so the ceiling is per
+# PROCESS, not per build: 7 workers on a 16 GB GitHub runner (ubuntu-24.04 /
+# ubuntu-24.04-arm, 4 vCPU) exhausted the host and buildkit failed the whole
+# step with `ResourceExhausted: ... cannot allocate memory`. The compile phase
+# always finished ("✓ Compiled successfully in 4.2min"); the kernel killed the
+# build right after "Collecting page data using N workers".
+#
+# #11419's first fix (8 → 3) modeled the per-worker peak as an INFERENCE
+# (2560 MB, guessed from "7 workers didn't fit") and assumed the parent
+# process's RSS tracked the V8 heap ceiling. Both assumptions were wrong: a
+# live VPS reproduction (issue #7518, dmesg OOM-killer report) measured the
+# real per-process RSS directly at ~4.5 GB, independent of the NODE_OPTIONS
+# heap flag (Turbopack itself is native/Rust, outside the V8 heap) — and it
+# applies to the parent process too, not just workers. 2 workers (3 processes
+# × 4.5 GB = 13.5 GB) still didn't fit the 12.288 GB (75%) budget on a 16 GB
+# runner, matching the still-live publish failures after #11419 merged. 1
+# worker (2 processes × 4.5 GB = 9 GB) fits with headroom to spare.
+# tests/unit/docker-build-memory-budget.test.ts does the arithmetic against
+# the measured figure and fails if either knob is raised past what a 16 GB
+# runner holds. Override for a big builder: `--build-arg
+# OMNIROUTE_BUILD_WORKERS=8`.
+ARG OMNIROUTE_BUILD_WORKERS=2
 ENV CIRCLE_NODE_TOTAL=${OMNIROUTE_BUILD_WORKERS}
 
 COPY . ./

README.md

@@ -7,7 +7,7 @@
 
 # 🚀 OmniRoute — The Free AI Gateway
 
-<img src="./docs/diagrams/readme-hero.svg" width="100%" alt="OmniRoute — Never stop coding. Every AI tool → 353 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini with auto-fallback. RTK + Caveman stacked compression saves 15–95% tokens (~89% avg) — never hit limits. 353 AI providers · 90+ free tiers · ~1.51B free tokens/mo · 19 routing strategies · $0 to start."/>
+<img src="./docs/diagrams/readme-hero.svg" width="100%" alt="OmniRoute — Never stop coding. Every AI tool → 357 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini with auto-fallback. RTK + Caveman stacked compression saves 15–95% tokens (~89% avg) — never hit limits. 357 AI providers · 90+ free tiers · ~1.51B free tokens/mo · 19 routing strategies · $0 to start."/>
 
 </div>
 
@@ -210,7 +210,7 @@ curl http://localhost:20128/v1/chat/completions \
 
 </div>
 
-<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint and 353 providers. Automatic fallback keeps routing while another healthy target is available. Six pillars: resilient fallback across 353 providers · up to 95% token savings on eligible workloads · $0 to start with 90+ free tiers and 56 recurring/keyless free-forever providers · 35 CLI/agent integrations through one config · OpenAI, Claude, Gemini and Responses API compatibility at /v1 · production controls including circuit breakers, TLS stealth, MCP 110 tools, A2A, memory, guardrails, evals and 39,000+ static test declarations across 5,100+ tracked test files."/>
+<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint and 357 providers. Automatic fallback keeps routing while another healthy target is available. Six pillars: resilient fallback across 357 providers · up to 95% token savings on eligible workloads · $0 to start with 90+ free tiers and 56 recurring/keyless free-forever providers · 35 CLI/agent integrations through one config · OpenAI, Claude, Gemini and Responses API compatibility at /v1 · production controls including circuit breakers, TLS stealth, MCP 110 tools, A2A, memory, guardrails, evals and 39,000+ static test declarations across 5,100+ tracked test files."/>
 
 <br/>
 <br/>
@@ -461,7 +461,7 @@ All **19** strategies — mix & match per combo step:
 
 </div>
 
-<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — a dated feature snapshot vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 353 providers, 90+ free tiers built in, 19 routing strategies, 12-engine token compression, built-in MCP server with 110 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA and 43 i18n UI locales. OmniRoute is MIT-licensed and self-hostable. Competitor capabilities and counts may change; see the linked methodology."/>
+<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — a dated feature snapshot vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 357 providers, 90+ free tiers built in, 19 routing strategies, 12-engine token compression, built-in MCP server with 110 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA and 43 i18n UI locales. OmniRoute is MIT-licensed and self-hostable. Competitor capabilities and counts may change; see the linked methodology."/>
 
 <sub>📊 Full methodology &amp; per-feature detail vs 9router, OpenRouter, CLIProxyAPI &amp; LiteLLM → [`docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md`](docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md)</sub>
 
@@ -559,7 +559,7 @@ the current catalog at **[radar.omniroute.online/planos](https://radar.omniroute
 - **🖼️ New endpoints** — `/v1/ocr` (Mistral OCR) and `/v1/audio/translations` (Whisper-style) round out the media surface. → [API Reference](docs/reference/API_REFERENCE.md)
 - **🎨 Image / video / audio generation** — one API for media: xAI Grok Imagine & Novita AI video, ComfyUI, Freepik, Adobe Firefly, Microsoft Designer, Segmind, EdgeTTS. → [API Reference](docs/reference/API_REFERENCE.md)
 - **🌍 Deployment & ops** — reverse-proxy `basePath`, browser-language auto-detect, per-key device tracking, root-less MITM trust, zh-TW localization. → [Environment](docs/reference/ENVIRONMENT.md)
-- **🤝 More providers & agents** — Cursor Cloud Agent, Grok Build (xAI) with browser + OAuth login, Ollama first-class card, Claude Opus 5 & Sonnet 5, Kimi official partnership (Code/Web/Moonshot), Zed, Requesty, SenseNova, Yuanbao, Agnes AI… and a refreshed **353-provider catalog**. → [Providers](docs/reference/PROVIDER_REFERENCE.md)
+- **🤝 More providers & agents** — Cursor Cloud Agent, Grok Build (xAI) with browser + OAuth login, Ollama first-class card, Claude Opus 5 & Sonnet 5, Kimi official partnership (Code/Web/Moonshot), Zed, Requesty, SenseNova, Yuanbao, Agnes AI… and a refreshed **357-provider catalog**. → [Providers](docs/reference/PROVIDER_REFERENCE.md)
 - **📡 Routing transparency** — every response carries an `X-OmniRoute-Decision` header naming the strategy/provider/latency that served it, a new `cache-optimized` combo strategy + Auto-Combo `cacheAffinity` factor route repeat requests back to the connection holding the cached prefix, and a read-only `/v1/auto-combo/{channel}/candidates` endpoint exposes an `auto/*` channel's live candidate pool. → [Auto-Combo](docs/routing/AUTO-COMBO.md)
 - **⚡ Local performance & infra** — one-click local Redis, Cloudflare Workers / Deno Deploy relay deployers, Bifrost & Mux as supervised embedded services. → [Embedded Services](docs/frameworks/EMBEDDED-SERVICES.md)
 
@@ -642,7 +642,7 @@ of your shell history. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)
 
 <div align="center">
 
-## 🌐 353 AI Providers — 154 Catalog-Marked Free
+## 🌐 357 AI Providers — 154 Catalog-Marked Free
 
 </div>
 

changelog.d/features/anysearch-search-provider.md

@@ -0,0 +1 @@
+- **feat(search):** Add AnySearch free web search + URL extract (webFetch) with typed results, credential validation, REST routing, and MCP selection - fallback-only

changelog.d/fixes/11296-kie-market-model-id-sweep.md

@@ -0,0 +1 @@
+- **fix(kie):** correct 12 more KIE Market catalog ids that were sent to `createTask` unchanged but diverge from KIE's documented upstream `model` values — GPT Image 2 T2I/I2I (drops the `gpt/` prefix), GPT Image 1.5 T2I/I2I (`gpt-image/` namespace), Seedream 5.0 Lite T2I/I2I (drops the `.0`), all 4 Flux 2 variants (`flux-2/` namespace, generic variant renamed `flex`), and Wan 2.7 Image / Image Pro (dash instead of dot) — each verified individually against the literal example request published on docs.kie.ai. `#11326`'s "everything else already matches" claim was wrong a second time (#11296); `z-image/4.0-*`/`z-image/4.5-*` and `flux/kontext` remain open, documented as unresolved in `KIE_MARKET_UPSTREAM_MODEL_IDS`'s comment pending further verification.

changelog.d/fixes/11324-skip-full-sync-on-manual-model-add.md

@@ -0,0 +1 @@
+- **fix(dashboard):** `useApiKeySave.handleSaveApiKey` no longer forces a full upstream `/models` catalog sync on every non-curated provider connection save — callers can now pass `skipModelSync: true` to opt out, so a workflow that only wants to add one manual model no longer floods the provider's available-models list with hundreds/thousands of synced entries. The flag is a client-side intent signal only and is stripped before the connection payload is POSTed to `/api/providers`; default behavior (full sync on save) is unchanged when the flag is omitted (#11324)

changelog.d/fixes/11433-opencode-alias-collision.md

@@ -0,0 +1 @@
+- **fix(combos):** the combo builder's precision-select, global-model-search, and manual-entry flows now serialize a model step's `model` string using the provider's already-computed routing-alias prefix (e.g. `oc/`) instead of rebuilding it from the raw canonical `providerId`, fixing the no-auth "OpenCode Free" provider (`opencode`) being routed to the unrelated paid "OpenCode Zen" provider (`opencode-zen`) because `opencode` doubles as a manual routing-prefix override ([#11433](https://github.com/diegosouzapw/OmniRoute/issues/11433)).

changelog.d/fixes/11449-anysearch-icon-fallback.md

@@ -0,0 +1 @@
+- fix(ui): let AnySearch use the normal provider-icon fallback when LobeHub has no matching icon (#11449)

changelog.d/fixes/11462-roundrobin-combo-diagnostics.md

@@ -0,0 +1 @@
+- **fix(combo):** attach the same combo-diagnostics trace (`poolSize`/`attemptOrder`/`excluded`/`terminalReason`, plus `x-omniroute-combo-*` headers) to the round-robin strategy's and the nested pipeline/fusion runtime-unit loop's "Maximum combo retry limit reached" 503 that the priority-strategy path already attaches for the identical terminal condition — previously those two paths returned a bare, contextless 503 ([#11462](https://github.com/diegosouzapw/OmniRoute/issues/11462)).

changelog.d/fixes/11500-decrypt-log-dedup.md

@@ -0,0 +1 @@
+- **fix(db):** dedupe the raw `[Encryption] Decryption failed...` log line emitted by the lazy-decrypt views (`createLazyRowProxy`/`createLazyConnectionView`), which power `getProviderConnections()` and were re-triggering that line on every CredentialHealth/model-sync cycle for the same corrupt or stale-key credential — a fresh Proxy over a fresh row on every cycle meant the per-proxy memoization never suppressed it, unlike the dedup `decryptConnectionFields()` already had since [#9927](https://github.com/diegosouzapw/OmniRoute/issues/9927). Now shares that dedupe tracking so the line logs at most once per credential ([#11500](https://github.com/diegosouzapw/OmniRoute/issues/11500)).

changelog.d/fixes/11510-gemini-parallel-tool-thought-signature.md

@@ -0,0 +1 @@
+- **fix(sse):** stop dropping resolved `thoughtSignature` values on parallel (multi tool-call) turns sent to Gemini 3.x — the claude→gemini and openai→gemini translators previously kept the signature only on the *first* function call of a message, causing Gemini to reject subsequent calls in the same turn with HTTP 400 "Function call is missing a thought_signature"; each function call now keeps its own resolved signature ([#11510](https://github.com/diegosouzapw/OmniRoute/issues/11510)).

changelog.d/fixes/11556-client-abort-guard-mjs-import.md

@@ -0,0 +1 @@
+- **sse:** fix LiveWS/embed-WS servers crashing at startup under the Node/tsx runtime — `liveServer.ts`, `embedWsProxy.ts` and `apiBridgeServer.ts` imported `@/shared/utils/httpClientAbortGuard` without the `.mjs` extension, so the client-abort crash guard added by [#11556](https://github.com/diegosouzapw/OmniRoute/pull/11556) was unreachable and every dependent test failed with `ERR_MODULE_NOT_FOUND` ([#11556](https://github.com/diegosouzapw/OmniRoute/pull/11556)).

changelog.d/fixes/11592-token-health-retry-budget-boundary.md

@@ -0,0 +1 @@
+- **resilience:** restore the expired-connection retry-budget probe in the token-health sweep — the `!isGitHubAccessTokenOnlyConnection` carve-out reintroduced by #11608 contradicted the boundary pinned by #11592, so a GitHub connection parked at `expired` with retry budget remaining was never probed and could never self-heal ([#11592](https://github.com/diegosouzapw/OmniRoute/pull/11592)).

changelog.d/fixes/11604-aggregate-profile-level-pin.md

@@ -0,0 +1 @@
+- **test(gamification):** pin the aggregate profile level to the XP-derived semantics of #11604 — `getAggregateXp()` now derives `currentLevel` from the summed XP (`calculateLevel(sum)`), not `MAX(stored current_level)`, and the #3484 fixture levels are aligned with the XP curve ([#11604](https://github.com/diegosouzapw/OmniRoute/pull/11604)).

changelog.d/fixes/11626-retired-model-test-updates.md

@@ -0,0 +1 @@
+- **test(chatcore):** move Codex/Claude combo fixtures off models the lifecycle guard now rejects — `gpt-5.1-codex`/`gpt-5-codex` are vendor-retired (snapshot, #11626) and `claude-3-5-sonnet-20241022` is shut down, so native-passthrough and combo-fallback tests switched to `gpt-5.6-sol` and `claude-sonnet-4.6` ([#11626](https://github.com/diegosouzapw/OmniRoute/pull/11626)).

changelog.d/fixes/11658-video-transcript-log-redaction.md

@@ -0,0 +1 @@
+- **fix(security):** Video Bridge transcript text is now omitted from OmniRoute-owned retained request, response, usage, error, stream, continuation, handoff, and Memory surfaces while the live bridge request remains intact. Server-generated descriptions are matched by bounded SHA-256/length identities emitted only by a successful Video Bridge rewrite; ordinary fields named `transcript` and caller-forged description prose remain untouched. Traversal is cycle-safe and bounded, and hostile getters, proxies, or budget overflow fail closed to a constant omission marker instead of leaking content or breaking the request. Custom plugins and guardrails remain privileged processors of the live payload and must secure any sinks they create themselves. ([#11658](https://github.com/diegosouzapw/OmniRoute/issues/11658))

changelog.d/fixes/11684-free-budget-magnitude-rounding.md

@@ -0,0 +1 @@
+- fix(opencode-plugin): stop a free-tier budget that rounds up across a magnitude from rendering as `1000K`/`1000M` in the model picker — `fmtTokens` chose its unit from the raw token count and then rounded with `toFixed(1)`, so 999,950–999,999 printed as `1000K` rather than `1M` and just under a billion printed as `1000M` rather than `1B` ([#11684](https://github.com/diegosouzapw/OmniRoute/pull/11684))

changelog.d/fixes/7518-docker-build-memory-budget.md

@@ -0,0 +1 @@
+- **fix(docker):** re-derive the Docker build's worker-pool memory budget from the MEASURED ~4.5 GB per-process RSS (the issue owner's own VPS dmesg OOM-killer reproduction) instead of the stale 2560 MB/worker inference #11419 shipped, and lower `OMNIROUTE_BUILD_WORKERS` 3 → 2 so 1 parent + 1 page-data worker (2 processes × 4.5 GB = 9 GB) fits the 12.288 GB (75%) budget on a 16 GB GitHub Actions runner — the previous default (1 parent + 2 workers = 13.5 GB) still overcommitted the runner and kept "Publish to Docker Hub" failing with `cannot allocate memory` after #11419 merged (#7518).

changelog.d/maintenance/11449-provider-count-docs-sync.md

@@ -0,0 +1 @@
+- **docs:** sync the canonical provider count 354 → 356 across `README.md`, `AGENTS.md`, `llm.txt` (+ 42 i18n mirrors), the four README SVG diagrams, `docs/reference/PROVIDER_REFERENCE.md` (regenerated) and the `package.json` description after Opper (#11629) and 1min.ai (#11631) boarded the catalog — closes the `check:docs-counts-sync` strict drifts that kept `release/v3.8.51` red ([#11449](https://github.com/diegosouzapw/OmniRoute/issues/11449)).

