fix(ollama): route models by advertised capability (#11088)

Landed with the design call resolved per the owner's pick — **option 1**: the synced store is now endpoint-agnostic (persistDiscoveredModels and managedModelImport no longer drop non-chat models at write time), and chat selectability moved to read time (auto-pool expansion in autoStrategy applies filterChatSelectableModels; the models-route projection already had its chatOnly filter). Your discovery test now passes end-to-end (3/3): /api/show capabilities persist per connection and image/embedding requests route through the advertising host.

Reconciliation notes: conflicted areas merged onto the current tip (adobe discovery import, requestedModel preflight signature, resolvedProvider fast-path coexists with the synced-route override — explicit resolution wins); carried base-red drains (#10055 memoization, #11071 test variants) dropped as already-landed; the managed-model-import exclusion test was propagated to the new contract (image/video models persist; the read filter still hides them from chat pickers — pinned by a new assertion). Full battery: 205/206 focused (the one red is a confirmed periodic-timer timing flake on the loaded devbox — 20/20 isolated), autoCombo vitest 30/30, combo suites 46/46, gates + typecheck clean.

Thank you @yourspraveen — the capability probe + routing design was right; it just needed the store contract opened up. Fixes #11087.

.env.example

@@ -65,12 +65,6 @@ INITIAL_PASSWORD=CHANGEME
 # OMNIROUTE_RELEASE_REF=origin/main
 # OMNIROUTE_ALLOW_CANARY_BUILD=1
 
-# Build-phase signal (#10060). Set to 1 by scripts/build/build-next-isolated.mjs and
-# inherited by every spawned build worker so the DB layer returns a no-op stub instead
-# of loading the native better-sqlite3 addon (which aborts the worker on exit).
-# Never set this for the running server. Used by: src/lib/buildPhase.ts, src/lib/db/core.ts
-# OMNIROUTE_BUILDING=1
-
 # Encryption key for SQLite database encryption at rest.
 # Used by: src/lib/db/encryption.ts — encrypts the entire SQLite database.
 # Generate: openssl rand -hex 32  |  Leave empty to disable DB encryption.
@@ -1330,14 +1324,8 @@ CURSOR_USER_AGENT="Cursor/3.4"
 # Approval policy passed to the app-server turn (e.g. never, on-request).
 # OMNIROUTE_CODEX_APPSERVER_APPROVAL=never
 # Sandbox policy passed to the app-server turn (e.g. read-only,
-# workspace-write, danger-full-access). When unset, the executor defaults to
-# "workspace-write" (hardened; used to be "danger-full-access").
+# workspace-write, danger-full-access).
 # OMNIROUTE_CODEX_APPSERVER_SANDBOX=read-only
-# Auto-approve the app-server's own approval prompts (command/file/permission
-# execution on the host). Defaults to OFF — prompts are auto-denied. Set to
-# true/1/yes only when you trust the deployment to run codex-decided host
-# commands. Per-connection override: providerSpecificData.codexAppServerAutoApprove.
-# OMNIROUTE_CODEX_APPSERVER_AUTO_APPROVE=false
 
 # ═══════════════════════════════════════════════════════════════════════════════
 # 13. CLI FINGERPRINT COMPATIBILITY (Anti-Detection)

.gitattributes

@@ -1,11 +0,0 @@
-# Shell scripts must always be checked out with LF line endings.
-#
-# On Windows, core.autocrlf=true converts text files to CRLF in the working
-# tree. Scripts that are kernel-exec'd (Docker ENTRYPOINT, bin/*.sh on Linux
-# hosts) then fail with `exec ...: no such file or directory` because the
-# shebang becomes "#!/bin/sh\r". eol=lf overrides autocrlf for these files.
-*.sh text eol=lf
-
-# This file must stay LF too: git parses it as-is, and a trailing CR would
-# corrupt every pattern (e.g. "*.sh\r" matches nothing).
-.gitattributes text eol=lf

.github/workflows/opencode-plugin-ci.yml

@@ -2,11 +2,11 @@ name: opencode-plugin CI
 
 on:
   push:
-    branches: [main, "release/**"]
+    branches: [main, release/v3.8.2]
     paths:
       - "@omniroute/opencode-plugin/**"
   pull_request:
-    branches: [main, "release/**"]
+    branches: [main, release/v3.8.2]
     paths:
       - "@omniroute/opencode-plugin/**"
     types: [opened, synchronize, reopened, ready_for_review]

@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",
     "prepublishOnly": "npm run clean && npm run build && npm test"
   },
   "keywords": [

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

@@ -1161,8 +1161,6 @@ export interface OmniRouteRawModelEntry {
     attachment?: boolean;
     structured_output?: boolean;
     temperature?: boolean;
-    /** Runtime-learned or synced reasoning tiers (server-gated, blind-mapped). */
-    effort_tiers?: string[];
   };
   release_date?: string;
   last_updated?: string;
@@ -1304,18 +1302,6 @@ export function mapRawModelToModelV2(
   ctx: { providerId: string; baseURL: string; apiFormat?: { anthropicPrefixes?: string[] } }
 ): ModelV2 {
   const caps = raw.capabilities ?? {};
-  // effort_tiers loop: server-declared tiers become ModelV2 variants so the
-  // UI offers exactly the tiers OmniRoute vouches for (instead of opencode's
-  // invented [low, medium, high] fallback). Blind: filtering/exclusion rules
-  // live server-side. Absent/empty/malformed => key omitted ENTIRELY (an
-  // empty variants object would suppress opencode's fallback for this model).
-  const declaredTiers = Array.isArray(caps.effort_tiers)
-    ? caps.effort_tiers.filter((t): t is string => typeof t === "string" && t.length > 0)
-    : [];
-  const variants =
-    declaredTiers.length > 0
-      ? Object.fromEntries(declaredTiers.map((tier) => [tier, { reasoningEffort: tier }]))
-      : undefined;
   const inMods = new Set(raw.input_modalities ?? ["text"]);
   const outMods = new Set(raw.output_modalities ?? ["text"]);
 
@@ -1329,7 +1315,10 @@ export function mapRawModelToModelV2(
     // OpenCode looks up `-m <plugin>/<combo>` as model id `<combo>` under
     // the plugin provider (#10345). Other bare ids still prefix with
     // `providerId` so credentials resolve as `(omniroute, model)`.
-    id: raw.id.includes("/") || raw.owned_by === "combo" ? raw.id : `${ctx.providerId}/${raw.id}`,
+    id:
+      raw.id.includes("/") || raw.owned_by === "combo"
+        ? raw.id
+        : `${ctx.providerId}/${raw.id}`,
     /**
      * Display name. Falls back to raw.id when no enrichment is available;
      * the caller (`createOmniRouteProviderHook`) overlays
@@ -1368,7 +1357,6 @@ export function mapRawModelToModelV2(
       ...(typeof raw.max_input_tokens === "number" ? { input: raw.max_input_tokens } : {}),
       output: typeof raw.max_output_tokens === "number" ? raw.max_output_tokens : 0,
     },
-    ...(variants ? { variants } : {}),
     status: "active",
     options: {},
     headers: {},

@omniroute/opencode-plugin/tests/effort-tier-variants.test.ts

@@ -1,62 +0,0 @@
-/**
- * effort_tiers loop — plugin maps server-declared tiers to ModelV2 variants.
- * Blind mapping (I3): no owned_by/provider knowledge here — the SERVER gates
- * eligibility (shouldExposeSyncedEffortVariants). Absence semantics (M3):
- * no tiers => NO variants key at all (an empty object would also kill
- * opencode's own fallback for non-tiered models).
- */
-import test from "node:test";
-import assert from "node:assert/strict";
-import { mapRawModelToModelV2, type OmniRouteRawModelEntry } from "../src/index.js";
-
-const CTX = { providerId: "omniroute", baseURL: "http://127.0.0.1:20128" } as const;
-
-test("maps declared tiers to reasoningEffort variants", () => {
-  const raw: OmniRouteRawModelEntry = {
-    id: "oc/x-preview-f-free",
-    owned_by: "opencode",
-    capabilities: { reasoning: true, effort_tiers: ["low", "high", "max"] },
-  };
-  const model = mapRawModelToModelV2(raw, { ...CTX });
-  const variants = (model as unknown as Record<string, unknown>).variants as
-    Record<string, Record<string, unknown>> | undefined;
-  assert.ok(variants, "variants key present when tiers declared");
-  assert.deepEqual(Object.keys(variants).sort(), ["high", "low", "max"]);
-  assert.deepEqual(variants.max, { reasoningEffort: "max" });
-  assert.deepEqual(variants.low, { reasoningEffort: "low" });
-});
-
-test("no tiers => NO variants key (not an empty object)", () => {
-  const raw: OmniRouteRawModelEntry = {
-    id: "plain-model",
-    capabilities: { reasoning: true },
-  };
-  const model = mapRawModelToModelV2(raw, { ...CTX }) as unknown as Record<string, unknown>;
-  assert.equal("variants" in model, false);
-});
-
-test("empty or malformed tiers array => NO variants key", () => {
-  const empty = mapRawModelToModelV2(
-    { id: "m", capabilities: { effort_tiers: [] } },
-    { ...CTX }
-  ) as unknown as Record<string, unknown>;
-  assert.equal("variants" in empty, false);
-
-  const junk = mapRawModelToModelV2(
-    { id: "m", capabilities: { effort_tiers: [42, null, "ok"] as unknown as string[] } },
-    { ...CTX }
-  ) as unknown as Record<string, unknown>;
-  const variants = junk.variants as Record<string, Record<string, unknown>> | undefined;
-  assert.deepEqual(Object.keys(variants ?? {}), ["ok"], "non-string tokens dropped");
-});
-
-test("static registry entry WITH tiers also gets variants (N1 blast radius)", () => {
-  const raw: OmniRouteRawModelEntry = {
-    id: "some-static-model",
-    owned_by: "registry",
-    capabilities: { effort_tiers: ["minimal", "high"] },
-  };
-  const model = mapRawModelToModelV2(raw, { ...CTX }) as unknown as Record<string, unknown>;
-  const variants = model.variants as Record<string, Record<string, unknown>> | undefined;
-  assert.deepEqual(Object.keys(variants ?? {}).sort(), ["high", "minimal"]);
-});

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

@@ -104,10 +104,7 @@ test("models: extracts apiKey from ctx.auth (type=api) and calls fetcher with it
   // #6859: dynamic-hook catalog keys use the unprefixed omnirouteProviderId
   // ("omniroute"), not the OC-gate-prefixed hook.id ("opencode-omniroute") —
   // that prefix must never leak into anything OmniRoute's server parses.
-  // #10345/#10821: bare combo ids (owned_by: "combo") stay unprefixed —
-  // OpenCode looks up `-m <plugin>/<combo>` as model id `<combo>` under the
-  // plugin provider, so `claude-primary` here carries no provider prefix.
-  assert.ok(out["claude-primary"]);
+  assert.ok(out["omniroute/claude-primary"]);
 });
 
 test("models: returns {} when ctx.auth is null/undefined/wrong-type/empty-key", async () => {
@@ -162,15 +159,11 @@ test("models: maps a sample /v1/models entry to ModelV2 (sanity)", async () => {
   // omnirouteProviderId ("omniroute") — the OC-gate prefix ("opencode-")
   // must stay OC-internal (hook.id / AuthHook.provider) and never leak into
   // anything OmniRoute's own server parses for credential lookup.
-  // #10345/#10821: bare **combo** ids (owned_by: "combo", e.g.
-  // "claude-primary") must also stay unprefixed — OpenCode looks up
-  // `-m <plugin>/<combo>` as model id `<combo>` under the plugin provider.
-  const claude = out["claude-primary"];
+  const claude = out["omniroute/claude-primary"];
   assert.ok(claude, "claude-primary present");
-  // `mapRawModelToModelV2` leaves bare combo ids unprefixed (see
-  // src/index.ts mapRawModelToModelV2) so OC's `-m <plugin>/<combo>` lookup
-  // resolves the combo id directly.
-  assert.equal(claude.id, "claude-primary");
+  // `mapRawModelToModelV2` stamps the provider prefix on the id so OC's
+  // static-catalog reader resolves `(providerID, modelID)` from the key.
+  assert.equal(claude.id, "omniroute/claude-primary");
   assert.equal(claude.name, "claude-primary");
   assert.equal(claude.providerID, "omniroute");
   assert.equal(claude.api.id, "openai-compatible");

AGENTS.md

@@ -46,7 +46,7 @@ Repository map and Reference Documentation sections below.
 
 ## Project at a Glance
 
-**OmniRoute** — unified AI proxy/router. One endpoint, 350 LLM providers, auto-fallback.
+**OmniRoute** — unified AI proxy/router. One endpoint, 351 LLM providers, auto-fallback.
 
 | Layer         | Location                | Purpose                                                                                                                                                                   |
 | ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

Dockerfile

@@ -59,12 +59,6 @@ RUN set -eux; \
 # ── Builder ────────────────────────────────────────────────────────────────
 FROM base AS builder
 
-# No telemetry, anywhere. Disable Next.js's anonymous build-time telemetry
-# (it otherwise pings Vercel during `next build`). Set on the builder stage so
-# every image build is silent; the runtime never builds, so this covers the
-# only phase Next telemetry can fire.
-ENV NEXT_TELEMETRY_DISABLED=1
-
 # Build tools for native module compilation
 # apt-get update needed here because base's rm -rf clears the shared cache
 RUN --mount=type=cache,id=s/92ca8a61-c1ba-421f-a389-d48ac7258c2d-apt-cache,target=/var/cache/apt,sharing=locked \
@@ -172,20 +166,9 @@ ENV OMNIROUTE_MITM_STUB=1
 # child (build-next-isolated.mjs → resolveNextBuildEnv spreads process.env).
 # Build-only; the runtime heap is set separately on the runner stage
 # (OMNIROUTE_MEMORY_MB). Override: `--build-arg OMNIROUTE_BUILD_MEMORY_MB=6144`.
-# Default raised 4096 → 6144 (#10060): the Next 16 production pass on a codebase
-# this size intermittently OOMs a build worker at 4 GB on memory-tight hosts.
-ARG OMNIROUTE_BUILD_MEMORY_MB=6144
+ARG OMNIROUTE_BUILD_MEMORY_MB=4096
 ENV NODE_OPTIONS="--max-old-space-size=${OMNIROUTE_BUILD_MEMORY_MB}"
 
-# Cap Next.js build worker pools. Next 16 defaults to `os.cpus().length - 1`
-# workers for page-data collection (31 on a 32-core builder); on memory-tight
-# hosts 31 workers + webpack's multi-GB heap blow past RAM and a worker dies
-# with SIGSEGV at teardown ("worker exited with code: null and signal: SIGSEGV"),
-# silently leaving no standalone bundle. Next derives the default worker count
-# from CIRCLE_NODE_TOTAL (workers = N-1), so N=8 → 7 workers: fast enough while
-# fitting comfortably in RAM on any host. (#10060)
-ENV CIRCLE_NODE_TOTAL=8
-
 COPY . ./
 RUN --mount=type=cache,id=s/92ca8a61-c1ba-421f-a389-d48ac7258c2d-next-cache,target=/app/.build/next/cache \
   mkdir -p /app/data \

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 → 350 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. 350 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 → 351 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. 351 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. 350 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 350 providers in milliseconds, zero downtime) · Save up to 95% tokens (RTK + Caveman stacked compression cuts 15–95%, ~89% avg on tool-heavy sessions) · $0 to start (90+ free tiers, 56 free forever — no card needed) · Every tool works (33 coding agents through one config) · One endpoint (OpenAI ↔ Claude ↔ Gemini ↔ Responses API at /v1) · Production-grade (circuit breakers, TLS stealth, MCP 110 tools, A2A, memory, guardrails, evals — 25,000+ tests)."/>
+<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint. 351 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 351 providers in milliseconds, zero downtime) · Save up to 95% tokens (RTK + Caveman stacked compression cuts 15–95%, ~89% avg on tool-heavy sessions) · $0 to start (90+ free tiers, 56 free forever — no card needed) · Every tool works (33 coding agents through one config) · One endpoint (OpenAI ↔ Claude ↔ Gemini ↔ Responses API at /v1) · Production-grade (circuit breakers, TLS stealth, MCP 110 tools, A2A, memory, guardrails, evals — 25,000+ tests)."/>
 
 <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 — comparison table vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 350 providers, 90+ free providers 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, 43 i18n UI locales, 100% MIT self-hosted. OmniRoute is the only one with the full set; competitors show a mix of checks, partials and crosses. Verified from each project&apos;s docs."/>
+<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — comparison table vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 351 providers, 90+ free providers 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, 43 i18n UI locales, 100% MIT self-hosted. OmniRoute is the only one with the full set; competitors show a mix of checks, partials and crosses. Verified from each project&apos;s docs."/>
 
 <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>
 
@@ -646,7 +646,7 @@ of your shell history. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)
 
 </div>
 
-> The most complete catalog of any open-source router: **350 providers**, **90+ with a free tier**, **56 free forever**.
+> The most complete catalog of any open-source router: **351 providers**, **90+ with a free tier**, **56 free forever**.
 
 <div align="center">
 

bin/cli/commands/auth-export.mjs

@@ -22,15 +22,8 @@ const VALID_FORMATS = new Set(["json", "env"]);
 const SECURE_FILE_MODE = 0o600;
 
 export function registerAuthExport(program) {
-  // #11226: `.command("auth export")` does NOT register a two-word command — commander
-  // parses the bare word `export` as a required positional argument of `auth`, so the
-  // action received (exportArgValue, options, command) while expecting (options, command)
-  // and crashed with "cmd.optsWithGlobals is not a function". Register `export` as a
-  // proper nested subcommand instead; the CLI surface stays `omniroute auth export`.
   program
-    .command("auth")
-    .description(t("authExport.description"))
-    .command("export")
+    .command("auth export")
     .description(t("authExport.description"))
     .option("--id <id>", t("authExport.idOpt"))
     .option("--format <format>", t("authExport.formatOpt"), "json")

bin/cli/commands/combo.mjs

@@ -3,7 +3,6 @@ import { printHeading } from "../io.mjs";
 import { withRuntime } from "../runtime.mjs";
 import { t } from "../i18n.mjs";
 import { apiFetch } from "../api.mjs";
-import { mcpCallTool } from "../mcpClient.mjs";
 import { emit } from "../output.mjs";
 import { resolveComboModels, collectModel } from "./comboModels.mjs";
 
@@ -64,7 +63,15 @@ export function extendComboSuggest(combo) {
         weights: opts.weights ? JSON.parse(opts.weights) : undefined,
         top: opts.top,
       };
-      const data = await mcpCallTool("omniroute_best_combo_for_task", body);
+      const res = await apiFetch("/api/mcp/tools/call", {
+        method: "POST",
+        body: { name: "omniroute_best_combo_for_task", arguments: body },
+      });
+      if (!res.ok) {
+        process.stderr.write(`Error: ${res.status}\n`);
+        process.exit(1);
+      }
+      const data = await res.json();
       const candidates = data.candidates ?? data;
       const rows = (Array.isArray(candidates) ? candidates : []).map((c, i) => ({
         rank: i + 1,

bin/cli/commands/compression.mjs

@@ -1,6 +1,5 @@
 import { readFileSync } from "node:fs";
 import { apiFetch } from "../api.mjs";
-import { mcpCallTool } from "../mcpClient.mjs";
 import { emit } from "../output.mjs";
 import { t } from "../i18n.mjs";
 
@@ -79,17 +78,18 @@ async function restComboStats(period) {
 }
 
 async function mcpCall(name, args, restFallback) {
-  try {
-    return await mcpCallTool(name, args);
-  } catch (err) {
-    // Keep the REST fallback behavior for builds where the MCP surface
-    // is unreachable / not mounted. Anything else rethrows as an error.
-    const status = err?.status || err?.cause?.status;
-    if ((status === 404 || status === 501) && typeof restFallback === "function") {
-      return restFallback();
-    }
-    throw err;
+  const res = await apiFetch("/api/mcp/tools/call", {
+    method: "POST",
+    body: { name, arguments: args },
+  });
+  if (res.ok) return res.json();
+  // 404 = MCP tool surface not mounted on this build; 501 = not implemented.
+  // Anything else is a genuine error and we surface it.
+  if ((res.status === 404 || res.status === 501) && typeof restFallback === "function") {
+    return restFallback();
   }
+  process.stderr.write(`Error: ${res.status}\n`);
+  process.exit(1);
 }
 
 async function confirm(q) {

bin/cli/commands/mcp.mjs

@@ -61,12 +61,27 @@ export function registerMcp(program) {
             ? JSON.parse(argsPositional)
             : {};
 
-      const exitCode = await runMcpCallCommand(tool, args, {
-        ...opts,
-        stream: opts.stream,
-      }, globalOpts);
+      if (opts.stream) {
+        await runMcpStream(tool, args, globalOpts);
+        return;
+      }
 
-      if (exitCode !== 0) process.exit(exitCode);
+      const extraHeaders = opts.scope?.length ? { "X-MCP-Scopes": opts.scope.join(",") } : {};
+      const res = await apiFetch("/api/mcp/tools/call", {
+        method: "POST",
+        body: { name: tool, arguments: args },
+        headers: extraHeaders,
+      });
+      if (res.status === 403) {
+        process.stderr.write("Scope denied\n");
+        process.exit(4);
+      }
+      if (!res.ok) {
+        process.stderr.write(`Error: ${res.status}\n`);
+        process.exit(1);
+      }
+      const data = await res.json();
+      emit(data, globalOpts);
     });
 
   mcp
@@ -84,132 +99,112 @@ export function registerMcp(program) {
       const data = await res.json();
       emit(data.scopes ?? data, cmd.optsWithGlobals());
     });
+
+  // 5.2 — mcp tools + mcp audit
+  const tools = mcp.command("tools").description(t("mcp.tools.description"));
+
+  tools
+    .command("list")
+    .description(t("mcp.tools.list.description"))
+    .option("--scope <s>", t("mcp.tools.list.scope"))
+    .action(async (opts, cmd) => {
+      const params = new URLSearchParams();
+      if (opts.scope) params.set("scope", opts.scope);
+      const res = await apiFetch(`/api/mcp/tools?${params}`);
+      if (!res.ok) {
+        process.stderr.write(`Error: ${res.status}\n`);
+        process.exit(1);
+      }
+      const data = await res.json();
+      emit(data.tools ?? data, cmd.optsWithGlobals(), mcpToolSchema);
+    });
+
+  tools
+    .command("info <name>")
+    .description(t("mcp.tools.info.description"))
+    .action(async (name, opts, cmd) => {
+      const res = await apiFetch(`/api/mcp/tools?name=${encodeURIComponent(name)}`);
+      if (!res.ok) {
+        process.stderr.write(`Not found: ${name}\n`);
+        process.exit(1);
+      }
+      emit(await res.json(), cmd.optsWithGlobals());
+    });
+
+  tools
+    .command("schema <name>")
+    .description(t("mcp.tools.schema.description"))
+    .option("--io <kind>", t("mcp.tools.schema.io"), "input")
+    .action(async (name, opts, cmd) => {
+      const res = await apiFetch(`/api/mcp/tools?name=${encodeURIComponent(name)}&io=${opts.io}`);
+      if (!res.ok) {
+        process.stderr.write(`Not found: ${name}\n`);
+        process.exit(1);
+      }
+      const data = await res.json();
+      const globalOpts = cmd.optsWithGlobals();
+      if (globalOpts.output === "json") {
+        process.stdout.write(JSON.stringify(data.schema ?? data, null, 2) + "\n");
+      } else {
+        emit(data.schema ?? data, globalOpts);
+      }
+    });
+
+  const audit = mcp.command("audit").description(t("mcp.audit.description"));
+
+  audit
+    .command("tail")
+    .option("--follow", t("audit.tail.follow"))
+    .option("--limit <n>", t("audit.tail.limit"), parseInt, 100)
+    .action(async (opts, cmd) => {
+      const { runAuditTail } = await import("./audit.mjs");
+      await runAuditTail({ ...opts, source: "mcp" }, cmd);
+    });
+
+  audit
+    .command("stats")
+    .option("--period <p>", t("audit.stats.period"), "7d")
+    .action(async (opts, cmd) => {
+      const res = await apiFetch(`/api/mcp/audit/stats?period=${opts.period}`);
+      if (!res.ok) {
+        process.stderr.write(`Error: ${res.status}\n`);
+        process.exit(1);
+      }
+      emit(await res.json(), cmd.optsWithGlobals());
+    });
 }
 
-/**
- * Shared JSON-RPC 2.0 MCP client used by both stream and non-stream `mcp call`.
- *
- * Protocol:
- *   1. POST /api/mcp/stream with initialize → get Mcp-Session-Id header
- *   2. POST /api/mcp/stream with tools/call + Mcp-Session-Id header
- *
- * When `stream` is true, writes SSE data chunks to stdout as they arrive.
- * When `stream` is false, returns the parsed JSON-RPC result.
- *
- * Returns the exit code (0 = success, non-zero = failure).
- */
-async function mcpJsonRpcCall(tool, args, { stream = false, globalOpts = {} } = {}) {
+async function runMcpStream(tool, args, globalOpts) {
   const baseUrl = globalOpts.baseUrl ?? "http://localhost:20128";
   const apiKey = globalOpts.apiKey ?? "";
-  const streamUrl = `${baseUrl}/api/mcp/stream`;
-
-  const hdrs = {
-    "Content-Type": "application/json",
-    Accept: stream ? "text/event-stream" : "application/json",
-    ...(apiKey ? { Authorization: `Bearer ${apiKey}` } : {}),
-  };
-
-  // Step 1 — initialize
-  const initRes = await fetch(streamUrl, {
+  const res = await fetch(`${baseUrl}/api/mcp/stream`, {
     method: "POST",
-    headers: hdrs,
-    body: JSON.stringify({
-      jsonrpc: "2.0",
-      id: 1,
-      method: "initialize",
-      params: {
-        protocolVersion: "2024-11-05",
-        capabilities: {},
-        clientInfo: { name: "omniroute-cli", version: "1.0" },
-      },
-    }),
+    headers: {
+      "Content-Type": "application/json",
+      ...(apiKey ? { Authorization: `Bearer ${apiKey}` } : {}),
+    },
+    body: JSON.stringify({ name: tool, arguments: args }),
   });
-
-  if (!initRes.ok) {
-    const text = await initRes.text().catch(() => "");
-    process.stderr.write(`MCP initialize failed: HTTP ${initRes.status}${text ? ` — ${text}` : ""}\n`);
-    return 1;
+  if (!res.ok) {
+    process.stderr.write(`HTTP ${res.status}\n`);
+    process.exit(1);
   }
-
-  const sessionId = initRes.headers.get("mcp-session-id");
-  if (!sessionId) {
-    process.stderr.write("MCP initialize failed: no Mcp-Session-Id in response\n");
-    return 1;
-  }
-
-  // Step 2 — tools/call
-  const callHeaders = {
-    ...hdrs,
-    "mcp-session-id": sessionId,
-  };
-
-  const callRes = await fetch(streamUrl, {
-    method: "POST",
-    headers: callHeaders,
-    body: JSON.stringify({
-      jsonrpc: "2.0",
-      id: 2,
-      method: "tools/call",
-      params: { name: tool, arguments: args },
-    }),
-  });
-
-  if (!callRes.ok) {
-    const text = await callRes.text().catch(() => "");
-    process.stderr.write(`MCP call failed: HTTP ${callRes.status}${text ? ` — ${text}` : ""}\n`);
-    return 1;
-  }
-
-  if (stream) {
-    return readMcpSseStream(callRes.body);
-  }
-
-  // Non-stream: parse JSON-RPC response
-  const data = await callRes.json();
-  if (data.error) {
-    process.stderr.write(`MCP error: ${data.error.message || JSON.stringify(data.error)}\n`);
-    return 1;
-  }
-  // Print the result content
-  const content = data.result?.content;
-  if (content) {
-    for (const item of content) {
-      if (item.type === "text") {
-        process.stdout.write(item.text + "\n");
-      } else if (item.type === "resource") {
-        process.stdout.write(JSON.stringify(item.resource) + "\n");
-      } else {
-        process.stdout.write(JSON.stringify(item) + "\n");
-      }
-    }
-  } else {
-    process.stdout.write(JSON.stringify(data.result, null, 2) + "\n");
-  }
-  return 0;
-}
-
-async function readMcpSseStream(body) {
-  if (!body) return 1;
-  const reader = body.getReader();
+  const reader = res.body.getReader();
   const dec = new TextDecoder();
   let buf = "";
   while (true) {
     const { done, value } = await reader.read();
     if (done) break;
     buf += dec.decode(value, { stream: true });
-  }
-  const lines = buf.split("\n");
-  for (const line of lines) {
-    if (line.startsWith("data: ")) {
-      const raw = line.slice(6).trim();
-      if (raw && raw !== "[DONE]") process.stdout.write(raw + "\n");
+    const lines = buf.split("\n");
+    buf = lines.pop() ?? "";
+    for (const line of lines) {
+      if (line.startsWith("data: ")) {
+        const raw = line.slice(6).trim();
+        if (raw && raw !== "[DONE]") process.stdout.write(raw + "\n");
+      }
     }
   }
-  return 0;
-}
-
-export async function runMcpCallCommand(tool, args, opts = {}, globalOpts = {}) {
-  return mcpJsonRpcCall(tool, args, { stream: opts.stream, globalOpts });
 }
 
 export async function runMcpStatusCommand(opts = {}) {
@@ -238,8 +233,7 @@ export async function runMcpStatusCommand(opts = {}) {
     }
 
     const transport = status.transport || "stdio";
-    const online = status.online ?? status.running;
-    console.log(online ? t("mcp.running", { transport }) : t("mcp.stopped"));
+    console.log(status.running ? t("mcp.running", { transport }) : t("mcp.stopped"));
     if (status.toolsCount !== undefined) console.log(`  Tools: ${status.toolsCount}`);
     if (status.scopes?.length) {
       console.log("  Scopes:");

bin/cli/commands/oauth.mjs

@@ -258,7 +258,8 @@ async function runDeviceFlow(def, opts) {
     process.stdout.write(`\nAuthorization URL not available\n\n`);
   }
 