changelog.d/maintenance/11449-provider-count-test-assertions.md

@@ -0,0 +1 @@
+- **test(providers):** update count-derived assertions after the v3.8.51 provider additions — `APIKEY_PROVIDERS` 233 → 235 (Opper #11629 + 1min.ai #11631), reserved-prefix REGISTRY walk 395 → 398, `WEB_FETCH_PROVIDERS` now includes `nimble-search` (#11620), and the provider translate-path golden snapshot regenerated ([#11449](https://github.com/diegosouzapw/OmniRoute/issues/11449)).

changelog.d/maintenance/11495-hard-lease-inventory-count.md

@@ -0,0 +1 @@
+- **test(sse):** bump the hard-lease connection-query inventory for `src/lib/tokenHealthCheck.ts` to 2 — the verify-only web-cookie sweep added by #11495 split the single `getProviderConnections` call into oauth + cookie variants, which the frozen inventory had not tracked ([#11495](https://github.com/diegosouzapw/OmniRoute/pull/11495)).

changelog.d/maintenance/11660-formatfreebudget-unit-tests.md

@@ -0,0 +1 @@
+- **test(opencode-plugin):** add unit test coverage for `formatFreeBudget()` naming helper ([#11660](https://github.com/diegosouzapw/OmniRoute/pull/11660)) — thanks @f9td56dbgh-hub

config/quality/eslint-suppressions.json

@@ -2790,11 +2790,6 @@
       "count": 3
     }
   },
-  "src/mitm/dns/dnsConfig.ts": {
-    "@typescript-eslint/no-unused-vars": {
-      "count": 1
-    }
-  },
   "src/mitm/dns/provision.ts": {
     "@typescript-eslint/no-unused-vars": {
       "count": 1
@@ -2926,11 +2921,6 @@
       "count": 1
     }
   },
-  "src/shared/middleware/chatBodyAdmission.ts": {
-    "@typescript-eslint/no-unused-vars": {
-      "count": 1
-    }
-  },
   "src/shared/services/apiKeyResolver.ts": {
     "no-restricted-imports": {
       "count": 1
@@ -3440,10 +3430,10 @@
   },
   "tests/integration/skills-pipeline.test.ts": {
     "@typescript-eslint/no-explicit-any": {
-      "count": 14
+      "count": 15
     },
     "@typescript-eslint/no-unused-vars": {
-      "count": 2
+      "count": 1
     }
   },
   "tests/integration/traffic-inspector-error-sanitization.test.ts": {
@@ -3690,11 +3680,6 @@
       "count": 15
     }
   },
-  "tests/unit/authz/probe-9033-repro.test.ts": {
-    "@typescript-eslint/no-unused-vars": {
-      "count": 1
-    }
-  },
   "tests/unit/autoCombo/tieredRotation.test.ts": {
     "@typescript-eslint/no-unused-vars": {
       "count": 3

config/quality/file-size-baseline.json

@@ -229,7 +229,8 @@
     "tests/unit/vscode-token-routes.test.ts": 1633,
     "tests/unit/executor-antigravity.test.ts": 1427,
     "tests/unit/guardrails/videoBridgeResultCache.test.ts": 1040,
-    "_rebaseline_2026_08_24_video_bridge_fu01_fu03_fu04_result_cache_tests": "PRs #11362 (FU-01 cache hardening) + #11382 (FU-03 visual dedup policy identity) + #11383 (FU-04 focused analysis mode) own test growth: videoBridgeResultCache.test.ts <1000->1040, +40 (sum of three stacked PRs boarded together in the same merge-batch, each adding its own cache-identity assertions on the shared result-cache seam). Owner pre-authorized rebaseline for legitimate PR growth (2026-08-19 directive)."
+    "_rebaseline_2026_08_24_video_bridge_fu01_fu03_fu04_result_cache_tests": "PRs #11362 (FU-01 cache hardening) + #11382 (FU-03 visual dedup policy identity) + #11383 (FU-04 focused analysis mode) own test growth: videoBridgeResultCache.test.ts <1000->1040, +40 (sum of three stacked PRs boarded together in the same merge-batch, each adding its own cache-identity assertions on the shared result-cache seam). Owner pre-authorized rebaseline for legitimate PR growth (2026-08-19 directive).",
+    "tests/integration/skills-pipeline.test.ts": 1010
   },
   "_rebaseline_2026_06_09": "Re-baseline consciente pre-release v3.8.19: 9 arquivos cresceram durante o ciclo (features mergeadas: RequestLoggerV2 +281 request-logger rework, stream +101, combo +73, chatCore +45, catalog +32 fable-5/catalog-flag, callLogs +4, accountFallback +2, usageHistory novo 840) + core.ts +7 (fix resetAllDbModuleState, PR 3536). A catraca segue valendo destes valores — proximo crescimento falha. Decisao: encolher (esp. RequestLoggerV2/chatCore) e a issue #3501 ficam para o ciclo seguinte.",
   "_rebaseline_2026_06_11_phase1f": "Phase 1f (#3501): ProviderDetailPageClient.tsx 4948→4062 (-886 LOC); 3 novos hooks extraídos. useProviderConnections.ts=954 acima do cap=800 — justificado: extração direta do god-component (zero lógica nova), própria redução do cliente supera o custo. useProviderSettings.ts=263 e useProviderModels.ts=154 já abaixo do cap.",
@@ -652,5 +653,6 @@
   "_rebaseline_2026_08_20_imageregistry_1034": "imageRegistry.ts 1033->1034: +1 line drift between #10842 (cursor image provider, froze at 1033) and its actual merged state on release (measured 1034) — trivial rebaseline, not a new feature.",
   "_rebaseline_2026_08_25_11146_subscription_first_auto": "PR #11146 (@yourspraveen, subscription-first auto groupings auto/subscription+auto/thrifty): open-sse/services/autoCombo/virtualFactory.ts is a NEW file in this PR landing at 1128 lines (+2 margin) — two opt-in flat auto ids built on the established auto/best-free pattern (connectionBillingCatalog + subscriptionLadder pure functions). Frozen at merge size per owner-authorized rebaseline directive (2026-08-19, merge-batch Step 4); no further growth without split rationale.",
   "_rebaseline_2026_08_26_mergebatch_v3851_batch1": "/merge-batch 2026-08-26 (v3.8.51): three legitimate growths from this batch. #11448 src/app/api/providers/[id]/test/route.ts 1237->1262 (auto-test-on-create wiring). #11495 src/sse/services/auth.ts 3346->3376 (web-cookie health-sweep verify-only path). #11561 src/lib/cloudflaredTunnel.ts new named-tunnel mode, lands at 1078 (+78 over the 1000 new-file cap) for the CLOUDFLARED_CONFIG named-tunnel flow (login->create->route dns config parsing + readiness detection). Owner-authorized rebaseline per merge-batch Step 4 (2026-08-19 directive); no further growth without split rationale.",
-  "_rebaseline_2026_08_26_mergebatch_v3851_batch2": "/merge-batch 2026-08-26 (v3.8.51) batch 2: three legitimate growths. #11083 src/shared/components/RequestLoggerDetail.tsx new-file cap, lands at 1018 (+18 over 1000) — copy-all button for request detail modal. #11631 src/shared/constants/providers/apikey/gateways.ts 1321->1330 (1min.ai gateway entry). #11628 src/sse/services/auth.ts 3376->3432 (credential-health isolation from model failures). Owner-authorized rebaseline per merge-batch Step 4 (2026-08-19 directive); no further growth without split rationale."
+  "_rebaseline_2026_08_26_mergebatch_v3851_batch2": "/merge-batch 2026-08-26 (v3.8.51) batch 2: three legitimate growths. #11083 src/shared/components/RequestLoggerDetail.tsx new-file cap, lands at 1018 (+18 over 1000) — copy-all button for request detail modal. #11631 src/shared/constants/providers/apikey/gateways.ts 1321->1330 (1min.ai gateway entry). #11628 src/sse/services/auth.ts 3376->3432 (credential-health isolation from model failures). Owner-authorized rebaseline per merge-batch Step 4 (2026-08-19 directive); no further growth without split rationale.",
+  "_rebaseline_2026_08_26_mergebatch_v3851_batch5": "/merge-batch 2026-08-26 (v3.8.51) batch 5: #11642 tests/integration/skills-pipeline.test.ts new regression test for the configured-provider-over-fallback search selection (#11524), lands at 1010 lines (+10 over the 1000 new-file testCap). Owner-authorized rebaseline per merge-batch Step 4 (2026-08-19 directive); no further growth without split rationale."
 }

config/quality/quality-baseline.json

@@ -188,14 +188,15 @@
       "dedicatedGate": true
     },
     "bundleSize": {
-      "value": 8461,
+      "value": 8653,
       "direction": "down",
       "dedicatedGate": true,
       "_rebaseline_2026_07_07_v3846_release_close": "5601->6534 (+933). v3.8.46 release close: gzip of the 4 bin/*.mjs entrypoints (size-limit + @size-limit/file) grew from this cycle's feature/fix merges pulled transitively into the CLI entrypoints (new providers, combo pipeline strategy #6396, effort/thinking standardization #6241, catalog cache-invalidation #6408). Measured 6534 locally via `check:bundle-size --ratchet` (deterministic gzip, matches CI). Legitimate cycle growth; shrink is separate debt.",
       "_rebaseline_2026_07_19_7808_codeql_alias_resolver_hook": "6534->6762 (+228). PR #7808 (CodeQL js/incomplete-url-substring-sanitization fix): the ESM loader hook source moved out of the inline `HOOK_SOURCE` template literal in bin/aliasResolver.mjs into a real file bin/aliasResolverHook.mjs, loaded via pathToFileURL() instead of a dynamically-built `data:text/javascript,...` URL. The new file is now counted by size-limit as a 5th bin/*.mjs entrypoint. Net +228 = the hook's gzip size (previously hidden inside aliasResolver.mjs because the template literal was compressed away). Security-driven; no shrink opportunity.",
       "_rebaseline_2026_07_28_v3849_release_preflight": "6762 -> 7666 (+904). Fechamento do ciclo v3.8.49: gzip dos entrypoints bin/*.mjs (size-limit + @size-limit/file) cresceu com o que os merges do ciclo puxam transitivamente para o CLI (novos provedores — 271->290, seletor de protocolo por conexão #8861, catálogos de busca #8814, resiliência). Crescimento legítimo de ciclo, medido localmente com `npm run check:bundle-size` = 7666 (gzip determinístico, bate com o CI). Encolher é dívida separada.",
       "_rebaseline_2026_08_09_v3850_release_close": "7666 -> 8045 (+379 gzip bytes, +4.9%). Release v3.8.50 close reconciliation measured twice with the real size-limit + @size-limit/file path on tip e0ce95c592. Per-entry measurements remain below their absolute budgets: omniroute.mjs 4380/15000, mcp-server.mjs 1195/5000, nodeRuntimeSupport.mjs 887/8000, reset-password.mjs 1583/6000. The growth accumulated through legitimate CLI/runtime work in this cycle, including global-install ESM alias resolution, Termux cache preparation, and MCP stdio startup hardening; no entrypoint is near its absolute ceiling. The direction:down ratchet stays blocking from this exact measured tip.",
-      "_rebaseline_2026_08_24_ci_green_gates_f95b03d7": "8045 -> 8461 (+416 gzip bytes, +5.2%). CI run 32786966560 (release PR #8875, tip f95b03d7) measured bundleSize=8461 via check:bundle-size --ratchet, above the 8045 baseline left at the v3.8.50 close. The growth comes from the post-freeze back-merge cycle landing in the CLI entrypoints (Synthetic + Kilo Gateway providers, kilo-gateway routing surface). Re-baseline per the gate's own instruction (legitimate cycle growth); shrinking the entrypoints remains separate debt; direction:down ratchet stays blocking from this measured tip."
+      "_rebaseline_2026_08_24_ci_green_gates_f95b03d7": "8045 -> 8461 (+416 gzip bytes, +5.2%). CI run 32786966560 (release PR #8875, tip f95b03d7) measured bundleSize=8461 via check:bundle-size --ratchet, above the 8045 baseline left at the v3.8.50 close. The growth comes from the post-freeze back-merge cycle landing in the CLI entrypoints (Synthetic + Kilo Gateway providers, kilo-gateway routing surface). Re-baseline per the gate's own instruction (legitimate cycle growth); shrinking the entrypoints remains separate debt; direction:down ratchet stays blocking from this measured tip.",
+      "_rebaseline_2026_08_27_v3851_volatile_env_warning_11437": "8461 -> 8653 (+192 gzip bytes, +2.3%). Exact paired size-limit measurements on the VPS compared f95b03d709 with release/v3.8.51: only bin/omniroute.mjs changed, 4700 -> 4892; the other three entries remained 1195/983/1583. The growth originates in 943b9aaa84 (#11437), which warns users before a package-local .env is lost on the next global install. The CLI entry remains 4892/15000 bytes (32.6% of its absolute budget). Legitimate bug-fix growth; shrinking stays separate debt and direction:down remains blocking from this measured tip."
     },
     "openapiBreaking": {
       "value": 4,

docs/diagrams/cli-terminal.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 350" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Animated terminal demoing the OmniRoute CLI: omniroute providers list (354 providers registered, anthropic, codex, glm, kimi shown active), omniroute combo list (always-on priority, cost-saver, fusion-panel, context-relay) and omniroute health (healthy, 18412 requests in 24h, p95 412ms, circuit breakers 24 closed, 1 half-open, 0 open), cycling over 85 top-level commands: providers, oauth, keys, combo, nodes, models, cache, compression, cost, usage, quota, health, resilience, telemetry, logs, audit, mcp, a2a, cloud, memory, skills, eval, doctor, repl, tunnel, backup, sync, webhooks, policy, pricing, translator, simulate and more.">
+<svg viewBox="0 0 1200 350" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Animated terminal demoing the OmniRoute CLI: omniroute providers list (357 providers registered, anthropic, codex, glm, kimi shown active), omniroute combo list (always-on priority, cost-saver, fusion-panel, context-relay) and omniroute health (healthy, 18412 requests in 24h, p95 412ms, circuit breakers 24 closed, 1 half-open, 0 open), cycling over 85 top-level commands: providers, oauth, keys, combo, nodes, models, cache, compression, cost, usage, quota, health, resilience, telemetry, logs, audit, mcp, a2a, cloud, memory, skills, eval, doctor, repl, tunnel, backup, sync, webhooks, policy, pricing, translator, simulate and more.">
 <desc>Compact animated terminal cycling three real OmniRoute CLI commands with a typewriter effect and a scrolling subcommand ticker; the first frame shows the completed providers-list screen.</desc>
 <defs><clipPath id="tickerClip"><rect x="12" y="304" width="1176" height="40"/></clipPath><clipPath id="tw0"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;31;61;92;122;153;184;214;245;245" keyTimes="0;0.012;0.018;0.024;0.030;0.036;0.042;0.048;0.054;1" dur="18s" repeatCount="indefinite"/></rect></clipPath><clipPath id="tw1"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;26;51;76;102;128;153;178;204;204" keyTimes="0;0.348;0.351;0.357;0.363;0.369;0.375;0.381;0.387;1" dur="18s" repeatCount="indefinite"/></rect></clipPath><clipPath id="tw2"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;20;41;61;82;102;122;143;163;163" keyTimes="0;0.678;0.684;0.690;0.696;0.702;0.708;0.714;0.720;1" dur="18s" repeatCount="indefinite"/></rect></clipPath></defs>
 <rect width="1200" height="350" fill="#0d1117"/>