-  if (opts.browser !== false && verificationUri) await openBrowser(verificationUri);
+  if (opts.browser !== false && verificationUri)
+    await openBrowser(verificationUri);
   process.stderr.write("Waiting for device authorization...\n");
   const deadline = Date.now() + (opts.timeout ?? 300000);
   const intervalMs = (start.intervalMs ?? start.interval ?? 5) * 1000;
@@ -319,18 +320,7 @@ export async function runOAuthStatus(opts, cmd) {
     process.exit(1);
   }
   const data = await res.json();
-  const payload = data?.connections ?? data?.providers ?? data?.items ?? data;
-  // #11236 (bug 5 residual): a 200 whose body is out of contract (no
-  // connections/providers/items array — e.g. `{"status":"ok"}`) used to fall
-  // through to `.filter` on a non-array and crash with a bare TypeError plus a
-  // libuv teardown assertion on Windows. Coerce to an empty list with a
-  // sanitized one-line warning instead of dumping a stack trace.
-  if (!Array.isArray(payload)) {
-    process.stderr.write(
-      "Warning: unexpected response shape from /api/providers; showing no connections.\n"
-    );
-  }
-  const connections = (Array.isArray(payload) ? payload : []).filter(
+  const connections = (data.connections ?? data.providers ?? data.items ?? data).filter(
     (c) => c.authType === "oauth" || c.authType === "oauth2"
   );
   emit(connections, globalOpts, connectionSchema);

bin/cli/commands/oneproxy.mjs

@@ -1,5 +1,4 @@
 import { apiFetch } from "../api.mjs";
-import { mcpCallTool } from "../mcpClient.mjs";
 import { emit } from "../output.mjs";
 import { t } from "../i18n.mjs";
 
@@ -9,7 +8,15 @@ function fmtTs(v) {
 }
 
 async function mcpCall(name, args) {
-  return mcpCallTool(name, args);
+  const res = await apiFetch("/api/mcp/tools/call", {
+    method: "POST",
+    body: { name, arguments: args },
+  });
+  if (!res.ok) {
+    process.stderr.write(`MCP error: ${res.status}\n`);
+    process.exit(1);
+  }
+  return res.json();
 }
 
 const proxySchema = [

bin/cli/commands/resilience.mjs

@@ -1,7 +1,6 @@
 import { createInterface } from "node:readline";
 import { Argument } from "commander";
 import { apiFetch } from "../api.mjs";
-import { mcpCallTool } from "../mcpClient.mjs";
 import { emit } from "../output.mjs";
 import { t } from "../i18n.mjs";
 
@@ -167,7 +166,14 @@ export function registerResilience(program) {
       ])
     )
     .action(async (name, opts, cmd) => {
-      await mcpCallTool("omniroute_set_resilience_profile", { profile: name });
+      const res = await apiFetch("/api/mcp/tools/call", {
+        method: "POST",
+        body: { name: "omniroute_set_resilience_profile", arguments: { profile: name } },
+      });
+      if (!res.ok) {
+        process.stderr.write(`Error: ${res.status}\n`);
+        process.exit(1);
+      }
       process.stdout.write(`Profile: ${name}\n`);
     });
 

bin/cli/commands/serve.mjs

@@ -1,7 +1,7 @@
 import { spawn } from "node:child_process";
 import { existsSync, readFileSync } from "node:fs";
 import { join, dirname } from "node:path";
-import { fileURLToPath, pathToFileURL } from "node:url";
+import { fileURLToPath } from "node:url";
 import { platform, totalmem } from "node:os";
 import { t } from "../i18n.mjs";
 import { writePidFile, cleanupPidFile, waitForServer } from "../utils/pid.mjs";
@@ -12,7 +12,7 @@ import {
   isFatalInstrumentationHookFailure,
   formatAndroidInstrumentationFailureHint,
 } from "../utils/ensureAndroidCacheDir.mjs";
-import { resolveServerHost, resolveExposureWarning } from "../utils/serverHost.mjs";
+import { resolveServerHost } from "../utils/serverHost.mjs";
 import {
   resolveMaxOldSpaceMb,
   calibrateHeapFallbackMb,
@@ -162,15 +162,6 @@ export async function runServe(opts = {}) {
 `);
   }
 
-  // GHSA-wmgv-ph3p-rv57: the default posture (all interfaces + no API key) is a
-  // deliberate local-first choice, but it must be loud at startup — an operator
-  // on an untrusted network learns the two escape hatches here, not after a
-  // surprise quota bill.
-  const exposureWarning = resolveExposureWarning();
-  if (exposureWarning) {
-    console.warn(`\x1b[33m  ⚠  ${exposureWarning}\x1b[0m\n`);
-  }
-
   const serverWsJs = join(APP_DIR, "server-ws.mjs");
   const serverJs = existsSync(serverWsJs) ? serverWsJs : join(APP_DIR, "server.js");
 
@@ -423,7 +414,7 @@ async function runWithSupervisor(
       if (detectMitmCrash(crashLog)) {
         try {
           const PROJECT_ROOT = join(dirname(fileURLToPath(import.meta.url)), "..", "..", "..");
-          const { updateSettings } = await import(pathToFileURL(join(PROJECT_ROOT, "src/lib/db/settings.ts")).href);
+          const { updateSettings } = await import(`${PROJECT_ROOT}/src/lib/db/settings.ts`);
           updateSettings({ mitmEnabled: false });
         } catch {}
         return "disable-mitm-and-retry";

bin/cli/commands/setup.mjs

@@ -1,4 +1,4 @@
-import { fileURLToPath, pathToFileURL } from "node:url";
+import { fileURLToPath } from "node:url";
 import { dirname, resolve } from "node:path";
 import { createPrompt, printHeading, printInfo, printSuccess } from "../io.mjs";
 import { openOmniRouteDb } from "../sqlite.mjs";
@@ -16,7 +16,7 @@ import { t } from "../i18n.mjs";
 const PROJECT_ROOT = resolve(dirname(fileURLToPath(import.meta.url)), "../../..");
 
 async function getListCliTools() {
-  const { listCliTools } = await import(pathToFileURL(resolve(PROJECT_ROOT, "src/shared/constants/cliTools.ts")).href);
+  const { listCliTools } = await import(`${PROJECT_ROOT}/src/shared/constants/cliTools.ts`);
   return listCliTools;
 }
 

bin/cli/commands/skills.mjs

@@ -1,6 +1,5 @@
 import { readFileSync } from "node:fs";
 import { apiFetch } from "../api.mjs";
-import { mcpCallTool } from "../mcpClient.mjs";
 import { emit } from "../output.mjs";
 import { t } from "../i18n.mjs";
 
@@ -107,7 +106,14 @@ export async function runSkillsInstall(opts, cmd) {
 }
 
 export async function runSkillsEnable(id, opts, cmd) {
-  await mcpCallTool("omniroute_skills_enable", { skillId: id, enabled: true });
+  const res = await apiFetch("/api/mcp/tools/call", {
+    method: "POST",
+    body: { name: "omniroute_skills_enable", arguments: { skillId: id, enabled: true } },
+  });
+  if (!res.ok) {
+    process.stderr.write(`Error: ${res.status}\n`);
+    process.exit(1);
+  }
   process.stdout.write(`Enabled: ${id}\n`);
 }
 
@@ -116,7 +122,14 @@ export async function runSkillsDisable(id, opts, cmd) {
     const ok = await confirm(`Disable ${id}?`);
     if (!ok) return;
   }
-  await mcpCallTool("omniroute_skills_enable", { skillId: id, enabled: false });
+  const res = await apiFetch("/api/mcp/tools/call", {
+    method: "POST",
+    body: { name: "omniroute_skills_enable", arguments: { skillId: id, enabled: false } },
+  });
+  if (!res.ok) {
+    process.stderr.write(`Error: ${res.status}\n`);
+    process.exit(1);
+  }
   process.stdout.write(`Disabled: ${id}\n`);
 }
 
@@ -140,11 +153,16 @@ export async function runSkillsExecute(id, opts, cmd) {
     : opts.inputFile
       ? JSON.parse(readFileSync(opts.inputFile, "utf8"))
       : {};
-  const data = await mcpCallTool(
-    "omniroute_skills_execute",
-    { skillId: id, input },
-    { timeout: opts.timeout ?? 30000 },
-  );
+  const res = await apiFetch("/api/mcp/tools/call", {
+    method: "POST",
+    body: { name: "omniroute_skills_execute", arguments: { skillId: id, input } },
+    timeout: opts.timeout ?? 30000,
+  });
+  if (!res.ok) {
+    process.stderr.write(`Error: ${res.status}\n`);
+    process.exit(1);
+  }
+  const data = await res.json();
   emit(data, globalOpts);
 }
 

bin/cli/mcpClient.mjs

@@ -1,127 +0,0 @@
-/**
- * Shared MCP JSON-RPC client for CLI commands.
- *
- * The server exposes MCP through /api/mcp/stream (Streamable HTTP transport).
- * Calling a tool requires:
- *   1. POST initialize → get Mcp-Session-Id response header
- *   2. POST tools/call with that session header
- *
- * Older CLI paths POSTed { name, arguments } to /api/mcp/tools/call, which is
- * not a registered route, so every MCP-backed command was broken.
- *
- * These functions route through apiFetch so CLI auth, remote contexts and
- * timeouts are handled the same way as every other management API call.
- */
-import { apiFetch } from "./api.mjs";
-
-function mcpError(message, status) {
-  const err = new Error(message);
-  if (status) err.status = status;
-  return err;
-}
-
-async function callMcpEndpoint(payload, { timeout, stream }) {
-  const res = await apiFetch("/api/mcp/stream", {
-    method: "POST",
-    body: payload,
-    timeout,
-    acceptNotOk: true,
-    headers: stream ? { Accept: "text/event-stream" } : {},
-  });
-
-  if (!res.ok) {
-    const text = await res.text().catch(() => "");
-    throw mcpError(
-      `${payload.method} ${payload.id}: HTTP ${res.status}${text ? ` — ${text}` : ""}`,
-      res.status,
-    );
-  }
-  return res;
-}
-
-/**
- * Call an MCP tool over /api/mcp/stream.
- *
- * Non-stream: returns the JSON-RPC result payload.
- * Stream: writes SSE `data:` chunks to stdout and returns null on success.
- */
-export async function mcpCallTool(name, args = {}, options = {}) {
-  const { timeout, scope } = options;
-  const scopeHeader = scope?.length ? { "X-MCP-Scopes": scope.join(",") } : {};
-
-  const initRes = await callMcpEndpoint(
-    {
-      jsonrpc: "2.0",
-      id: 1,
-      method: "initialize",
-      params: {
-        protocolVersion: "2024-11-05",
-        capabilities: {},
-        clientInfo: { name: "omniroute-cli", version: "1.0" },
-      },
-    },
-    { timeout, stream: options.stream },
-  );
-
-  const sessionId = initRes.headers.get("mcp-session-id");
-  if (!sessionId) {
-    throw mcpError("MCP initialize failed: no Mcp-Session-Id in response", 500);
-  }
-
-  const callRes = await callMcpEndpoint(
-    {
-      jsonrpc: "2.0",
-      id: 2,
-      method: "tools/call",
-      params: { name, arguments: args },
-    },
-    { timeout, stream: options.stream },
-  );
-
-  if (options.stream) {
-    return consumeSse(callRes.body, options.onChunk);
-  }
-
-  const data = await callRes.json();
-  if (data.error) {
-    const err = mcpError(`MCP error: ${data.error.message || JSON.stringify(data.error)}`);
-    err.code = data.error.code;
-    throw err;
-  }
-  if (data.result?.isError) {
-    const msg = data.result?.content?.[0]?.text || "unknown tool error";
-    throw mcpError(`MCP error: ${msg}`, 500);
-  }
-  return data.result;
-}
-
-async function consumeSse(body, onChunk) {
-  if (!body) throw mcpError("MCP stream returned no body", 500);
-  const reader = body.getReader();
-  const decoder = new TextDecoder();
-  let buf = "";
-  const flushLines = () => {
-    let idx;
-    while ((idx = buf.indexOf("\n")) >= 0) {
-      const line = buf.slice(0, idx);
-      buf = buf.slice(idx + 1);
-      if (line.startsWith("data: ")) {
-        const raw = line.slice(6).trim();
-        if (raw && raw !== "[DONE]") (onChunk ?? writeStdout)(raw);
-      }
-    }
-  };
-  while (true) {
-    const { done, value } = await reader.read();
-    if (done) break;
-    buf += decoder.decode(value, { stream: true });
-    flushLines();
-  }
-  buf += decoder.decode();
-  flushLines();
-  return null;
-}
-
-function writeStdout(raw) {
-  process.stdout.write(raw + "\n");
-}

bin/cli/provider-test.mjs

@@ -10,10 +10,6 @@ const PROVIDER_TEST_CONFIGS = {
     format: "openai",
     baseUrl: "https://openrouter.ai/api/v1",
     model: "openai/gpt-4o-mini",
-    // #11226: /models is public on OpenRouter (200 with any or no key) — probe the
-    // authenticated key-info endpoint instead so a bad key fails the test here
-    // instead of on the first real chat request.
-    keyCheckPath: "/auth/key",
   },
   groq: {
     format: "openai",
@@ -105,19 +101,13 @@ async function testOpenAILikeProvider(input, config) {
     "Content-Type": "application/json",
   };
 
-  // Providers whose /models endpoint is public (e.g. OpenRouter) declare a
-  // keyCheckPath pointing at an authenticated endpoint so the probe actually
-  // exercises the key instead of the public catalog.
-  const probeRes = await fetchWithTimeout(
-    joinUrl(config.baseUrl, config.keyCheckPath || "/models"),
-    {
-      method: "GET",
-      headers,
-    }
-  );
+  const modelsRes = await fetchWithTimeout(joinUrl(config.baseUrl, "/models"), {
+    method: "GET",
+    headers,
+  });
 
-  if (probeRes.ok || probeRes.status === 401 || probeRes.status === 403) {
-    return classifyResponse(probeRes);
+  if (modelsRes.ok || modelsRes.status === 401 || modelsRes.status === 403) {
+    return classifyResponse(modelsRes);
   }
 
   const chatRes = await fetchWithTimeout(joinUrl(config.baseUrl, "/chat/completions"), {

bin/cli/runtime.mjs

@@ -1,14 +1,9 @@
-import { fileURLToPath, pathToFileURL } from "node:url";
+import { fileURLToPath } from "node:url";
 import { dirname, resolve } from "node:path";
 import { apiFetch, isServerUp } from "./api.mjs";
 
 const PROJECT_ROOT = resolve(dirname(fileURLToPath(import.meta.url)), "../..");
 
-// Dynamic `import()` resolves its specifier as a URL, not as a filesystem path.
-// On Windows an absolute path starts with a drive letter, which the ESM loader
-// reads as the unsupported URL scheme `e:` and rejects. Pass a file:// URL.
-const projectFileUrl = (relPath) => pathToFileURL(resolve(PROJECT_ROOT, relPath)).href;
-
 export class ServerOfflineError extends Error {
   constructor(message = "Server is offline and operation requires HTTP runtime") {
     super(message);
@@ -27,8 +22,8 @@ function makeHttpContext(opts) {
 
 async function importDbModules() {
   const [combos, recovery] = await Promise.all([
-    import(projectFileUrl("src/lib/db/combos.ts")),
-    import(projectFileUrl("src/lib/db/recovery.ts")),
+    import(`${PROJECT_ROOT}/src/lib/db/combos.ts`),
+    import(`${PROJECT_ROOT}/src/lib/db/recovery.ts`),
   ]);
   return { combos, recovery };
 }

bin/cli/runtime/sqliteRuntime.mjs

@@ -6,9 +6,7 @@ import { pathToFileURL } from "node:url";
 import { validateBinaryMagic, platformBinaryLabel } from "./magicBytes.mjs";
 
 const RUNTIME_DIR = join(homedir(), ".omniroute", "runtime");
-// Exported so the packaging coherence guard (tests/unit/pack-boot-runtime-paths.test.ts)
-// can assert this stays on the same major as optionalDependencies.better-sqlite3 (#11242).
-export const BETTER_SQLITE3_VERSION = "better-sqlite3@^13.0.2";
+const BETTER_SQLITE3_VERSION = "better-sqlite3@^12.10.1";
 
 let resolvedCached = null;
 

bin/cli/utils/serverHost.mjs

@@ -24,34 +24,3 @@ export function resolveServerHost(
   }
   return "0.0.0.0";
 }
-
-const LOOPBACK_HOSTS = new Set(["127.0.0.1", "localhost", "::1", "[::1]"]);
-
-/**
- * Boot-time exposure warning (GHSA-wmgv-ph3p-rv57): the shipped default binds
- * all interfaces while the inference plane requires no credentials, so any
- * LAN peer can spend the operator's quota. That local-first posture is a
- * deliberate, documented default — but it must be LOUD at startup so an
- * operator who never read the docs still learns the two escape hatches.
- *
- * Returns the warning text when the server will listen on a non-loopback
- * interface with no API-key requirement, or null when the exposure is closed.
- *
- * @param {NodeJS.ProcessEnv} [env]
- * @param {string} [host]
- * @returns {string | null}
- */
-export function resolveExposureWarning(env = process.env, host = resolveServerHost(env)) {
-  if (LOOPBACK_HOSTS.has(host)) return null;
-  const requireKey = String(env.REQUIRE_API_KEY || "")
-    .trim()
-    .toLowerCase();
-  if (requireKey === "true" || requireKey === "1" || requireKey === "yes") return null;
-  return (
-    `SECURITY: listening on ${host} with NO API-key requirement — the inference ` +
-    `plane (/v1/*) is reachable by ANY device that can route to this host, and ` +
-    `requests are billed to your configured providers. This local-first default ` +
-    `is intentional, but on an untrusted network either set REQUIRE_API_KEY=true ` +
-    `or bind loopback with OMNIROUTE_SERVER_HOST=127.0.0.1.`
-  );
-}

changelog.d/features/11134-configurable-max-global-attempts.md

@@ -1 +0,0 @@
-- **feat(combo):** the shared per-request combo attempt budget is now operator-configurable via `maxGlobalAttempts` (combo config / `comboDefaults` cascade), instead of the hardcoded 30. Lower it to fail fast on a dead target pool, raise it for large combos; clamped to `[1, 200]` so an unbounded budget can never cause runaway background requests ([#11134](https://github.com/diegosouzapw/OmniRoute/issues/11134))

changelog.d/features/11251-connection-max-wait-ms-override.md

@@ -1 +0,0 @@
-- **feat(providers):** allow overriding the rate-limit queue wait timeout (`maxWaitMs`) per connection, alongside the existing `rpm`/`tpm`/`tpd`/`minTime`/`maxConcurrent` overrides — a single slow provider no longer has to lower the global wait budget for every other provider (#11251)

changelog.d/features/11282-first-run-readiness-card.md

@@ -1 +0,0 @@
-- **feat(dashboard):** replace the hard Home → onboarding redirect with a dismissable first-run readiness card so returning users can stay on Home while new users still get a clear 4-step path ([#11282](https://github.com/diegosouzapw/OmniRoute/pull/11282))

changelog.d/features/11283-traffic-inspector-purpose-header.md

@@ -1 +0,0 @@
-- **feat(dashboard):** lead Traffic Inspector with a purpose-first header that separates "what happened" from "how it happened", so beginners can read request outcomes without drowning in protocol detail ([#11283](https://github.com/diegosouzapw/OmniRoute/pull/11283))

changelog.d/features/11286-essentials-sidebar-preset.md

@@ -1 +0,0 @@
-- **feat(dashboard):** add an Essentials sidebar preset that shows only the beginner core path (Home → Endpoints → API Keys → Providers → Health → Settings) while keeping Advanced tools reachable via Command Palette search ([#11286](https://github.com/diegosouzapw/OmniRoute/pull/11286))

changelog.d/features/effort-tiers-loop-learned-sets.md

@@ -1 +0,0 @@
-- **feat(catalog):** surface runtime-learned `reasoning_effort` tiers in `/v1/models` `capabilities.effort_tiers` (learned set replaces synced metadata when present), map them to OpenCode `ModelV2.variants` in the OmniRoute plugin, and align dispatch `-<tier>` suffix validation to the effective (learned ?? synced) set — so the UI offers exactly the tiers the upstream accepts (e.g. `{low, high, max}` for `oc/x-preview-f-free`) and each advertised variant completes. Excludes codex/glm/kimi, which keep their own dedicated `-{effort}` suffix mechanism and never gain `effort_tiers` from this path (related to #7694, builds on #11232)

changelog.d/fixes/10060-build-sqlite-native-addon-guard.md

@@ -1 +0,0 @@
-- **fix(build):** stop the native `better-sqlite3` addon from loading during the Next.js production build (#10060). Its `Statement` destructor aborts with `SIGABRT` when a build worker thread exits (assertion in `node::RemoveEnvironmentCleanupHook`, `env == nullptr`), which can leave the build with no standalone bundle. Every DB entry point now keys off a reliable `OMNIROUTE_BUILDING=1` signal (set by `build-next-isolated.mjs` and inherited by every spawned build worker, because Next.js workers sometimes drop `NEXT_PHASE`): `getDbInstance()` returns a no-op SQLite stub during build, `driverFactory` skips the native driver and falls through to `node:sqlite`, and the `codegraph`/`kiro-import` lazy loaders fail closed. A build-time `better-sqlite3` alias to a stub (`next.config.mjs`, turbopack) backs this up without changing runtime behaviour (the real package is still `require()`d natively via `serverExternalPackages`). Also raises the default build heap 4096→6144 MB and caps Next build worker pools (`CIRCLE_NODE_TOTAL=8`) to avoid the many-core page-data-collection SIGSEGV, and adds `.gitattributes` (`*.sh text eol=lf`) so kernel-exec'd shell scripts never ship with CRLF shebangs. Deliberately does NOT downgrade the Node base image: per the maintainer's review on #10060, `release/v3.8.50` moved to `node:26-trixie-slim` through several considered commits, so the `OMNIROUTE_BUILDING` guard is re-derived against the current base rather than reverting the FROM line; the npm pin and binary-hide dance from the original PR are dropped because our build already rebuilds `better-sqlite3` deterministically via `node-gyp` and floats `npm@latest` for the CVE overlay.

changelog.d/fixes/10286-gemini-3-5-flash-thinking.md

@@ -0,0 +1 @@
+- fix(sse): mark gemini-3.5-flash as thinking-capable so reasoning_effort is no longer rejected with a spurious 400 (#10286)

changelog.d/fixes/10815-kiro-social-multi-account.md

@@ -1 +0,0 @@
-- fix(oauth): stop treating the Kiro profile ARN as an account identity in `findKiroConnectionByIdentity()`, so a second Google/GitHub social login creates a new connection instead of overwriting the first — distinct Builder ID accounts share the same CodeWhisperer profile ARN, and the social token is not a JWT, so no e-mail was available to disambiguate them (#10815)

changelog.d/fixes/10851-openapi-spec-auth-contract.md

@@ -1 +0,0 @@
-- Document the conditional management authentication and 401/403 responses for `GET /api/openapi/spec`.

changelog.d/fixes/11088-ollama-capability-routing.md

@@ -0,0 +1 @@
+- fix(ollama): route models by advertised capability — synced store now persists non-chat models and chat filtering moved to read time (#11088, option 1)

changelog.d/fixes/11271-ollama-capability-routing.md

@@ -1 +0,0 @@
-- **fix(ollama):** Ollama Local models are no longer flattened to `chat` at sync time — the synced store persists every advertised capability and chat filtering moves to read time, so `/v1/embeddings` and `/v1/images/generations` stop rejecting models the daemon reports as capable ([#11271](https://github.com/diegosouzapw/OmniRoute/pull/11271)) — thanks @yourspraveen

changelog.d/fixes/11297-opencode-subagent-sessionid.md

@@ -1 +0,0 @@
-- **fix(translator):** preserve omitted OpenCode `subagent.sessionID` values — optional default-less plain strings now use the Responses `null = omit` sentinel and are stripped before the client sees the tool call, so Codex/Responses no longer invent filler session IDs ([#11297](https://github.com/diegosouzapw/OmniRoute/pull/11297)) — thanks @ofonseca-pyming

changelog.d/fixes/7764-quota-window-order.md

@@ -1 +0,0 @@
-- **fix(usage):** keep session/weekly/monthly quota windows in chronological order on every provider card. The order is now derived from the quota keys themselves instead of a provider whitelist, so Claude, MiniMax, Z.ai and Command Code stop rendering the two bars in opposite positions across sibling accounts ([#7764](https://github.com/diegosouzapw/OmniRoute/issues/7764))

changelog.d/fixes/codex-appserver-hardening.md

@@ -1 +0,0 @@
-- Hardened the Codex app-server transport after the post-merge security review of #11205: approval prompts from the app-server (its own command/file/permission execution — not the harness tool passthrough) are now auto-denied by default, with opt-in auto-approval via `providerSpecificData.codexAppServerAutoApprove` / `OMNIROUTE_CODEX_APPSERVER_AUTO_APPROVE`; the default codex sandbox changed from `danger-full-access` to `workspace-write` (override per connection or env); env-sourced capability tokens are now only sent to env-sourced URLs or operator-local hosts (loopback/RFC1918/link-local/ULA/localhost/single-label LAN names/*.local/*.ts.net/*.internal), so a connection's providerSpecificData URL can no longer exfiltrate the operator's env token; and the `/readyz` health probe no longer follows redirects while carrying the bearer token.

changelog.d/fixes/secret-leak-error-surface-hardening.md

@@ -1 +0,0 @@
-- **fix(security):** harden three secret-leak paths surfaced by an audit of the error/log surface. (1) `upstreamErrorPassthrough` relays an upstream provider's 4xx body verbatim to Claude-Code-format clients (the capability-recovery contract needs the exact wording); it now refuses passthrough when the body actually carries a credential pattern (`Bearer`/`Basic` token, `sk-…`, or an `api_key`/`token`/`authorization`/`cookie`/`secret` assignment) so a provider that echoes the offending request can't relay a key to the client, falling back to the sanitized error path. The credential regex is bounded (ReDoS-safe, verified linear at 60k chars). (2) The OCR and moderations handlers no longer forward an upstream error body byte-for-byte; they run it through the (now exported) structure-preserving `redactSensitiveErrorText` first. (3) `protectPayloadForLog`'s sensitive-key set gains `cookie`/`storageState`/`runtimeKey`/`capability` so web-impersonation credentials (Meta AI `ecto_1_sess`, chatgpt-web `storageState`) that land in a request/response body field are redacted before the call-log artifact is written to disk. No behavior change for secret-free error bodies; the Claude Code verbatim-wording contract is preserved.

changelog.d/maintenance/11018-database-cache-docs.md

@@ -1 +0,0 @@
-- **docs(database):** align the SQLite cache guide with the 65,536 KiB runtime default, supported 1–1,000,000 KiB range, and live Settings application behavior ([#11018](https://github.com/diegosouzapw/OmniRoute/issues/11018))

changelog.d/maintenance/11247-ratchet-no-unused-vars.md

@@ -1 +0,0 @@
-- **chore(lint):** ratchet `@typescript-eslint/no-unused-vars` scoped to `src/` + `open-sse/` + `tests/` (`args: "all"`, `_`-prefix escape hatch) and freeze the 1393 pre-existing violations via bulk suppressions — same pattern as the #7879 `toNumber` ratchet. New unused bindings now fail lint. ([#11247](https://github.com/diegosouzapw/OmniRoute/pull/11247))

config/quality/dependency-allowlist.json

@@ -1,9 +1,5 @@
 {
   "_comment": "Allowlist anti-slopsquatting (check-deps.mjs). Toda dep nova exige adicao EXPLICITA aqui apos verificar que e legitima.",
-  "_justifications": {
-    "@testing-library/dom": "Peer dep obrigatoria de @testing-library/react v16 (adicionada no PR #11224); Refs #9985.",
-    "@testing-library/user-event": "Utilitario oficial do ecossistema testing-library para testes de UI (adicionada no PR #11224); Refs #9985."
-  },
   "allowed": [
     "@atjsh/llmlingua-2",
     "@aws-sdk/client-bedrock-runtime",
@@ -24,10 +20,8 @@
     "@stryker-mutator/tap-runner",
     "@swc/helpers",
     "@tailwindcss/postcss",
-    "@testing-library/dom",
     "@testing-library/jest-dom",
     "@testing-library/react",
-    "@testing-library/user-event",
     "@toon-format/toon",
     "@types/better-sqlite3",
     "@types/bun",

config/quality/file-size-baseline.json

@@ -433,7 +433,7 @@
     "src/shared/components/analytics/charts.tsx": 1346,
     "src/shared/services/cliRuntime.ts": 1459,
     "src/sse/handlers/chat.ts": 2493,
-    "src/sse/services/auth.ts": 3344,
+    "src/sse/services/auth.ts": 3337,
     "_rebaseline_2026_08_23_11186_synced_inventory_routing": "PR #11186 (pacocartones) own growth: src/sse/services/auth.ts 3260->3337 (+77, loadAdvertisedModelsForSelfHostedConnections + the modelNotAdvertised candidate-filter predicate — pins chat routing to the connection whose synced inventory actually advertises the model, fixing spurious model-not-found on multi-host self-hosted setups; at the existing credential-selection chokepoint, not extractable without splitting the selection flow). Covered by tests/unit/chat-routing-synced-inventory-11089.test.ts. Owner pre-authorized baseline bumps 2026-08-22.",
     "tests/unit/account-fallback-service.test.ts": 2044,
     "tests/unit/provider-validation-specialty.test.ts": 3880,
@@ -464,15 +464,14 @@
     "src/app/(dashboard)/dashboard/providers/[id]/providerPageHelpers.ts": 1014,
     "open-sse/config/imageRegistry.ts": 1034,
     "src/sse/handlers/chatHelpers.ts": 1019,
-    "src/shared/middleware/chatBodyAdmission.ts": 1118,
+    "src/shared/middleware/chatBodyAdmission.ts": 1009,
     "_rebaseline_2026_08_22_11020_sigterm_drain": "PR #11020 (RaviTharuma) own growth: chatBodyAdmission.ts 1005->1009 (+4, heavyweight admission leases now increment the SIGTERM drain counter and releaseChatAdmissionWhenDone holds it for the SSE lifetime — closes #11015; +4 are the lease/drain wiring lines at the existing admission chokepoint). Covered by tests/unit/chat-body-admission.test.ts heavyweight-lease cases. Owner pre-authorized baseline bumps 2026-08-22.",
     "_rebaseline_2026_08_20_10668_tabitoken_gateway": "#10668 (yawar-aquil) own catalog growth: src/shared/constants/providers/apikey/gateways.ts 1268->1283 (+15, entirely this PR diff -- one new tabitoken gateway entry, data lines only; base moved from 1255 to 1268 via other merges since the PR forked). Not combination drift: reproducible on the PR branch alone, so the WS5.5 release-captain rule does not apply. Extraction is not available -- the file is pure data (own header: \"Pure data; merged by apikey/index.ts via spread\") and already split into 6 family files under apikey/. Same precedent as _rebaseline_2026_08_14_imagetotext_servicekinds (#10275/#10291, gateways.ts 1250->1255, data lines only) and _rebaseline_2026_08_11_v3850_merge_storm_provider_registry (owner-authorized for this same file).",
     "open-sse/executors/commandCode.ts": 1059,
     "_rebaseline_2026_08_21_10859_vision_bridge_catalog": "#10859 own growth (Vision Bridge fixes #10808/#10809): src/lib/modelCapabilities.ts 1006->1016 (+10, cmd/gpt-5.3-codex* text-only capability resolution) and open-sse/executors/commandCode.ts 988->1023 (+35, Command Code wire-model normalization for bare ids + reasoning field fallback for opencode-routed gateways). Cohesive bug fixes at the existing capability-resolution / executor chokepoints; not extractable mid-fix. Covered by tests/unit/model-capabilities-command-code-codex-textonly-10703.test.ts, tests/unit/command-code-vision.test.ts, tests/unit/opencode-mimo-reasoning-details-nonstream.test.ts. Pushed directly to release (own-session miss: the original rebaseline was made in a throwaway validation worktree and never landed on the PR branch or the release before merge).",
     "_rebaseline_2026_08_21_10907_sticky_pin_clear": "#10907 own growth: open-sse/executors/commandCode.ts 1023->1038 (+15, effort-suffix sanitization threading for the sticky-pin-clear fix). Cohesive change at the existing executor chokepoint. Covered by tests/unit/command-code-executor.test.ts.",
     "_rebaseline_2026_08_21_10986_reasoning_only_content": "#10986 own growth: open-sse/executors/commandCode.ts 1038->1059 (+21, reasoning-only content fallback — when upstream emits only reasoning-delta events and never a text-delta, surface the reasoning text as message.content in createJsonResponse and emit a synthetic content delta in createStreamResponse). Cohesive bug fix at the existing executor chokepoint (mirrors precedent style of #10907/#10859). Covered by tests/unit/command-code-executor.test.ts (2 new cases: non-stream + streaming).",
-    "_rebaseline_2026_08_21_11069_m365_har_import": "#11069 own growth: AddApiKeyModal.tsx 1073->1080 (+7 = Import .har file button for the copilot-m365-web credential modal — M365 is the only provider whose credential (access_token+chathubPath) must be extracted from a DevTools HAR WebSocket URL, added as a new modal affordance). Cohesive UI at the existing modal chokepoint; not extractable. Covered by tests/unit/m365-har-import*.test.ts.",
-    "_rebaseline_2026_08_23_tip_drift_post_batch0823": "Tip drift after the 2026-08-23 merge wave: chatBodyAdmission.ts 1009->1118 (+109, gate count incl. +1) and auth.ts 3337->3344 (+7), both grown by merges already on origin/release/v3.8.50 (verified identical on the pristine tip) — not by the codex-appserver-hardening PR that carries this bump. Owner pre-authorized baseline bumps 2026-08-22."
+    "_rebaseline_2026_08_21_11069_m365_har_import": "#11069 own growth: AddApiKeyModal.tsx 1073->1080 (+7 = Import .har file button for the copilot-m365-web credential modal — M365 is the only provider whose credential (access_token+chathubPath) must be extracted from a DevTools HAR WebSocket URL, added as a new modal affordance). Cohesive UI at the existing modal chokepoint; not extractable. Covered by tests/unit/m365-har-import*.test.ts."
   },
   "_rebaseline_base_2026_08_10_proxyfetch": "Base-red fix (green-prs sweep, issue #9985): open-sse/utils/proxyFetch.ts 1207 > cap 1000 — new proxied-TLS fetch helper introduced by the Fal reference-image work. Owner-authorized quick rebaseline to green; structural slim tracked for v3.9.0.",
   "_rebaseline_2026_07_27_v3849_train2": "Merge-train 2 (7 PRs) — owner-approved 2026-07-27. Single entry: chatCore.ts 4955->5006 (#8595, Responses multi-turn image compaction before the context hard-reject). Genuine irreducible growth at the existing compaction chokepoint in handleChatCore — the PR adds a last-resort retry against the concrete budget plus the estimateFinalInputTokens helper, both wired at the pre-existing call site rather than a new branch. Covered by tests/unit/8560-responses-image-compaction.test.ts (4 tests).",

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 (350 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 the 80+ command surface: 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 (351 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 the 80+ command surface: 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: 350 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: 351 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, 350 providers — never stop building, OmniRoute picks the cheapest one that works. Six pillars. Never hit limits: auto-fallback across 350 providers in milliseconds, quota out means the next provider takes over with zero downtime. Save up to 95 percent of tokens: RTK plus Caveman stacked compression cuts 15 to 95 percent of eligible tokens, about 89 percent average on tool-heavy sessions. Zero dollars to start: 90+ providers with a free tier, 56 free forever — Qoder, Pollinations, Cloudflare, SiliconFlow — no card needed. Every tool works: 33 coding agents including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation — point any tool at /v1 and it just works. Production-grade: circuit breakers, TLS stealth, MCP with 110 tools, A2A, memory, guardrails, evals — 25,000+ tests.">
+<svg viewBox="0 0 1200 540" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="The OmniRoute promise: one endpoint, 351 providers — never stop building, OmniRoute picks the cheapest one that works. Six pillars. Never hit limits: auto-fallback across 351 providers in milliseconds, quota out means the next provider takes over with zero downtime. Save up to 95 percent of tokens: RTK plus Caveman stacked compression cuts 15 to 95 percent of eligible tokens, about 89 percent average on tool-heavy sessions. Zero dollars to start: 90+ providers with a free tier, 56 free forever — Qoder, Pollinations, Cloudflare, SiliconFlow — no card needed. Every tool works: 33 coding agents including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation — point any tool at /v1 and it just works. Production-grade: circuit breakers, TLS stealth, MCP with 110 tools, A2A, memory, guardrails, evals — 25,000+ tests.">
   <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">350 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">351 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 350 providers in</text>
+      <text x="66" y="204" font-size="13.5" fill="#a1a1aa">Auto-fallback across 351 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 — zero downtime.</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 350 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: 350 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 351 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: 351 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">350 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">351 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/guides/ANTIGRAVITY-ONBOARDING.md

@@ -6,7 +6,7 @@ lastUpdated: 2026-07-31
 
 # OmniRoute Antigravity (Google One AI) Onboarding Guide
 
-> **What you get**: Access to Gemini 3.1 Pro, Gemini 3.7 Flash, Claude Sonnet 4.6, and other models through your Google One AI Pro subscription — routed through OmniRoute as a unified gateway.
+> **What you get**: Access to Gemini 3.1 Pro, Gemini 3.5 Flash, Claude Sonnet 4.6, and other models through your Google One AI Pro subscription — routed through OmniRoute as a unified gateway.
 
 **Official references**:
 
@@ -45,7 +45,7 @@ Both providers share the **same Google backend** — identical OAuth client, tok
 
 **Why the model catalog differs**: Google's CLI is "optimized for speed and low overhead" and "co-optimized with Gemini models" (per Google's official blog). The Web/IDE product is "optimized for comprehensiveness." The CLI uses `:fetchAvailableModels` to dynamically discover models, while the IDE uses a static curated list.
 
-**In practice**: Use `agy/` prefix for Gemini models (e.g. `agy/gemini-3.7-flash-high`). Use `antigravity/` for the static curated list. Both hit the same Google backend, but expose different model naming. The quota is shared — using either provider counts against the same Google account's limits.
+**In practice**: Use `agy/` prefix for Gemini models (e.g. `agy/gemini-3.5-flash-high`). Use `antigravity/` for the static curated list. Both hit the same Google backend, but expose different model naming. The quota is shared — using either provider counts against the same Google account's limits.
 
 ---
 

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

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 350 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 351 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
-- **350 AI providers** with automatic format translation
+- **351 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

docs/i18n/tr/CLAUDE.md

@@ -1,49 +1,390 @@
 # CLAUDE.md (Türkçe)
 
-🌐 **Languages:** 🇺🇸 [English](../../../CLAUDE.md) · 🇸🇦 [ar](../ar/CLAUDE.md) · 🇦🇿 [az](../az/CLAUDE.md) · 🇧🇬 [bg](../bg/CLAUDE.md) · 🇧🇩 [bn](../bn/CLAUDE.md) · 🇨🇿 [cs](../cs/CLAUDE.md) · 🇩🇰 [da](../da/CLAUDE.md) · 🇩🇪 [de](../de/CLAUDE.md) · 🇪🇸 [es](../es/CLAUDE.md) · 🇮🇷 [fa](../fa/CLAUDE.md) · 🇫🇮 [fi](../fi/CLAUDE.md) · 🇫🇷 [fr](../fr/CLAUDE.md) · 🇮🇳 [gu](../gu/CLAUDE.md) · 🇮🇱 [he](../he/CLAUDE.md) · 🇮🇳 [hi](../hi/CLAUDE.md) · 🇭🇺 [hu](../hu/CLAUDE.md) · 🇮🇩 [id](../id/CLAUDE.md) · 🇮🇩 [in](../in/CLAUDE.md) · 🇮🇹 [it](../it/CLAUDE.md) · 🇯🇵 [ja](../ja/CLAUDE.md) · 🇰🇷 [ko](../ko/CLAUDE.md) · 🇮🇳 [mr](../mr/CLAUDE.md) · 🇲🇾 [ms](../ms/CLAUDE.md) · 🇳🇱 [nl](../nl/CLAUDE.md) · 🇳🇴 [no](../no/CLAUDE.md) · 🇵🇭 [phi](../phi/CLAUDE.md) · 🇵🇱 [pl](../pl/CLAUDE.md) · 🇵🇹 [pt](../pt/CLAUDE.md) · 🇧🇷 [pt-BR](../pt-BR/CLAUDE.md) · 🇷🇴 [ro](../ro/CLAUDE.md) · 🇷🇺 [ru](../ru/CLAUDE.md) · 🇸🇰 [sk](../sk/CLAUDE.md) · 🇸🇪 [sv](../sv/CLAUDE.md) · 🇰🇪 [sw](../sw/CLAUDE.md) · 🇮🇳 [ta](../ta/CLAUDE.md) · 🇮🇳 [te](../te/CLAUDE.md) · 🇹🇭 [th](../th/CLAUDE.md) · 🇹🇷 [tr](../tr/CLAUDE.md) · 🇺🇦 [uk-UA](../uk-UA/CLAUDE.md) · 🇵🇰 [ur](../ur/CLAUDE.md) · 🇻🇳 [vi](../vi/CLAUDE.md) · 🇨🇳 [zh-CN](../zh-CN/CLAUDE.md)
+🌐 **Languages:** 🇺🇸 [English](../../../CLAUDE.md) · 🇸🇦 [ar](../ar/CLAUDE.md) · 🇦🇿 [az](../az/CLAUDE.md) · 🇧🇬 [bg](../bg/CLAUDE.md) · 🇧🇩 [bn](../bn/CLAUDE.md) · 🇨🇿 [cs](../cs/CLAUDE.md) · 🇩🇰 [da](../da/CLAUDE.md) · 🇩🇪 [de](../de/CLAUDE.md) · 🇪🇸 [es](../es/CLAUDE.md) · 🇮🇷 [fa](../fa/CLAUDE.md) · 🇫🇮 [fi](../fi/CLAUDE.md) · 🇫🇷 [fr](../fr/CLAUDE.md) · 🇮🇳 [gu](../gu/CLAUDE.md) · 🇮🇱 [he](../he/CLAUDE.md) · 🇮🇳 [hi](../hi/CLAUDE.md) · 🇭🇺 [hu](../hu/CLAUDE.md) · 🇮🇩 [id](../id/CLAUDE.md) · 🇮🇩 [in](../in/CLAUDE.md) · 🇮🇹 [it](../it/CLAUDE.md) · 🇯🇵 [ja](../ja/CLAUDE.md) · 🇰🇷 [ko](../ko/CLAUDE.md) · 🇮🇳 [mr](../mr/CLAUDE.md) · 🇲🇾 [ms](../ms/CLAUDE.md) · 🇳🇱 [nl](../nl/CLAUDE.md) · 🇳🇴 [no](../no/CLAUDE.md) · 🇵🇭 [phi](../phi/CLAUDE.md) · 🇵🇱 [pl](../pl/CLAUDE.md) · 🇵🇹 [pt](../pt/CLAUDE.md) · 🇧🇷 [pt-BR](../pt-BR/CLAUDE.md) · 🇷🇴 [ro](../ro/CLAUDE.md) · 🇷🇺 [ru](../ru/CLAUDE.md) · 🇸🇰 [sk](../sk/CLAUDE.md) · 🇸🇪 [sv](../sv/CLAUDE.md) · 🇰🇪 [sw](../sw/CLAUDE.md) · 🇮🇳 [ta](../ta/CLAUDE.md) · 🇮🇳 [te](../te/CLAUDE.md) · 🇹🇭 [th](../th/CLAUDE.md) · 🇺🇦 [uk-UA](../uk-UA/CLAUDE.md) · 🇵🇰 [ur](../ur/CLAUDE.md) · 🇻🇳 [vi](../vi/CLAUDE.md) · 🇨🇳 [zh-CN](../zh-CN/CLAUDE.md)
 
 ---
 
-@AGENTS.md
+Bu dosya, bu depoda kod çalıştırırken Claude Code (claude.ai/code) için rehberlik sağlar.
 
-**Tüm proje kuralları [`AGENTS.md`](AGENTS.md) dosyasında yer almaktadır** — her yapay zeka asistanı için tek doğruluk kaynağıdır (mimari, kurallar, testler, kalite kapıları, git iş akışı, 23 Katı Kural, PII öğrenimleri). Tamamını okuyun; buraya yeniden proje kuralları eklemeyin. Aşağıdaki her şey YALNIZCA Claude Code için geçerlidir — `AGENTS.md` içinde zaten tanımlanmış kuralların operasyonel ayrıntılarıdır.
+## Hızlı Başlangıç
 
-## Worktree İzolasyonu — Claude Code Özel Notları
+```bash
+npm install                    # Bağımlılıkları yükle (otomatik olarak .env.example'dan .env oluşturur)
+npm run dev                    # Geliştirme sunucusu http://localhost:20128
+npm run build                  # Üretim derlemesi (Next.js 16 bağımsız)
+npm run lint                   # ESLint (0 hata bekleniyor; uyarılar önceden mevcut)
+npm run typecheck:core         # TypeScript kontrolü (temiz olmalı)
+npm run typecheck:noimplicit:core  # Sıkı kontrol (implicit any yok)
+npm run test:coverage          # Birim testleri + kapsama kapısı (75/75/75/70 — ifadeler/hatlar/fonksiyonlar/dallar)
+npm run check                  # lint + test birleştirilmiş
+npm run check:cycles           # Dairesel bağımlılıkları tespit et
+```
 
-Tam zorunlu worktree protokolü (hedef dal onayı, `.claude/worktrees/` kurallı yolu, `cp -al` node_modules, kaldırma kuralları) `AGENTS.md` → Git Workflow → "Worktree isolation" bölümündedir. Claude Code özel noktaları:
+### Testleri Çalıştırma
 
-- Operatör daha önce belirtmediyse, hedef dalı `AskUserQuestion` (Katı Kural #19) ile onaylayın.
-- Yerel `EnterWorktree` aracını tercih edin — worktree'leri zaten `.claude/worktrees/` altında oluşturur (kurallı yol). Belgelenen `git worktree add` komutuyla worktree oluşturun, ardından `path` parametresi ile `EnterWorktree` çağırın.
+```bash
+# Tek test dosyası (Node.js yerel test koşucusu — çoğu test)
+node --import tsx/esm --test tests/unit/your-file.test.ts
 
-## Oturumlar Arası Güvenlik — Claude Code Özel Notları
+# Vitest (MCP sunucusu, autoCombo, önbellek)
+npm run test:vitest
 
-Katı Kurallar #19/#21/#22 (`AGENTS.md` içinde) paralel oturumları yönetir. Bu ortam için operasyonel hatırlatmalar:
+# Tüm test paketleri
+npm run test:all
+```
 
-- **Git'e dokunan her alt ajanın isteminde `git stash` yasağını kelimesi kelimesine tekrarlayın** (Agent tool / Workflow betikleri) — alt ajanlar bu dosyayı devralmaz ve kaydedilen stash olayı bir alt ajan aracılığıyla gerçekleşti.
-- _Bu oturumda_ oluşturmadığınız herhangi bir PR'ı birleştirmeden veya push etmeden önce `git worktree list` çalıştırın ve `gh pr view <N> --json state,headRefOid` kontrolü yapın (Katı Kural #22b).
-- Her oturumu, ana checkout başladığı dalda olacak şekilde sonlandırın.
+Tam test matrisini görmek için `CONTRIBUTING.md` → "Testleri Çalıştırma" kısmına bakın. Derin mimari için `AGENTS.md` dosyasına bakın.
 
-## Superpowers / Planlama Yapıtları — Yol Geçersiz Kılmaları
+---
 
-`_tasks/` kuralı `AGENTS.md` → "Planning & Research Artifacts" içinde tanımlanmıştır. Superpowers yetenekleri `docs/…` dizinini işaret eden varsayılanlarla gelir — bu varsayılanlar **burada geçersiz kılınmıştır**. Bir superpowers yeteneği "saved to `docs/superpowers/plans/…`" gibi bir yol duyurduğunda, yazmadan önce onu `_tasks/…` eşdeğerine yeniden yazın:
+## Projeye Genel Bakış
 
-| Yapıt (Yetenek)                    | Varsayılan (KULLANMAYIN)  | Bunun yerine buraya kaydedin                                  |
-| ---------------------------------- | ------------------------- | ------------------------------------------------------------- |
-| Planlar (`writing-plans`)          | `docs/superpowers/plans/` | `_tasks/superpowers/plans/YYYY-MM-DD-<feature>.md`            |
-| Şartnameler / tasarım (`brainstorming`) | `docs/superpowers/specs/` | `_tasks/superpowers/specs/YYYY-MM-DD-<topic>-design.md`       |
-| Araştırma (`deep-research`, ad-hoc)| `docs/research/`          | `_tasks/research/…`                                           |
-| Devirler (`/handoff`)              | —                         | `_tasks/hands-off/<YYYY-MM-DD>_<branch>_v<versão>_sess-<id>/` |
+**OmniRoute** — birleşik AI proxy/yönlendirici. Tek uç nokta, 329 LLM sağlayıcısı, otomatik geri dönüş.
 
-Bu yapıtları `_tasks/` deposu içinde commit edin (`git -C _tasks …`), asla ana depoda değil.
+| Katman        | Konum                   | Amaç                                                                      |
+| ------------- | ----------------------- | ------------------------------------------------------------------------- |
+| API Yolları   | `src/app/api/v1/`       | Next.js Uygulama Yönlendiricisi — giriş noktaları                         |
+| İşleyiciler   | `open-sse/handlers/`    | İstek işleme (sohbet, gömme, vb.)                                         |
+| Yürütücüler   | `open-sse/executors/`   | Sağlayıcıya özel HTTP dağıtımı                                            |
+| Çeviriciler   | `open-sse/translator/`  | Format dönüşümü (OpenAI↔Claude↔Gemini)                                    |
+| Dönüştürücü   | `open-sse/transformer/` | Yanıtlar API ↔ Sohbet Tamamlamaları                                       |
+| Hizmetler     | `open-sse/services/`    | Kombinasyon yönlendirme, hız sınırlamaları, önbellekleme, vb.             |
+| Veritabanı    | `src/lib/db/`           | 110 top-level SQLite domain modules, 130 migrations                       |
+| Alan/Politika | `src/domain/`           | Politika motoru, maliyet kuralları, geri dönüş mantığı                    |
+| MCP Sunucusu  | `open-sse/mcp-server/`  | 107 unique tools, 3 transports (stdio / SSE / Streamable HTTP), 32 scopes |
+| A2A Sunucusu  | `src/lib/a2a/`          | JSON-RPC 2.0 ajan protokolü                                               |
+| Beceriler     | `src/lib/skills/`       | Genişletilebilir beceri çerçevesi                                         |
+| Bellek        | `src/lib/memory/`       | Kalıcı konuşma belleği                                                    |
 
-## Geçici Dosyalar — `/tmp` Değil `_artifacts/` Kullanın
+Monorepo: `src/` (Next.js 16 uygulaması), `open-sse/` (akış motoru çalışma alanı), `electron/` (masaüstü uygulaması), `tests/`, `bin/` (CLI giriş noktası).
 