docs/diagrams/comparison-table.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 780" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Comparison table: OmniRoute versus 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute is the only one with the full set: 354 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, a built-in MCP server with 110 tools, A2A protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, desktop/Termux/PWA, 43 UI locales and 100% MIT self-hosted. 9router has free providers, RTK compression and translation but no MCP, A2A, memory, guardrails, cloud agents or stealth. OpenRouter is a hosted SaaS with 400+ models, guardrails and a hosted MCP but is not self-hosted and lacks A2A, memory, cloud agents and stealth. CLIProxyAPI is a light OAuth proxy with two routing strategies. LiteLLM has 100+ providers, A2A and extensive guardrails but no memory, compression, free tier, stealth or cloud agents.">
+<svg viewBox="0 0 1200 780" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Comparison table: OmniRoute versus 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute is the only one with the full set: 357 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, a built-in MCP server with 110 tools, A2A protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, desktop/Termux/PWA, 43 UI locales and 100% MIT self-hosted. 9router has free providers, RTK compression and translation but no MCP, A2A, memory, guardrails, cloud agents or stealth. OpenRouter is a hosted SaaS with 400+ models, guardrails and a hosted MCP but is not self-hosted and lacks A2A, memory, cloud agents and stealth. CLIProxyAPI is a light OAuth proxy with two routing strategies. LiteLLM has 100+ providers, A2A and extensive guardrails but no memory, compression, free tier, stealth or cloud agents.">
   <desc>Static-header comparison table where each capability row fades in top to bottom; the OmniRoute column is highlighted and shows a check or a leading value in every row, while competitors show a mix of checks, partials and crosses.</desc>
   <defs>
     <pattern id="gC" width="32" height="32" patternUnits="userSpaceOnUse"><path d="M 32 0 L 0 0 0 32" fill="none" stroke="#ffffff" stroke-opacity="0.05" stroke-width="1"/></pattern>

docs/diagrams/promise-pillars.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 540" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="The OmniRoute promise: one endpoint and 354 providers. Six pillars. Resilient fallback: automatic routing continues while another healthy target is available. Save up to 95 percent of eligible tokens: RTK plus Caveman stacked compression averages about 89 percent on tool-heavy sessions. Zero dollars to start: 90+ providers with a free tier and 56 recurring or keyless free-forever providers. Every tool works: 35 CLI and agent integration records, including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity, through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation at /v1. Production controls: circuit breakers, TLS stealth, MCP with 110 tools, A2A, memory, guardrails, evals, and 39,000+ static test declarations across 5,100+ tracked test files.">
+<svg viewBox="0 0 1200 540" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="The OmniRoute promise: one endpoint and 357 providers. Six pillars. Resilient fallback: automatic routing continues while another healthy target is available. Save up to 95 percent of eligible tokens: RTK plus Caveman stacked compression averages about 89 percent on tool-heavy sessions. Zero dollars to start: 90+ providers with a free tier and 56 recurring or keyless free-forever providers. Every tool works: 35 CLI and agent integration records, including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity, through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation at /v1. Production controls: circuit breakers, TLS stealth, MCP with 110 tools, A2A, memory, guardrails, evals, and 39,000+ static test declarations across 5,100+ tracked test files.">
   <desc>Animated promise card: six pillar tiles fade in in reading order, then a soft colored border highlight sweeps from tile to tile in a continuous cycle.</desc>
   <defs>
     <pattern id="gridPaperP" width="32" height="32" patternUnits="userSpaceOnUse">
@@ -21,7 +21,7 @@
     <line x1="150" y1="53" x2="1160" y2="53" stroke="#232b38" stroke-width="1.5"/>
   </g>
   <g>
-    <text x="40" y="100" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="23" font-weight="600" fill="#c9d1d9">One endpoint. <tspan fill="#a78bfa" font-weight="800">354 providers.</tspan> Never stop building — OmniRoute picks <tspan fill="#7ee787" font-weight="700">the cheapest one that works</tspan>.</text>
+    <text x="40" y="100" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="23" font-weight="600" fill="#c9d1d9">One endpoint. <tspan fill="#a78bfa" font-weight="800">357 providers.</tspan> Never stop building — OmniRoute picks <tspan fill="#7ee787" font-weight="700">the cheapest one that works</tspan>.</text>
   </g>
 
   <g font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif">
@@ -38,7 +38,7 @@
         <line x1="3.9" y1="3.9" x2="18.1" y2="18.1"/>
       </g>
       <text x="102" y="170" font-size="18" font-weight="800" fill="#74b9ff">Never hit limits</text>
-      <text x="66" y="204" font-size="13.5" fill="#a1a1aa">Auto-fallback across 354 providers in</text>
+      <text x="66" y="204" font-size="13.5" fill="#a1a1aa">Auto-fallback across 357 providers in</text>
       <text x="66" y="226" font-size="13.5" fill="#a1a1aa">milliseconds. Quota out? The next provider</text>
       <text x="66" y="248" font-size="13.5" fill="#a1a1aa">takes over while a healthy target remains.</text>
     </g>

docs/diagrams/readme-hero.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 548" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="OmniRoute hero: Never stop coding. Every AI tool to 354 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot and Antigravity into free Claude, GPT and Gemini with auto-fallback. RTK + Caveman stacked compression saves 15 to 95 percent of tokens — about 89 percent average on tool-heavy sessions — so you never hit limits. Stats: 354 AI providers, 90+ free tiers, about 1.51B free tokens per month, 15 to 95 percent token savings, 19 routing strategies, zero dollars to start.">
+<svg viewBox="0 0 1200 548" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="OmniRoute hero: Never stop coding. Every AI tool to 357 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot and Antigravity into free Claude, GPT and Gemini with auto-fallback. RTK + Caveman stacked compression saves 15 to 95 percent of tokens — about 89 percent average on tool-heavy sessions — so you never hit limits. Stats: 357 AI providers, 90+ free tiers, about 1.51B free tokens per month, 15 to 95 percent token savings, 19 routing strategies, zero dollars to start.">
   <desc>Animated hero card: a pulse travels the divider line and a compression bar demo repeatedly shrinks a prompt by up to 95 percent; all headline content is static and readable on the first frame.</desc>
   <defs>
     <pattern id="gridPaperH" width="32" height="32" patternUnits="userSpaceOnUse">
@@ -28,7 +28,7 @@
   <text x="48" y="138" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="60" font-weight="800" fill="#e9edf3">Never stop coding<tspan fill="#a855f7">.</tspan></text>
 
   <!-- subheadline -->
-  <text x="48" y="184" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="25" font-weight="600" fill="#c9d1d9">Every AI tool → <tspan fill="#a78bfa" font-weight="800">354 providers</tspan> — <tspan fill="#7ee787" font-weight="800">90+ free</tspan> — through one endpoint.</text>
+  <text x="48" y="184" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="25" font-weight="600" fill="#c9d1d9">Every AI tool → <tspan fill="#a78bfa" font-weight="800">357 providers</tspan> — <tspan fill="#7ee787" font-weight="800">90+ free</tspan> — through one endpoint.</text>
 
   <!-- plug line -->
   <text x="48" y="222" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="16.5" fill="#a1a1aa">Claude Code · Codex · Cursor · Cline · Copilot · Antigravity&#160;&#160;→&#160;&#160;<tspan fill="#7ee787" font-weight="700">FREE</tspan> Claude / GPT / Gemini · auto-fallback</text>

docs/frameworks/SEARCH_TOOLS_STUDIO.md

@@ -57,7 +57,7 @@ New tab for extracting content from a URL via `POST /v1/web/fetch` (created in p
 - Submit → fetch → render `ScrapeResult.tsx`.
 - `ScrapeResult` renders markdown preview + raw toggle.
 - Cap: if response body > **256 KB**, UI shows `(truncated, view raw)` and opens raw in a Monaco modal (D21).
-- Metadata panel: provider (firecrawl/jina-reader/tavily-search/tinyfish/nimble-search), latency, cost, response size, links count.
+- Metadata panel: provider (firecrawl/jina-reader/tavily-search/tinyfish/nimble-search/anysearch-search), latency, cost, response size, links count.
 - Uses `useScrapeFetch.ts` hook.
 
 ### Compare Tab
@@ -105,15 +105,7 @@ Runs the same query/URL across up to **4 providers in parallel** (D22):
 `ProviderCatalog.tsx` exposes the full provider list from `GET /api/search/providers`
 (extended in F4 to include fetch providers):
 
-| Field                          | Source                                                                                     |
-| ------------------------------ | ------------------------------------------------------------------------------------------ |
-| `id`, `name`                   | `searchRegistry.ts`                                                                        |
-| `kind`                         | `"search"` or `"fetch"` (firecrawl, jina-reader, tavily-search, tinyfish, nimble-search)   |
-| `costPerQuery`                 | Registry data                                                                              |
-| `freeMonthlyQuota`             | Registry data                                                                              |
-| `searchTypes` / `fetchFormats` | Registry data                                                                              |
-| `status`                       | `"configured"` / `"missing"` / `"rate_limited"` — derived at runtime from credential store |
-| `configureHref`                | `/dashboard/providers`                                                                     |
+| `kind` | `"search"` (20 providers) or `"fetch"` (firecrawl, jina-reader, tavily-search, tinyfish, nimble-search, anysearch-search) |
 
 The status is **derived at request time** by checking whether credentials exist and whether
 all keys are currently in cooldown.
@@ -136,7 +128,7 @@ Only one backend change was needed for this feature:
 
 `src/app/api/search/providers/route.ts` was extended to:
 
-- Include every fetch provider (`firecrawl`, `jina-reader`, `tavily-search`, `tinyfish`, `nimble-search`) in the array.
+- Include all 6 fetch providers (`firecrawl`, `jina-reader`, `tavily-search`, `tinyfish`, `nimble-search`, `anysearch-search`) in the array.
 - Add `kind: "search" | "fetch"` to every item.
 - Add `status: "configured" | "missing" | "rate_limited"` derived from live credential state.
 - Maintain backward compatibility — existing fields (`id`, `name`, etc.) unchanged.

docs/guides/DOCKER_GUIDE.md

@@ -226,16 +226,21 @@ Three build args control what the `builder` stage costs. They are build-time onl
 | --------------------------- | ------- | ----------------------------------------------------------------------------------- |
 | `OMNIROUTE_USE_TURBOPACK`   | `1`     | `0` builds with webpack instead. Lower peak memory, slower.                         |
 | `OMNIROUTE_BUILD_MEMORY_MB` | `6144`  | V8 heap ceiling (`--max-old-space-size`) for the spawned `next build`.              |
-| `OMNIROUTE_BUILD_WORKERS`   | `3`     | Feeds `CIRCLE_NODE_TOTAL`; Next derives `workers = N - 1` for page-data collection. |
+| `OMNIROUTE_BUILD_WORKERS`   | `2`     | Feeds `CIRCLE_NODE_TOTAL`; Next derives `workers = N - 1` for page-data collection. |
 
 `OMNIROUTE_BUILD_WORKERS` is the one to raise on a big builder and the one to
 suspect when a constrained build dies **after** `✓ Compiled successfully`. Each
-page-data worker is its own process and inherits `NODE_OPTIONS`, so the heap
-ceiling is per process, not per build: the default of `3` (→ 2 workers) is sized
-for the 16 GB / 4 vCPU GitHub-hosted runners the publish pipeline uses. At `8`
-(→ 7 workers) that runner ran out of memory and buildkit failed the step with
-`ResourceExhausted: ... cannot allocate memory`. `tests/unit/docker-build-memory-budget.test.ts`
-does the arithmetic and fails if either knob outgrows the runner.
+page-data worker is its own process, and so is the parent `next build` itself;
+a live VPS reproduction (issue #7518) measured each process's peak RSS at
+~4.5 GB independent of the `NODE_OPTIONS` heap flag (Turbopack compiles in
+native/Rust memory outside the V8 heap). The default of `2` (→ 1 worker, 2
+processes total) is sized for the 16 GB / 4 vCPU GitHub-hosted runners the
+publish pipeline uses. At `8` (→ 7 workers) that runner ran out of memory and
+buildkit failed the step with `ResourceExhausted: ... cannot allocate memory`;
+`3` (→ 2 workers) still didn't fit once the per-process RSS was measured
+directly instead of inferred. `tests/unit/docker-build-memory-budget.test.ts`
+does the arithmetic against the measured figure and fails if either knob
+outgrows the runner.
 
 Turbopack compiles in native Rust memory that lives **outside** the V8 heap, so
 `OMNIROUTE_BUILD_MEMORY_MB` does not bound it. On a host with a memory ceiling the

docs/i18n/ar/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/az/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/bg/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/bn/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/cs/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/da/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/de/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/es/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/fa/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/fi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/fr/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/gu/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/he/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/hi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/hu/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/id/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/in/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/it/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/ja/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/ko/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/mr/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/ms/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/nl/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/no/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/phi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/pl/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/pt-BR/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/pt/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/ro/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/ru/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/sk/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/sv/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/sw/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/ta/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/te/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/th/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/tr/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/uk-UA/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/ur/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/vi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/zh-CN/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/i18n/zh-TW/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

docs/openapi.yaml

@@ -1199,6 +1199,8 @@ paths:
         Searches the web, news, or X through a configured provider. Set `provider`
         to `xquik-search` to use Xquik for X search. The aliases `xquik` and
         `xquik_search` resolve to the same provider.
+        AnySearch (`anysearch-search`, aliases `anysearch` / `anysearch_search`)
+        provides free fallback-only web search.
       security:
         - BearerAuth: []
       requestBody:

docs/plans/11690-anysearch-provider-integration.md

@@ -0,0 +1,45 @@
+# AnySearch provider integration (PR #11690)
+
+Template: xquik #11370 (merged in release/v3.8.51). Posture: `fallbackOnly`.
+Upstream proposal: issue diegosouzapw/OmniRoute#11637.
+
+## 1. Service ground truth (official docs, cross-checked)
+
+- Base URL: `https://api.anysearch.com` (REST) + `POST /mcp` (MCP, JSON-RPC 2.0).
+- `POST /v1/search` - params: `query` (required), `max_results` (1-10, default 10), `tag` (`{domain}.{sub_domain}` vertical routing), `zone` (cn/intl), `language`, `params` (structured vertical fields), `format` (json/markdown).
+- `GET /v1/sub-domains?domain=...` - capability catalog, does NOT count against quota.
+- `POST /v1/extract` - fetch/extract `{url, title, content}`; strict JSON body, 16 KiB cap.
+- `POST /v1/auth/email/register` - single-call registration, returns one-time plaintext key `as_sk_...`.
+- Auth: optional `Authorization: Bearer <as_sk_...>`; anonymous degrades to per-IP limits consuming the daily free quota; invalid key returns 401/403 with NO silent anonymous fallback.
+- Free tier: 1000 requests/day, 20 QPS per key. Paid tier: unpriced (Coming Soon).
+- Response envelope: success `{code: 0, message: "success", request_id, data}`; failure `{code: -1, message}`. Auth/quota errors carry no structured `error_code` (the message text is the signal); extract-specific errors do carry `error_code` (`invalid_extract_url`, `extract_failed`). No `Retry-After` header on 429.
+
+## 2. Touch set (~10 layers, mirrors the xquik footprint)
+
+| Layer                 | File                                                                                                                                                                                                                                                                        | Change                                                                                                |
+| --------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------- |
+| Registry entry        | `open-sse/config/searchRegistry.ts`                                                                                                                                                                                                                                         | `anysearch-search` entry + aliases `anysearch`, `anysearch_search`                                    |
+| Executor              | `open-sse/handlers/search/anysearchSearch.ts`                                                                                                                                                                                                                               | `buildAnysearchSearchRequest`, `normalizeAnysearchSearchResponse`, `AnysearchSearchEnvelopeError`     |
+| Dispatch maps         | `open-sse/handlers/search.ts` + `searchProxy.ts`                                                                                                                                                                                                                            | request-builder map + response-normalizer map; envelope error -> 402 (quota) / 502 (other)            |
+| Fetch executor        | `open-sse/executors/anysearch-fetch.ts` + `open-sse/handlers/webFetch.ts`                                                                                                                                                                                                   | `POST /v1/extract`; union + `WEB_FETCH_PROVIDERS` + dispatch case; quota envelope -> 402              |
+| UI catalog            | `src/shared/constants/providers/search.ts`                                                                                                                                                                                                                                  | metadata entry (`serviceKinds: ["webSearch", "webFetch"]`); authHint documents the 1000/day free tier |
+| Credential validation | `src/lib/providers/validation/searchProviders.ts`                                                                                                                                                                                                                           | `SEARCH_VALIDATOR_CONFIGS["anysearch-search"]` (Bearer probe)                                         |
+| MCP                   | `open-sse/mcp-server/schemas/tools.ts`                                                                                                                                                                                                                                      | fetch enum + web_search description                                                                   |
+| API schema            | `src/shared/validation/schemas/apiV1.ts`, `docs/openapi.yaml`                                                                                                                                                                                                               | alias canonicalization + provider enum                                                                |
+| Docs                  | `docs/reference/PROVIDER_REFERENCE.md`, `docs/frameworks/SEARCH_TOOLS_STUDIO.md`, `changelog.d/features/anysearch-search-provider.md`                                                                                                                                       | consistency copies                                                                                    |
+| Tests                 | `tests/unit/anysearch-search-provider.test.ts` (8 cases), `tests/unit/executor-anysearch-fetch.test.ts` (2 cases), `search-registry.test.ts`, `search-route.test.ts`, `tests/integration/search-providers-catalog.test.ts`, `tests/snapshots/executors/dispatch-rules.json` | mirror xquik suite; catalog counts 20 search / 6 fetch (coexisting with nimble-search)                |
+
+## 3. Decisions (all reached 2026-08-26)
+
+1. **Routing posture: `fallbackOnly`.** Rationale: a cost-0 free provider must never dominate automatic cost routing; explicit selection and failover return are unaffected. Precedent: merged xquik entry.
+2. **Scope: webSearch + webFetch via `POST /v1/extract` in v1.** Aligned with the tavily/exa dual-capability mental model. Vertical surfaces (`tag`, `sub-domains`, `batch_search`) stay out of scope — there is no IR for vertical params today.
+3. **Quota display: `freeMonthlyQuota: 0`** (xquik-style conservative display). The real allowance (1000 req/day, daily reset) is carried in the UI catalog `authHint` copy instead. Rationale: quota display must match reset semantics; converting a daily cap to a monthly-equivalent (30000) is a false promise the UI cannot honor.
+4. **searchTypes: `["web"]` only.** No public evidence of a news/images vertical in the AnySearch API; gateways integrating APIs without a documented vertical (e.g. Google Custom Search) expose web only rather than silently mapping news -> web.
+5. **Key posture:** keyless works; an invalid key returns 401/403 and is never silently downgraded to anonymous (mirrors the upstream contract).
+6. **Deliberate exclusions:** `FETCH_BACKEND_TO_PROVIDER` / `FetchInterceptionBackend` (chat interception stays firecrawl/jina/tavily); `ANONYMOUS_CAPABLE_WEB_FETCH_PROVIDERS` (anonymous remote endpoints share one IP-limited pool per egress IP, so keyless extract is opt-in, not an auto-routing candidate); `QUOTA_STATUS_PROVIDERS` (AnySearch signals quota via 429/envelope, not 402/403 status).
+
+## 4. References
+
+- xquik template: commit a0ceccc, PR #11370 (in-tree at release/v3.8.51).
+- AnySearch official docs: https://anysearch.com/docs, https://anysearch.com/pricing; MCP catalog mcpservers.org/servers/anysearch-ai/anysearch-mcp-server; skill repo github.com/anysearch-ai/anysearch-skill.
+- Industry mental model: LiteLLM search docs (registry + unified search() + Perplexity-spec IR), open-webui web search (built-in providers, search_web/fetch_url dual tools), Dify tool plugin pattern; cost-fallback ladder: self-hosted -> free quota -> paid.