-Bu proje, çalışma ortamının varsayılan oturum karalama alanını (`/tmp/claude-*/…`) geçersiz kılar. Geçici/çalışma dosyalarını — dışa aktarmaları, oluşturulan zip'leri, tek seferlik ara çıktıları, aksi halde `/tmp` içine koyacağınız her şeyi — bunun yerine `/home/diegosouzapw/dev/proxys/OmniRoute/_artifacts/` dizinine yazın.
+---
 
-- `_artifacts/` bir kök `_*` yoludur: zaten gitignore edilmiştir (`AGENTS.md` → "Root `_*` paths"), yalnızca diskte yaşar, asla takip edilmez.
-- Gerekçe: karalama çıktılarını proje içinde tutmak (vs `/tmp`), operatörün geçici her şeyi tek bir yerde bulup silmesini kolaylaştırır.
-- Bunu `_tasks/` (Katı Kural #23, kalıcı planlar/şartnameler/araştırmalar için kendi özel git deposu) ile **karıştırmayın** — `_artifacts/` yalnızca tek kullanımlık çalışma dosyaları içindir.
+## İstek Boru Hattı
 
-## PR Açmadan Önce Base-Green Kontrolü
+```
+Client → /v1/chat/completions (Next.js route)
+  → CORS → Zod doğrulama → kimlik doğrulama? → politika kontrolü → istemci enjeksiyon koruması
+  → handleChatCore() [open-sse/handlers/chatCore.ts]
+    → önbellek kontrolü → oran sınırlaması → kombinasyon yönlendirmesi?
+      → resolveComboTargets() → hedef başına handleSingleModel()
+    → translateRequest() → getExecutor() → executor.execute()
+      → fetch() yukarı akış → geri çekilme ile yeniden deneme
+    → yanıt çevirisi → SSE akışı veya JSON
+    → Eğer Yanıtlar API'si: responsesTransformer.ts TransformStream
+```
 
-Bir dal açmadan veya PR oluşturmadan önce base-green kontrolünü çalıştırın (`AGENTS.md` → Git Workflow → "Base-green check"; proje yetenekleri bunu `.agents/skills/_shared/base-green.md` olarak referans alır). Temel uç (base tip) kırmızı iken açılan bir PR, gövdesinde `⚠️ base-red inherited: #<issue>` taşımalıdır. Birikmiş kırmızı durumu (temel uç + kırmızı PR'lar) boşaltmak için `/sweep-reds` yeteneğini kullanın.
+API yolları tutarlı bir desen izler: `Route → CORS ön uç → Zod gövde doğrulama → Opsiyonel kimlik doğrulama (extractApiKey/isValidApiKey) → API anahtarı politika uygulaması → İşleyici delegasyonu (open-sse)`. Global Next.js ara yazılımı yok — kesme işlemi yol spesifik.
+
+**Combo routing** (`open-sse/services/combo.ts`): 19 public strategies (priority, weighted, fill-first, round-robin, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline). Each target calls `handleSingleModel()`, which wraps `handleChatCore()` with per-target error handling and circuit-breaker checks. See `docs/routing/AUTO-COMBO.md` for the 13-factor Auto-Combo scoring and `docs/architecture/RESILIENCE_GUIDE.md` for the 3 resilience layers.
+
+---
+
+## Dayanıklılık Çalışma Durumu
+
+OmniRoute, üç ilgili ancak farklı geçici hata mekanizmasına sahiptir. Yönlendirme davranışını hata ayıklarken kapsamlarını ayrı tutun. Bir bakışta harita için [3 katmanlı dayanıklılık diyagramı](./docs/diagrams/exported/resilience-3layers.svg) (kaynak: [docs/diagrams/resilience-3layers.mmd](./docs/diagrams/resilience-3layers.mmd))'na bakın.
+
+### Sağlayıcı Devre Kesici
+
+**Kapsam**: tüm sağlayıcı, örneğin `glm`, `openai`, `anthropic`.
+
+**Amaç**: yukarı akış/hizmet seviyesinde sürekli olarak başarısız olan bir sağlayıcıya trafik göndermeyi durdurmak, böylece bir sağlıksız sağlayıcı her isteği yavaşlatmaz.
+
+**Uygulama**:
+
+- Temel sınıf: `src/shared/utils/circuitBreaker.ts`
+- Sohbet kapısı/uygulama kablolaması: `src/sse/handlers/chatHelpers.ts`, `src/sse/handlers/chat.ts`
+- Çalışma durumu API'si: `src/app/api/monitoring/health/route.ts`
+- Paylaşılan sarmalayıcılar: `open-sse/services/accountFallback.ts`
+- Kalıcı durum tablosu: `domain_circuit_breakers`
+
+**Durumlar**:
+
+- `CLOSED`: normal trafik izin verilir.
+- `OPEN`: sağlayıcı geçici olarak engellenmiştir; arayanlar bir sağlayıcı-devre-açık yanıtı alır veya kombinasyon yönlendirmesi başka bir hedefe atlar.
+- `HALF_OPEN`: sıfırlama zaman aşımı dolmuştur; bir prob isteğine izin verilir. Başarı devre kesiciyi kapatır, başarısızlık tekrar açar.
+
+**Varsayılanlar** (`open-sse/config/constants.ts`):
+
+- OAuth sağlayıcıları: eşik `3`, sıfırlama zaman aşımı `60s`.
+- API anahtarı sağlayıcıları: eşik `5`, sıfırlama zaman aşımı `30s`.
+- Yerel sağlayıcılar: eşik `2`, sıfırlama zaman aşımı `15s`.
+
+Sadece sağlayıcı düzeyindeki hata durumları sağlayıcı devre kesicisini tetiklemelidir:
+
+```ts
+(408, 500, 502, 503, 504);
+```
+
+Normal hesap/anahtar/model hataları gibi çoğu `401`, `403` veya `429` durumları için tüm sağlayıcı devre kesicisini tetiklemeyin. Bunlar genellikle bağlantı soğuma veya model kilitlenmesi ile ilgilidir. Genel bir API anahtarı sağlayıcı `403` kurtarılabilir olmalıdır, aksi takdirde terminal sağlayıcı/hesap hatası olarak sınıflandırılır.
+
+Devre kesici tembel kurtarma kullanır, arka planda bir zamanlayıcı değil. `OPEN` süresi dolduğunda, `getStatus()`, `canExecute()` ve `getRetryAfterMs()` gibi okumalar durumu `HALF_OPEN` olarak yeniler, böylece paneller ve kombinasyon aday oluşturucuları süresi dolmuş bir sağlayıcıyı sonsuza kadar hariç tutmaz.
+
+### Bağlantı Soğuma
+
+**Kapsam**: bir sağlayıcı bağlantısı/hesap/anahtar.
+
+**Amaç**: aynı sağlayıcı için diğer bağlantıların istekleri karşılamaya devam etmesine izin verirken, bir kötü anahtar/hesabı geçici olarak atlamak.
+
+**Uygulama**:
+
+- Yazma/güncelleme yolu: `src/sse/services/auth.ts::markAccountUnavailable()`
+- Hesap seçimi/filtreleme: `src/sse/services/auth.ts::getProviderCredentials...`
+- Soğuma hesaplaması: `open-sse/services/accountFallback.ts::checkFallbackError()`
+- Ayarlar: `src/lib/resilience/settings.ts`
+
+Sağlayıcı bağlantılarındaki önemli alanlar:
+
+```ts
+rateLimitedUntil;
+testStatus: "unavailable";
+lastError;
+lastErrorType;
+errorCode;
+backoffLevel;
+```
+
+Hesap seçimi sırasında, bir bağlantı atlanırken:
+
+```ts
+new Date(rateLimitedUntil).getTime() > Date.now();
+```
+
+Soğumalar da tembel: `rateLimitedUntil` geçmişte olduğunda, bağlantı tekrar uygun hale gelir. Başarılı kullanımda, `clearAccountError()` `testStatus`, `rateLimitedUntil`, hata alanlarını ve `backoffLevel`'ı temizler.
+
+Varsayılan bağlantı soğuma davranışı:
+
+- OAuth temel soğuma: `5s`.
+- API anahtarı temel soğuma: `3s`.
+- API anahtarı `429`, mevcut olduğunda yukarı akış yeniden deneme ipuçlarını (`Retry-After`, sıfırlama başlıkları veya ayrıştırılabilir sıfırlama metni) tercih etmelidir.
+- Tekrarlanan kurtarılabilir hatalar üstel geri çekilme kullanır:
+
+```ts
+baseCooldownMs * 2 ** failureIndex;
+```
+
+Anti-thundering-herd koruması, aynı bağlantıda eşzamanlı hataların soğumayı sürekli uzatmasını veya `backoffLevel`'ı iki katına çıkarmasını önler.
+
+Terminal durumlar soğumalar değildir. `banned`, `expired` ve `credits_exhausted` kimlik bilgileri/ayarlar değişene kadar veya bir operatör bunları sıfırlayana kadar kullanılamaz durumda kalması amaçlanmıştır. Terminal durumları geçici soğuma durumu ile üzerine yazmayın.
+
+### Model Kilitlenmesi
+
+**Kapsam**: sağlayıcı + bağlantı + model.
+
+**Amaç**: yalnızca bir modelin kullanılamaz veya kota sınırlı olduğu durumlarda tüm bağlantıyı devre dışı bırakmaktan kaçınmak.
+
+Örnekler:
+
+- Her model için kota sağlayıcıları `429` döndürüyor.
+- Bir eksik model için `404` döndüren yerel sağlayıcılar.
+- Seçilen Grok modları gibi sağlayıcıya özgü mod/model izin hataları.
+
+Model kilitlenmesi `open-sse/services/accountFallback.ts` içinde yer alır ve aynı bağlantının diğer modelleri sunmaya devam etmesine izin verir.
+
+### Hata Ayıklama Rehberi
+
+- Bir sağlayıcı için tüm anahtarlar atlanıyorsa, hem sağlayıcı devre kesici durumunu hem de her bağlantının `rateLimitedUntil`/`testStatus`'ını kontrol edin.
+- Bir sağlayıcı sıfırlama penceresinden sonra kalıcı olarak hariç tutuluyorsa, kodun `getStatus()`/`canExecute()` yerine ham `state` okuduğundan emin olun.
+- Bir sağlayıcı anahtarı başarısız olursa ancak diğerleri çalışıyorsa, sağlayıcı devre kesicisi yerine bağlantı soğumasını tercih edin.
+- Sadece bir model başarısız olursa, bağlantı soğuması yerine model kilitlenmesini tercih edin.
+- Bir durum kendiliğinden kurtulmalıysa, gelecekteki bir zaman damgasına/sıfırlama zaman aşımına ve süresi dolmuş durumu yenileyen bir okuma yoluna sahip olmalıdır. Kalıcı durumlar manuel kimlik bilgisi veya yapılandırma değişiklikleri gerektirir.
+
+## Anahtar Sözleşmeler
+
+### Kod Stili
+
+- **2 boşluk**, noktalı virgüller, çift tırnak, 100 karakter genişliği, es5 son virgüller (lint-staged tarafından Prettier ile zorunlu kılınır)
+- **İthalatlar**: harici → dahili (`@/`, `@omniroute/open-sse`) → göreceli
+- **İsimlendirme**: dosyalar=camelCase/kebab, bileşenler=PascalCase, sabitler=UPPER_SNAKE
+- **ESLint**: `no-eval`, `no-implied-eval`, `no-new-func` = her yerde hata; `no-explicit-any` = `open-sse/` ve `tests/` içinde uyarı
+- **TypeScript**: `strict: false`, hedef ES2022, modül esnext, çözümleyici paketleyici. Açık türleri tercih edin.
+
+### Veritabanı
+
+- **Her zaman** `src/lib/db/` alan modüllerinden geçin — **asla** rotalarda veya işleyicilerde ham SQL yazmayın
+- **Asla** `src/lib/localDb.ts` içine mantık eklemeyin (sadece yeniden ihracat katmanı)
+- **Asla** `localDb.ts`'den silindirik ithalat yapmayın — bunun yerine belirli `db/` modüllerini içe aktarın
+- DB singleton: `getDbInstance()` `src/lib/db/core.ts`'den (WAL günlüğü)
+- Göçler: `src/lib/db/migrations/` — sürümlü SQL dosyaları, idempotent, işlemler içinde çalıştırılır
+
+### Hata Yönetimi
+
+- belirli hata türleri ile try/catch, pino bağlamı ile günlüğe kaydet
+- SSE akışlarında hataları yutmayın — temizlik için iptal sinyalleri kullanın
+- Uygun HTTP durum kodlarını döndürün (4xx/5xx)
+
+### Güvenlik
+
+- **Asla** `eval()`, `new Function()`, veya dolaylı eval kullanmayın
+- Tüm girdileri Zod şemaları ile doğrulayın
+- Kimlik bilgilerini dinlenirken şifreleyin (AES-256-GCM)
+- Yukarı akış başlıkları yasak listesi: `src/shared/constants/upstreamHeaders.ts` — düzenlerken temizleme, Zod şemaları ve birim testlerinin uyumlu kalmasını sağlayın
+- **Halka açık yukarı akış kimlik bilgileri** (Gemini/Antigravity/Windsurf tarzı OAuth client_id/secret + halka açık CLI'lerden çıkarılan Firebase Web anahtarları): **MUTLAKA** `resolvePublicCred()` ile gömülmelidir `open-sse/utils/publicCreds.ts`'den — **asla** dize sabitleri olarak. Zorunlu desen için `docs/security/PUBLIC_CREDS.md`'ye bakın.
+- **Hata yanıtları** (HTTP / SSE / yürütücü / MCP işleyici): **MUTLAKA** `buildErrorBody()` veya `sanitizeErrorMessage()` üzerinden yönlendirilmelidir `open-sse/utils/error.ts`'den — **asla** ham `err.stack` veya `err.message`'i bir yanıt gövdesine koymayın. `docs/security/ERROR_SANITIZATION.md`'ye bakın.
+- **Değişkenlerden oluşturulan kabuk komutları**: `exec()`/`spawn()` ile çalışma zamanı değerlerine ihtiyaç duyan bir betik çağırırken, bunları `env` seçeneği aracılığıyla geçirin (otomatik olarak kabukta kaçış yapılır) — **asla** güvenilmeyen/dış yolları betik gövdesine dize ile birleştirmeyin. Referans: `src/mitm/cert/install.ts::updateNssDatabases`.
+- **Varsayılan olarak güvenli kütüphaneler** ([tldrsec/awesome-secure-defaults](https://github.com/tldrsec/awesome-secure-defaults)): yeni güvenlik hassas yüzeyleri eklerken, özel uygulamalar yerine Helmet.js, DOMPurify, ssrf-req-filter, safe-regex, Google Tink'i tercih edin.
+
+---
+
+## Yaygın Değişiklik Senaryoları
+
+### Yeni Bir Sağlayıcı Ekleme
+
+1. `src/shared/constants/providers.ts` içinde kaydedin (yükleme sırasında Zod ile doğrulanır)
+2. Özel mantık gerekiyorsa `open-sse/executors/` içinde yürütücü ekleyin ( `BaseExecutor`'ı genişletin)
+3. OpenAI dışı bir format varsa `open-sse/translator/` içinde çevirmen ekleyin
+4. OAuth tabanlı ise `src/lib/oauth/constants/oauth.ts` içinde OAuth yapılandırması ekleyin — yukarı akış CLI'si halka açık bir client_id/secret gönderiyorsa, `resolvePublicCred()` aracılığıyla gömün (bkz. `docs/security/PUBLIC_CREDS.md`), **asla** bir literal olarak
+5. `open-sse/config/providerRegistry.ts` içinde modelleri kaydedin
+6. `tests/unit/` içinde testler yazın (yeni bir gömülü varsayılan eklediyseniz publicCreds şekil doğrulamasını dahil edin)
+
+### Yeni Bir API Rotası Ekleme
+
+1. `src/app/api/v1/your-route/` altında dizin oluşturun
+2. `GET`/`POST` işleyicileri ile `route.ts` oluşturun
+3. Deseni takip edin: CORS → Zod gövde doğrulaması → isteğe bağlı kimlik doğrulama → işleyici delegasyonu
+4. İşleyici `open-sse/handlers/` içinde yer alır (oradan içe aktarın, satır içinde değil)
+5. Hata yanıtları `buildErrorBody()` / `errorResponse()` kullanır `open-sse/utils/error.ts`'den (otomatik olarak temizlenir — asla `err.stack` veya `err.message`'i ham olarak gövdeye koymayın). `docs/security/ERROR_SANITIZATION.md`'ye bakın.
+6. Testler ekleyin — hata yanıtlarının yığın izlerini sızdırmadığını doğrulayan en az bir doğrulama dahil edin (`!body.error.message.includes("at /")`)
+
+### Yeni Bir DB Modülü Ekleme
+
+1. `src/lib/db/yourModule.ts` oluşturun — `./core.ts`'den `getDbInstance`'i içe aktarın
+2. Alan tablonuz için CRUD işlevlerini dışa aktarın
+3. Yeni tablolara ihtiyaç varsa `src/lib/db/migrations/` içinde göç ekleyin
+4. `src/lib/localDb.ts`'den yeniden dışa aktarın (sadece yeniden dışa aktarma listesine ekleyin)
+5. Testler yazın
+
+### Yeni Bir MCP Aracı Ekleme
+
+1. Zod girdi şeması + asenkron işleyici ile `open-sse/mcp-server/tools/` içinde araç tanımını ekleyin
+2. Araç setinde kaydedin ( `createMcpServer()` ile bağlanır)
+3. Uygun kapsam(lar)a atayın
+4. Testler yazın (araç çağrısı `mcp_audit` tablosuna kaydedilir)
+
+### Yeni Bir A2A Yeteneği Ekleme
+
+1. `src/lib/a2a/skills/` içinde yetenek oluşturun (zaten 5 tane var: akıllı yönlendirme, kota yönetimi, sağlayıcı keşfi, maliyet analizi, sağlık raporu)
+2. Yetenek görev bağlamını alır (mesajlar, meta veriler) → yapılandırılmış sonuç döndürür
+3. `src/lib/a2a/taskExecution.ts` içinde `A2A_SKILL_HANDLERS`'da kaydedin
+4. `src/app/.well-known/agent.json/route.ts` içinde açığa çıkarın (Agent Kartı)
+5. `tests/unit/` içinde testler yazın
+6. `docs/frameworks/A2A-SERVER.md` içinde yetenek tablosunu belgeleyin
+
+### Yeni Bir Bulut Ajanı Ekleme
+
+1. `src/lib/cloudAgent/agents/` içinde `CloudAgentBase`'i genişleten ajan sınıfı oluşturun (zaten 3 tane var: codex-cloud, devin, jules)
+2. `createTask`, `getStatus`, `approvePlan`, `sendMessage`, `listSources`'ı uygulayın
+3. `src/lib/cloudAgent/registry.ts` içinde kaydedin
+4. Gerekirse OAuth/kimlik bilgileri yönetimini ekleyin (`src/lib/oauth/providers/`)
+5. Testler + `docs/frameworks/CLOUD_AGENT.md` içinde belgeleyin
+
+### Yeni Bir Guardrail / Eval / Yetenek / Webhook olayı Ekleme
+
+- Guardrail: `src/lib/guardrails/` → belgeler: `docs/security/GUARDRAILS.md`
+- Eval paketi: `src/lib/evals/` → belgeler: `docs/frameworks/EVALS.md`
+- Yetenek (sandbox): `src/lib/skills/` → belgeler: `docs/frameworks/SKILLS.md`
+- Webhook olayı: `src/lib/webhookDispatcher.ts` → belgeler: `docs/frameworks/WEBHOOKS.md`
+
+## Referans Dokümantasyonu
+
+Herhangi bir önemsiz değişiklik için, önce ilgili derinlemesine incelemeyi okuyun:
+
+| Alan                                                     | Doküman                                                           |
+| -------------------------------------------------------- | ----------------------------------------------------------------- |
+| Repo navigasyonu                                         | `docs/architecture/REPOSITORY_MAP.md`                             |
+| Mimari                                                   | `docs/architecture/ARCHITECTURE.md`                               |
+| Mühendislik referansı                                    | `docs/architecture/CODEBASE_DOCUMENTATION.md`                     |
+| Auto-Combo (13-factor scoring, 19 public strategies) | `docs/routing/AUTO-COMBO.md` |
+| Dayanıklılık (3 mekanizma)                               | `docs/architecture/RESILIENCE_GUIDE.md`                           |
+| Akıl yürütme tekrarları                                  | `docs/routing/REASONING_REPLAY.md`                                |
+| Yetenekler çerçevesi                                     | `docs/frameworks/SKILLS.md`                                       |
+| Bellek sistemi (FTS5 + Qdrant)                           | `docs/frameworks/MEMORY.md`                                       |
+| Bulut ajanları                                           | `docs/frameworks/CLOUD_AGENT.md`                                  |
+| Koruma önlemleri (Kişisel Veriler / enjeksiyon / vizyon) | `docs/security/GUARDRAILS.md`                                     |
+| Kamu üst akış kimlik bilgileri (Gemini/vb.)              | `docs/security/PUBLIC_CREDS.md`                                   |
+| Hata mesajı temizleme                                    | `docs/security/ERROR_SANITIZATION.md`                             |
+| Değerlendirmeler                                         | `docs/frameworks/EVALS.md`                                        |
+| Uyum / denetim                                           | `docs/security/COMPLIANCE.md`                                     |
+| Webhook'lar                                              | `docs/frameworks/WEBHOOKS.md`                                     |
+| Yetkilendirme akışı                                      | `docs/architecture/AUTHZ_GUIDE.md`                                |
+| Gizlilik (TLS / parmak izi)                              | `docs/security/STEALTH_GUIDE.md`                                  |
+| Ajan protokolleri (A2A / ACP / Bulut)                    | `docs/frameworks/AGENT_PROTOCOLS_GUIDE.md`                        |
+| MCP sunucusu                                             | `docs/frameworks/MCP-SERVER.md`                                   |
+| A2A sunucusu                                             | `docs/frameworks/A2A-SERVER.md`                                   |
+| API referansı + OpenAPI                                  | `docs/reference/API_REFERENCE.md` + `docs/reference/openapi.yaml` |
+| Sağlayıcı kataloğu (otomatik oluşturulmuş)               | `docs/reference/PROVIDER_REFERENCE.md`                            |
+| Sürüm akışı                                              | `docs/ops/RELEASE_CHECKLIST.md`                                   |
+
+## Test Etme
+
+| Ne                      | Komut                                                                         |
+| ----------------------- | ----------------------------------------------------------------------------- |
+| Birim testleri          | `npm run test:unit`                                                           |
+| Tek dosya               | `node --import tsx/esm --test tests/unit/file.test.ts`                        |
+| Vitest (MCP, autoCombo) | `npm run test:vitest`                                                         |
+| E2E (Playwright)        | `npm run test:e2e`                                                            |
+| Protokol E2E (MCP+A2A)  | `npm run test:protocols:e2e`                                                  |
+| Ekosistem               | `npm run test:ecosystem`                                                      |
+| Kapsam kapısı           | `npm run test:coverage` (75/75/75/70 — ifadeler/hatlar/fonksiyonlar/kolonlar) |
+| Kapsam raporu           | `npm run coverage:report`                                                     |
+
+**PR kuralı**: Eğer `src/`, `open-sse/`, `electron/` veya `bin/` içindeki üretim kodunu değiştirirseniz, aynı PR içinde testleri eklemeli veya güncellemelisiniz.
+
+**Test katmanı tercihi**: birim önce → entegrasyon (çok modüllü veya DB durumu) → e2e (sadece UI/iş akışı). Hata yeniden üretimlerini düzeltmeden önce veya yanında otomatik testler olarak kodlayın.
+
+**Copilot kapsam politikası**: Bir PR üretim kodunu değiştiriyorsa ve kapsam %75'in (ifadeler/hatlar/fonksiyonlar) veya %70'in (kolonlar) altındaysa, sadece rapor etmekle kalmayın — test ekleyin veya güncelleyin, kapsam kapısını yeniden çalıştırın, ardından onay isteyin. Çalıştırılan komutları, değiştirilen test dosyalarını ve son kapsam sonucunu PR raporuna dahil edin.
+
+---
+
+## Git İş Akışı
+
+```bash
+# Asla doğrudan main'e commit yapmayın
+git checkout -b feat/your-feature
+git commit -m "feat: değişikliğinizi tanımlayın"
+git push -u origin feat/your-feature
+```
+
+**Dal ön ekleri**: `feat/`, `fix/`, `refactor/`, `docs/`, `test/`, `chore/`
+
+**Commit formatı** (Geleneksel Commits): `feat(db): devre kesici ekle` — kapsamlar: `db`, `sse`, `oauth`, `dashboard`, `api`, `cli`, `docker`, `ci`, `mcp`, `a2a`, `memory`, `skills`
+
+**Husky kancaları**:
+
+- **pre-commit**: lint-staged + `check-docs-sync` + `check:any-budget:t11`
+- **pre-push**: `npm run test:unit`
+
+---
+
+## Ortam
+
+- **Çalışma Zamanı**: Node.js ≥20.20.2 <21 |
+  | ≥22.22.2 <23 |
+  | ≥24 <25, ES Modülleri
+- **TypeScript**: 5.9+, hedef ES2022, modül esnext, çözümleyici paketleyici
+- **Yol takma adları**: `@/*` → `src/`, `@omniroute/open-sse` → `open-sse/`, `@omniroute/open-sse/*` → `open-sse/*`
+- **Varsayılan port**: 20128 (API + kontrol paneli aynı portta)
+- **Veri dizini**: `DATA_DIR` env değişkeni, varsayılan olarak `~/.omniroute/`
+- **Ana env değişkenleri**: `PORT`, `JWT_SECRET`, `API_KEY_SECRET`, `INITIAL_PASSWORD`, `REQUIRE_API_KEY`, `APP_LOG_LEVEL`
+- Kurulum: `cp .env.example .env` ardından `JWT_SECRET` (`openssl rand -base64 48`) ve `API_KEY_SECRET` (`openssl rand -hex 32`) oluşturun
+
+---
+
+## Sert Kurallar
+
+1. Asla gizli bilgileri veya kimlik bilgilerini commit etmeyin
+2. Asla `localDb.ts` içine mantık eklemeyin
+3. Asla `eval()` / `new Function()` / dolaylı eval kullanmayın
+4. Asla doğrudan `main`'e commit yapmayın
+5. Asla rotalarda ham SQL yazmayın — `src/lib/db/` modüllerini kullanın
+6. Asla SSE akışlarında hataları sessizce yutmayın
+7. Her zaman Zod şemaları ile girdileri doğrulayın
+8. Üretim kodunu değiştirirken her zaman testleri dahil edin
+9. Kapsam ≥%75 (ifadeler, hatlar, fonksiyonlar) / ≥%70 (kolonlar) olmalıdır. Mevcut ölçülen: ~%82.
+10. Açık operatör onayı olmadan Husky kancalarını (`--no-verify`, `--no-gpg-sign`) asla atlamayın.
+11. Asla kamuya açık yukarı akış OAuth client_id/secret veya Firebase Web anahtarlarını string literal olarak gömün — her zaman `resolvePublicCred()` üzerinden geçin (`open-sse/utils/publicCreds.ts`). `docs/security/PUBLIC_CREDS.md`'ye bakın.
+12. Asla HTTP / SSE / yürütücü yanıtlarında ham `err.stack` / `err.message` döndürmeyin — her zaman `buildErrorBody()` veya `sanitizeErrorMessage()` üzerinden yönlendirin (`open-sse/utils/error.ts`). `docs/security/ERROR_SANITIZATION.md`'ye bakın.
+13. Asla dış yolları veya çalışma zamanı değerlerini `exec()`/`spawn()`'a geçirilen shell betiklerine string-interpolate etmeyin — bunun yerine `env` seçeneği aracılığıyla geçirin. Referans: `src/mitm/cert/install.ts::updateNssDatabases`.
+14. Asla bir CodeQL / Secret-Scanning uyarısını (a) yukarıdaki desen belgelerini kontrol etmeden ve (b) reddetme yorumunda teknik gerekçeyi kaydetmeden geçiştirmeyin. Örnek: `js/stack-trace-exposure` hatası, zaten `sanitizeErrorMessage()` üzerinden yönlendirilmiş çağrı noktalarında ortaya çıkmaktadır ve bu bilinen bir CodeQL sınırlamasıdır (özel temizleyiciler tanınmaz) — `docs/security/ERROR_SANITIZATION.md`'ye atıfta bulunarak `false positive` olarak reddedin.
+15. Asla çocuk süreçleri başlatan rotaları (`/api/mcp/`, `/api/cli-tools/runtime/`) `src/server/authz/routeGuard.ts` içinde `isLocalOnlyPath()` sınıflandırması olmadan dahil etmeyin. Döngü geri uygulaması, herhangi bir kimlik doğrulama kontrolünden önce koşulsuz olarak gerçekleşir — tünel aracılığıyla sızdırılan JWT, süreç başlatmayı tetikleyemez. `docs/security/ROUTE_GUARD_TIERS.md`'ye bakın.
+16. Asla AI asistanı, LLM veya otomasyon hesabını krediye alan `Co-Authored-By` ekleri içermeyin (örn. "Claude", "GPT", "Copilot", "Bot" içeren isimler; `anthropic.com` / `openai.com` / bot sahipli `noreply.github.com` adreslerindeki e-postalar). Bu tür ekler GitHub'da commit atfını bot hesabına yönlendirir ve PR geçmişinde gerçek yazarı (`diegosouzapw`) gizler. İnsan katkıda bulunanlar — upstream PR yazarları ve OmniRoute'a port edilen issue raporlayıcıları dahil — standart `Co-authored-by: Name <email>` ekleriyle krediye ALINABİLİR ve ALINMALIDIR; upstream-port iş akışları (`/port-upstream-features`, `/port-upstream-issues`) buna bağlıdır.

docs/i18n/tr/CODE_OF_CONDUCT.md

@@ -1,88 +1,132 @@
-# Katılımcı Sözleşmesi Davranış Kuralları (Türkçe)
+# Contributor Covenant Code of Conduct (Türkçe)
 
 🌐 **Languages:** 🇺🇸 [English](../../../CODE_OF_CONDUCT.md) · 🇸🇦 [ar](../ar/CODE_OF_CONDUCT.md) · 🇧🇬 [bg](../bg/CODE_OF_CONDUCT.md) · 🇧🇩 [bn](../bn/CODE_OF_CONDUCT.md) · 🇨🇿 [cs](../cs/CODE_OF_CONDUCT.md) · 🇩🇰 [da](../da/CODE_OF_CONDUCT.md) · 🇩🇪 [de](../de/CODE_OF_CONDUCT.md) · 🇪🇸 [es](../es/CODE_OF_CONDUCT.md) · 🇮🇷 [fa](../fa/CODE_OF_CONDUCT.md) · 🇫🇮 [fi](../fi/CODE_OF_CONDUCT.md) · 🇫🇷 [fr](../fr/CODE_OF_CONDUCT.md) · 🇮🇳 [gu](../gu/CODE_OF_CONDUCT.md) · 🇮🇱 [he](../he/CODE_OF_CONDUCT.md) · 🇮🇳 [hi](../hi/CODE_OF_CONDUCT.md) · 🇭🇺 [hu](../hu/CODE_OF_CONDUCT.md) · 🇮🇩 [id](../id/CODE_OF_CONDUCT.md) · 🇮🇹 [it](../it/CODE_OF_CONDUCT.md) · 🇯🇵 [ja](../ja/CODE_OF_CONDUCT.md) · 🇰🇷 [ko](../ko/CODE_OF_CONDUCT.md) · 🇮🇳 [mr](../mr/CODE_OF_CONDUCT.md) · 🇲🇾 [ms](../ms/CODE_OF_CONDUCT.md) · 🇳🇱 [nl](../nl/CODE_OF_CONDUCT.md) · 🇳🇴 [no](../no/CODE_OF_CONDUCT.md) · 🇵🇭 [phi](../phi/CODE_OF_CONDUCT.md) · 🇵🇱 [pl](../pl/CODE_OF_CONDUCT.md) · 🇵🇹 [pt](../pt/CODE_OF_CONDUCT.md) · 🇧🇷 [pt-BR](../pt-BR/CODE_OF_CONDUCT.md) · 🇷🇴 [ro](../ro/CODE_OF_CONDUCT.md) · 🇷🇺 [ru](../ru/CODE_OF_CONDUCT.md) · 🇸🇰 [sk](../sk/CODE_OF_CONDUCT.md) · 🇸🇪 [sv](../sv/CODE_OF_CONDUCT.md) · 🇰🇪 [sw](../sw/CODE_OF_CONDUCT.md) · 🇮🇳 [ta](../ta/CODE_OF_CONDUCT.md) · 🇮🇳 [te](../te/CODE_OF_CONDUCT.md) · 🇹🇭 [th](../th/CODE_OF_CONDUCT.md) · 🇹🇷 [tr](../tr/CODE_OF_CONDUCT.md) · 🇺🇦 [uk-UA](../uk-UA/CODE_OF_CONDUCT.md) · 🇵🇰 [ur](../ur/CODE_OF_CONDUCT.md) · 🇻🇳 [vi](../vi/CODE_OF_CONDUCT.md) · 🇨🇳 [zh-CN](../zh-CN/CODE_OF_CONDUCT.md)
 
 ---
 
-## Taahhüdümüz
+## Our Pledge
 
-Topluluk üyeleri, katkıda bulunanlar ve liderler olarak; yaş, vücut ölçüsü, görünür veya görünmez engellilik, etnik köken, cinsiyet özellikleri, cinsiyet kimliği ve ifadesi, deneyim düzeyi, eğitim, sosyo-ekonomik durum, milliyet, kişisel görünüm, ırk, din veya cinsel kimlik ve yönelim gözetilmeksizin herkes için topluluğumuza katılımı tacizden uzak bir deneyim haline getirmeyi taahhüt ediyoruz.
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
 
-Açık, sıcak, çeşitli, kapsayıcı ve sağlıklı bir topluluğa katkıda bulunacak şekilde davranmayı ve etkileşim kurmayı taahhüt ediyoruz.
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
 
-## Standartlarımız
+## Our Standards
 
-Topluluğumuz için olumlu bir ortama katkıda bulunan davranış örnekleri şunlardır:
+Examples of behavior that contributes to a positive environment for our
+community include:
 
-- Diğer insanlara karşı empati ve nezaket göstermek
-- Farklı görüşlere, bakış açılarına ve deneyimlere saygılı olmak
-- Yapıcı geri bildirim vermek ve bunu olgunlukla kabul etmek
-- Hatalarımızdan etkilenenlerden sorumluluk alıp özür dilemek ve bu deneyimden ders çıkarmak
-- Sadece bireysel olarak bizim için değil, tüm topluluk için en iyi olana odaklanmak
+- Demonstrating empathy and kindness toward other people
+- Being respectful of differing opinions, viewpoints, and experiences
+- Giving and gracefully accepting constructive feedback
+- Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+- Focusing on what is best not just for us as individuals, but for the
+  overall community
 
-Kabul edilemez davranış örnekleri şunlardır:
+Examples of unacceptable behavior include:
 
-- Cinselleştirilmiş dil veya görsellerin kullanımı ile her türlü cinsel ilgi veya yakınlaşma
-- Trolleme, aşağılayıcı veya rencide edici yorumlar ve kişisel ya da politik saldırılar
-- Kamuya açık veya özel alanda taciz
-- Açık izinleri olmadan başkalarının fiziksel adres veya e-posta adresi gibi özel bilgilerini yayımlamak
-- Profesyonel bir ortamda makul olarak uygunsuz kabul edilebilecek diğer davranışlar
+- The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+- Trolling, insulting or derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+- Other conduct which could reasonably be considered inappropriate in a
+  professional setting
 
-## Uygulama Sorumlulukları
+## Enforcement Responsibilities
 
-Topluluk liderleri, kabul edilebilir davranış standartlarımızı açıklığa kavuşturmaktan ve uygulamaktan sorumludur; uygunsuz, tehdit edici, saldırgan veya zararlı gördükleri herhangi bir davranışa karşılık adil ve uygun düzeltici önlemleri alacaklardır.
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
 
-Topluluk liderleri, bu Davranış Kuralları ile uyumlu olmayan yorumları, commit'leri, kodları, wiki düzenlemelerini, issue'ları ve diğer katkıları kaldırma, düzenleme veya reddetme hakkına ve sorumluluğuna sahiptir ve uygun olduğunda moderasyon kararlarının gerekçelerini ileteceklerdir.
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
 
-## Kapsam
+## Scope
 
-Bu Davranış Kuralları tüm topluluk alanlarında geçerlidir ve ayrıca bir birey topluluğu kamusal alanlarda resmi olarak temsil ettiğinde de geçerlidir. Topluluğumuzu temsil etme örnekleri arasında resmi bir e-posta adresi kullanmak, resmi bir sosyal medya hesabı aracılığıyla paylaşım yapmak veya çevrimiçi ya da çevrimdışı bir etkinlikte atanmış bir temsilci olarak hareket etmek yer alır.
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
 
-## Yaptırım
+## Enforcement
 
-İstismar edici, taciz edici veya başka bir şekilde kabul edilemez davranış durumları, yaptırımdan sorumlu topluluk liderlerine şu adresten özel bir güvenlik bildirimi (security advisory) açılarak bildirilebilir:
-<https://github.com/diegosouzapw/OmniRoute/security/advisories/new>
-veya proje yöneticisine diegosouza.pw@outlook.com adresinden e-posta gönderilebilir.
-Güvenlikle ilgili hassas olaylar için bkz. [`SECURITY.md`](SECURITY.md).
-Tüm şikayetler derhal ve adil bir şekilde incelenecek ve araştırılacaktır.
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+.
+All complaints will be reviewed and investigated promptly and fairly.
 
-Tüm topluluk liderleri, herhangi bir olayı bildiren kişinin gizliliğine ve güvenliğine saygı duymakla yükümlüdür.
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
 
-## Yaptırım Yönergeleri
+## Enforcement Guidelines
 
-Topluluk liderleri, bu Davranış Kurallarını ihlal ettiğini düşündükleri herhangi bir eylemin sonuçlarını belirlerken aşağıdaki Topluluk Etki Yönergelerini izleyecektir:
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
 
-### 1. Düzeltme
+### 1. Correction
 
-**Topluluk Etkisi**: Toplulukta uygunsuz veya profesyonellik dışı kabul edilen dil kullanımı veya diğer davranışlar.
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
 
-**Sonuç**: Topluluk liderlerinden ihlalin niteliğini açıklayan ve davranışın neden uygunsuz olduğunu belirten özel, yazılı bir uyarı. Kamuya açık bir özür talep edilebilir.
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
 
-### 2. Uyarı
+### 2. Warning
 
-**Topluluk Etkisi**: Tek bir olay veya bir dizi eylem yoluyla yapılan bir ihlal.
+**Community Impact**: A violation through a single incident or series
+of actions.
 
-**Sonuç**: Davranışın devam etmesi durumunda doğacak sonuçları içeren bir uyarı. Belirli bir süre boyunca, Davranış Kurallarını uygulayan kişilerle talep edilmeyen etkileşimler de dahil olmak üzere, ilgili kişilerle hiçbir etkileşimde bulunulamaz. Buna topluluk alanlarının yanı sıra sosyal medya gibi harici kanallardaki etkileşimlerden kaçınmak da dahildir. Bu koşulların ihlali geçici veya kalıcı bir uzaklaştırmaya yol açabilir.
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
 
-### 3. Geçici Uzaklaştırma
+### 3. Temporary Ban
 
-**Topluluk Etkisi**: Sürekli uygunsuz davranışlar da dahil olmak üzere topluluk standartlarının ciddi bir şekilde ihlali.
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
 
-**Sonuç**: Belirli bir süre boyunca toplulukla her türlü etkileşimden veya kamusal iletişimden geçici olarak men edilme. Bu süre zarfında, Davranış Kurallarını uygulayan kişilerle talep edilmeyen etkileşimler de dahil olmak üzere, ilgili kişilerle kamuya açık veya özel hiçbir etkileşime izin verilmez. Bu koşulların ihlali kalıcı bir uzaklaştırmaya yol açabilir.
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
 
-### 4. Kalıcı Uzaklaştırma
+### 4. Permanent Ban
 
-**Topluluk Etkisi**: Sürekli uygunsuz davranışlar, bir bireyin taciz edilmesi veya belirli insan gruplarına yönelik saldırganlık ya da aşağılama da dahil olmak üzere topluluk standartlarını sistematik olarak ihlal etme kalıbı sergilemek.
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior, harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
 
-**Sonuç**: Topluluk içindeki her türlü kamusal etkileşimden kalıcı olarak men edilme.
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
 
-## Kaynak ve Atıf
+## Attribution
 
-Bu Davranış Kuralları, [Contributor Covenant][homepage] sürüm 2.1'den uyarlanmıştır; orijinaline şu adresten ulaşılabilir:
-https://www.contributor-covenant.org/version/2/1/code_of_conduct.html.
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
 
-Topluluk Etki Yönergeleri, [Mozilla'nın davranış kuralları yaptırım merdiveninden](https://github.com/mozilla/diversity) esinlenmiştir.
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
 
 [homepage]: https://www.contributor-covenant.org
 
-Bu davranış kuralları hakkında sık sorulan soruların yanıtları için https://www.contributor-covenant.org/faq adresindeki SSS bölümüne bakın. Çeviriler https://www.contributor-covenant.org/translations adresinde mevcuttur.
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.

docs/i18n/tr/CONTRIBUTING.md

@@ -1,30 +1,22 @@
-# OmniRoute'a Katkıda Bulunma (Türkçe)
+# Contributing to OmniRoute (Türkçe)
 
 🌐 **Languages:** 🇺🇸 [English](../../../CONTRIBUTING.md) · 🇸🇦 [ar](../ar/CONTRIBUTING.md) · 🇧🇬 [bg](../bg/CONTRIBUTING.md) · 🇧🇩 [bn](../bn/CONTRIBUTING.md) · 🇨🇿 [cs](../cs/CONTRIBUTING.md) · 🇩🇰 [da](../da/CONTRIBUTING.md) · 🇩🇪 [de](../de/CONTRIBUTING.md) · 🇪🇸 [es](../es/CONTRIBUTING.md) · 🇮🇷 [fa](../fa/CONTRIBUTING.md) · 🇫🇮 [fi](../fi/CONTRIBUTING.md) · 🇫🇷 [fr](../fr/CONTRIBUTING.md) · 🇮🇳 [gu](../gu/CONTRIBUTING.md) · 🇮🇱 [he](../he/CONTRIBUTING.md) · 🇮🇳 [hi](../hi/CONTRIBUTING.md) · 🇭🇺 [hu](../hu/CONTRIBUTING.md) · 🇮🇩 [id](../id/CONTRIBUTING.md) · 🇮🇹 [it](../it/CONTRIBUTING.md) · 🇯🇵 [ja](../ja/CONTRIBUTING.md) · 🇰🇷 [ko](../ko/CONTRIBUTING.md) · 🇮🇳 [mr](../mr/CONTRIBUTING.md) · 🇲🇾 [ms](../ms/CONTRIBUTING.md) · 🇳🇱 [nl](../nl/CONTRIBUTING.md) · 🇳🇴 [no](../no/CONTRIBUTING.md) · 🇵🇭 [phi](../phi/CONTRIBUTING.md) · 🇵🇱 [pl](../pl/CONTRIBUTING.md) · 🇵🇹 [pt](../pt/CONTRIBUTING.md) · 🇧🇷 [pt-BR](../pt-BR/CONTRIBUTING.md) · 🇷🇴 [ro](../ro/CONTRIBUTING.md) · 🇷🇺 [ru](../ru/CONTRIBUTING.md) · 🇸🇰 [sk](../sk/CONTRIBUTING.md) · 🇸🇪 [sv](../sv/CONTRIBUTING.md) · 🇰🇪 [sw](../sw/CONTRIBUTING.md) · 🇮🇳 [ta](../ta/CONTRIBUTING.md) · 🇮🇳 [te](../te/CONTRIBUTING.md) · 🇹🇭 [th](../th/CONTRIBUTING.md) · 🇹🇷 [tr](../tr/CONTRIBUTING.md) · 🇺🇦 [uk-UA](../uk-UA/CONTRIBUTING.md) · 🇵🇰 [ur](../ur/CONTRIBUTING.md) · 🇻🇳 [vi](../vi/CONTRIBUTING.md) · 🇨🇳 [zh-CN](../zh-CN/CONTRIBUTING.md)
 
 ---
 
-Katkıda bulunmak istediğiniz için teşekkür ederiz! Bu kılavuz başlamak için ihtiyacınız olan her şeyi kapsar.
-
-Değişiklik başına resmi iş akışı için [Katkı Altın Yolu (Contribution Golden Path)](docs/ops/CONTRIBUTION_GOLDEN_PATH.md) belgesiyle başlayın. Sağlayıcı, yönlendirme, UI/UX, i18n, CLI, veritabanı ve derleme/dağıtım değişikliklerini ilgili sözleşmelere, odaklanmış testlere, CI kapsamına ve mutabakat adımlarına eşler.
+Thank you for your interest in contributing! This guide covers everything you need to get started.
 
 ---
 
-## Geliştirme Ortamı Kurulumu
+## Development Setup
 
-### Ön Koşullar
+### Prerequisites
 
-- **Node.js** `>=22.22.3 <23` veya `>=24.0.0 <27` (önerilen: 24 LTS)
+- **Node.js** >= 18 < 24 (recommended: 22 LTS)
 - **npm** 10+
-
-> **npm v11+ kullanıcıları (Node 24+):** `npm install` sonrasında yerel modüllerin kurulduğunu doğrulayın:
-> `node -e "require('better-sqlite3')"`. Eğer `MODULE_NOT_FOUND` hatası alırsanız,
-> `npm approve-scripts better-sqlite3 && npm install` komutunu çalıştırın. Bkz.
-> [Sorun Giderme](docs/guides/TROUBLESHOOTING.md#npm-v11-better-sqlite3-not-installed-cannot-find-module).
-
 - **Git**
 
-### Klonlama ve Kurulum
+### Clone & Install
 
 ```bash
 git clone https://github.com/diegosouzapw/OmniRoute.git
@@ -32,117 +24,85 @@ cd OmniRoute
 npm install
 ```
 
-### Ortam Değişkenleri
+### Environment Variables
 
 ```bash
-# Şablondan kendi .env dosyanızı oluşturun
+# Create your .env from the template
 cp .env.example .env
 
-# Gerekli gizli anahtarları oluşturun
+# Generate required secrets
 echo "JWT_SECRET=$(openssl rand -base64 48)" >> .env
 echo "API_KEY_SECRET=$(openssl rand -hex 32)" >> .env
 ```
 
-Geliştirme için temel değişkenler:
+Key variables for development:
 
-| Değişken               | Geliştirme Varsayılanı   | Açıklama              |
+| Variable               | Development Default      | Description           |
 | ---------------------- | ------------------------ | --------------------- |
-| `PORT`                 | `20128`                  | Sunucu portu          |
-| `NEXT_PUBLIC_BASE_URL` | `http://localhost:20128` | Ön uç için temel URL  |
-| `JWT_SECRET`           | (yukarıda oluşturulur)   | JWT imzalama sırrı    |
-| `INITIAL_PASSWORD`     | `CHANGEME`               | İlk giriş parolası    |
-| `APP_LOG_LEVEL`        | `info`                   | Günlük ayrıntı düzeyi |
+| `PORT`                 | `20128`                  | Server port           |
+| `NEXT_PUBLIC_BASE_URL` | `http://localhost:20128` | Base URL for frontend |
+| `JWT_SECRET`           | (generate above)         | JWT signing secret    |
+| `INITIAL_PASSWORD`     | `CHANGEME`               | First login password  |
+| `APP_LOG_LEVEL`        | `info`                   | Log verbosity level   |
 
-### Pano Ayarları
+### Dashboard Settings
 
-Pano, ortam değişkenleri aracılığıyla da yapılandırılabilen özellikler için arayüz anahtarları sunar:
+The dashboard provides UI toggles for features that can also be configured via environment variables:
 
-| Ayar Konumu         | Anahtar            | Açıklama                              |
-| ------------------- | ------------------ | ------------------------------------- |
-| Ayarlar → Gelişmiş  | Hata Ayıklama Modu | İstek günlüklerini etkinleştirir (UI) |
-| Ayarlar → Genel     | Kenar Çubuğu Görünürlüğü | Kenar çubuğu bölümlerini göster/gizle |
+| Setting Location    | Toggle             | Description                    |
+| ------------------- | ------------------ | ------------------------------ |
+| Settings → Advanced | Debug Mode         | Enable debug request logs (UI) |
+| Settings → General  | Sidebar Visibility | Show/hide sidebar sections     |
 
-Bu ayarlar veritabanında saklanır ve yeniden başlatmalar arasında kalıcıdır; ayarlandıklarında ortam değişkeni varsayılanlarını geçersiz kılarlar.
+These settings are stored in the database and persist across restarts, overriding env var defaults when set.
 
-### Yerel Olarak Çalıştırma
+### Running Locally
 
 ```bash
-# Geliştirme modu (hot reload)
+# Development mode (hot reload)
 npm run dev
 
-# Üretim derlemesi
-npm run build    # next build → .build/next/ ardından assembleStandalone → dist/
+# Production build
+npm run build
 npm run start
 
-# Sürüm derlemesi (temiz yeniden derleme + HEAD nöbetçisi — dağıtım için gereklidir)
-npm run build:release   # rm -rf .build dist && build + dist/BUILD_SHA yazar
-
-# Yaygın port yapılandırması
+# Common port configuration
 PORT=20128 NEXT_PUBLIC_BASE_URL=http://localhost:20128 npm run dev
 ```
 
-### Derleme Çıktısı Düzeni
+Default URLs:
 
-| Dizin     | İçerik                                                                    | Takip Ediliyor mu? |
-| --------- | ------------------------------------------------------------------------- | ------------------ |
-| `src/`    | Uygulama kaynak kodu (TypeScript / TSX)                                   | Evet               |
-| `.build/` | Ara dosyalar — `next build` çıktısı (gitignored, `distDir = .build/next`) | Hayır              |
-| `dist/`   | Dağıtılabilir paket — `assembleStandalone` tarafından toplanır (gitignored) | Hayır              |
-
-Derleme hattı tek geçişlidir:
-
-```
-npm run build
-  └─ next build → .build/next/standalone  (Next.js çıktısı)
-  └─ assembleStandalone()                 (standalone + static + public + yerel varlıkları kopyalar)
-       └─ çıktı: dist/                    (server.js, .next/static/, public/, node_modules/)
-```
-
-`npm run build:release` ek olarak önce her iki dizini de temizler ve dağıtım bütünlüğü nöbetçisi olarak
-`dist/BUILD_SHA` (= `git rev-parse --short HEAD`) yazar.
-
-> **VPS dağıtım notu:** uzak imaj dizini `/usr/lib/node_modules/omniroute/app/`
-> değişmemiştir. Dağıtım yetenekleri `dist/` içeriğini rsync ile buraya aktarır.
-> Yalnızca repo içi derleme çıktı yolu taşınmıştır (`app/` → `dist/`).
-
-Varsayılan URL'ler:
-
-- **Pano**: `http://localhost:20128/dashboard`
+- **Dashboard**: `http://localhost:20128/dashboard`
 - **API**: `http://localhost:20128/v1`
 
 ---
 
-## Git İş Akışı
+## Git Workflow
 
-> ⚠️ **KESİNLİKLE doğrudan `main` dalına commit atmayın.** Her zaman özellik dalları (feature branch) kullanın.
->
-> **PR hedefi:** aktif `release/vX.Y.Z` dalını hedefleyin (`main` değil). Dal başına sürüm + yayımlama anında etiket modeli için
-> [`docs/ops/BRANCHING_MODEL.md`](docs/ops/BRANCHING_MODEL.md) belgesine bakın.
+> ⚠️ **NEVER commit directly to `main`.** Always use feature branches.
 
 ```bash
-# Aktif sürüm ucundan dal oluşturun (örnek: release/v3.8.49)
-git fetch origin
-git checkout -b feat/ozellik-adiniz origin/release/v3.8.49
-# ... değişiklikleri yapın ...
-git commit -m "feat: degisikliginizi aciklayin"
-git push -u origin feat/ozellik-adiniz
-# Hedef dal = release/v3.8.49 olacak şekilde Pull Request açın
+git checkout -b feat/your-feature-name
+# ... make changes ...
+git commit -m "feat: describe your change"
+git push -u origin feat/your-feature-name
+# Open a Pull Request on GitHub
 ```
 
-### Dal Adlandırma
+### Branch Naming
 
-| Önek        | Amaç                                |
-| ----------- | ----------------------------------- |
-| `feat/`     | Yeni özellikler                     |
-| `fix/`      | Hata düzeltmeleri                   |
-| `refactor/` | Kod yeniden yapılandırması          |
-| `docs/`     | Dokümantasyon değişiklikleri        |
-| `test/`     | Test ekleme/düzeltme                |
-| `chore/`    | Araçlar, CI, bağımlılıklar          |
+| Prefix      | Purpose                   |
+| ----------- | ------------------------- |
+| `feat/`     | New features              |
+| `fix/`      | Bug fixes                 |
+| `refactor/` | Code restructuring        |
+| `docs/`     | Documentation changes     |
+| `test/`     | Test additions/fixes      |
+| `chore/`    | Tooling, CI, dependencies |
 
-### Commit Mesajları
+### Commit Messages
 
-[Conventional Commits](https://www.conventionalcommits.org/) standartlarını izleyin:
+Follow [Conventional Commits](https://www.conventionalcommits.org/):
 
 ```
 feat: add circuit breaker for provider calls
@@ -152,248 +112,200 @@ test: add observability unit tests
 refactor(db): consolidate rate limit tables
 ```
 
-Kapsamlar (v3.8): `db`, `sse`, `oauth`, `dashboard`, `api`, `cli`, `docker`, `ci`, `mcp`, `a2a`, `memory`, `skills`, `cloud-agent`, `guardrails`, `compression`, `auto-combo`, `resilience`, `providers`, `executors`, `translator`, `domain`, `authz`.
+Scopes: `db`, `sse`, `oauth`, `dashboard`, `api`, `cli`, `docker`, `ci`, `mcp`, `a2a`, `memory`, `skills`.
 