docs/reference/PROVIDER_REFERENCE.md

@@ -1,16 +1,16 @@
 ---
 title: "Provider Reference"
 version: 3.8.51
-lastUpdated: 2026-08-26
+lastUpdated: 2026-08-27
 ---
 
 # Provider Reference
 
 > **Auto-generated** from `src/shared/constants/providers.ts` — do not edit by hand.
 > Regenerate with: `npm run gen:provider-reference`
-> **Last generated:** 2026-08-26
+> **Last generated:** 2026-08-27
 
-Total providers: **354**. See category breakdown below.
+Total providers: **357**. See category breakdown below.
 
 ## Categories
 
@@ -122,7 +122,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `zai-web` | `zw` | Z.ai Web | Web cookie | [link](https://chat.z.ai) | Copy the "token" value from chat.z.ai → DevTools → Application → Local Storage. Do not copy cookies; OmniRoute handles the per-request CAPTCHA through its browser transport. | — |
 | `zenmux-free` | `zmf` | ZenMux Free (Web) | Web cookie | [link](https://zenmux.ai) | Login at zenmux.ai, then export all cookies using EditThisCookie or Cookie-Editor and paste the full Cookie header string here. Refresh every ~30 days. | — |
 
-## API Key Providers (paid / paid-with-free-credits) (234)
+## API Key Providers (paid / paid-with-free-credits) (235)
 
 | ID | Alias | Name | Tags | Website | Notes |
 |----|-------|------|------|---------|-------|
@@ -277,6 +277,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `oci` | `oci` | OCI Generative AI | API key, enterprise | [link](https://www.oracle.com/artificial-intelligence/generative-ai) | Use your OCI Generative AI API key or IAM bearer token. Base URL can be https://inference.generativeai.<region>.oci.oraclecloud.com/openai/v1/. |
 | `ofoxai` | `ofoxai` | OfoxAI | API key, aggregator | [link](https://ofox.ai) | The current catalog advertises 10+ free models without a public numeric quota; review upstream provenance, retention and training terms before production use. |
 | `ollama-cloud` | `ollamacloud` | Ollama Cloud | API key | [link](https://ollama.com/settings/keys) | — |
+| `oneminai` | `1min` | 1min.AI | API key | [link](https://1min.ai) | Create an API key at https://docs.1min.ai/docs/api/create-api-key, then paste it here. |
 | `openadapter` | `oad` | OpenAdapter | API key | [link](https://openadapter.dev) | Use your OpenAdapter API key in Authorization: Bearer sk-cv-<key>. Fully OpenAI-compatible. API base URL: https://api.openadapter.in/v1. |
 | `openai` | `openai` | OpenAI | API key | [link](https://platform.openai.com) | — |
 | `opencode-go` | `opencode-go` | OpenCode Go | API key | [link](https://opencode.ai/go) | — |
@@ -380,10 +381,11 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `vllm` | `vllm` | vLLM | Local, self-hosted | [link](https://github.com/vllm-project/vllm) | API key optional. Configure the local vLLM OpenAI-compatible base URL (default: http://localhost:8000/v1). |
 | `xinference` | `xinference` | XInference | Local, self-hosted | [link](https://inference.readthedocs.io) | API key optional. Configure the local XInference OpenAI-compatible base URL (default: http://localhost:9997/v1). |
 
-## Search Providers (16)
+## Search Providers (17)
 
 | ID | Alias | Name | Tags | Website | Notes |
 |----|-------|------|------|---------|-------|
+| `anysearch-search` | `anysearch` | AnySearch | Search | [link](https://anysearch.com) | Optional API key from anysearch.com (as_sk_...) - free 1000/day; keyless tier has lower limits |
 | `brave-search` | `brave-search` | Brave Search | Search | [link](https://brave.com/search/api) | Subscription token from Brave Search API dashboard |
 | `context7` | `context7` | Context7 (library docs) | Search | [link](https://context7.com) | API key optional (ctx7sk-...) — anonymous tier works without a key; a key raises the rate limit |
 | `exa-search` | `exa-search` | Exa Search | Search | [link](https://exa.ai) | API key from dashboard.exa.ai |
@@ -443,7 +445,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 
 - Catalog: [`src/shared/constants/providers.ts`](../../src/shared/constants/providers.ts)
 - Registry (per-model details): [`open-sse/config/providerRegistry.ts`](../../open-sse/config/providerRegistry.ts)
-- Executors: [`open-sse/executors/`](../../open-sse/executors/) (110 implementations)
+- Executors: [`open-sse/executors/`](../../open-sse/executors/) (112 implementations)
 - Translators: [`open-sse/translator/`](../../open-sse/translator/)
 
 ## See Also

docs/security/GUARDRAILS.md

@@ -1,13 +1,13 @@
 ---
 title: "Guardrails"
-version: 3.8.50
-lastUpdated: 2026-08-24
+version: 3.8.51
+lastUpdated: 2026-08-27
 ---
 
 # Guardrails
 
 > **Source of truth:** `src/lib/guardrails/`
-> **Last updated:** 2026-08-24 — v3.8.50 (Video Bridge visual dedup hardening + focused captions)
+> **Last updated:** 2026-08-27 — v3.8.51 (Video Bridge transcript-retention boundary)
 
 Guardrails enforce safety, policy, and content transformations at the boundary
 between OmniRoute and upstream providers. Each guardrail can inspect (and
@@ -439,6 +439,69 @@ are rendered as untrusted observations alongside the frame captions. Invalid,
 out-of-range, or provenance-free text is rejected rather than mixed into the
 caption stream.
 
+#### Transcript retention boundary
+
+Transcript text remains available to the live bridge and upstream request, but it is not retained
+by OmniRoute's logging and memory surfaces. `videoTranscriptLogRedaction.ts` recognizes
+`transcript` and `audioTranscript` only inside supported video carriers. A field with either name
+in an ordinary tool argument or application object is preserved, and delimiter-shaped caller
+prose is not trusted as a bridge result.
+
+When the Video Bridge produces a description containing validated cues, it emits only a
+SHA-256/length identity in guardrail metadata. The request pipeline accepts those identities only
+from a successful, payload-modifying `video-bridge` result and uses them to omit the exact generated
+description segment after translation or concatenation. Raw transcript text is never placed in the
+metadata.
+
+The retention policy covers raw, converted, and provider request logs; provider and client response
+bodies; detailed pipeline artifacts; call logs, active/pending usage, rejected requests, proxy/error
+diagnostics, SSE chunks, and Memory extraction. Response bodies and stream chunks for a sensitive
+request are omitted because an upstream may echo request text. Safe operational metadata such as
+status, timing, provider, model, headers-presence, token counts, and the fact that redaction occurred
+remains available. The constant retained marker is `[omitted: video transcript]`.
+
+Sensitivity is resolved before the guardrail chain from the original client body and resolved again
+after the chain from the original body, processed body, and trusted description identities. A
+guardrail that removes or replaces the raw carrier therefore cannot clear the request-scoped bit.
+Explicit video parts remain sensitive when malformed, and nested carrier objects are inspected under
+the same bounds. Rejected-request persistence also inspects the body itself, so forgetting to pass the
+bit at one caller does not expose a raw carrier.
+
+The request-scoped bit protects OmniRoute-owned application paths in addition to structured payload
+clones. Native priority, round-robin, pinned, and fusion diagnostics; quality-rejection and live-event
+logs; terminal combo errors; proxy fast-fail logs; guardrail-registry logs; plugin-dispatcher failure
+logs; and stream lifecycle callbacks retain only the constant marker when their detail could echo the
+request. A request-scoped executor logger keeps the diagnostic tag but replaces arbitrary executor
+messages with the marker and drops attached metadata before those values reach the application
+logger. Context Relay and Universal Handoff summaries are still generated from a sanitized clone:
+safe adjacent conversation context remains available while recognized carriers and trusted generated
+descriptions are omitted. Memory may likewise extract safe request-derived text from the sanitized
+copy, but response-derived Memory extraction is skipped because an upstream response may echo the
+transcript. Daily-quota classification still inspects the original upstream error, while sensitive
+requests use the server-resolved model as the retained lockout key instead of promoting a model token
+parsed from that diagnostic. These rules affect retained copies, not the live provider request or the
+functional response returned to the same client.
+
+Inspection is bounded by depth, aggregate entries, trusted identities, description-prefix
+occurrences, candidate hashes, and total hashed text. Cycles and binary views are handled without
+retaining their contents. If a bound is exceeded, or an enumerable getter/proxy throws during
+inspection, the retained copy fails closed to the omission marker; the live request is not changed.
+
+Privacy-redacted Responses artifacts cannot reconstruct the omitted transcript portion of
+`previous_response_id` history. `responsesContinuationStore.ts` therefore reuses only valid,
+non-truncated retained `input` and `output` arrays, including the explicit omission marker, and never
+attempts to restore raw transcript text from the pipeline marker. This preserves continuation for the
+safe portions of the turn while making the missing private segment visible; a client that needs that
+context again must submit it as part of a new live request.
+
+Custom guardrails and plugins are privileged, in-process processors: they intentionally receive the
+live payload so they can inspect, transform, or block it. OmniRoute supplies the server-owned
+`videoTranscriptSensitive` bit, wraps `GuardrailContext.log`, and protects errors emitted by its native
+plugin dispatcher. It cannot control a third-party processor that independently writes the live body
+to `console`, a file, a database, or the network. Operators must audit such code and treat its own
+sinks as outside the OmniRoute-owned retention boundary; clearing or ignoring the bit does not make
+the transcript safe to persist.
+
 An advanced caller may provide an already-authorized `audioTranscript` track
 for the same video. The fusion seam runs visual and audio observations under
 one deadline and abort signal, orders them on a common timeline, collapses

llm.txt

@@ -1,6 +1,6 @@
 # OmniRoute
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 357 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -277,7 +277,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **354 AI providers** with automatic format translation
+- **357 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -475,7 +475,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 ## v3.8.x Highlights
 
-- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
+- **357-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
 - **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
 - **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
 - **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

open-sse/config/searchRegistry.ts

@@ -370,6 +370,26 @@ export const SEARCH_PROVIDERS: Record<string, SearchProviderConfig> = {
     cacheTTLMs: 5 * 60 * 1000,
     fallbackOnly: true,
   },
+
+  // Free public web search for AI agents (https://anysearch.com). fallback-only:
+  // a cost-0 provider never overrides configured paid providers in automatic
+  // selection. max_results is capped at 10 upstream.
+  "anysearch-search": {
+    id: "anysearch-search",
+    name: "AnySearch",
+    baseUrl: "https://api.anysearch.com/v1/search",
+    method: "POST",
+    authType: "apikey",
+    authHeader: "bearer",
+    costPerQuery: 0,
+    freeMonthlyQuota: 0, // free tier is 1000 req/day (daily reset, not monthly) — 0 matches the xquik convention; the daily figure lives in the UI catalog authHint
+    searchTypes: ["web"],
+    defaultMaxResults: 5,
+    maxMaxResults: 10,
+    timeoutMs: 10_000,
+    cacheTTLMs: 5 * 60 * 1000,
+    fallbackOnly: true,
+  },
 };
 
 /**
@@ -419,6 +439,8 @@ export const SEARCH_PROVIDER_ALIASES: Record<string, string> = {
   x: "x-search",
   xquik: "xquik-search",
   xquik_search: "xquik-search",
+  anysearch: "anysearch-search",
+  anysearch_search: "anysearch-search",
 };
 