 ---
 
-## Testleri Çalıştırma
+## Running Tests
 
 ```bash
-# Tüm testler (unit + vitest + ecosystem + e2e)
+# All tests (unit + vitest + ecosystem + e2e)
 npm run test:all
 
-# Tek bir test dosyası (Node.js yerel test çalıştırıcısı — çoğu test bunu kullanır)
+# Single test file (Node.js native test runner — most tests use this)
 node --import tsx/esm --test tests/unit/your-file.test.ts
 
-# Vitest (MCP sunucusu, autoCombo, önbellek)
+# Vitest (MCP server, autoCombo, cache)
 npm run test:vitest
 
-# E2E testleri (Playwright gerektirir)
+# E2E tests (requires Playwright)
 npm run test:e2e
 
-# Protokol istemcileri E2E (MCP taşımaları, A2A)
+# Protocol clients E2E (MCP transports, A2A)
 npm run test:protocols:e2e
 
-# Ekosistem uyumluluk testleri
+# Ecosystem compatibility tests
 npm run test:ecosystem
 
-# Kapsam kapısı: %60 statements/lines/functions/branches
+# Coverage (60% min statements/lines/functions/branches)
 npm run test:coverage
 npm run coverage:report
 
-# Lint + biçimlendirme kontrolü
+# Lint + format check
 npm run lint
 npm run check
-
-# Gerçek yukarı akış kombo testi (VPS erişimi + gerçek sağlayıcı kredisi gerektirir)
-# GERÇEK sağlayıcılara istek atar — küçük bir maliyeti vardır. CI'da ASLA çalışmaz.
-RUN_COMBO_LIVE=1 npm run test:combo:live
-
-# Aşama-3 VPS canlı testi — doğrudan canlı .15 sunucusuna istek atar.
-npm run test:combo:live:vps              # 7 HTTP senaryosu (priority/round-robin/weighted/cost/fusion/auto + health)
-npm run test:combo:live:vps:failover     # gerçek sağlayıcılar arası geçiş senaryosu ekler (toplam 8)
 ```
 
-Test kapsamı notları:
+Coverage notes:
 
-- `npm run test:coverage` ana birim test paketi için kaynak kapsamını ölçer, `tests/**` dizinini hariç tutar ve `open-sse/**` dizinini dahil eder
-- Pull Request'ler kapsam kapısını **%60+** (statements/lines/functions/branches) seviyesinde tutmalıdır
-- Bir PR `src/`, `open-sse/`, `electron/` veya `bin/` altındaki üretim kodunu değiştiriyorsa, aynı PR'da otomatik testler eklemeli veya güncellemelidir
-- `npm run coverage:report` en son test çalıştırmasından detaylı dosya bazlı raporu yazdırır
-- Kademeli kapsam iyileştirme yol haritası için `docs/ops/COVERAGE_PLAN.md` dosyasına bakın
+- `npm run test:coverage` measures source coverage for the main unit test suite, excludes `tests/**`, and includes `open-sse/**`
+- Pull requests must keep the overall coverage gate at **60% or higher** for statements, lines, functions, and branches
+- If a PR changes production code in `src/`, `open-sse/`, `electron/`, or `bin/`, it must add or update automated tests in the same PR
+- `npm run coverage:report` prints the detailed file-by-file report from the latest coverage run
+- `npm run test:coverage:legacy` preserves the older metric for historical comparison
+- See `docs/ops/COVERAGE_PLAN.md` for the phased coverage improvement roadmap
 
-### Pull Request Gereksinimleri
+### Pull Request Requirements
 
-Bir PR açmadan önce, değiştirdiğiniz alan için odaklanmış döngüyü çalıştırmak üzere [Katkı Altın Yolu](docs/ops/CONTRIBUTION_GOLDEN_PATH.md) belgesini kullanın:
+Before opening or merging a PR:
 
-- Değişikliğinizi kapsayan test dosyalarını çalıştırın: `node --import tsx/esm --test tests/unit/<dosya>.test.ts`
-- `npm run lint` çalıştırın
-- Üretim kodu değiştiğinde her zaman aynı PR'a otomatik testler ekleyin veya güncelleyin
-- Üretim kodu değiştiğinde PR açıklamasına değiştirilen veya eklenen test dosyalarını ekleyin
-- CI'da proje sırları yapılandırıldığında PR üzerindeki SonarQube sonucunu kontrol edin
+- Run `npm run test:unit`
+- Run `npm run test:coverage`
+- Ensure the coverage gate stays at **60%+** for all metrics
+- Include the changed or added test files in the PR description when production code changed
+- Check the SonarQube result on the PR when the project secrets are configured in CI
 
-Mevcut test durumu: **122 birim test dosyası** şunları kapsar:
+Current test status: **122 unit test files** covering:
 
-- Sağlayıcı çevirmenleri ve format dönüştürme
-- Hız sınırlaması, devre kesici ve dayanıklılık
-- Anlamsal önbellek, tekilleştirme, ilerleme takibi
-- Veritabanı işlemleri ve şeması (21 DB modülü)
-- OAuth akışları ve kimlik doğrulama
-- API uç noktası doğrulaması (Zod v4)
-- MCP sunucu araçları ve kapsam denetimi
-- Bellek ve Yetenek (Skills) sistemleri
+- Provider translators and format conversion
+- Rate limiting, circuit breaker, and resilience
+- Semantic cache, idempotency, progress tracking
+- Database operations and schema (21 DB modules)
+- OAuth flows and authentication
+- API endpoint validation (Zod v4)
+- MCP server tools and scope enforcement
+- Memory and Skills systems
 
 ---
 
-## Kod Stili
+## Code Style
 
-- **ESLint** — Commit öncesinde `npm run lint` çalıştırın
-- **Prettier** — Commit sırasında `lint-staged` aracılığıyla otomatik biçimlendirilir (2 boşluk, noktalı virgül, çift tırnak, 100 karakter genişlik, es5 son virgüller)
-- **TypeScript** — Tüm `src/` kodu `.ts`/`.tsx` kullanır; `open-sse/` `.ts`/`.js` kullanır; TSDoc (`@param`, `@returns`, `@throws`) ile belgeleyin
-- **`eval()` Yasaktır** — ESLint `no-eval`, `no-implied-eval`, `no-new-func` kurallarını zorunlu kılar
-- **Zod doğrulaması** — Tüm API girdi doğrulamaları için Zod v4 şemalarını kullanın
-- **Adlandırma**: Dosyalar = camelCase/kebab-case, bileşenler = PascalCase, sabitler = UPPER_SNAKE
-
-### Hata Yönetimi / Boş Catch Blokları
-
-Bir `catch` bloğunu asla açıklamasız bırakmayın. İki kategoriden birine ayırın:
-
-- **Kasıtlı (kendi en iyi çaba temizliğimiz/telemetrimiz)** — burada bir hata beklenir ve zararsızdır; tek satırlık bir gerekçe yorumu ekleyin, günlük kaydı yapmayın:
-
-  ```ts
-  } catch {} // istemci bağlantısı kesildikten sonra zaten kapalı bir denetleyiciyi kapatmak beklenen bir durumdur
-  ```
-
-- **Günlüğe kaydedilmeli (harici kod veya akışı değiştiren durumlar)** — catch'i koruyun ancak hatanın keşfedilebilmesi için bağlamsal bir `console.debug`/`warn` yayınlayın:
-
-  ```ts
-  } catch (e) {
-    console.debug("[STREAM] onFailure callback error:", e);
-  }
-  ```
-
-Uygulamalı örnekler için `open-sse/utils/stream.ts` ve `open-sse/utils/streamHandler.ts` dosyalarına bakın.
+- **ESLint** — Run `npm run lint` before committing
+- **Prettier** — Auto-formatted via `lint-staged` on commit (2 spaces, semicolons, double quotes, 100 char width, es5 trailing commas)
+- **TypeScript** — All `src/` code uses `.ts`/`.tsx`; `open-sse/` uses `.ts`/`.js`; document with TSDoc (`@param`, `@returns`, `@throws`)
+- **No `eval()`** — ESLint enforces `no-eval`, `no-implied-eval`, `no-new-func`
+- **Zod validation** — Use Zod v4 schemas for all API input validation
+- **Naming**: Files = camelCase/kebab-case, components = PascalCase, constants = UPPER_SNAKE
 
 ---
 
-## Proje Yapısı
+## Project Structure
 
 ```
 src/                        # TypeScript (.ts / .tsx)
 ├── app/                    # Next.js 16 App Router
-│   ├── (dashboard)/        # Pano sayfaları (23 bölüm)
-│   ├── api/                # API rotaları (51 dizin)
-│   └── login/              # Kimlik doğrulama sayfaları (.tsx)
-├── domain/                 # Politika motoru (policyEngine, comboResolver, costRules, vb.)
-├── lib/                    # Çekirdek iş mantığı (.ts)
-│   ├── a2a/                # Agent-to-Agent v0.3 protokol sunucusu
-│   ├── acp/                # Ajan İletişim Protokolü kayıt defteri
-│   ├── compliance/         # Uyumluluk politika motoru
-│   ├── db/                 # SQLite alan modülleri + 130 migrasyon
-│   ├── memory/             # Kalıcı konuşma belleği
-│   ├── oauth/              # OAuth sağlayıcıları, servisleri ve yardımcıları
-│   ├── skills/             # Genişletilebilir yetenek çerçevesi
-│   ├── usage/              # Kullanım takibi ve maliyet hesaplama
-│   └── localDb.ts          # Yalnızca yeniden dışa aktarma katmanı — buraya asla mantık eklemeyin
-├── middleware/              # İstek ara yazılımı (promptInjectionGuard)
-├── mitm/                   # MITM proxy (sertifika, DNS, hedef yönlendirme)
+│   ├── (dashboard)/        # Dashboard pages (23 sections)
+│   ├── api/                # API routes (51 directories)
+│   └── login/              # Auth pages (.tsx)
+├── domain/                 # Policy engine (policyEngine, comboResolver, costRules, etc.)
+├── lib/                    # Core business logic (.ts)
+│   ├── a2a/                # Agent-to-Agent v0.3 protocol server
+│   ├── acp/                # Agent Communication Protocol registry
+│   ├── compliance/         # Compliance policy engine
+│   ├── db/                 # SQLite database layer (110 top-level modules + 130 migrations)
+│   ├── memory/             # Persistent conversational memory
+│   ├── oauth/              # OAuth providers, services, and utilities
+│   ├── skills/             # Extensible skill framework
+│   ├── usage/              # Usage tracking and cost calculation
+│   └── localDb.ts          # Re-export layer only — never add logic here
+├── middleware/              # Request middleware (promptInjectionGuard)
+├── mitm/                   # MITM proxy (cert, DNS, target routing)
 ├── shared/
-│   ├── components/         # React bileşenleri (.tsx)
-│   ├── constants/          # Sağlayıcı tanımları (329), MCP kapsamları, 19 yönlendirme stratejisi
-│   ├── utils/              # Devre kesici, temizleyici, kimlik doğrulama yardımcıları
-│   └── validation/         # Zod v4 şemaları
-└── sse/                    # SSE proxy hattı
+│   ├── components/         # React components (.tsx)
+│   ├── constants/          # Provider definitions (329), MCP scopes, routing strategies
+│   ├── utils/              # Circuit breaker, sanitizer, auth helpers
+│   └── validation/         # Zod v4 schemas
+└── sse/                    # SSE proxy pipeline
 
-open-sse/                   # @omniroute/open-sse çalışma alanı
-├── executors/              # 89 yürütücü uygulama modülü
-├── handlers/               # 11 istek işleyici (chat, responses, embeddings, images, vb.)
-├── mcp-server/             # MCP sunucusu (107 benzersiz araç, 3 taşıma, 32 kapsam)
-├── services/               # 178 üst düzey servis (combo, autoCombo, rateLimitManager, vb.)
-├── translator/             # Format çevirmenleri (OpenAI ↔ Claude ↔ Gemini ↔ Responses ↔ Ollama)
-├── transformer/            # Responses API dönüştürücüsü
-└── utils/                  # 22 yardımcı modül (stream, TLS, proxy, logging)
+open-sse/                   # @omniroute/open-sse workspace
+├── executors/              # 89 executor implementation modules
+├── handlers/               # 11 request handlers (chat, responses, embeddings, images, etc.)
+├── mcp-server/             # MCP server (107 tools, 3 transports, 32 scopes)
+├── services/               # 178 top-level services (combo, autoCombo, rateLimitManager, etc.)
+├── translator/             # Format translators (OpenAI ↔ Claude ↔ Gemini ↔ Responses ↔ Ollama)
+├── transformer/            # Responses API transformer
+└── utils/                  # 22 utility modules (stream, TLS, proxy, logging)
 
-electron/                   # Electron masaüstü uygulaması (platformlar arası)
+electron/                   # Electron desktop app (cross-platform)
 
 tests/
-├── unit/                   # Node.js test çalıştırıcısı (1.574 test dosyası)
-├── integration/            # Entegrasyon testleri
-├── e2e/                    # Playwright testleri
-├── security/               # Güvenlik testleri
-├── translator/             # Çevirmene özel testler
-└── load/                   # Yük testleri
+├── unit/                   # Node.js test runner (122 test files)
+├── integration/            # Integration tests
+├── e2e/                    # Playwright tests
+├── security/               # Security tests
+├── translator/             # Translator-specific tests
+└── load/                   # Load tests
 
-docs/
-├── adr/                     # Mimari Karar Kayıtları (ADR)
-├── architecture/            # Sistem mimarisi ve dayanıklılık
-├── comparison/              # OmniRoute ve alternatifler
-├── compression/             # Sıkıştırma kılavuzları ve kuralları
-├── dev/                     # Geliştirme kılavuzları
-├── diagrams/                # Mimari diyagramları
-├── frameworks/              # MCP, A2A, OpenCode, Bellek, Yetenekler
-├── guides/                  # Kullanıcı kılavuzu, Docker, kurulum, sorun giderme
-├── i18n/                    # Çok dilli README çevirileri
-├── marketing/               # Pazarlama materyalleri
-├── ops/                     # Dağıtım, proxy, test kapsamı, sürümler
-├── providers/               # Sağlayıcıya özel belgeler
-├── reference/               # API referansı, ortam değişkenleri, CLI araçları, ücretsiz katmanlar
-├── releases/                # Sürüm notları
-├── routing/                 # Auto-combo motoru, akıl yürütme tekrarı
-├── screenshots/             # Pano ekran görüntüleri
-├── security/                # Güvenlik önlemleri, uyumluluk, gizlilik, belirteçler
-└── specs/                   # Tasarım özellikleri
+docs/                       # Documentation
+├── ARCHITECTURE.md         # System architecture
+├── API_REFERENCE.md        # All endpoints
+├── USER_GUIDE.md           # Provider setup, CLI integration
+├── TROUBLESHOOTING.md      # Common issues
+├── MCP-SERVER.md           # MCP server (107 tools)
+├── A2A-SERVER.md           # A2A agent protocol
+├── AUTO-COMBO.md           # Auto-combo engine
+├── CLI-TOOLS.md            # CLI tools integration
+├── COVERAGE_PLAN.md        # Test coverage improvement plan
+├── openapi.yaml            # OpenAPI specification
+└── adr/                    # Architecture Decision Records
 ```
 
 ---
 
-## Yeni Bir Sağlayıcı Ekleme
+## Adding a New Provider
 
-### Adım 1: Sağlayıcı Sabitlerini Kaydedin
+### Step 1: Register Provider Constants
 
-`src/shared/constants/providers.ts` dosyasına ekleyin — modül yükleme sırasında Zod ile doğrulanır.
+Add to `src/shared/constants/providers.ts` — Zod-validated at module load.
 
-### Adım 2: Yürütücü (Executor) Ekleyin (özel mantık gerekiyorsa)
+### Step 2: Add Executor (if custom logic needed)
 
-`open-sse/executors/your-provider.ts` içinde temel yürütücüyü genişleten bir yürütücü oluşturun.
+Create executor in `open-sse/executors/your-provider.ts` extending the base executor.
 
-### Adım 3: Çevirmen (Translator) Ekleyin (OpenAI dışı format ise)
+### Step 3: Add Translator (if non-OpenAI format)
 
-`open-sse/translator/` altında istek/yanıt çevirmenleri oluşturun.
+Create request/response translators in `open-sse/translator/`.
 
-### Adım 4: OAuth Yapılandırması Ekleyin (OAuth tabanlıysa)
+### Step 4: Add OAuth Config (if OAuth-based)
 
-`src/lib/oauth/constants/oauth.ts` içine OAuth kimlik bilgilerini ve `src/lib/oauth/services/` içine servisini ekleyin.
+Add OAuth credentials in `src/lib/oauth/constants/oauth.ts` and service in `src/lib/oauth/services/`.
 
-Yukarı akış sağlayıcısı genel bir OAuth client_id/secret veya Firebase Web API anahtarı dağıtıyorsa, bunu kaynak koda **dize sabiti olarak gömmeyin**. `open-sse/utils/publicCreds.ts` dosyasındaki `resolvePublicCred()` fonksiyonunu kullanın ve `EMBEDDED_DEFAULTS` içine maskelenmiş bayt girişi ekleyin. Zorunlu iş akışı [`docs/security/PUBLIC_CREDS.md`](docs/security/PUBLIC_CREDS.md) içinde belgelenmiştir.
+### Step 5: Register Models
 
-İşleyiciler/yürütücüler içinde istemciye ulaşan hata mesajları `open-sse/utils/error.ts` içindeki `buildErrorBody()` / `sanitizeErrorMessage()` üzerinden geçmelidir — Response gövdesine asla ham `err.stack` veya `err.message` koymayın. Bkz. [`docs/security/ERROR_SANITIZATION.md`](docs/security/ERROR_SANITIZATION.md).
+Add model definitions in `open-sse/config/providerRegistry.ts`.
 
-### Adım 5: Modelleri Kaydedin
+### Step 6: Add Tests
 
-`open-sse/config/providerRegistry.ts` dosyasına model tanımlarını ekleyin.
+Write unit tests in `tests/unit/` covering at minimum:
 
-### Adım 6: Testleri Ekleyin
-
-`tests/unit/` altında en az şunları kapsayan birim testleri yazın:
-
-- Sağlayıcı kaydı
-- İstek/yanıt çevirisi
-- Hata yönetimi
+- Provider registration
+- Request/response translation
+- Error handling
 
 ---
 
-## Pull Request Kontrol Listesi
+## Pull Request Checklist
 
-- [ ] Testler geçiyor (`npm test`)
-- [ ] Linting geçiyor (`npm run lint`)
-- [ ] Derleme başarılı (`npm run build`)
-- [ ] Yeni genel fonksiyonlar ve arayüzler için TypeScript tipleri eklendi
-- [ ] Sabit kodlanmış sırlar veya geri dönüş değerleri yok
-- [ ] Genel yukarı akış kimlik bilgileri `resolvePublicCred()` ile eklendi ([`docs/security/PUBLIC_CREDS.md`](docs/security/PUBLIC_CREDS.md)), asla sabit dize olarak değil
-- [ ] Hata yanıtları `buildErrorBody()` / `sanitizeErrorMessage()` üzerinden geçiyor — yanıt gövdelerinde ham yığın izi (stack trace) yok ([`docs/security/ERROR_SANITIZATION.md`](docs/security/ERROR_SANITIZATION.md))
-- [ ] Kabuk komutları (`exec` / `spawn`) çalışma zamanı değerlerini dize birleştirme ile değil `env` ile iletiyor
-- [ ] Tüm girdiler Zod şemaları ile doğrulanıyor
-- [ ] Kullanıcıya yönelik değişiklikler için `changelog.d/{features|fixes|maintenance}/<PR>-<slug>.md` altında değişiklik günlüğü parçacığı (fragment) eklendi ([`changelog.d/README.md`](changelog.d/README.md)) — doğrudan `CHANGELOG.md` dosyasını düzenlemeyin
-- [ ] Dokümantasyon güncellendi (varsa)
-- [ ] Yeni CodeQL / Secret-Scanning uyarısı açılmadı veya her biri ilgili `docs/security/` belgesine atıfta bulunarak teknik gerekçeyle kapatıldı
-- [ ] Alt süreçler başlatan rotalar (`/api/mcp/`, `/api/cli-tools/runtime/`) `src/server/authz/routeGuard.ts` içinde `isLocalOnlyPath()` olarak sınıflandırıldı
-- [ ] Commit mesajlarında `Co-Authored-By` bulunmuyor — commit'ler yalnızca depo sahibinin Git kimliği altında görünmelidir
+- [ ] Tests pass (`npm test`)
+- [ ] Linting passes (`npm run lint`)
+- [ ] Build succeeds (`npm run build`)
+- [ ] TypeScript types added for new public functions and interfaces
+- [ ] No hardcoded secrets or fallback values
+- [ ] All inputs validated with Zod schemas
+- [ ] CHANGELOG updated (if user-facing change)
+- [ ] Documentation updated (if applicable)
 
 ---
 
-## Sürüm Yayımlama
+## Releasing
 
-Sürümler `/generate-release` iş akışı aracılığıyla yönetilir. Yeni bir GitHub Sürümü oluşturulduğunda, paket GitHub Actions aracılığıyla **otomatik olarak npm'de yayımlanır**.
-
-VPS dağıtımları için `npm run build:release` kullanın — temiz bir yeniden derleme gerçekleştirir, paketi `dist/` içine toplar ve `dist/BUILD_SHA` nöbetçisini yazar. Ardından `dist/` dizinini uzak `app/` dizinine rsync eden `/deploy-vps-*-cc` yeteneklerini kullanın.
+Releases are managed via the `/generate-release` workflow. When a new GitHub Release is created, the package is **automatically published to npm** via GitHub Actions.
 
 ---
 
-## Yardım Alma
+## Getting Help
 
-- **Mimari**: Bkz. [`docs/architecture/ARCHITECTURE.md`](docs/architecture/ARCHITECTURE.md)
-- **API Referansı**: Bkz. [`docs/reference/API_REFERENCE.md`](docs/reference/API_REFERENCE.md)
-- **Güvenlik belgeleri**: [`docs/security/CLI_TOKEN.md`](docs/security/CLI_TOKEN.md), [`docs/security/ROUTE_GUARD_TIERS.md`](docs/security/ROUTE_GUARD_TIERS.md), [`docs/security/ERROR_SANITIZATION.md`](docs/security/ERROR_SANITIZATION.md), [`docs/security/PUBLIC_CREDS.md`](docs/security/PUBLIC_CREDS.md)
-- **Operasyon belgeleri**: [`docs/ops/SQLITE_RUNTIME.md`](docs/ops/SQLITE_RUNTIME.md)
-- **Sorun Bildirimi (Issues)**: [github.com/diegosouzapw/OmniRoute/issues](https://github.com/diegosouzapw/OmniRoute/issues)
-- **Mimari Karar Kayıtları (ADR)**: Mimari karar kayıtları için `docs/adr/` dizinine bakın
+- **Architecture**: See [`docs/architecture/ARCHITECTURE.md`](docs/architecture/ARCHITECTURE.md)
+- **API Reference**: See [`docs/reference/API_REFERENCE.md`](docs/reference/API_REFERENCE.md)
+- **Issues**: [github.com/diegosouzapw/OmniRoute/issues](https://github.com/diegosouzapw/OmniRoute/issues)
+- **ADRs**: See `docs/adr/` for architectural decision records

docs/i18n/tr/GEMINI.md

@@ -1,12 +1,25 @@
-# GEMINI.md (Türkçe)
+# Security and Cleanliness Rules for AI Assistants (Türkçe)
 
 🌐 **Languages:** 🇺🇸 [English](../../../GEMINI.md) · 🇸🇦 [ar](../ar/GEMINI.md) · 🇧🇬 [bg](../bg/GEMINI.md) · 🇧🇩 [bn](../bn/GEMINI.md) · 🇨🇿 [cs](../cs/GEMINI.md) · 🇩🇰 [da](../da/GEMINI.md) · 🇩🇪 [de](../de/GEMINI.md) · 🇪🇸 [es](../es/GEMINI.md) · 🇮🇷 [fa](../fa/GEMINI.md) · 🇫🇮 [fi](../fi/GEMINI.md) · 🇫🇷 [fr](../fr/GEMINI.md) · 🇮🇳 [gu](../gu/GEMINI.md) · 🇮🇱 [he](../he/GEMINI.md) · 🇮🇳 [hi](../hi/GEMINI.md) · 🇭🇺 [hu](../hu/GEMINI.md) · 🇮🇩 [id](../id/GEMINI.md) · 🇮🇹 [it](../it/GEMINI.md) · 🇯🇵 [ja](../ja/GEMINI.md) · 🇰🇷 [ko](../ko/GEMINI.md) · 🇮🇳 [mr](../mr/GEMINI.md) · 🇲🇾 [ms](../ms/GEMINI.md) · 🇳🇱 [nl](../nl/GEMINI.md) · 🇳🇴 [no](../no/GEMINI.md) · 🇵🇭 [phi](../phi/GEMINI.md) · 🇵🇱 [pl](../pl/GEMINI.md) · 🇵🇹 [pt](../pt/GEMINI.md) · 🇧🇷 [pt-BR](../pt-BR/GEMINI.md) · 🇷🇴 [ro](../ro/GEMINI.md) · 🇷🇺 [ru](../ru/GEMINI.md) · 🇸🇰 [sk](../sk/GEMINI.md) · 🇸🇪 [sv](../sv/GEMINI.md) · 🇰🇪 [sw](../sw/GEMINI.md) · 🇮🇳 [ta](../ta/GEMINI.md) · 🇮🇳 [te](../te/GEMINI.md) · 🇹🇭 [th](../th/GEMINI.md) · 🇹🇷 [tr](../tr/GEMINI.md) · 🇺🇦 [uk-UA](../uk-UA/GEMINI.md) · 🇵🇰 [ur](../ur/GEMINI.md) · 🇻🇳 [vi](../vi/GEMINI.md) · 🇨🇳 [zh-CN](../zh-CN/GEMINI.md)
 
 ---
 
-> **Tek doğruluk kaynağı:** Yapay zeka asistanları için tüm proje kuralları [`AGENTS.md`](AGENTS.md) dosyasında yer almaktadır. Herhangi bir değişiklik yapmadan önce tamamını okuyun — 23 Katı Kuralı, kalite kapılarını, kod kurallarını, dosya yerleşimi / depo kökü hijyen kurallarını, depo haritasını ve daha önce bu dosyada bulunan yerel geliştirme erişim notlarını içerir.
+## 1. File Placement & Organization
 
-Gemini'ye özel notlar:
+- **Test Files**: ALL unit tests, integration tests, ecosystem tests, or Vitest files MUST strictly be placed within the `tests/` directory (e.g., `tests/unit/`, `tests/integration/`). NEVER create test files in the project root (`/`).
+- **Scripts and Utilities**: ALL maintenance, debugging, generation, or experimental scripts (`.cjs`, `.mjs`, `.js`, `.ts`) MUST be placed strictly inside the `scripts/` directory or `scripts/scratch/` for temporary one-offs. NEVER dump loose scripts in the project root (`/`).
 
-- Yetenekler (Skills), `activate_skill` aracı aracılığıyla etkinleştirilir (yetenek meta verileri oturum başlangıcında yüklenir ve tam içerik talep üzerine etkinleştirilir).
-- Bugün için Gemini'ye özel başka bir kural yoktur. Buraya yeniden proje kuralları eklemeyin — her asistanın aynı talimatları görmesi için `AGENTS.md` dosyasını düzenleyin.
+**The Project Root MUST ONLY CONTAIN:**
+
+- Configuration files (`vitest.config.ts`, `next.config.mjs`, `eslint.config.mjs`, etc.)
+- Dependency files (`package.json`, `package-lock.json`)
+- Documentation files (`README.md`, `CHANGELOG.md`, `AGENTS.md`)
+- CI/CD files and ignore definitions (`.gitignore`, `.dockerignore`)
+
+When creating _any_ validation tests or one-off logic scripts, default to using `scripts/scratch/` or the `tests/unit/` directories according to your goals. Do not pollute the `/` root context.
+
+## 2. VPS Dashboard Credentials
+
+| Environment | URL                       | Password |
+| ----------- | ------------------------- | -------- |
+| Local VPS   | http://192.168.0.15:20128 | 123456   |

docs/i18n/tr/SECURITY.md

@@ -1,184 +1,159 @@
-# Güvenlik Politikası (Türkçe)
+# Security Policy (Türkçe)
 
 🌐 **Languages:** 🇺🇸 [English](../../../SECURITY.md) · 🇸🇦 [ar](../ar/SECURITY.md) · 🇧🇬 [bg](../bg/SECURITY.md) · 🇧🇩 [bn](../bn/SECURITY.md) · 🇨🇿 [cs](../cs/SECURITY.md) · 🇩🇰 [da](../da/SECURITY.md) · 🇩🇪 [de](../de/SECURITY.md) · 🇪🇸 [es](../es/SECURITY.md) · 🇮🇷 [fa](../fa/SECURITY.md) · 🇫🇮 [fi](../fi/SECURITY.md) · 🇫🇷 [fr](../fr/SECURITY.md) · 🇮🇳 [gu](../gu/SECURITY.md) · 🇮🇱 [he](../he/SECURITY.md) · 🇮🇳 [hi](../hi/SECURITY.md) · 🇭🇺 [hu](../hu/SECURITY.md) · 🇮🇩 [id](../id/SECURITY.md) · 🇮🇹 [it](../it/SECURITY.md) · 🇯🇵 [ja](../ja/SECURITY.md) · 🇰🇷 [ko](../ko/SECURITY.md) · 🇮🇳 [mr](../mr/SECURITY.md) · 🇲🇾 [ms](../ms/SECURITY.md) · 🇳🇱 [nl](../nl/SECURITY.md) · 🇳🇴 [no](../no/SECURITY.md) · 🇵🇭 [phi](../phi/SECURITY.md) · 🇵🇱 [pl](../pl/SECURITY.md) · 🇵🇹 [pt](../pt/SECURITY.md) · 🇧🇷 [pt-BR](../pt-BR/SECURITY.md) · 🇷🇴 [ro](../ro/SECURITY.md) · 🇷🇺 [ru](../ru/SECURITY.md) · 🇸🇰 [sk](../sk/SECURITY.md) · 🇸🇪 [sv](../sv/SECURITY.md) · 🇰🇪 [sw](../sw/SECURITY.md) · 🇮🇳 [ta](../ta/SECURITY.md) · 🇮🇳 [te](../te/SECURITY.md) · 🇹🇭 [th](../th/SECURITY.md) · 🇹🇷 [tr](../tr/SECURITY.md) · 🇺🇦 [uk-UA](../uk-UA/SECURITY.md) · 🇵🇰 [ur](../ur/SECURITY.md) · 🇻🇳 [vi](../vi/SECURITY.md) · 🇨🇳 [zh-CN](../zh-CN/SECURITY.md)
 
 ---
 
-## Güvenlik Açıklarını Bildirme
+## Reporting Vulnerabilities
 
-OmniRoute'ta bir güvenlik açığı keşfederseniz, lütfen sorumlu bir şekilde bildirin:
+If you discover a security vulnerability in OmniRoute, please report it responsibly:
 
-1. **KESİNLİKLE** herkese açık bir GitHub issue'su açmayın
-2. [GitHub Security Advisories](https://github.com/diegosouzapw/OmniRoute/security/advisories/new) kullanın
-3. Şunları ekleyin: açıklama, yeniden oluşturma adımları ve olası etki
+1. **DO NOT** open a public GitHub issue
+2. Use [GitHub Security Advisories](https://github.com/diegosouzapw/OmniRoute/security/advisories/new)
+3. Include: description, reproduction steps, and potential impact
 