 export function resolveSearchProviderId(providerId: string): string {

open-sse/executors/anysearch-fetch.ts

@@ -0,0 +1,109 @@
+/**
+ * AnySearch Web Fetch Executor
+ *
+ * Fetches readable content from a URL using the AnySearch Extract API.
+ * POST https://api.anysearch.com/v1/extract
+ *
+ * Free tier: 1000 requests/day per key, shared with /v1/search. Bearer auth
+ * is optional upstream - keyless calls use the lower anonymous tier. Routing
+ * stays key-gated; anonymity only applies at call time.
+ * Docs: https://anysearch.com/docs
+ */
+
+import { sanitizeErrorMessage, buildErrorBody } from "../utils/error.ts";
+import type { WebFetchResult, WebFetchFormat, WebFetchCredentials } from "../handlers/webFetch.ts";
+
+const ANYSEARCH_EXTRACT_URL = "https://api.anysearch.com/v1/extract";
+const ANYSEARCH_TIMEOUT_MS = 30_000;
+
+interface AnysearchFetchOptions {
+  url: string;
+  format: WebFetchFormat;
+  includeMetadata: boolean;
+  credentials: WebFetchCredentials;
+}
+
+/**
+ * Execute an AnySearch extract request.
+ * The upstream contract is strict JSON: a single { url } object with no
+ * unknown fields, capped at 16 KiB - do not add request fields here.
+ */
+export async function anysearchFetch(opts: AnysearchFetchOptions): Promise<WebFetchResult> {
+  // format is accepted but unused: AnySearch extract always returns markdown-ish text
+  // (mirroring the context7 pattern of accepting the field without rejecting).
+  const { url, includeMetadata, credentials } = opts;
+
+  const controller = new AbortController();
+  const timeoutId = setTimeout(() => {
+    const err = new Error(`anysearch-fetch timeout after ${ANYSEARCH_TIMEOUT_MS}ms`);
+    err.name = "TimeoutError";
+    controller.abort(err);
+  }, ANYSEARCH_TIMEOUT_MS);
+
+  try {
+    const response = await fetch(ANYSEARCH_EXTRACT_URL, {
+      method: "POST",
+      headers: {
+        "Content-Type": "application/json",
+        ...(credentials.apiKey ? { Authorization: `Bearer ${credentials.apiKey}` } : {}),
+      },
+      body: JSON.stringify({ url }),
+      signal: controller.signal,
+    });
+
+    if (!response.ok) {
+      const rawError = await response.text().catch(() => `HTTP ${response.status}`);
+      const msg = sanitizeErrorMessage(`AnySearch error ${response.status}: ${rawError}`);
+      const body = buildErrorBody(response.status, msg);
+      return { success: false, status: response.status, error: body.error.message };
+    }
+
+    const data = (await response.json()) as Record<string, unknown>;
+
+    // Envelope: { code, message, data: { url, title, content } } - tolerate the
+    // enveloped and flat shapes before giving up.
+    const envelope =
+      data.data && typeof data.data === "object" && !Array.isArray(data.data)
+        ? (data.data as Record<string, unknown>)
+        : data;
+    const code = typeof data.code === "number" ? data.code : 0;
+    if (code !== 0) {
+      const errorMsg = String(data.error_code ?? data.message ?? code);
+      // Quota-shaped envelope errors map to 402 (failover-eligible), mirroring
+      // the search-side AnysearchSearchEnvelopeError → 402 pattern in anysearchSearch.ts.
+      const isQuota = /quota|exceed|limit|balance|credit|exhaust/i.test(errorMsg);
+      const status = isQuota ? 402 : 422;
+      const msg = sanitizeErrorMessage(`AnySearch extract failed: ${errorMsg}`);
+      const body = buildErrorBody(status, msg);
+      return { success: false, status, error: body.error.message };
+    }
+
+    const content = String(envelope.content ?? "");
+    const title = envelope.title != null ? String(envelope.title) : null;
+
+    const metadata = includeMetadata ? { title, description: null } : null;
+
+    return {
+      success: true,
+      data: {
+        provider: "anysearch-search",
+        url,
+        content,
+        links: [],
+        metadata,
+        screenshot_url: null,
+      },
+    };
+  } catch (err: unknown) {
+    if (err instanceof Error && err.name === "AbortError") {
+      const body = buildErrorBody(504, "AnySearch request timed out");
+      return { success: false, status: 504, error: body.error.message };
+    }
+    const msg =
+      err instanceof Error ? sanitizeErrorMessage(err.message) : sanitizeErrorMessage(String(err));
+    const body = buildErrorBody(502, msg);
+    return { success: false, status: 502, error: body.error.message };
+  } finally {
+    clearTimeout(timeoutId);
+  }
+}

open-sse/executors/base.ts

@@ -179,10 +179,10 @@ export type ProviderCredentials = {
 };
 
 export type ExecutorLog = {
-  debug?: (tag: string, message: string) => void;
-  info?: (tag: string, message: string) => void;
-  warn?: (tag: string, message: string) => void;
-  error?: (tag: string, message: string) => void;
+  debug?: (tag: string, message: string, data?: Record<string, unknown> | null) => void;
+  info?: (tag: string, message: string, data?: Record<string, unknown> | null) => void;
+  warn?: (tag: string, message: string, data?: Record<string, unknown> | null) => void;
+  error?: (tag: string, message: string, data?: Record<string, unknown> | null) => void;
 };
 
 export type ExecuteInput = {
@@ -202,6 +202,10 @@ export type ExecuteInput = {
    * this to apply client-format-aware policies such as `</think>` close-marker
    * suppression. */
   clientResponseFormat?: string | null;
+  /** True when upstream diagnostics may echo a video transcript. Executors must
+   * preserve operational responses/errors while omitting those echoes from
+   * retained logs. */
+  videoTranscriptSensitive?: boolean;
   /** Callback to persist tokens that are proactively refreshed during execution.
    * Accepts a partial credentials patch (e.g. `{ accessToken, refreshToken }` or
    * `{ testStatus: "expired", isActive: false }`); the caller merges into the

open-sse/executors/duckduckgo-web.ts

@@ -16,6 +16,7 @@ import { prepareToolMessages, buildToolAwareResult } from "../translator/webTool
 import type { Session } from "../services/sessionPool/session.ts";
 import { tryBackedChat } from "../services/browserBackedChat.ts";
 import { sanitizeErrorMessage } from "../utils/error.ts";
+import { normalizeSystemRole } from "../services/roleNormalizer.ts";
 
 // Issue #6999: Lightweight circuit breaker for the DuckDuckGo executor.
 // After CB_THRESHOLD consecutive failures (429, 5xx, or network errors),
@@ -559,8 +560,17 @@ export class DuckDuckGoWebExecutor extends BaseExecutor {
         }
       }
 
+      // #ddgw defense-in-depth: duckchat/v1/chat accepts only user/assistant roles.
+      // Normalize after catalog resolution so the effective upstream model is used.
+      // This also shields the system tool prompt injected by prepareToolMessages.
+      const normalizedMessages = normalizeSystemRole(
+        messages,
+        "duckduckgo-web",
+        upstreamModel
+      ) as typeof messages;
+
       const sendChat = async (vqdHeaders: DuckDuckGoAuthHeaders): Promise<Response> => {
-        const payload = buildDuckDuckGoPayload(upstreamModel, messages);
+        const payload = buildDuckDuckGoPayload(upstreamModel, normalizedMessages);
         const response = await fetch(CHAT_URL, {
           method: "POST",
           headers: mergeHeadersCaseInsensitive(
@@ -786,10 +796,7 @@ export class DuckDuckGoWebExecutor extends BaseExecutor {
           try {
             return {
               vqd4: retry.vqd4,
-              vqdHash1: await solveDuckDuckGoChallenge(
-                retry.vqdHash1,
-                FAKE_HEADERS["User-Agent"]
-              ),
+              vqdHash1: await solveDuckDuckGoChallenge(retry.vqdHash1, FAKE_HEADERS["User-Agent"]),
               status: retry.status,
               retryAfter: retry.retryAfter,
             };

open-sse/executors/glm.ts

@@ -1,4 +1,5 @@
 import { randomUUID } from "node:crypto";
+import { redactVideoTranscriptSensitiveText } from "../../src/lib/guardrails/videoTranscriptLogRedaction.ts";
 import type { KeyHealth } from "../services/apiKeyRotator.ts";
 
 import { DefaultExecutor } from "./default.ts";
@@ -45,6 +46,11 @@ function asRecord(value: unknown): JsonRecord | null {
   return value && typeof value === "object" && !Array.isArray(value) ? (value as JsonRecord) : null;
 }
 
+function retainGlmDiagnostic(error: unknown, input: ExecuteInput): string {
+  const message = error instanceof Error ? error.message : String(error);
+  return redactVideoTranscriptSensitiveText(message, input.videoTranscriptSensitive === true);
+}
+
 function getEffectiveKey(credentials: ProviderCredentials): string {
   const extraKeys = (credentials.providerSpecificData?.extraApiKeys as string[] | undefined) ?? [];
   if (credentials.apiKey && credentials.connectionId && extraKeys.length > 0) {
@@ -465,6 +471,7 @@ export class GlmExecutor extends DefaultExecutor {
         timeoutMs: STREAM_READINESS_TIMEOUT_MS,
         provider: this.provider,
         model: input.model,
+        redactUpstreamDiagnosticForLog: input.videoTranscriptSensitive === true,
         log: input.log,
       });
       response = readiness.response;
@@ -559,7 +566,7 @@ export class GlmExecutor extends DefaultExecutor {
       if (!isRetryableGlmFallbackError(error)) throw error;
       input.log?.debug?.(
         "GLM_FALLBACK",
-        `${primaryTransport} error (${error instanceof Error ? error.message : String(error)}); trying ${fallbackTransport}`
+        `${primaryTransport} error (${retainGlmDiagnostic(error, input)}); trying ${fallbackTransport}`
       );
     }
 
@@ -572,7 +579,7 @@ export class GlmExecutor extends DefaultExecutor {
       if (!primaryResult) throw error;
       input.log?.debug?.(
         "GLM_FALLBACK",
-        `${fallbackTransport} fallback failed (${error instanceof Error ? error.message : String(error)}); returning primary response`
+        `${fallbackTransport} fallback failed (${retainGlmDiagnostic(error, input)}); returning primary response`
       );
     }
 

open-sse/handlers/chatCore.ts

@@ -166,6 +166,11 @@ import {
   runWithCasGuard,
 } from "../services/tokenRefresh.ts";
 import { createRequestLogger } from "../utils/requestLogger.ts";
+import {
+  redactVideoTranscriptSensitiveText,
+  resolveVideoTranscriptLogSensitivity,
+} from "@/lib/guardrails/videoTranscriptLogRedaction";
+import { createExecutorRetentionLog } from "./chatCore/executorRetentionLog.ts";
 import { createPreparedRequestLogger, runWithCapture } from "../utils/providerRequestLogging.ts";
 import { summarizeToolSources } from "../utils/toolSources.ts";
 import { applyResponsesPreviousResponseIdPolicy } from "../utils/responsesStatePolicy.ts";
@@ -524,7 +529,22 @@ export async function handleChatCore({
   skipResourcePressureGuard = false,
   reasoningTransportFallback = "drop",
   managedLease = null,
+  videoTranscriptSensitive = false,
+  videoTranscriptDescriptionFingerprints = [],
 }) {
+  videoTranscriptSensitive =
+    videoTranscriptSensitive ||
+    resolveVideoTranscriptLogSensitivity({
+      rawRequestBody: clientRawRequest?.body,
+      processedBody: body,
+      trustedDescriptionFingerprints: videoTranscriptDescriptionFingerprints,
+    });
+  const retainedErrorTextForLog = (error: unknown): string =>
+    redactVideoTranscriptSensitiveText(
+      error instanceof Error ? error.message : String(error),
+      videoTranscriptSensitive
+    );
+  const retainedExecutorLog = createExecutorRetentionLog(log, videoTranscriptSensitive);
   let { provider, model, extendedContext } = modelInfo;
   const resilienceSettings = resolveResilienceSettings(cachedSettings);
   if (!skipResourcePressureGuard) {
@@ -637,6 +657,7 @@ export async function handleChatCore({
     apiKeyInfo,
     headers: clientRawRequest?.headers,
     log,
+    videoTranscriptSensitive,
   });
   if (pluginGate.blocked === true) {
     return {
@@ -721,6 +742,7 @@ export async function handleChatCore({
     effectiveServiceTier,
     startTime,
     log,
+    videoTranscriptSensitive,
   });
   if (idempotencyHit) {
     return idempotencyHit;
@@ -902,6 +924,8 @@ export async function handleChatCore({
       stage: "registered",
       correlationId,
       sessionTag: conversationId || null,
+      videoTranscriptSensitive,
+      videoTranscriptDescriptionFingerprints,
     }) || generateRequestId();
 
   // Initialize rate limit settings from persisted DB (once, lazy)
@@ -1034,6 +1058,8 @@ export async function handleChatCore({
       noLogEnabled,
       correlationId,
       modelPinned,
+      videoTranscriptSensitive,
+      videoTranscriptDescriptionFingerprints,
       // Resolved conversationId (open-sse/services/conversationTracker.ts) wins when
       // present — it's populated for every request now, not just ones where the
       // client explicitly sent x-omniroute-session-id. The raw header remains a
@@ -1156,8 +1182,17 @@ export async function handleChatCore({
     model,
     provider: provider || undefined,
     connectionId: connectionId || credentials?.connectionId || undefined,
+    videoTranscriptSensitive,
+    videoTranscriptDescriptionFingerprints,
   });
-  const pendingScope = { id: pendingRequestId, model, provider, connectionId: pendingConnId };
+  const pendingScope = {
+    id: pendingRequestId,
+    model,
+    provider,
+    connectionId: pendingConnId,
+    videoTranscriptSensitive,
+    videoTranscriptDescriptionFingerprints,
+  };
   const providerRequestCapture = createPreparedRequestLogger(reqLogger, pendingScope);
   // 0. Log client raw request (before format conversion)
   if (clientRawRequest) {
@@ -1203,6 +1238,7 @@ export async function handleChatCore({
     apiKeyId: apiKeyInfo?.id ?? undefined,
     cacheDefaultMode: (apiKeyInfo as { cacheDefaultMode?: "legacy" | "bypass" } | null)
       ?.cacheDefaultMode,
+    videoTranscriptSensitive,
   });
   if (cacheHit) {
     return cacheHit;
@@ -1482,8 +1518,7 @@ export async function handleChatCore({
         } catch (err) {
           log?.debug?.(
             "COMPRESSION",
-            "Combo compression override lookup skipped: " +
-              (err instanceof Error ? err.message : String(err))
+            "Combo compression override lookup skipped: " + retainedErrorTextForLog(err)
           );
         }
       }
@@ -1492,10 +1527,7 @@ export async function handleChatCore({
         const { listCompressionCombos } = await import("../../src/lib/db/compressionCombos.ts");
         namedCombos = buildNamedComboLookup(listCompressionCombos());
       } catch (err) {
-        log?.debug?.(
-          "COMPRESSION",
-          "Named combos load skipped: " + (err instanceof Error ? err.message : String(err))
-        );
+        log?.debug?.("COMPRESSION", "Named combos load skipped: " + retainedErrorTextForLog(err));
       }
       // Phase 3: per-request override. Unknown values fall through in the resolver (never error).
       const compressionHeader = resolveCompressionHeader(clientRawRequest?.headers ?? null);
@@ -1543,8 +1575,7 @@ export async function handleChatCore({
         } catch (err) {
           log?.debug?.(
             "COMPRESSION",
-            "Default compression combo lookup skipped: " +
-              (err instanceof Error ? err.message : String(err))
+            "Default compression combo lookup skipped: " + retainedErrorTextForLog(err)
           );
         }
       }
@@ -1586,10 +1617,7 @@ export async function handleChatCore({
             }
           }
         } catch (err) {
-          log?.debug?.(
-            "COMPRESSION",
-            "Output styles skipped: " + (err instanceof Error ? err.message : String(err))
-          );
+          log?.debug?.("COMPRESSION", "Output styles skipped: " + retainedErrorTextForLog(err));
         }
       }
       const compressionInputBody = body as Record<string, unknown>;
@@ -1899,8 +1927,7 @@ export async function handleChatCore({
     } catch (err) {
       log?.warn?.(
         "COMPRESSION",
-        "Compression pipeline error (non-fatal): " +
-          (err instanceof Error ? err.message : String(err))
+        "Compression pipeline error (non-fatal): " + retainedErrorTextForLog(err)
       );
     }
     // --- End Modular Compression Pipeline ---
@@ -1954,7 +1981,10 @@ export async function handleChatCore({
           `Combo context limit: ${resolved.limit} (source=${resolved.source})`
         );
       } catch (err) {
-        log?.warn?.("CONTEXT", "Failed to resolve combo limits for compression: " + err);
+        log?.warn?.(
+          "CONTEXT",
+          "Failed to resolve combo limits for compression: " + retainedErrorTextForLog(err)
+        );
       }
     }
 
@@ -2432,13 +2462,21 @@ export async function handleChatCore({
     try {
       const { runOnError } = await import("@/lib/plugins/hooks");
       await runOnError(
-        { requestId: traceId, body, model, provider, apiKeyInfo, metadata: {} },
+        {
+          requestId: traceId,
+          body,
+          model,
+          provider,
+          apiKeyInfo,
+          metadata: {},
+          videoTranscriptSensitive,
+        },
         error instanceof Error ? error : new Error(String(error))
       );
     } catch (pluginErr) {
       log?.debug?.(
         "PLUGIN",
-        `onError hook error (non-fatal): ${pluginErr instanceof Error ? pluginErr.message : String(pluginErr)}`
+        `onError hook error (non-fatal): ${retainedErrorTextForLog(pluginErr)}`
       );
     }
 
@@ -2450,7 +2488,13 @@ export async function handleChatCore({
     const message = error?.message || "Invalid request";
     const errorType = typeof error?.errorType === "string" ? error.errorType : null;
 
-    log?.warn?.("TRANSLATE", `Request translation failed: ${message}`);
+    log?.warn?.(
+      "TRANSLATE",
+      `Request translation failed: ${redactVideoTranscriptSensitiveText(
+        message,
+        videoTranscriptSensitive
+      )}`
+    );
 
     if (errorType) {
       trackPendingRequest(model, provider, connectionId, false);
@@ -2544,8 +2588,7 @@ export async function handleChatCore({
       // must never turn an otherwise valid translated request into a 500.
       log?.warn?.(
         "COMPRESSION",
-        "Post-translation OmniGlyph skipped: " +
-          (error instanceof Error ? error.message : String(error))
+        "Post-translation OmniGlyph skipped: " + retainedErrorTextForLog(error)
       );
     }
   }
@@ -2839,7 +2882,7 @@ export async function handleChatCore({
   const resolveExecutorWithProxy = (prov: string) =>
     resolveExecutorWithProxyFor(
       prov,
-      log,
+      retainedExecutorLog,
       (credentials?.providerSpecificData as Record<string, unknown> | null | undefined) ?? null
     );
 