-## Yanıt Zaman Çizelgesi
+## Response Timeline
 
-| Aşama                 | Hedef Süre                  |
-| --------------------- | --------------------------- |
-| İlk Bildirim Teyidi   | 48 saat                     |
-| Ön İnceleme ve Değerlendirme | 5 iş günü             |
-| Yama Sürümü (Patch)   | 14 iş günü (kritik)         |
+| Stage               | Target                      |
+| ------------------- | --------------------------- |
+| Acknowledgment      | 48 hours                    |
+| Triage & Assessment | 5 business days             |
+| Patch Release       | 14 business days (critical) |
 
-## Desteklenen Sürümler
+## Supported Versions
 
-| Sürüm   | Destek Durumu  |
+| Version | Support Status |
 | ------- | -------------- |
-| 3.8.x   | ✅ Aktif       |
-| 3.7.x   | ✅ Güvenlik    |
-| < 3.7.0 | ❌ Desteklenmiyor |
+| 3.6.x   | ✅ Active      |
+| 3.5.x   | ✅ Security    |
+| < 3.5.0 | ❌ Unsupported |
 
 ---
 
-## Güvenlik Mimarisi
+## Security Architecture
 
-OmniRoute çok katmanlı bir güvenlik modeli uygular:
+OmniRoute implements a multi-layered security model:
 
 ```
-Request → CORS → Authz pipeline (classify → policies → enforce)
-       → Guardrails (PII masker, prompt injection, vision bridge)
-       → Rate Limiter → Circuit Breaker → Cooldown → Model Lockout → Provider
+Request → CORS → API Key Auth → Prompt Injection Guard → Input Sanitizer → Rate Limiter → Circuit Breaker → Provider
 ```
 
-### 🔐 Kimlik Doğrulama ve Yetkilendirme
+### 🔐 Authentication & Authorization
 
-| Özellik               | Uygulama                                                                                                                                  |
-| --------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
-| **Pano Girişi**       | JWT belirteçleri ile parola tabanlı kimlik doğrulama (HttpOnly çerezler)                                                                 |
-| **API Anahtarı Doğrulaması** | CRC doğrulamalı HMAC imzalı anahtarlar                                                                                            |
-| **OAuth 2.0 + PKCE**  | Sağlayıcıya özel tarayıcı/cihaz OAuth'u desteklenen yerlerde PKCE kullanır; yalnızca içe aktarılan Devin kimlik bilgileri ayrı işlenir.  |
-| **Belirteç Yenileme** | Süresi dolmadan önce otomatik OAuth belirteci yenileme                                                                                    |
-| **Güvenli Çerezler**  | HTTPS ortamları için `AUTH_COOKIE_SECURE=true`                                                                                            |
-| **Yetkilendirme Hattı** | Rota sınıflandırması (PUBLIC / CLIENT_API / MANAGEMENT) — bkz. `docs/architecture/AUTHZ_GUIDE.md`                                        |
-| **Rota Koruma Katmanları** | Yönetim rotaları için 3 katmanlı model (LOCAL_ONLY / ALWAYS_PROTECTED / MANAGEMENT) — bkz. `docs/security/ROUTE_GUARD_TIERS.md`         |
-| **Yönetim Kapsamlı MCP** | `manage` kapsamına sahip API anahtarlarıyla korunan uzak `/api/mcp/*` erişimi; `/api/cli-tools/runtime/*` katı yerel döngüde kalır.     |
-| **MCP Kapsamları**    | 32 ayrıntılı kapsam (read:health, write:combos, execute:completions vb.) — bkz. `docs/frameworks/MCP-SERVER.md`                          |
+| Feature              | Implementation                                             |
+| -------------------- | ---------------------------------------------------------- |
+| **Dashboard Login**  | Password-based auth with JWT tokens (HttpOnly cookies)     |
+| **API Key Auth**     | HMAC-signed keys with CRC validation                       |
+| **OAuth 2.0 + PKCE** | Secure provider auth (Claude, Codex, Gemini, Cursor, etc.) |
+| **Token Refresh**    | Automatic OAuth token refresh before expiry                |
+| **Secure Cookies**   | `AUTH_COOKIE_SECURE=true` for HTTPS environments           |
+| **MCP Scopes**       | 32 granular scopes for MCP tool access control             |
 
-### 🛡️ Dinlenmede Şifreleme (Encryption at Rest)
+### 🛡️ Encryption at Rest
 
-SQLite'ta saklanan tüm hassas veriler, scrypt anahtar türetme ile **AES-256-GCM** kullanılarak şifrelenir:
+All sensitive data stored in SQLite is encrypted using **AES-256-GCM** with scrypt key derivation:
 
-- API anahtarları, erişim belirteçleri, yenileme belirteçleri ve ID belirteçleri
-- Sürümlendirilmiş format: `enc:v1:<iv>:<ciphertext>:<authTag>`
-- `STORAGE_ENCRYPTION_KEY` ayarlanmadığında doğrudan geçiş modu (düz metin)
+- API keys, access tokens, refresh tokens, and ID tokens
+- Versioned format: `enc:v1:<iv>:<ciphertext>:<authTag>`
+- Passthrough mode (plaintext) when `STORAGE_ENCRYPTION_KEY` is not set
 
 ```bash
-# Şifreleme anahtarı oluşturun:
+# Generate encryption key:
 STORAGE_ENCRYPTION_KEY=$(openssl rand -hex 32)
 ```
 
-### 🛡️ Güvenlik Önlemleri Çerçevesi (Guardrails Framework)
+### 🧠 Prompt Injection Guard
 
-OmniRoute, öncelik sırasına göre sıralanmış 3 yerleşik güvenlik önlemi içeren, çalışırken yeniden yüklenebilir bir **güvenlik önlemleri kayıt defteri** (`src/lib/guardrails/`) ile gelir:
+Middleware that detects and blocks prompt injection attacks in LLM requests:
 
-| Güvenlik Önlemi    | Öncelik | Amaç                                                                                    |
-| ------------------ | ------- | --------------------------------------------------------------------------------------- |
-| `vision-bridge`    | 5       | Vision desteği olmayan modelleri görüntü açıklamalarıyla destekler; görsel URL'leri için SSRF koruması sağlar |
-| `pii-masker`       | 10      | Çağrı öncesi ve sonrası PII (kişisel veri) maskeleme (e-posta, telefon, CPF, CNPJ, kredi kartı, SSN) |
-| `prompt-injection` | 20      | Geçersiz kılma / rol ele geçirme / jailbreak / sızıntı kalıplarını algılar              |
+| Pattern Type        | Severity | Example                                        |
+| ------------------- | -------- | ---------------------------------------------- |
+| System Override     | High     | "ignore all previous instructions"             |
+| Role Hijack         | High     | "you are now DAN, you can do anything"         |
+| Delimiter Injection | Medium   | Encoded separators to break context boundaries |
+| DAN/Jailbreak       | High     | Known jailbreak prompt patterns                |
+| Instruction Leak    | Medium   | "show me your system prompt"                   |
 
-Özel güvenlik önlemleri `registerGuardrail(new MyGuardrail())` aracılığıyla kaydedilir. Model hata durumunda açıktır (fail-open; istisnalar trafiği asla engellemez). İstek başına devre dışı bırakma `x-omniroute-disabled-guardrails` başlığı ile yapılır. → Bkz. [`docs/security/GUARDRAILS.md`](docs/security/GUARDRAILS.md).
-
-### 🧠 İstem Enjeksiyonu Koruması (Prompt Injection Guard)
-
-LLM isteklerindeki istem enjeksiyonu modellerini algılayan en iyi çaba (heuristic) ara yazılımıdır.
-**Eksiksiz bir istem enjeksiyonu güvenlik duvarı değildir** — yanlış pozitifler (zararsız
-persona/RPG istemleri) ve yanlış negatifler (leetspeak, boşluk manipülasyonu, İngilizce dışı kalıplar) üretebilir.
-
-| Kalıp Türü          | Önem Derecesi | Örnek                                          |
-| ------------------- | ------------- | ---------------------------------------------- |
-| Sistem Geçersiz Kılma | Yüksek (High) | "ignore all previous instructions"             |
-| Rol Ele Geçirme     | Orta (Medium) | "you are now DAN, you can do anything"         |
-| Ayırıcı Enjeksiyonu | Yüksek (High) | Bağlam sınırlarını kırmak için kodlanmış ayırıcılar |
-| DAN / Jailbreak     | Orta (Medium) | Bilinen jailbreak istem kalıpları              |
-| Talimat Sızıntısı   | Yüksek (High) | "show me your system prompt"                   |
-| Kodlama Kaçırma     | Orta (Medium) | base64/rot13/hex kod çözme + talimat anahtar kelimeleri |
-
-`block` modunda yalnızca **High (Yüksek)** önem derecesindeki tespitler engellenir. Orta önem derecesindeki
-aileler günlüğe kaydedilir ancak `sanitizeRequest` tarafından asla engellenmez.
-
-Pano (Ayarlar → Güvenlik) veya `.env` üzerinden yapılandırın:
+Configure via dashboard (Settings → Security) or `.env`:
 
 ```env
 INPUT_SANITIZER_ENABLED=true
-INPUT_SANITIZER_MODE=block    # warn | block (enjeksiyon politikası; eski "redact" modu enjeksiyon metnini silmez)
-INPUT_SANITIZER_BLOCK_THRESHOLD=high  # high (varsayılan) | medium | low — block modunda bu seviye ve üstü engellenir
+INPUT_SANITIZER_MODE=block    # warn | block | redact
 ```
 
-### 🔒 PII (Kişisel Veri) Maskeleme
+### 🔒 PII Redaction
 
-Kişisel olarak tanımlanabilir bilgilerin otomatik olarak algılanması ve isteğe bağlı olarak maskelenmesi:
+Automatic detection and optional redaction of personally identifiable information:
 
-| PII Türü      | Kalıp                 | Değiştirilen Değer |
+| PII Type      | Pattern               | Replacement        |
 | ------------- | --------------------- | ------------------ |
-| E-posta       | `user@domain.com`     | `[EMAIL_REDACTED]` |
-| CPF (Brezilya)| `123.456.789-00`      | `[CPF_REDACTED]`   |
-| CNPJ (Brezilya)| `12.345.678/0001-00` | `[CNPJ_REDACTED]`  |
-| Kredi Kartı   | `4111-1111-1111-1111` | `[CC_REDACTED]`    |
-| Telefon       | `+55 11 99999-9999`   | `[PHONE_REDACTED]` |
-| SSN (ABD)     | `123-45-6789`         | `[SSN_REDACTED]`   |
+| Email         | `user@domain.com`     | `[EMAIL_REDACTED]` |
+| CPF (Brazil)  | `123.456.789-00`      | `[CPF_REDACTED]`   |
+| CNPJ (Brazil) | `12.345.678/0001-00`  | `[CNPJ_REDACTED]`  |
+| Credit Card   | `4111-1111-1111-1111` | `[CC_REDACTED]`    |
+| Phone         | `+55 11 99999-9999`   | `[PHONE_REDACTED]` |
+| SSN (US)      | `123-45-6789`         | `[SSN_REDACTED]`   |
 
 ```env
-PII_REDACTION_ENABLED=true   # istek PII yeniden yazımı; INPUT_SANITIZER_MODE'dan bağımsızdır
-PII_RESPONSE_SANITIZATION=true  # isteğe bağlı: istemcilere döndürülen sağlayıcı yanıtlarındaki PII'yi maskeler
+PII_REDACTION_ENABLED=true
 ```
 
-### 🌐 Ağ Güvenliği
+### 🌐 Network Security
 
-| Özellik                  | Açıklama                                                                       |
-| ------------------------ | ------------------------------------------------------------------------------ |
-| **CORS**                 | Açık kaynaklar arası izin listesi (`CORS_ALLOWED_ORIGINS`; eski `CORS_ORIGIN`)  |
-| **IP Filtreleme**        | Panoda IP aralıklarını izin listesine / engelleme listesine alma                |
-| **Hız Sınırlaması**      | Otomatik geri çekilme ile sağlayıcı başına hız sınırları                       |
-| **Sürü Önleme (Anti-Thundering Herd)** | Mutex + bağlantı başına kilitleme ile basamaklı 502 hatalarını önler |
-| **TLS Parmak İzi**       | Bot algılamasını azaltmak için tarayıcı benzeri TLS parmak izi taklidi         |
-| **CLI Parmak İzi**       | Yerel CLI imzalarıyla eşleşmesi için sağlayıcı başına başlık/gövde sıralaması  |
+| Feature                  | Description                                                      |
+| ------------------------ | ---------------------------------------------------------------- |
+| **CORS**                 | Configurable origin control (`CORS_ORIGIN` env var, default `*`) |
+| **IP Filtering**         | Allowlist/blocklist IP ranges in dashboard                       |
+| **Rate Limiting**        | Per-provider rate limits with automatic backoff                  |
+| **Anti-Thundering Herd** | Mutex + per-connection locking prevents cascading 502s           |
+| **TLS Fingerprint**      | Browser-like TLS fingerprint spoofing to reduce bot detection    |
+| **CLI Fingerprint**      | Per-provider header/body ordering to match native CLI signatures |
 
-### 🔌 Dayanıklılık ve Erişilebilirlik
+### 🔌 Resilience & Availability
 
-| Özellik                 | Açıklama                                                           |
+| Feature                 | Description                                                        |
 | ----------------------- | ------------------------------------------------------------------ |
-| **Devre Kesici (Circuit Breaker)** | Sağlayıcı başına 3 durumlu (Kapalı → Açık → Yarı Açık), SQLite ile kalıcı |
-| **İstek Tekilleştirme** | Yinelenen istekler için 5 saniyelik tekilleştirme penceresi        |
-| **Üstel Geri Çekilme**  | Artan gecikmelerle otomatik yeniden deneme                         |
-| **Sağlık Panosu**       | Gerçek zamanlı sağlayıcı sağlığı izleme                            |
+| **Circuit Breaker**     | 3-state (Closed → Open → Half-Open) per provider, SQLite-persisted |
+| **Request Idempotency** | 5-second dedup window for duplicate requests                       |
+| **Exponential Backoff** | Automatic retry with increasing delays                             |
+| **Health Dashboard**    | Real-time provider health monitoring                               |
 
-### 📋 Uyumluluk (Compliance)
+### 📋 Compliance
 
-| Özellik            | Açıklama                                                    |
+| Feature            | Description                                                 |
 | ------------------ | ----------------------------------------------------------- |
-| **Günlük Saklama** | `CALL_LOG_RETENTION_DAYS` sonrasında otomatik temizleme     |
-| **Günlük Tutmama Tercihi** | API anahtarı başına `noLog` bayrağı istek kaydını devre dışı bırakır |
-| **Denetim Günlüğü**| `audit_log` tablosunda izlenen yönetim eylemleri            |
-| **MCP Denetimi**   | Tüm MCP araç çağrıları için SQLite tabanlı denetim kaydı    |
-| **Zod Doğrulaması**| Modül yükleme sırasında Zod v4 şemalarıyla doğrulanan tüm API girdileri |
+| **Log Retention**  | Automatic cleanup after `CALL_LOG_RETENTION_DAYS`           |
+| **No-Log Opt-out** | Per API key `noLog` flag disables request logging           |
+| **Audit Log**      | Administrative actions tracked in `audit_log` table         |
+| **MCP Audit**      | SQLite-backed audit logging for all MCP tool calls          |
+| **Zod Validation** | All API inputs validated with Zod v4 schemas at module load |
 
 ---
 
-## Gerekli Ortam Değişkenleri
+## Required Environment Variables
 
-Sunucuyu başlatmadan önce tüm gizli anahtarlar ayarlanmalıdır. Eksik veya zayıf olmaları durumunda sunucu **hızlı bir şekilde hata vererek (fail fast)** durur.
+All secrets must be set before starting the server. The server will **fail fast** if they are missing or weak.
 
 ```bash
-# GEREKLİ — sunucu bunlar olmadan başlamaz:
-JWT_SECRET=$(openssl rand -base64 48)     # min 32 karakter
-API_KEY_SECRET=$(openssl rand -hex 32)    # min 16 karakter
+# REQUIRED — server will not start without these:
+JWT_SECRET=$(openssl rand -base64 48)     # min 32 chars
+API_KEY_SECRET=$(openssl rand -hex 32)    # min 16 chars
 
-# ÖNERİLEN — dinlenmede şifrelemeyi etkinleştirir:
+# RECOMMENDED — enables encryption at rest:
 STORAGE_ENCRYPTION_KEY=$(openssl rand -hex 32)
 ```
 
-Sunucu `changeme`, `secret` veya `password` gibi bilinen zayıf değerleri açıkça reddeder.
+The server actively rejects known-weak values like `changeme`, `secret`, or `password`.
 
 ---
 
-## Docker Güvenliği
+## Docker Security
 
-- Üretimde root olmayan bir kullanıcı kullanın
-- Gizli anahtarları salt okunur birimler (read-only volumes) olarak bağlayın
-- `.env` dosyalarını asla Docker imajlarına kopyalamayın
-- Hassas dosyaları hariç tutmak için `.dockerignore` kullanın
-- HTTPS arkasındayken `AUTH_COOKIE_SECURE=true` ayarlayın
+- Use non-root user in production
+- Mount secrets as read-only volumes
+- Never copy `.env` files into Docker images
+- Use `.dockerignore` to exclude sensitive files
+- Set `AUTH_COOKIE_SECURE=true` when behind HTTPS
 
 ```bash
 docker run -d \
@@ -195,52 +170,10 @@ docker run -d \
 
 ---
 
-## Bağımlılıklar
+## Dependencies
 
-- Düzenli olarak `npm audit` çalıştırın (`npm run audit:deps` ana projeyi + electron'u kapsar)
-- Bağımlılıkları güncel tutun
-- Proje, commit öncesi kontroller için `husky` + `lint-staged` kullanır (lint-staged + check-docs-sync + check:any-budget:t11)
-- CI hattı her push işleminde ESLint güvenlik kurallarını çalıştırır (`no-eval`, `no-implied-eval`, `no-new-func` = hata)
-- Sağlayıcı sabitleri modül yükleme sırasında Zod aracılığıyla doğrulanır (`src/shared/validation/schemas.ts`)
-- Varsayılan olarak güvenli kütüphaneler kullanılır: `dompurify` / `isomorphic-dompurify` (XSS), `jose` (JWT), `better-sqlite3` (parametreli sorgularla sıfır SQLi riski), `bcryptjs` (şifre karma)
-
-## Katı Güvenlik Kuralları (Hard Security Rules)
-
-Bu kurallar araçlar ve inceleyiciler tarafından zorunlu kılınmıştır:
-
-1. **Sırları asla commit etmeyin** — `.env` gitignore edilmiştir; `.env.example` şablondur (sabit değerler yok, yalnızca yorumlar — bkz. PUBLIC_CREDS.md)
-2. **Asla `eval()`, `new Function()` veya dolaylı eval kullanmayın** — ESLint tarafından zorunlu kılınır
-3. **Husky kancalarını asla atlamayın** (`--no-verify`, `--no-gpg-sign`), açık operatör onayı olmadan
-4. **Rotalarda asla ham SQL yazmayın** — her zaman `src/lib/db/` üzerinden geçin (parametrelendirilmiş)
-5. **Girdileri her zaman Zod ile doğrulayın** — `src/shared/validation/schemas.ts`
-6. **Yukarı akış başlıklarını her zaman temizleyin** — `src/shared/constants/upstreamHeaders.ts` içindeki engelleme listesi
-7. **Kimlik bilgilerini dinlenmede şifreleyin** — `src/lib/db/encryption.ts` aracılığıyla AES-256-GCM
-8. **Genel yukarı akış OAuth kimlikleri `resolvePublicCred()` aracılığıyla kullanılmalıdır** — kaynak koda asla `AIza…` / `GOCSPX-…` / `…apps.googleusercontent.com` sabit değerlerini gömmeyin. Bkz. [`docs/security/PUBLIC_CREDS.md`](docs/security/PUBLIC_CREDS.md).
-9. **Hata yanıtları `buildErrorBody()` / `sanitizeErrorMessage()` üzerinden geçmelidir** — HTTP / SSE / executor / MCP yanıt gövdelerine asla ham `err.stack` / `err.message` koymayın. Bkz. [`docs/security/ERROR_SANITIZATION.md`](docs/security/ERROR_SANITIZATION.md).
-10. **`exec()` / `spawn()` çalışma zamanı değerleri `env` seçeneği üzerinden iletilmelidir** — kabuk komutlarına harici yolları veya güvenilmeyen değerleri asla dize birleştirme ile eklemeyin. Referans: `src/mitm/cert/install.ts::updateNssDatabases`.
-11. **Varsayılan olarak güvenli kütüphaneleri tercih edin** — bkz. [tldrsec/awesome-secure-defaults](https://github.com/tldrsec/awesome-secure-defaults) (Helmet.js, DOMPurify, ssrf-req-filter, safe-regex, Google Tink). Kendi çözümünüzü yazmadan önce bunlara başvurun.
-
-## Tedarik Zinciri Tarayıcı Bulguları (Socket.dev / Snyk / Benzeri)
-
-Yayımlanan `omniroute` npm paketi, Next.js `output: "standalone"` derlemesini paketler; bu da belgelenmiş ayrıcalıklı özellikler (MITM, Zed içe aktarma, Cloud Sync, gömülü servis süpervizörü) dahil her rota işleyicisinin `.next/server/*.js` küçültülmüş yığınlarında yer alması anlamına gelir. Sezgisel tedarik zinciri tarayıcıları bu yığınları sıklıkla kötü amaçlı yazılım imzalarıyla eşleştirebilir.
-
-Her bulgu kategorisi için proje yöneticisi onay beyanı tutulmaktadır:
-
-- **[`docs/security/SOCKET_DEV_FINDINGS.md`](docs/security/SOCKET_DEV_FINDINGS.md)** —
-  bulgu başına harita: kaynak dosya ↔ işaretlenen yığın ↔ davranış ↔ v3.8.6'da uygulanan hafifletme.
-- İşaretlenen her fonksiyondaki kaynak içi `SECURITY-AUDITOR-NOTE:` blokları aynı belgeye işaret eder.
-
-Geliştirme hattında uyarıları esnetemeyen kullanıcılar için: `OMNIROUTE_BUILD_PROFILE=minimal npm run build` ile derleme yapın. Bu, dört hassas modülü çalışma zamanında HTTP 503 `feature-disabled` döndüren taslaklarla değiştirir; böylece ayrıcalıklı kod yolları pakette fiziksel olarak bulunmaz. Yayımlama tarifi için bkz. [`docs/security/SOCKET_DEV_FINDINGS.md`](docs/security/SOCKET_DEV_FINDINGS.md).
-
-## Referanslar
-
-- [`docs/architecture/AUTHZ_GUIDE.md`](docs/architecture/AUTHZ_GUIDE.md) — yetkilendirme hattı
-- [`docs/security/GUARDRAILS.md`](docs/security/GUARDRAILS.md) — güvenlik önlemleri çerçevesi
-- [`docs/security/COMPLIANCE.md`](docs/security/COMPLIANCE.md) — denetim günlüğü ve saklama
-- [`docs/security/PUBLIC_CREDS.md`](docs/security/PUBLIC_CREDS.md) — genel yukarı akış kimlik bilgileri için **zorunlu** model
-- [`docs/security/ERROR_SANITIZATION.md`](docs/security/ERROR_SANITIZATION.md) — hata yanıtları için **zorunlu** model
-- [`docs/security/SOCKET_DEV_FINDINGS.md`](docs/security/SOCKET_DEV_FINDINGS.md) — tedarik zinciri tarayıcı bulguları için onay beyanı
-- [`docs/architecture/RESILIENCE_GUIDE.md`](docs/architecture/RESILIENCE_GUIDE.md) — devre kesici + soğuma süresi + model kilitleme
-- [`docs/security/STEALTH_GUIDE.md`](docs/security/STEALTH_GUIDE.md) — TLS parmak izi (yasal/etik bildirim)
-- [`CLAUDE.md`](CLAUDE.md) — yapay zeka ajanları için katı kurallar
-- [tldrsec/awesome-secure-defaults](https://github.com/tldrsec/awesome-secure-defaults) — derlenmiş varsayılan olarak güvenli kütüphaneler
+- Run `npm audit` regularly
+- Keep dependencies updated
+- The project uses `husky` + `lint-staged` for pre-commit checks
+- CI pipeline runs ESLint security rules on every push
+- Provider constants validated at module load via Zod (`src/shared/validation/providerSchema.ts`)

docs/i18n/tr/docs/architecture/CODEBASE_DOCUMENTATION.md

@@ -1,107 +1,587 @@
----
-title: "OmniRoute Kod Tabanı Dokümantasyonu"
-version: 3.8.50
-lastUpdated: 2026-08-23
----
+# omniroute — Codebase Documentation (Türkçe)
 
-# OmniRoute Kod Tabanı Dokümantasyonu (Türkçe)
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇸🇦 [ar](../../ar/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇧🇬 [bg](../../bg/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇧🇩 [bn](../../bn/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇨🇿 [cs](../../cs/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇩🇰 [da](../../da/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇩🇪 [de](../../de/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇪🇸 [es](../../es/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇮🇷 [fa](../../fa/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇫🇮 [fi](../../fi/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇫🇷 [fr](../../fr/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇮🇳 [gu](../../gu/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇮🇱 [he](../../he/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇮🇳 [hi](../../hi/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇭🇺 [hu](../../hu/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇮🇩 [id](../../id/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇮🇹 [it](../../it/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇯🇵 [ja](../../ja/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇰🇷 [ko](../../ko/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇮🇳 [mr](../../mr/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇲🇾 [ms](../../ms/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇳🇱 [nl](../../nl/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇳🇴 [no](../..//no/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇵🇭 [phi](../../phi/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇵🇱 [pl](../../pl/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇵🇹 [pt](../../pt/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇷🇴 [ro](../../ro/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇷🇺 [ru](../../ru/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇸🇰 [sk](../../sk/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇸🇪 [sv](../../sv/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇰🇪 [sw](../../sw/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇮🇳 [ta](../../ta/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇮🇳 [te](../../te/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇹🇭 [th](../../th/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇹🇷 [tr](../../tr/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇵🇰 [ur](../../ur/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇻🇳 [vi](../../vi/docs/architecture/CODEBASE_DOCUMENTATION.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/architecture/CODEBASE_DOCUMENTATION.md)
+🌐 **Languages:** 🇺🇸 [English](../../../../docs/CODEBASE_DOCUMENTATION.md) · 🇸🇦 [ar](../../ar/docs/CODEBASE_DOCUMENTATION.md) · 🇧🇬 [bg](../../bg/docs/CODEBASE_DOCUMENTATION.md) · 🇧🇩 [bn](../../bn/docs/CODEBASE_DOCUMENTATION.md) · 🇨🇿 [cs](../../cs/docs/CODEBASE_DOCUMENTATION.md) · 🇩🇰 [da](../../da/docs/CODEBASE_DOCUMENTATION.md) · 🇩🇪 [de](../../de/docs/CODEBASE_DOCUMENTATION.md) · 🇪🇸 [es](../../es/docs/CODEBASE_DOCUMENTATION.md) · 🇮🇷 [fa](../../fa/docs/CODEBASE_DOCUMENTATION.md) · 🇫🇮 [fi](../../fi/docs/CODEBASE_DOCUMENTATION.md) · 🇫🇷 [fr](../../fr/docs/CODEBASE_DOCUMENTATION.md) · 🇮🇳 [gu](../../gu/docs/CODEBASE_DOCUMENTATION.md) · 🇮🇱 [he](../../he/docs/CODEBASE_DOCUMENTATION.md) · 🇮🇳 [hi](../../hi/docs/CODEBASE_DOCUMENTATION.md) · 🇭🇺 [hu](../../hu/docs/CODEBASE_DOCUMENTATION.md) · 🇮🇩 [id](../../id/docs/CODEBASE_DOCUMENTATION.md) · 🇮🇹 [it](../../it/docs/CODEBASE_DOCUMENTATION.md) · 🇯🇵 [ja](../../ja/docs/CODEBASE_DOCUMENTATION.md) · 🇰🇷 [ko](../../ko/docs/CODEBASE_DOCUMENTATION.md) · 🇮🇳 [mr](../../mr/docs/CODEBASE_DOCUMENTATION.md) · 🇲🇾 [ms](../../ms/docs/CODEBASE_DOCUMENTATION.md) · 🇳🇱 [nl](../../nl/docs/CODEBASE_DOCUMENTATION.md) · 🇳🇴 [no](../../no/docs/CODEBASE_DOCUMENTATION.md) · 🇵🇭 [phi](../../phi/docs/CODEBASE_DOCUMENTATION.md) · 🇵🇱 [pl](../../pl/docs/CODEBASE_DOCUMENTATION.md) · 🇵🇹 [pt](../../pt/docs/CODEBASE_DOCUMENTATION.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/CODEBASE_DOCUMENTATION.md) · 🇷🇴 [ro](../../ro/docs/CODEBASE_DOCUMENTATION.md) · 🇷🇺 [ru](../../ru/docs/CODEBASE_DOCUMENTATION.md) · 🇸🇰 [sk](../../sk/docs/CODEBASE_DOCUMENTATION.md) · 🇸🇪 [sv](../../sv/docs/CODEBASE_DOCUMENTATION.md) · 🇰🇪 [sw](../../sw/docs/CODEBASE_DOCUMENTATION.md) · 🇮🇳 [ta](../../ta/docs/CODEBASE_DOCUMENTATION.md) · 🇮🇳 [te](../../te/docs/CODEBASE_DOCUMENTATION.md) · 🇹🇭 [th](../../th/docs/CODEBASE_DOCUMENTATION.md) · 🇹🇷 [tr](../../tr/docs/CODEBASE_DOCUMENTATION.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/CODEBASE_DOCUMENTATION.md) · 🇵🇰 [ur](../../ur/docs/CODEBASE_DOCUMENTATION.md) · 🇻🇳 [vi](../../vi/docs/CODEBASE_DOCUMENTATION.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/CODEBASE_DOCUMENTATION.md)
 
 ---
 
-> **Hedef Kitle:** OmniRoute'a katkıda bulunan veya üzerine entegrasyonlar oluşturan mühendisler.
->
-> Yüksek düzey mimari diyagramları ve her alt sistemin gerekçeleri için [ARCHITECTURE.md](docs/architecture/ARCHITECTURE.md) dosyasını okuyun.
-
-Bu belge, yeni bir mühendisin proje ağacında gezinebilmesi, çalışma zamanı katmanlarını anlaması ve yeni modüller icat etmeden nereye kod ekleyeceğini bilmesi için **bugün depoda neyin var olduğunu** açıklar.
+> A comprehensive, beginner-friendly guide to the **omniroute** multi-provider AI proxy router.
 
 ---
 
-## 1. Teknoloji Yığını
+## 1. What Is omniroute?
 
-| Alan          | Tercih                                                                                                                   |
-| ------------- | ------------------------------------------------------------------------------------------------------------------------ |
-| Web framework | **Next.js 16** (App Router, standalone çıktı, global middleware yok)                                                     |
-| Dil           | **TypeScript 6.0+** — hedef `ES2022`, `module: esnext`, `moduleResolution: bundler`, `strict: false`                    |
-| Çalışma Zamanı| **Node.js** `>=22.22.2 <23` veya `>=24.0.0 <27`                                                                          |
-| Veritabanı    | `better-sqlite3` ile **SQLite** (singleton, WAL günlük kaydı)                                                            |
-| Masaüstü      | **Electron 41** + `electron-builder` (`electron/` altında ayrı çalışma alanı)                                           |
-| Testler       | **Node yerel test çalıştırıcısı** (unit/integration), **Vitest** (MCP, autoCombo, önbellek), **Playwright** (E2E)        |
-| Derleme       | `scripts/build/build-next-isolated.mjs` üzerinden Next.js standalone                                                      |
-| Lint/Format   | ESLint flat config + Prettier (`lint-staged` ile Husky pre-commit)                                                       |
-| Modül Sistemi | Her yerde ESM (`"type": "module"`)                                                                                       |
-| Çalışma Alanı | npm workspace — `open-sse` alt çalışma alanıdır                                                                          |
+omniroute is a **proxy router** that sits between AI clients (Claude CLI, Codex, Cursor IDE, etc.) and AI providers (Anthropic, Google, OpenAI, AWS, GitHub, etc.). It solves one big problem:
 
-Yol Takma Adları (`tsconfig.json`):
+> **Different AI clients speak different "languages" (API formats), and different AI providers expect different "languages" too.** omniroute translates between them automatically.
 
-- `@/*` → `src/*`
-- `@omniroute/open-sse` → `open-sse/index.ts`
-- `@omniroute/open-sse/*` → `open-sse/*`
-
-Varsayılan HTTP portu: **`20128`** (API ve pano aynı süreci paylaşır). Veri dizini `DATA_DIR` ortam değişkenidir (varsayılan: `~/.omniroute/`).
+Think of it like a universal translator at the United Nations — any delegate can speak any language, and the translator converts it for any other delegate.
 
 ---
 
-## 2. Depo Düzeni
+## 2. Architecture Overview
+
+```mermaid
+graph LR
+    subgraph Clients
+        A[Claude CLI]
+        B[Codex]
+        C[Cursor IDE]
+        D[OpenAI-compatible]
+    end
+
+    subgraph omniroute
+        E[Handler Layer]
+        F[Translator Layer]
+        G[Executor Layer]
+        H[Services Layer]
+    end
+
+    subgraph Providers
+        I[Anthropic Claude]
+        J[Google Gemini]
+        K[OpenAI / Codex]
+        L[GitHub Copilot]
+        M[AWS Kiro]
+        N[Antigravity]
+        O[Cursor API]
+    end
+
+    A --> E
+    B --> E
+    C --> E
+    D --> E
+    E --> F
+    F --> G
+    G --> I
+    G --> J
+    G --> K
+    G --> L
+    G --> M
+    G --> N
+    G --> O
+    H -.-> E
+    H -.-> G
+```
+
+### Core Principle: Hub-and-Spoke Translation
+
+All format translation passes through **OpenAI format as the hub**:
 