@@ -2861,7 +2904,7 @@ export async function handleChatCore({
       }).catch((err: unknown): EnforceDecision => {
         log?.warn?.(
           "QUOTA_SHARE",
-          `enforceQuotaShare failed; fail-open: ${err instanceof Error ? err.message : String(err)}`
+          `enforceQuotaShare failed; fail-open: ${retainedErrorTextForLog(err)}`
         );
         return { kind: "allow" as const };
       });
@@ -2903,7 +2946,7 @@ export async function handleChatCore({
       // Outer fail-open guard — should not be reached (inner .catch covers it)
       log?.warn?.(
         "QUOTA_SHARE",
-        `[quotaShare] enforceQuotaShare unexpected error; fail-open: ${err instanceof Error ? err.message : String(err)}`
+        `[quotaShare] enforceQuotaShare unexpected error; fail-open: ${retainedErrorTextForLog(err)}`
       );
     }
   }
@@ -2915,7 +2958,7 @@ export async function handleChatCore({
     } catch (err) {
       log?.warn?.(
         "QUOTA_SHARE",
-        `[quotaShare] could not set soft penalty on candidate: ${err instanceof Error ? err.message : String(err)}`
+        `[quotaShare] could not set soft penalty on candidate: ${retainedErrorTextForLog(err)}`
       );
     }
   }
@@ -2949,6 +2992,8 @@ export async function handleChatCore({
   let onPipelineStreamError: streamFailure.PipelineStreamErrorHandler | null = null;
   let onClientDisconnectFinalize:
     ((event: { reason: string; duration: number }) => boolean) | null = null;
+  const redactStreamDiagnosticsForLog =
+    videoTranscriptSensitive || reqLogger.isVideoTranscriptSensitive();
 
   // Create stream controller for disconnect detection
   const streamController = createStreamController({
@@ -2980,11 +3025,15 @@ export async function handleChatCore({
     clientAbortSignal: clientRawRequest?.signal,
     allowCompletedToolHandoffGrace: isCodexResponsesEcho,
     clientDisconnectGracePeriodMs: STREAM_DISCONNECT_GRACE_PERIOD_MS,
+    redactStreamDiagnosticsForLog,
   });
 
   const dedupRequestBody = { ...translatedBody, model: `${provider}/${model}`, stream };
   const dedupEnabled = shouldDeduplicate(dedupRequestBody);
-  const dedupHash = dedupEnabled ? computeRequestHash(dedupRequestBody) : null;
+  // Namespaced by the calling API key: dedup hands the SAME response object to
+  // every joiner, so a shared hash across keys is a cross-principal response
+  // leak (GHSA-6c7w-56xp-wpc6).
+  const dedupHash = dedupEnabled ? computeRequestHash(dedupRequestBody, apiKeyInfo?.id) : null;
 
   const executeProviderRequest = async (modelToCall = effectiveModel, allowDedup = false) => {
     const execute = async () => {
@@ -3109,7 +3158,7 @@ export async function handleChatCore({
                       execCreds?.providerSpecificData
                     ),
                     signal: streamController.signal,
-                    log,
+                    log: retainedExecutorLog,
                     execute: (signal) =>
                       runWithCapture(providerRequestCapture, () =>
                         executor.execute({
@@ -3118,7 +3167,7 @@ export async function handleChatCore({
                           stream: upstreamStream,
                           credentials: execCreds,
                           signal,
-                          log,
+                          log: retainedExecutorLog,
                           extendedContext,
                           upstreamExtraHeaders: buildUpstreamHeadersForExecute(modelToCall),
                           clientHeaders: buildExecutorClientHeaders(
@@ -3126,6 +3175,7 @@ export async function handleChatCore({
                             userAgent
                           ),
                           clientResponseFormat,
+                          videoTranscriptSensitive,
                           onCredentialsRefreshed,
                           skipUpstreamRetry,
                           contextEditing: { enabled: contextEditingEnabled },
@@ -3160,7 +3210,7 @@ export async function handleChatCore({
                     invalidateCodexQuotaCache(String(attemptConnectionId));
                   }
                 } catch (err) {
-                  const errMessage = err instanceof Error ? err.message : String(err);
+                  const errMessage = retainedErrorTextForLog(err);
                   log?.debug?.("CODEX", `Failed to persist codex quota state: ${errMessage}`);
                 }
               }
@@ -3425,7 +3475,7 @@ export async function handleChatCore({
                           execCreds?.providerSpecificData
                         ),
                         signal: streamController.signal,
-                        log,
+                        log: retainedExecutorLog,
                         execute: (signal) =>
                           runWithCapture(providerRequestCapture, () =>
                             executor.execute({
@@ -3434,7 +3484,7 @@ export async function handleChatCore({
                               stream: upstreamStream,
                               credentials: execCreds,
                               signal,
-                              log,
+                              log: retainedExecutorLog,
                               extendedContext,
                               upstreamExtraHeaders: buildUpstreamHeadersForExecute(modelToCall),
                               clientHeaders: buildExecutorClientHeaders(
@@ -3442,6 +3492,7 @@ export async function handleChatCore({
                                 userAgent
                               ),
                               clientResponseFormat,
+                              videoTranscriptSensitive,
                               onCredentialsRefreshed,
                               skipUpstreamRetry,
                               contextEditing: { enabled: contextEditingEnabled },
@@ -3674,7 +3725,9 @@ export async function handleChatCore({
     } catch (err) {
       // Fail-open at Tier 2: Tier 1 already enforced the model/global limit pre-dispatch.
       // A transient counter read error here must not break an otherwise-valid request.
-      log?.warn?.("TOKEN_LIMIT", "Tier 2 token-limit check failed; allowing request", { err });
+      log?.warn?.("TOKEN_LIMIT", "Tier 2 token-limit check failed; allowing request", {
+        error: retainedErrorTextForLog(err),
+      });
     }
   }
 
@@ -3693,7 +3746,9 @@ export async function handleChatCore({
         );
       }
     } catch (err) {
-      log?.warn?.("GEMINI_RATE_LIMIT", "Pre-dispatch TPM check failed; allowing request", { err });
+      log?.warn?.("GEMINI_RATE_LIMIT", "Pre-dispatch TPM check failed; allowing request", {
+        error: retainedErrorTextForLog(err),
+      });
     }
   }
 
@@ -3843,7 +3898,12 @@ export async function handleChatCore({
       failureStatus,
       upstreamErrorCode || (error instanceof Error && error.name ? error.name : "upstream_error")
     );
-    console.log(`${COLORS.red}[ERROR] ${failureMessage}${COLORS.reset}`);
+    console.log(
+      `${COLORS.red}[ERROR] ${redactVideoTranscriptSensitiveText(
+        failureMessage,
+        videoTranscriptSensitive
+      )}${COLORS.reset}`
+    );
     if (stream && upstreamErrorCode) {
       const result = createStreamingErrorResult(
         failureStatus,
@@ -3975,11 +4035,12 @@ export async function handleChatCore({
               stream: upstreamStream,
               credentials: getExecutionCredentials(),
               signal: streamController.signal,
-              log,
+              log: retainedExecutorLog,
               extendedContext,
               upstreamExtraHeaders: buildUpstreamHeadersForExecute(retryModelId),
               clientHeaders: buildExecutorClientHeaders(clientRawRequest?.headers, userAgent),
               clientResponseFormat,
+              videoTranscriptSensitive,
               onCredentialsRefreshed,
               skipUpstreamRetry: isCombo,
               contextEditing: { enabled: contextEditingEnabled },
@@ -4009,9 +4070,13 @@ export async function handleChatCore({
         // executor throw). Don't swallow — the operator-visible signal "the user
         // saw 401 even though auth was actually fixed" is much more confusing
         // than the original 401 alone. Surface at error level with sanitization.
+        const retainedRetryError = redactVideoTranscriptSensitiveText(
+          sanitizeErrorMessage(retryErr),
+          videoTranscriptSensitive
+        );
         log?.error?.(
           "TOKEN",
-          `${provider?.toUpperCase()} | retry after refresh failed: ${sanitizeErrorMessage(retryErr)}`
+          `${provider?.toUpperCase()} | retry after refresh failed: ${retainedRetryError}`
         );
       }
     } else {
@@ -4128,6 +4193,11 @@ export async function handleChatCore({
 
     if (signatureRecovery.succeeded) break providerFailure;
 
+    const retainedProviderMessage = redactVideoTranscriptSensitiveText(
+      message,
+      videoTranscriptSensitive
+    );
+
     // #10281 — tiny-budget reasoning probes (e.g. Claude Code's `/model` check
     // sends `max_tokens: 1`): the model burns the whole budget on thinking, and
     // some upstreams (e.g. api.cline.bot for deepseek-v4-flash) answer the empty
@@ -4150,7 +4220,7 @@ export async function handleChatCore({
       });
       log?.warn?.(
         "PROBE",
-        `Reasoning probe (max_tokens < ${REASONING_BUFFER_MIN_TRIGGER}) answered with truncated 200 — upstream reported "${message}"`
+        `Reasoning probe (max_tokens < ${REASONING_BUFFER_MIN_TRIGGER}) answered with truncated 200 — upstream reported "${retainedProviderMessage}"`
       );
       break providerFailure;
     }
@@ -4179,7 +4249,7 @@ export async function handleChatCore({
               {
                 testStatus: "banned",
                 isActive: false,
-                lastError: message,
+                lastError: retainedProviderMessage,
                 lastErrorType: errorType,
                 errorCode: String(statusCode),
               },
@@ -4210,7 +4280,7 @@ export async function handleChatCore({
           ) {
             await updateProviderConnection(errorConnectionId, {
               lastErrorType: errorType,
-              lastError: message,
+              lastError: retainedProviderMessage,
               errorCode: statusCode,
             });
             console.warn(
@@ -4223,7 +4293,7 @@ export async function handleChatCore({
               {
                 testStatus: "deactivated",
                 isActive: false,
-                lastError: message,
+                lastError: retainedProviderMessage,
                 lastErrorType: errorType,
                 errorCode: String(statusCode),
               },
@@ -4247,7 +4317,7 @@ export async function handleChatCore({
                 errorConnectionId,
                 {
                   testStatus: "credits_exhausted",
-                  lastError: message,
+                  lastError: retainedProviderMessage,
                   lastErrorType: errorType,
                   errorCode: String(statusCode),
                 },
@@ -4295,7 +4365,7 @@ export async function handleChatCore({
                   rateLimitedUntil: kimiRateLimitResetAt,
                   backoffLevel: 0,
                   lastErrorType: PROVIDER_ERROR_TYPES.RATE_LIMITED,
-                  lastError: message,
+                  lastError: retainedProviderMessage,
                   errorCode: statusCode,
                 });
                 console.warn(
@@ -4325,7 +4395,7 @@ export async function handleChatCore({
                   errorConnectionId,
                   {
                     testStatus: "credits_exhausted",
-                    lastError: message,
+                    lastError: retainedProviderMessage,
                     lastErrorType: errorType,
                     errorCode: String(statusCode),
                   },
@@ -4341,14 +4411,14 @@ export async function handleChatCore({
           // Normal 401 (token/session auth issue): keep account active for refresh/re-auth.
           await updateProviderConnection(errorConnectionId, {
             lastErrorType: errorType,
-            lastError: message,
+            lastError: retainedProviderMessage,
             errorCode: statusCode,
           });
         } else if (errorType === PROVIDER_ERROR_TYPES.OAUTH_INVALID_TOKEN) {
           // OAuth 401 with invalid credentials - token refresh can recover
           await updateProviderConnection(errorConnectionId, {
             lastErrorType: errorType,
-            lastError: message,
+            lastError: retainedProviderMessage,
             errorCode: statusCode,
           });
           console.warn(
@@ -4358,7 +4428,7 @@ export async function handleChatCore({
           // Cloud Code 403 with stale project: not a ban, keep account active.
           await updateProviderConnection(errorConnectionId, {
             lastErrorType: errorType,
-            lastError: message,
+            lastError: retainedProviderMessage,
             errorCode: statusCode,
           });
           console.warn(
@@ -4374,7 +4444,7 @@ export async function handleChatCore({
           const geoCooldownMs = COOLDOWN_MS.geoBlocked ?? 24 * 60 * 60 * 1000;
           await updateProviderConnection(errorConnectionId, {
             lastErrorType: errorType,
-            lastError: message,
+            lastError: retainedProviderMessage,
             errorCode: statusCode,
           });
           // T-PROBE: the 24h exclusion is a routing mutation — a probe must
@@ -4399,7 +4469,7 @@ export async function handleChatCore({
           const byopCooldownMs = COOLDOWN_MS.gcpProjectRequired ?? 24 * 60 * 60 * 1000;
           await updateProviderConnection(errorConnectionId, {
             lastErrorType: errorType,
-            lastError: message,
+            lastError: retainedProviderMessage,
             errorCode: statusCode,
           });
           try {
@@ -4445,7 +4515,13 @@ export async function handleChatCore({
     }).catch(() => {});
 
     const errMsg = formatProviderError(new Error(message), provider, model, statusCode);
-    console.log(`${COLORS.red}[ERROR] ${errMsg}${COLORS.reset}`);
+    const retainedErrMsg = formatProviderError(
+      new Error(retainedProviderMessage),
+      provider,
+      model,
+      statusCode
+    );
+    console.log(`${COLORS.red}[ERROR] ${retainedErrMsg}${COLORS.reset}`);
 
     // Log Antigravity retry time if available
     if (retryAfterMs && provider === "antigravity") {
@@ -4772,12 +4848,11 @@ export async function handleChatCore({
             }
           }
         } catch (retryErr) {
-          log?.warn?.(
-            "RETRY",
-            `clinepass retry failed: ${
-              retryErr instanceof Error ? retryErr.message : String(retryErr)
-            }`
+          const retainedRetryError = redactVideoTranscriptSensitiveText(
+            retryErr instanceof Error ? retryErr.message : String(retryErr),
+            videoTranscriptSensitive
           );
+          log?.warn?.("RETRY", `clinepass retry failed: ${retainedRetryError}`);
         }
       }
       if (envError) {
@@ -4996,6 +5071,7 @@ export async function handleChatCore({
         cacheReasoningFromAssistantMessage(msg, provider, model, {
           scope: reasoningCacheScope,
           historyMessages: Array.isArray(historyMessages) ? historyMessages : [],
+          videoTranscriptSensitive,
         });
       }
     } catch {
@@ -5047,12 +5123,18 @@ export async function handleChatCore({
     );
 
     if (memoryOwnerId && memorySettings?.enabled && memorySettings.maxTokens > 0) {
-      const requestMemoryText = extractMemoryTextFromRequestBody(body as Record<string, unknown>);
+      const requestMemoryText = extractMemoryTextFromRequestBody(
+        body as Record<string, unknown>,
+        videoTranscriptSensitive,
+        { trustedDescriptionFingerprints: videoTranscriptDescriptionFingerprints }
+      );
       if (requestMemoryText) {
         extractFacts(requestMemoryText, memoryOwnerId, pipelineSessionId);
       }
 
-      const memoryText = extractMemoryTextFromResponse(memoryExtractionResponse);
+      const memoryText = videoTranscriptSensitive
+        ? ""
+        : extractMemoryTextFromResponse(memoryExtractionResponse);
       if (memoryText) {
         extractFacts(memoryText, memoryOwnerId, pipelineSessionId);
       }
@@ -5092,6 +5174,7 @@ export async function handleChatCore({
       provider,
       responsePayloadFormat,
       clientResponseFormat,
+      videoTranscriptSensitive,
     });
     const postCallGuardrails = await guardrailRegistry.runPostCallHooks(
       translatedResponse,
@@ -5133,7 +5216,10 @@ export async function handleChatCore({
       }
       log?.warn?.(
         "GUARDRAIL",
-        `Response blocked by ${postCallGuardrails.guardrail || "guardrail"}: ${guardrailMessage}`
+        `Response blocked by ${postCallGuardrails.guardrail || "guardrail"}: ${redactVideoTranscriptSensitiveText(
+          guardrailMessage,
+          videoTranscriptSensitive
+        )}`
       );
       finalizePendingScope(pendingScope, {
         providerResponse: responseBody,
@@ -5236,6 +5322,7 @@ export async function handleChatCore({
       apiKeyId: apiKeyInfo?.id ?? undefined,
       usage,
       log,
+      videoTranscriptSensitive,
     });
 
     // ── Phase 9.2: Save for idempotency ──
@@ -5315,6 +5402,7 @@ export async function handleChatCore({
       apiKeyInfo,
       headers: clientRawRequest?.headers,
       response: { status: 200, data: translatedResponse },
+      videoTranscriptSensitive,
     });
 
     // Routing event (feedback foundation) — fire-and-forget, cheap.
@@ -5390,6 +5478,7 @@ export async function handleChatCore({
     provider,
     model,
     log,
+    redactUpstreamDiagnosticForLog: videoTranscriptSensitive,
   });
   if (streamReadiness.ok === false) {
     const { response: failureResponse, reason } = streamReadiness;
@@ -5521,6 +5610,7 @@ export async function handleChatCore({
           cacheReasoningFromAssistantMessage(msg, provider, model, {
             scope: reasoningCacheScope,
             historyMessages: Array.isArray(historyMessages) ? historyMessages : [],
+            videoTranscriptSensitive,
           });
         }
       } catch {
@@ -5553,6 +5643,7 @@ export async function handleChatCore({
       status: normalizedStreamStatus,
       error: streamError,
       errorCode: streamErrorCode,
+      videoTranscriptSensitive,
     });
 
     // Track cache token metrics for streaming responses
@@ -5675,14 +5766,20 @@ export async function handleChatCore({
       memorySettings.maxTokens > 0 &&
       streamStatus === 200
     ) {
-      const requestMemoryText = extractMemoryTextFromRequestBody(body as Record<string, unknown>);
+      const requestMemoryText = extractMemoryTextFromRequestBody(
+        body as Record<string, unknown>,
+        videoTranscriptSensitive,
+        { trustedDescriptionFingerprints: videoTranscriptDescriptionFingerprints }
+      );
       if (requestMemoryText) {
         extractFacts(requestMemoryText, memoryOwnerId, pipelineSessionId);
       }
 
-      const streamedMemoryText = extractMemoryTextFromResponse(
-        (streamResponseBody ?? null) as Record<string, unknown> | null
-      );
+      const streamedMemoryText = videoTranscriptSensitive
+        ? ""
+        : extractMemoryTextFromResponse(
+            (streamResponseBody ?? null) as Record<string, unknown> | null
+          );
       if (streamedMemoryText) {
         extractFacts(streamedMemoryText, memoryOwnerId, pipelineSessionId);
       }
@@ -5699,6 +5796,7 @@ export async function handleChatCore({
       apiKeyId: apiKeyInfo?.id ?? undefined,
       streamUsage,
       log,
+      videoTranscriptSensitive,
     });
 
     // Plugin onStreamComplete hook — fire-and-forget, fail-open (#9571)
@@ -5767,7 +5865,8 @@ export async function handleChatCore({
       // openai-responses → openai translation still wants the namespace identity
       // map for #7936-style round-trip closure when the client also speaks
       // Responses (Codex CLI).
-      requestToolIdentityMap
+      requestToolIdentityMap,
+      redactStreamDiagnosticsForLog
     );
   } else if (needsTranslation(targetFormat, clientResponseFormat)) {
     // Standard translation for other providers
@@ -5797,7 +5896,8 @@ export async function handleChatCore({
         clientResponseFormat,
       }),
       customToolNames,
-      requestToolIdentityMap
+      requestToolIdentityMap,
+      redactStreamDiagnosticsForLog
     );
   } else {
     log?.debug?.("STREAM", `Standard passthrough mode`);
@@ -5812,7 +5912,8 @@ export async function handleChatCore({
       apiKeyInfo,
       handleStreamFailure,
       clientResponseFormat,
-      requestToolIdentityMap
+      requestToolIdentityMap,
+      redactStreamDiagnosticsForLog
     );
   }
 
@@ -5824,6 +5925,7 @@ export async function handleChatCore({
     clientRawRequestHeaders: clientRawRequest?.headers,
     clientResponseFormat,
     echoModel,
+    redactStreamDiagnosticsForLog,
     responseHeaders,
   });
 
@@ -5839,6 +5941,7 @@ export async function handleChatCore({
     apiKeyInfo,
     headers: clientRawRequest?.headers,
     response: { status: 200, streamed: true },
+    videoTranscriptSensitive,
   });
 
   return {

open-sse/handlers/chatCore/attemptLogging.ts

@@ -15,6 +15,10 @@ import { logAuditEvent } from "@/lib/compliance";
 import { emit } from "@/lib/events/eventBus";
 import type { RequestCompletedPayload, RequestFailedPayload } from "@/lib/events/types";
 import { saveCallLog } from "@/lib/usageDb";
+import {
+  VIDEO_TRANSCRIPT_LOG_OMISSION_MARKER,
+  VIDEO_TRANSCRIPT_REDACTION_PIPELINE_KEY,
+} from "@/lib/guardrails/videoTranscriptLogRedaction";
 import { FORMATS } from "../../translator/formats.ts";
 import { takeEarlyKeepaliveBytes } from "../../utils/earlyKeepaliveByteBuffer.ts";
 import { cloneBoundedChatLogPayload, truncateForLog } from "./logTruncation.ts";
@@ -68,7 +72,13 @@ export type PersistAttemptLogsContext = {
   model: string | null | undefined;
   skillRequestId: string;
   detailedLoggingEnabled: boolean;
-  reqLogger: { getPipelinePayloads?: () => Record<string, unknown> | undefined } | null | undefined;
+  reqLogger:
+    | {
+        getPipelinePayloads?: () => Record<string, unknown> | undefined;
+        isVideoTranscriptSensitive?: () => boolean;
+      }
+    | null
+    | undefined;
   pendingRequestId: unknown;
   clientRawRequest: { endpoint?: string } | null | undefined;
   requestedModel: unknown;
@@ -89,12 +99,34 @@ export type PersistAttemptLogsContext = {
    * explicitly present (never synthesized from skillRequestId) — persisted as call_logs.session_tag
    * for per-session cost attribution. */
   sessionTag?: string | null;
+  /** Trusted request state derived from the Video Bridge guardrail result. */
+  videoTranscriptSensitive?: boolean;
+  /** Exact SHA-256 identities of transcript descriptions generated by the guardrail. */
+  videoTranscriptDescriptionFingerprints?: readonly string[];
 };
 
 function toConnectionId(value: unknown): string | null {
   return typeof value === "string" && value.trim().length > 0 ? value.trim() : null;
 }
 
+function omitSensitivePipelineResponse(value: unknown): Record<string, unknown> {
+  const record =
+    value && typeof value === "object" && !Array.isArray(value)
+      ? (value as Record<string, unknown>)
+      : {};
+  return {
+    ...(typeof record.timestamp === "string" ? { timestamp: record.timestamp } : {}),
+    ...(typeof record.status === "number" && Number.isFinite(record.status)
+      ? { status: record.status }
+      : {}),
+    ...(record.headers !== undefined ? { headers: VIDEO_TRANSCRIPT_LOG_OMISSION_MARKER } : {}),
+    ...(record.statusText !== undefined
+      ? { statusText: VIDEO_TRANSCRIPT_LOG_OMISSION_MARKER }
+      : {}),
+    body: VIDEO_TRANSCRIPT_LOG_OMISSION_MARKER,
+  };
+}
+
 function buildAccountRotationMeta(
   provider: string | null | undefined,
   initialConnectionId: string | null,
@@ -204,6 +236,8 @@ export function persistAttemptLogs(args: PersistAttemptLogsArgs, ctx: PersistAtt
     correlationId,
     modelPinned,
     sessionTag,
+    videoTranscriptSensitive,
+    videoTranscriptDescriptionFingerprints,
   } = ctx;
   const initialConnectionId = toConnectionId(connectionId);
   const finalConnectionId = toConnectionId(credentials?.connectionId) || initialConnectionId;
@@ -212,8 +246,21 @@ export function persistAttemptLogs(args: PersistAttemptLogsArgs, ctx: PersistAtt
     initialConnectionId,
     finalConnectionId
   );
+  const transcriptSensitive =
+    videoTranscriptSensitive === true || reqLogger?.isVideoTranscriptSensitive?.() === true;
+  const descriptionLogContext = {
+    trustedDescriptionFingerprints: videoTranscriptDescriptionFingerprints ?? [],
+  };
 
-  const providerWarnings = extractProviderWarnings(providerResponse, clientResponse, responseBody);
+  const detectedProviderWarnings = extractProviderWarnings(
+    providerResponse,
+    clientResponse,
+    responseBody
+  );
+  const providerWarnings =
+    transcriptSensitive && detectedProviderWarnings.length > 0
+      ? [VIDEO_TRANSCRIPT_LOG_OMISSION_MARKER]
+      : detectedProviderWarnings;
   if (providerWarnings.length > 0) {
     logAuditEvent({
       action: "provider.warning",
@@ -227,6 +274,7 @@ export function persistAttemptLogs(args: PersistAttemptLogsArgs, ctx: PersistAtt
         model,
         connectionId: finalConnectionId,
         httpStatus: status,
+        warningCount: detectedProviderWarnings.length,
         warnings: providerWarnings,
       },
     });
@@ -273,8 +321,51 @@ export function persistAttemptLogs(args: PersistAttemptLogsArgs, ctx: PersistAtt
         };
       }
     }
+    if (transcriptSensitive) {
+      pipelinePayloads[VIDEO_TRANSCRIPT_REDACTION_PIPELINE_KEY] = true;
+      for (const requestStage of [
+        "clientRawRequest",
+        "openaiRequest",
+        "providerRequest",
+      ] as const) {
+        if (pipelinePayloads[requestStage] !== undefined) {
+          pipelinePayloads[requestStage] = cloneBoundedChatLogPayload(
+            pipelinePayloads[requestStage],
+            0,
+            requestStage !== "clientRawRequest" ? descriptionLogContext : {}
+          ) as Record<string, unknown>;
+        }
+      }
+      if (pipelinePayloads.providerResponse !== undefined || providerResponse !== undefined) {
+        pipelinePayloads.providerResponse = omitSensitivePipelineResponse(
+          pipelinePayloads.providerResponse ?? providerResponse
+        );
+      }
+      if (pipelinePayloads.clientResponse !== undefined || clientResponse !== undefined) {
+        pipelinePayloads.clientResponse = omitSensitivePipelineResponse(
+          pipelinePayloads.clientResponse ?? clientResponse
+        );
+      }
+      if (pipelinePayloads.error !== undefined || error) {
+        const errorRecord =
+          pipelinePayloads.error && typeof pipelinePayloads.error === "object"
+            ? pipelinePayloads.error
+            : {};
+        pipelinePayloads.error = {
+          ...(typeof errorRecord.timestamp === "string"
+            ? { timestamp: errorRecord.timestamp }
+            : {}),
+          message: VIDEO_TRANSCRIPT_LOG_OMISSION_MARKER,
+        };
+      }
+      delete pipelinePayloads.streamChunks;
+    }
   }
 
+  const responseBodyForLog = transcriptSensitive
+    ? VIDEO_TRANSCRIPT_LOG_OMISSION_MARKER
+    : responseBody;
+
   saveCallLog({
     id: pendingRequestId,
     method: "POST",
@@ -290,10 +381,12 @@ export function persistAttemptLogs(args: PersistAttemptLogsArgs, ctx: PersistAtt
       attachLogMeta(truncateForLog(body as Record<string, unknown>), {
         ...accountRotationMeta,
         claudePromptCache: claudeCacheMeta,
-      })
+      }),
+      0,
+      descriptionLogContext
     ),
     responseBody: cloneBoundedChatLogPayload(
-      attachLogMeta(truncateForLog(responseBody as Record<string, unknown>), {
+      attachLogMeta(truncateForLog(responseBodyForLog as Record<string, unknown>), {
         ...accountRotationMeta,
         claudePromptCache: claudeCacheMeta
           ? {
@@ -305,7 +398,7 @@ export function persistAttemptLogs(args: PersistAttemptLogsArgs, ctx: PersistAtt
         claudePromptCacheUsage: claudeCacheUsageMeta,
       })
     ),
-    error: error || null,
+    error: transcriptSensitive && error ? VIDEO_TRANSCRIPT_LOG_OMISSION_MARKER : error || null,
     sourceFormat,
     targetFormat,
     comboName,
@@ -332,7 +425,7 @@ export function persistAttemptLogs(args: PersistAttemptLogsArgs, ctx: PersistAtt
     const lifecycle = resolveRequestLifecycleEvent({
       traceId,
       status,
-      error,
+      error: transcriptSensitive && error ? VIDEO_TRANSCRIPT_LOG_OMISSION_MARKER : error,
       model,
       provider,
       comboName,

open-sse/handlers/chatCore/executorProxy.ts

@@ -17,8 +17,10 @@
  */
 
 import { getExecutor } from "../../executors/index.ts";
+import type { ExecuteInput } from "../../executors/base.ts";
 import { isCliproxyapiDeepModeEnabled } from "../../executors/cliproxyapi.ts";
 import { isDarioDeepModeEnabled } from "../../executors/dario.ts";
+import { redactVideoTranscriptSensitiveText } from "../../../src/lib/guardrails/videoTranscriptLogRedaction.ts";
 import { getCachedSettings } from "@/lib/db/readCache";
 import { getUpstreamProxyConfigCached } from "./comboContextCache.ts";
 import type { FallbackBackend } from "@/lib/db/upstreamProxy";
@@ -48,6 +50,11 @@ function parseFallbackCodes(raw: unknown): number[] | null {
   return parsed.length > 0 ? parsed : null;
 }
 
+function retainExecutorDiagnostic(error: unknown, input: ExecuteInput): string {
+  const message = error instanceof Error ? error.message : String(error);
+  return redactVideoTranscriptSensitiveText(message, input.videoTranscriptSensitive === true);
+}
+
 /**
  * Reads the CLIProxyAPI-related settings shared by both the direct
  * `mode: "cliproxyapi"` passthrough leg and the `mode: "fallback"` retry leg:
@@ -155,25 +162,20 @@ export async function resolveExecutorWithProxy(
   const isRetryableStatus = (s: number) => fallbackCodes.includes(s) || s === 0;
 
   const wrapper = Object.create(nativeExec);
-  wrapper.execute = async (input: {
-    model: string;
-    body: unknown;
-    stream: boolean;
-    credentials: unknown;
-    signal?: AbortSignal | null;
-    log?: unknown;
-    upstreamExtraHeaders?: Record<string, string> | null;
-  }) => {
+  wrapper.execute = async (input: ExecuteInput) => {
     let result;
     try {
       result = await nativeExec.execute(input);
     } catch (err) {
-      const errMsg = err instanceof Error ? err.message : String(err);
-      log?.info?.("UPSTREAM_PROXY", `${prov} native error (${errMsg}), retrying via ${backendLabel}`);
+      const errMsg = retainExecutorDiagnostic(err, input);
+      log?.info?.(
+        "UPSTREAM_PROXY",
+        `${prov} native error (${errMsg}), retrying via ${backendLabel}`
+      );
       try {
         return await proxyExec.execute(input);
       } catch (proxyErr) {
-        const proxyMsg = proxyErr instanceof Error ? proxyErr.message : String(proxyErr);
+        const proxyMsg = retainExecutorDiagnostic(proxyErr, input);
         log?.error?.("UPSTREAM_PROXY", `${prov} ${backendLabel} fallback also failed: ${proxyMsg}`);
         throw proxyErr;
       }
@@ -189,7 +191,7 @@ export async function resolveExecutorWithProxy(
     try {
       return await proxyExec.execute(input);
     } catch (proxyErr) {
-      const proxyMsg = proxyErr instanceof Error ? proxyErr.message : String(proxyErr);
+      const proxyMsg = retainExecutorDiagnostic(proxyErr, input);
       log?.error?.("UPSTREAM_PROXY", `${prov} ${backendLabel} fallback also failed: ${proxyMsg}`);
       throw proxyErr;
     }

open-sse/handlers/chatCore/executorRetentionLog.ts

@@ -0,0 +1,36 @@
+import { VIDEO_TRANSCRIPT_LOG_OMISSION_MARKER } from "@/lib/guardrails/videoTranscriptLogRedaction";
+
+import type { ExecutorLog } from "../../executors/base.ts";
+
+type ExecutorLogMethod = NonNullable<ExecutorLog["debug"]>;
+
+function retainMethod(
+  owner: ExecutorLog,
+  method: ExecutorLogMethod | undefined
+): ExecutorLogMethod | undefined {
+  if (!method) return undefined;
+
+  return (tag) => {
+    method.call(owner, tag, VIDEO_TRANSCRIPT_LOG_OMISSION_MARKER);
+  };
+}
+
+/**
+ * Executor diagnostics can contain arbitrary provider text, including request echoes.
+ * Keep the original logger for ordinary requests, but give every executor a request-scoped
+ * fail-closed view when the Video Bridge marked the request sensitive. Tags remain useful;
+ * messages and optional structured metadata are replaced/dropped only at the retention seam.
+ */
+export function createExecutorRetentionLog(
+  log: ExecutorLog | null | undefined,
+  videoTranscriptSensitive: boolean
+): ExecutorLog | null | undefined {
+  if (!log || !videoTranscriptSensitive) return log;
+
+  return {
+    debug: retainMethod(log, log.debug),
+    info: retainMethod(log, log.info),
+    warn: retainMethod(log, log.warn),
+    error: retainMethod(log, log.error),
+  };
+}

open-sse/handlers/chatCore/idempotency.ts

@@ -124,6 +124,7 @@ export async function checkIdempotencyCache({
   effectiveServiceTier,
   startTime,
   log,
+  videoTranscriptSensitive,
 }: {
   clientRawRequest: IdempotencyRequest;
   provider: string;
@@ -132,7 +133,9 @@ export async function checkIdempotencyCache({
   effectiveServiceTier: EffectiveServiceTier | null | undefined;
   startTime: number;
   log: LoggerLike;
+  videoTranscriptSensitive: boolean;
 }): Promise<{ hit: { success: true; response: Response } | null; idempotencyKey: string | null }> {
+  if (videoTranscriptSensitive) return { hit: null, idempotencyKey: null };
   // NEXA fusion-idempotency fix: namespace the raw header key (see composeIdempotencyKey).
   const rawIdempotencyKey = getIdempotencyKey(clientRawRequest?.headers);
   const idempotencyKey = composeIdempotencyKey({

open-sse/handlers/chatCore/logTruncation.ts

@@ -5,6 +5,10 @@ import {
   getChatLogMaxObjectKeys,
   getChatLogMaxBodyBytes,
 } from "@/lib/logEnv";
+import {
+  omitVideoTranscriptForLog,
+  type VideoTranscriptLogContext,
+} from "@/lib/guardrails/videoTranscriptLogRedaction";
 import { estimateSizeFast } from "../../utils/estimateSize.ts";
 
 export const MEMORY_EXTRACTION_TEXT_LIMIT = 64 * 1024;
@@ -22,7 +26,7 @@ export function truncateChatLogText(value: string): string {
   return `${head}\n[...truncated ${value.length - limit} chars...]\n${tail}`;
 }
 
-export function cloneBoundedChatLogPayload(value: unknown, depth = 0): unknown {
+function cloneBoundedChatLogPayloadValue(value: unknown, depth = 0): unknown {
   if (value === null || value === undefined) return value;
   if (typeof value === "string") return truncateChatLogText(value);
   if (typeof value !== "object") return value;
@@ -32,7 +36,7 @@ export function cloneBoundedChatLogPayload(value: unknown, depth = 0): unknown {
 
   if (Array.isArray(value)) {
     const retained = value.length > maxTailItems ? value.slice(-maxTailItems) : value;
-    const cloned = retained.map((item) => cloneBoundedChatLogPayload(item, depth + 1));
+    const cloned = retained.map((item) => cloneBoundedChatLogPayloadValue(item, depth + 1));
     if (value.length > maxTailItems) {
       return [
         {
@@ -47,10 +51,11 @@ export function cloneBoundedChatLogPayload(value: unknown, depth = 0): unknown {
   }
 
   const result: Record<string, unknown> = {};
-  const entries = Object.entries(value as Record<string, unknown>);
+  const record = value as Record<string, unknown>;
+  const entries = Object.entries(record);
   const maxKeys = getChatLogMaxObjectKeys();
   for (const [key, item] of maxKeys > 0 ? entries.slice(0, maxKeys) : entries) {
-    result[key] = cloneBoundedChatLogPayload(item, depth + 1);
+    result[key] = cloneBoundedChatLogPayloadValue(item, depth + 1);
   }
   if (maxKeys > 0 && entries.length > maxKeys) {
     result._omniroute_truncated_keys = entries.length - maxKeys;
@@ -58,6 +63,16 @@ export function cloneBoundedChatLogPayload(value: unknown, depth = 0): unknown {
   return result;
 }
 
+export function cloneBoundedChatLogPayload(
+  value: unknown,
+  depth = 0,
+  descriptionContext: VideoTranscriptLogContext = {}
+): unknown {
+  const transcriptSafeValue =
+    depth === 0 ? omitVideoTranscriptForLog(value, descriptionContext) : value;
+  return cloneBoundedChatLogPayloadValue(transcriptSafeValue, depth);
+}
+
 /**
  * Truncate a large object for logging. If its JSON representation exceeds
  * getChatLogMaxBodyBytes() (default 1MB; CHAT_LOG_MAX_BODY_KB env override),

open-sse/handlers/chatCore/memoryExtraction.ts

@@ -1,5 +1,39 @@
+import {
+  containsVideoTranscriptForLog,
+  omitVideoTranscriptDerivedTextForMemory,
+  type VideoTranscriptLogContext,
+} from "../../../src/lib/guardrails/videoTranscriptLogRedaction.ts";
 import { capMemoryExtractionText, MEMORY_EXTRACTION_TEXT_LIMIT } from "./logTruncation.ts";
 
+function normalizeMemoryInputText(value: unknown, context: VideoTranscriptLogContext = {}): string {
+  if (typeof value !== "string") return "";
+  return omitVideoTranscriptDerivedTextForMemory(value, context).trim();
+}
+
+function extractMemoryTextPart(
+  part: Record<string, unknown>,
+  transcriptSensitive: boolean,
+  context: VideoTranscriptLogContext
+): string {
+  try {
+    const rawText = typeof part?.text === "string" ? part.text : "";
+    if (!rawText) return "";
+
+    const retainedText = normalizeMemoryInputText(rawText, context);
+    if (!retainedText) return "";
+    if (
+      transcriptSensitive &&
+      containsVideoTranscriptForLog(part, context) &&
+      retainedText === rawText.trim()
+    ) {
+      return "";
+    }
+    return retainedText;
+  } catch {
+    return "";
+  }
+}
+
 export function extractMemoryTextFromResponse(
   response: Record<string, unknown> | null | undefined
 ): string {
@@ -29,9 +63,16 @@ export function extractMemoryTextFromResponse(
 }
 
 export function extractMemoryTextFromRequestBody(
-  body: Record<string, unknown> | null | undefined
+  body: Record<string, unknown> | null | undefined,
+  videoTranscriptSensitive = false,
+  context: VideoTranscriptLogContext = {}
 ): string {
   if (!body || typeof body !== "object") return "";
+  // Re-check the structured body at the sink boundary. The explicit bit covers
+  // processed requests whose raw carrier was already replaced; trusted hashes
+  // identify only descriptions emitted by a modified Video Bridge guardrail.
+  const transcriptSensitive =
+    videoTranscriptSensitive || containsVideoTranscriptForLog(body, context);
 
   const messages = Array.isArray(body.messages) ? body.messages : null;
   if (messages && messages.length > 0) {
@@ -39,18 +80,16 @@ export function extractMemoryTextFromRequestBody(
       const msg = messages[i] as Record<string, unknown>;
       if (msg?.role !== "user") continue;
 
-      if (typeof msg.content === "string" && msg.content.trim().length > 0) {
-        return capMemoryExtractionText(msg.content.trim());
+      const messageText = normalizeMemoryInputText(msg.content, context);
+      if (messageText) {
+        return capMemoryExtractionText(messageText);
       }
 
       if (Array.isArray(msg.content)) {
         const text = msg.content
-          .map((part: Record<string, unknown>) => {
-            if (typeof part?.text === "string") return part.text.trim();
-            if (part?.type === "input_text" && typeof part?.text === "string")
-              return part.text.trim();
-            return "";
-          })
+          .map((part: Record<string, unknown>) =>
+            extractMemoryTextPart(part, transcriptSensitive, context)
+          )
           .filter(Boolean)
           .join("\n")
           .trim();
@@ -68,17 +107,15 @@ export function extractMemoryTextFromRequestBody(
       if (role && role !== "user") continue;
       if (itemType && itemType !== "message") continue;
 
-      if (typeof item?.content === "string" && item.content.trim()) {
-        return capMemoryExtractionText(item.content.trim());
+      const itemText = normalizeMemoryInputText(item?.content, context);
+      if (itemText) {
+        return capMemoryExtractionText(itemText);
       }
       if (Array.isArray(item?.content)) {
         const text = item.content
-          .map((part: Record<string, unknown>) => {
-            if (typeof part?.text === "string") return part.text.trim();
-            if (part?.type === "input_text" && typeof part?.text === "string")
-              return part.text.trim();
-            return "";
-          })
+          .map((part: Record<string, unknown>) =>
+            extractMemoryTextPart(part, transcriptSensitive, context)
+          )
           .filter(Boolean)
           .join("\n")
           .trim();
@@ -96,15 +133,14 @@ export function extractMemoryTextFromRequestBody(
         if (role && role !== "user") return "";
         if (itemType && itemType !== "message") return "";
 
-        if (typeof item?.content === "string") return item.content.trim();
+        if (typeof item?.content === "string") {
+          return normalizeMemoryInputText(item.content, context);
+        }
         if (Array.isArray(item?.content)) {
           return item.content
-            .map((part: Record<string, unknown>) => {
-              if (typeof part?.text === "string") return part.text.trim();
-              if (part?.type === "input_text" && typeof part?.text === "string")
-                return part.text.trim();
-              return "";
-            })
+            .map((part: Record<string, unknown>) =>
+              extractMemoryTextPart(part, transcriptSensitive, context)
+            )
             .filter(Boolean)
             .join("\n")
             .trim();

open-sse/handlers/chatCore/pluginOnRequest.ts

@@ -9,6 +9,8 @@
  * byte-identical to the previous inline block.
  */
 
+import { redactVideoTranscriptSensitiveText } from "@/lib/guardrails/videoTranscriptLogRedaction";
+
 type LoggerLike =
   { info?: (...args: unknown[]) => void; debug?: (...args: unknown[]) => void } | null | undefined;
 
@@ -25,6 +27,7 @@ export async function runPluginOnRequestHook(args: {
   apiKeyInfo: unknown;
   headers?: Record<string, string | string[] | undefined>;
   log?: LoggerLike;
+  videoTranscriptSensitive?: boolean;
 }): Promise<PluginOnRequestGate> {
   try {
     const { runOnRequest } = await import("@/lib/plugins/hooks");
@@ -36,6 +39,7 @@ export async function runPluginOnRequestHook(args: {
       apiKeyInfo: args.apiKeyInfo,
       headers: args.headers,
       metadata: {},
+      videoTranscriptSensitive: args.videoTranscriptSensitive === true,
     };
     const pluginResult = await runOnRequest(pluginCtx);
     if (pluginResult?.blocked) {
@@ -55,10 +59,11 @@ export async function runPluginOnRequestHook(args: {
     }
     return { blocked: false, body: pluginResult?.body };
   } catch (pluginErr) {
-    args.log?.debug?.(
-      "PLUGIN",
-      `onRequest hook error (non-fatal): ${pluginErr instanceof Error ? pluginErr.message : String(pluginErr)}`
+    const retainedPluginError = redactVideoTranscriptSensitiveText(
+      pluginErr instanceof Error ? pluginErr.message : String(pluginErr),
+      args.videoTranscriptSensitive === true
     );
+    args.log?.debug?.("PLUGIN", `onRequest hook error (non-fatal): ${retainedPluginError}`);
     return { blocked: false };
   }
 }

open-sse/handlers/chatCore/pluginOnResponse.ts

@@ -26,6 +26,7 @@ export async function runPluginOnResponseHook(args: {
   apiKeyInfo: unknown;
   headers?: Record<string, string | string[] | undefined>;
   response: PluginOnResponsePayload;
+  videoTranscriptSensitive?: boolean;
 }): Promise<void> {
   try {
     const { runOnResponse } = await import("@/lib/plugins/hooks");
@@ -38,6 +39,7 @@ export async function runPluginOnResponseHook(args: {
         apiKeyInfo: args.apiKeyInfo,
         headers: args.headers,
         metadata: {},
+        videoTranscriptSensitive: args.videoTranscriptSensitive === true,
       },
       args.response
     ).catch(() => {});

open-sse/handlers/chatCore/postCallGuardrailContext.ts

@@ -36,6 +36,7 @@ export function buildPostCallGuardrailContext(
     provider: string | null | undefined;
     responsePayloadFormat: unknown;
     clientResponseFormat: unknown;
+    videoTranscriptSensitive?: boolean;
   },
   resolveDisabledGuardrails: typeof defaultResolveDisabled = defaultResolveDisabled
 ): GuardrailContext {
@@ -57,5 +58,6 @@ export function buildPostCallGuardrailContext(
     sourceFormat: optionalString(args.responsePayloadFormat),
     stream: false,
     targetFormat: optionalString(args.clientResponseFormat),
+    videoTranscriptSensitive: args.videoTranscriptSensitive === true,
   };
 }

open-sse/handlers/chatCore/semanticCache.ts

@@ -1,8 +1,4 @@
-import {
-  generateSignature,
-  getCachedResponse,
-  isCacheableForRead,
-} from "@/lib/semanticCache";
+import { generateSignature, getCachedResponse, isCacheableForRead } from "@/lib/semanticCache";
 import { calculateCost } from "@/lib/usage/costCalculator";
 import { trackPendingRequest } from "@/lib/usageDb";
 import { synthesizeOpenAiSseFromJson } from "../../utils/jsonToSse.ts";
@@ -25,6 +21,7 @@ export async function checkSemanticCache({
   persistAttemptLogs,
   apiKeyId,
   cacheDefaultMode,
+  videoTranscriptSensitive,
 }: {
   semanticCacheEnabled: boolean;
   // Only the fields this read path actually touches are named; everything else
@@ -42,7 +39,9 @@ export async function checkSemanticCache({
   persistAttemptLogs: (args: unknown) => void;
   apiKeyId?: string | null;
   cacheDefaultMode?: "legacy" | "bypass" | null;
+  videoTranscriptSensitive: boolean;
 }) {
+  if (videoTranscriptSensitive) return null;
   // Per-key bypass: skip cache lookup entirely when the API key opts out.
   if (cacheDefaultMode === "bypass") return null;
   if (semanticCacheEnabled && isCacheableForRead(body, clientRawRequest?.headers)) {

open-sse/handlers/chatCore/semanticCacheStore.ts

@@ -50,10 +50,12 @@ export function storeSemanticCacheResponse(
     apiKeyId?: string;
     usage?: UsageLike;
     log?: LoggerLike;
+    videoTranscriptSensitive: boolean;
   },
   deps: SemanticCacheStoreDeps = DEFAULT_DEPS
 ): void {
   if (
+    args.videoTranscriptSensitive ||
     !args.enabled ||
     !deps.isCacheableForWrite(args.body, args.headers) ||
     !deps.isSmallEnoughForSemanticCache(args.translatedResponse)

open-sse/handlers/chatCore/streamingPipeline.ts

@@ -68,6 +68,7 @@ export function assembleStreamingPipeline(
     clientRawRequestHeaders: HeadersLike;
     clientResponseFormat: Parameters<typeof defaultShape>[0];
     echoModel: string | null | undefined;
+    redactStreamDiagnosticsForLog?: boolean;
     responseHeaders: Record<string, string>;
   },
   deps: StreamingPipelineDeps = DEFAULT_DEPS
@@ -83,7 +84,8 @@ export function assembleStreamingPipeline(
   let piiStream = deps.pipeWithDisconnect(
     args.providerResponse,
     args.transformStream,
-    args.streamController
+    args.streamController,
+    { redactStreamDiagnosticsForLog: args.redactStreamDiagnosticsForLog }
   );
   if (typeof args.createPiiTransform === "function") {
     piiStream = piiStream.pipeThrough((args.createPiiTransform as () => TransformStream)());