 ```
-OmniRoute/
-├── src/                  Next.js uygulaması (App Router, kütüphaneler, alan katmanı, sunucu, paylaşılanlar)
-├── open-sse/             Akış motoru çalışma alanı (@omniroute/open-sse)
-├── electron/             Masaüstü uygulaması (Electron 41 main + preload)
-├── bin/                  CLI giriş noktaları (omniroute, reset-password)
-├── tests/                Birim, entegrasyon, e2e, protokol, çevirmen, güvenlik testleri
-├── scripts/              Derleme, senkronizasyon, kontrol, migrasyon ve çalışma zamanı yardımcı betikleri
-├── docs/                 Genel dokümantasyon
-├── public/               Statik varlıklar, PWA manifesti, servis çalışanı
-├── config/               Çalışma zamanı yapılandırma örnekleri
-├── CLAUDE.md             Claude Code için kurallar
-├── AGENTS.md             Yapay zeka ajanları için derin mimari referansı
-├── package.json          Çalışma alanı kökü
-└── tsconfig.json         Yol takma adları ve derleyici seçenekleri
+Client Format → [OpenAI Hub] → Provider Format    (request)
+Provider Format → [OpenAI Hub] → Client Format    (response)
+```
+
+This means you only need **N translators** (one per format) instead of **N²** (every pair).
+
+---
+
+## 3. Project Structure
+
+```
+omniroute/
+├── open-sse/                  ← Core proxy library (portable, framework-agnostic)
+│   ├── index.js               ← Main entry point, exports everything
+│   ├── config/                ← Configuration & constants
+│   ├── executors/             ← Provider-specific request execution
+│   ├── handlers/              ← Request handling orchestration
+│   ├── services/              ← Business logic (auth, models, fallback, usage)
+│   ├── translator/            ← Format translation engine
+│   │   ├── request/           ← Request translators (8 files)
+│   │   ├── response/          ← Response translators (7 files)
+│   │   └── helpers/           ← Shared translation utilities (6 files)
+│   └── utils/                 ← Utility functions
+├── src/                       ← Application layer (Express/Worker runtime)
+│   ├── app/                   ← Web UI, API routes, middleware
+│   ├── lib/                   ← Database, auth, and shared library code
+│   ├── mitm/                  ← Man-in-the-middle proxy utilities
+│   ├── models/                ← Database models
+│   ├── shared/                ← Shared utilities (wrappers around open-sse)
+│   ├── sse/                   ← SSE endpoint handlers
+│   └── store/                 ← State management
+├── data/                      ← Runtime data (credentials, logs)
+│   └── provider-credentials.json   (external credentials override, gitignored)
+└── tester/                    ← Test utilities
 ```
 
 ---
 
-## 3. `src/` — Next.js Uygulaması
+## 4. Module-by-Module Breakdown
 
-```
-src/
-├── app/                  App Router sayfaları + API rotaları
-├── lib/                  Çekirdek kütüphaneler (DB, kimlik doğrulama, OAuth, yetenekler, bellek vb.)
-├── domain/               Saf alan katmanı (politika, geri dönüş, maliyet, kilitleme vb.)
-├── server/               Yalnızca sunucu tarafı modüller (authz, cors, auth)
-├── shared/               Tipler, sabitler, doğrulama, sözleşmeler, yardımcılar
-├── mitm/                 CLI entegrasyonu için Man-in-the-middle proxy yardımcıları
-├── models/               Yerel model meta verileri / takma adlar
-├── sse/                  src/ altında yaşayan SSE işleyicileri
-├── store/                İstemci tarafı Zustand durum depoları
-├── middleware/           Rota düzeyinde ara yazılım yardımcıları (Next.js global middleware DEĞİL)
-└── types/                TypeScript tip tanımları
+### 4.1 Config (`open-sse/config/`)
+
+The **single source of truth** for all provider configuration.
+
+| File                          | Purpose                                                                                                                                                                                                                   |
+| ----------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `constants.ts`                | `PROVIDERS` object with base URLs, OAuth credentials (defaults), headers, and default system prompts for every provider. Also defines `HTTP_STATUS`, `ERROR_TYPES`, `COOLDOWN_MS`, `BACKOFF_CONFIG`, and `SKIP_PATTERNS`. |
+| `credentialLoader.ts`         | Loads external credentials from `data/provider-credentials.json` and merges them over the hardcoded defaults in `PROVIDERS`. Keeps secrets out of source control while maintaining backwards compatibility.               |
+| `providerModels.ts`           | Central model registry: maps provider aliases → model IDs. Functions like `getModels()`, `getProviderByAlias()`.                                                                                                          |
+| `codexInstructions.ts`        | System instructions injected into Codex requests (editing constraints, sandbox rules, approval policies).                                                                                                                 |
+| `defaultThinkingSignature.ts` | Default "thinking" signatures for Claude and Gemini models.                                                                                                                                                               |
+| `ollamaModels.ts`             | Schema definition for local Ollama models (name, size, family, quantization).                                                                                                                                             |
+
+#### Credential Loading Flow
+
+```mermaid
+flowchart TD
+    A["App starts"] --> B["constants.ts defines PROVIDERS\nwith hardcoded defaults"]
+    B --> C{"data/provider-credentials.json\nexists?"}
+    C -->|Yes| D["credentialLoader reads JSON"]
+    C -->|No| E["Use hardcoded defaults"]
+    D --> F{"For each provider in JSON"}
+    F --> G{"Provider exists\nin PROVIDERS?"}
+    G -->|No| H["Log warning, skip"]
+    G -->|Yes| I{"Value is object?"}
+    I -->|No| J["Log warning, skip"]
+    I -->|Yes| K["Merge clientId, clientSecret,\ntokenUrl, authUrl, refreshUrl"]
+    K --> F
+    H --> F
+    J --> F
+    F -->|Done| L["PROVIDERS ready with\nmerged credentials"]
+    E --> L
 ```
 
 ---
 
-## 4. `open-sse/` — Akış ve Yürütücü Motoru
+### 4.2 Executors (`open-sse/executors/`)
 
+Executors encapsulate **provider-specific logic** using the **Strategy Pattern**. Each executor overrides base methods as needed.
+
+```mermaid
+classDiagram
+    class BaseExecutor {
+        +buildUrl(model, stream, options)
+        +buildHeaders(credentials, stream, body)
+        +transformRequest(body, model, stream, credentials)
+        +execute(url, options)
+        +shouldRetry(status, error)
+        +refreshCredentials(credentials, log)
+    }
+
+    class DefaultExecutor {
+        +refreshCredentials()
+    }
+
+    class AntigravityExecutor {
+        +buildUrl()
+        +buildHeaders()
+        +transformRequest()
+        +shouldRetry()
+        +refreshCredentials()
+    }
+
+    class CursorExecutor {
+        +buildUrl()
+        +buildHeaders()
+        +transformRequest()
+        +parseResponse()
+        +generateChecksum()
+    }
+
+    class KiroExecutor {
+        +buildUrl()
+        +buildHeaders()
+        +transformRequest()
+        +parseEventStream()
+        +refreshCredentials()
+    }
+
+    BaseExecutor <|-- DefaultExecutor
+    BaseExecutor <|-- AntigravityExecutor
+    BaseExecutor <|-- CursorExecutor
+    BaseExecutor <|-- KiroExecutor
+    BaseExecutor <|-- CodexExecutor
+    BaseExecutor <|-- GithubExecutor
 ```
-open-sse/
-├── executors/            Sağlayıcıya özel istek yürütücüleri (101 modül)
-├── handlers/             API türü başına istek işleyicileri (chat, responses, embeddings, images vb.)
-├── mcp-server/           110 araç ve 33 kapsam içeren yerleşik MCP sunucusu
-├── services/             Yönlendirme, hız sınırlamaları, auto-combo, oturum yönetimi vb.
-├── translator/           OpenAI ↔ Claude ↔ Gemini ↔ Ollama ↔ DeepSeek format çevirmenleri
-├── transformer/          OpenAI Responses API dönüştürücüsü
-└── utils/                Akış, TLS, proxy, günlük kaydı yardımcıları
+
+| Executor         | Provider                                   | Key Specializations                                                                                                 |
+| ---------------- | ------------------------------------------ | ------------------------------------------------------------------------------------------------------------------- |
+| `base.ts`        | —                                          | Abstract base: URL building, headers, retry logic, credential refresh                                               |
+| `default.ts`     | Claude, Gemini, OpenAI, GLM, Kimi, MiniMax | Generic OAuth token refresh for standard providers                                                                  |
+| `antigravity.ts` | Google Cloud Code                          | Project/session ID generation, multi-URL fallback, custom retry parsing from error messages ("reset after 2h7m23s") |
+| `cursor.ts`      | Cursor IDE                                 | **Most complex**: SHA-256 checksum auth, Protobuf request encoding, binary EventStream → SSE response parsing       |
+| `codex.ts`       | OpenAI Codex                               | Injects system instructions, manages thinking levels, removes unsupported parameters                                |
+| `github.ts`      | GitHub Copilot                             | Dual token system (GitHub OAuth + Copilot token), VSCode header mimicking                                           |
+| `kiro.ts`        | AWS CodeWhisperer                          | AWS EventStream binary parsing, AMZN event frames, token estimation                                                 |
+| `index.ts`       | —                                          | Factory: maps provider name → executor class, with default fallback                                                 |
+
+---
+
+### 4.3 Handlers (`open-sse/handlers/`)
+
+The **orchestration layer** — coordinates translation, execution, streaming, and error handling.
+
+| File                  | Purpose                                                                                                                                                                                                                |
+| --------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `chatCore.ts`         | **Central orchestrator** (~600 lines). Handles the complete request lifecycle: format detection → translation → executor dispatch → streaming/non-streaming response → token refresh → error handling → usage logging. |
+| `responsesHandler.ts` | Adapter for OpenAI's Responses API: converts Responses format → Chat Completions → sends to `chatCore` → converts SSE back to Responses format.                                                                        |
+| `embeddings.ts`       | Embedding generation handler: resolves embedding model → provider, dispatches to provider API, returns OpenAI-compatible embedding response. Supports 6+ providers.                                                    |
+| `imageGeneration.ts`  | Image generation handler: resolves image model → provider, supports OpenAI-compatible, Gemini-image (Antigravity), and fallback (Nebius) modes. Returns base64 or URL images.                                          |
+
+#### Request Lifecycle (chatCore.ts)
+
+```mermaid
+sequenceDiagram
+    participant Client
+    participant chatCore
+    participant Translator
+    participant Executor
+    participant Provider
+
+    Client->>chatCore: Request (any format)
+    chatCore->>chatCore: Detect source format
+    chatCore->>chatCore: Check bypass patterns
+    chatCore->>chatCore: Resolve model & provider
+    chatCore->>Translator: Translate request (source → OpenAI → target)
+    chatCore->>Executor: Get executor for provider
+    Executor->>Executor: Build URL, headers, transform request
+    Executor->>Executor: Refresh credentials if needed
+    Executor->>Provider: HTTP fetch (streaming or non-streaming)
+
+    alt Streaming
+        Provider-->>chatCore: SSE stream
+        chatCore->>chatCore: Pipe through SSE transform stream
+        Note over chatCore: Transform stream translates<br/>each chunk: target → OpenAI → source
+        chatCore-->>Client: Translated SSE stream
+    else Non-streaming
+        Provider-->>chatCore: JSON response
+        chatCore->>Translator: Translate response
+        chatCore-->>Client: Translated JSON
+    end
+
+    alt Error (401, 429, 500...)
+        chatCore->>Executor: Retry with credential refresh
+        chatCore->>chatCore: Account fallback logic
+    end
 ```
 
 ---
 
-## 5. `tests/` — Test Paketleri
+### 4.4 Services (`open-sse/services/`)
 
-- `tests/unit/`: Node.js yerleşik test çalıştırıcısı ile 2.700'den fazla test dosyası
-- `tests/integration/`: Modüller arası entegrasyon testleri
-- `tests/e2e/`: Playwright uçtan uca tarayıcı testleri
-- `tests/security/`: İstem enjeksiyonu, PII, yetkilendirme güvenlik testleri
-- `tests/translator/`: Format çevirmen doğruluk testleri
+Business logic that supports the handlers and executors.
+
+| File                 | Purpose                                                                                                                                                                                                                                                                                                                                |
+| -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `provider.ts`        | **Format detection** (`detectFormat`): analyzes request body structure to identify Claude/OpenAI/Gemini/Antigravity/Responses formats (includes `max_tokens` heuristic for Claude). Also: URL building, header building, thinking config normalization. Supports `openai-compatible-*` and `anthropic-compatible-*` dynamic providers. |
+| `model.ts`           | Model string parsing (`claude/model-name` → `{provider: "claude", model: "model-name"}`), alias resolution with collision detection, input sanitization (rejects path traversal/control chars), and model info resolution with async alias getter support.                                                                             |
+| `accountFallback.ts` | Rate-limit handling: exponential backoff (1s → 2s → 4s → max 2min), account cooldown management, error classification (which errors trigger fallback vs. not).                                                                                                                                                                         |
+| `tokenRefresh.ts`    | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, Qoder, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff.                                                                       |
+| `combo.ts`           | **Combo models**: chains of fallback models. If model A fails with a fallback-eligible error, try model B, then C, etc. Returns actual upstream status codes.                                                                                                                                                                          |
+| `usage.ts`           | Fetches quota/usage data from provider APIs (GitHub Copilot quotas, Antigravity model quotas, Codex rate limits, Kiro usage breakdowns, Claude settings).                                                                                                                                                                              |
+| `accountSelector.ts` | Smart account selection with scoring algorithm: considers priority, health status, round-robin position, and cooldown state to pick the optimal account for each request.                                                                                                                                                              |
+| `contextManager.ts`  | Request context lifecycle management: creates and tracks per-request context objects with metadata (request ID, timestamps, provider info) for debugging and logging.                                                                                                                                                                  |
+| `ipFilter.ts`        | IP-based access control: supports allowlist and blocklist modes. Validates client IP against configured rules before processing API requests.                                                                                                                                                                                          |
+| `sessionManager.ts`  | Session tracking with client fingerprinting: tracks active sessions using hashed client identifiers, monitors request counts, and provides session metrics.                                                                                                                                                                            |
+| `signatureCache.ts`  | Request signature-based deduplication cache: prevents duplicate requests by caching recent request signatures and returning cached responses for identical requests within a time window.                                                                                                                                              |
+| `systemPrompt.ts`    | Global system prompt injection: prepends or appends a configurable system prompt to all requests, with per-provider compatibility handling.                                                                                                                                                                                            |
+| `thinkingBudget.ts`  | Reasoning token budget management: supports passthrough, auto (strip thinking config), custom (fixed budget), and adaptive (complexity-scaled) modes for controlling thinking/reasoning tokens.                                                                                                                                        |
+| `wildcardRouter.ts`  | Wildcard model pattern routing: resolves wildcard patterns (e.g., `*/claude-*`) to concrete provider/model pairs based on availability and priority.                                                                                                                                                                                   |
+
+#### Token Refresh Deduplication
+
+```mermaid
+sequenceDiagram
+    participant R1 as Request 1
+    participant R2 as Request 2
+    participant Cache as refreshPromiseCache
+    participant OAuth as OAuth Provider
+
+    R1->>Cache: getAccessToken("gemini", token)
+    Cache->>Cache: No in-flight promise
+    Cache->>OAuth: Start refresh
+    R2->>Cache: getAccessToken("gemini", token)
+    Cache->>Cache: Found in-flight promise
+    Cache-->>R2: Return existing promise
+    OAuth-->>Cache: New access token
+    Cache-->>R1: New access token
+    Cache-->>R2: Same access token (shared)
+    Cache->>Cache: Delete cache entry
+```
+
+#### Account Fallback State Machine
+
+```mermaid
+stateDiagram-v2
+    [*] --> Active
+    Active --> Error: Request fails (401/429/500)
+    Error --> Cooldown: Apply backoff
+    Cooldown --> Active: Cooldown expires
+    Active --> Active: Request succeeds (reset backoff)
+
+    state Error {
+        [*] --> ClassifyError
+        ClassifyError --> ShouldFallback: Rate limit / Auth / Transient
+        ClassifyError --> NoFallback: 400 Bad Request
+    }
+
+    state Cooldown {
+        [*] --> ExponentialBackoff
+        ExponentialBackoff: Level 0 = 1s
+        ExponentialBackoff: Level 1 = 2s
+        ExponentialBackoff: Level 2 = 4s
+        ExponentialBackoff: Max = 2min
+    }
+```
+
+#### Combo Model Chain
+
+```mermaid
+flowchart LR
+    A["Request with\ncombo model"] --> B["Model A"]
+    B -->|"2xx Success"| C["Return response"]
+    B -->|"429/401/500"| D{"Fallback\neligible?"}
+    D -->|Yes| E["Model B"]
+    D -->|No| F["Return error"]
+    E -->|"2xx Success"| C
+    E -->|"429/401/500"| G{"Fallback\neligible?"}
+    G -->|Yes| H["Model C"]
+    G -->|No| F
+    H -->|"2xx Success"| C
+    H -->|"Fail"| I["All failed →\nReturn last status"]
+```
+
+---
+
+### 4.5 Translator (`open-sse/translator/`)
+
+The **format translation engine** using a self-registering plugin system.
+
+#### Mimari
+
+```mermaid
+graph TD
+    subgraph "Request Translation"
+        A["Claude → OpenAI"]
+        B["Gemini → OpenAI"]
+        C["Antigravity → OpenAI"]
+        D["OpenAI Responses → OpenAI"]
+        E["OpenAI → Claude"]
+        F["OpenAI → Gemini"]
+        G["OpenAI → Kiro"]
+        H["OpenAI → Cursor"]
+    end
+
+    subgraph "Response Translation"
+        I["Claude → OpenAI"]
+        J["Gemini → OpenAI"]
+        K["Kiro → OpenAI"]
+        L["Cursor → OpenAI"]
+        M["OpenAI → Claude"]
+        N["OpenAI → Antigravity"]
+        O["OpenAI → Responses"]
+    end
+```
+
+| Directory    | Files         | Description                                                                                                                                                                                                                                                      |
+| ------------ | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `request/`   | 8 translators | Convert request bodies between formats. Each file self-registers via `register(from, to, fn)` on import.                                                                                                                                                         |
+| `response/`  | 7 translators | Convert streaming response chunks between formats. Handles SSE event types, thinking blocks, tool calls.                                                                                                                                                         |
+| `helpers/`   | 6 helpers     | Shared utilities: `claudeHelper` (system prompt extraction, thinking config), `geminiHelper` (parts/contents mapping), `openaiHelper` (format filtering), `toolCallHelper` (ID generation, missing response injection), `maxTokensHelper`, `responsesApiHelper`. |
+| `index.ts`   | —             | Translation engine: `translateRequest()`, `translateResponse()`, state management, registry.                                                                                                                                                                     |
+| `formats.ts` | —             | Format constants: `OPENAI`, `CLAUDE`, `GEMINI`, `ANTIGRAVITY`, `KIRO`, `CURSOR`, `OPENAI_RESPONSES`.                                                                                                                                                             |
+
+#### Key Design: Self-Registering Plugins
+
+```javascript
+// Each translator file calls register() on import:
+import { register } from "../index.js";
+register("claude", "openai", translateClaudeToOpenAI);
+
+// The index.js imports all translator files, triggering registration:
+import "./request/claude-to-openai.js"; // ← self-registers
+```
+
+---
+
+### 4.6 Utils (`open-sse/utils/`)
+
+| File               | Purpose                                                                                                                                                                                                                                                                              |
+| ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `error.ts`         | Error response building (OpenAI-compatible format), upstream error parsing, Antigravity retry-time extraction from error messages, SSE error streaming.                                                                                                                              |
+| `stream.ts`        | **SSE Transform Stream** — the core streaming pipeline. Two modes: `TRANSLATE` (full format translation) and `PASSTHROUGH` (normalize + extract usage). Handles chunk buffering, usage estimation, content length tracking. Per-stream encoder/decoder instances avoid shared state. |
+| `streamHelpers.ts` | Low-level SSE utilities: `parseSSELine` (whitespace-tolerant), `hasValuableContent` (filters empty chunks for OpenAI/Claude/Gemini), `fixInvalidId`, `formatSSE` (format-aware SSE serialization with `perf_metrics` cleanup).                                                       |
+| `usageTracking.ts` | Token usage extraction from any format (Claude/OpenAI/Gemini/Responses), estimation with separate tool/message char-per-token ratios, buffer addition (2000 tokens safety margin), format-specific field filtering, console logging with ANSI colors.                                |
+| `requestLogger.ts` | Legacy file-based request logging helper kept for compatibility. Current deployments should prefer `APP_LOG_TO_FILE` for application logs and the call log pipeline for persisted request artifacts.                                                                                 |
+| `bypassHandler.ts` | Intercepts specific patterns from Claude CLI (title extraction, warmup, count) and returns fake responses without calling any provider. Supports both streaming and non-streaming. Intentionally limited to Claude CLI scope.                                                        |
+| `networkProxy.ts`  | Resolves outbound proxy URL for a given provider with precedence: provider-specific config → global config → environment variables (`HTTPS_PROXY`/`HTTP_PROXY`/`ALL_PROXY`). Supports `NO_PROXY` exclusions. Caches config for 30s.                                                  |
+
+#### SSE Streaming Pipeline
+
+```mermaid
+flowchart TD
+    A["Provider SSE stream"] --> B["TextDecoder\n(per-stream instance)"]
+    B --> C["Buffer lines\n(split on newline)"]
+    C --> D["parseSSELine()\n(trim whitespace, parse JSON)"]
+    D --> E{"Mode?"}
+    E -->|TRANSLATE| F["translateResponse()\ntarget → OpenAI → source"]
+    E -->|PASSTHROUGH| G["fixInvalidId()\nnormalize chunk"]
+    F --> H["hasValuableContent()\nfilter empty chunks"]
+    G --> H
+    H -->|"Has content"| I["extractUsage()\ntrack token counts"]
+    H -->|"Empty"| J["Skip chunk"]
+    I --> K["formatSSE()\nserialize + clean perf_metrics"]
+    K --> L["TextEncoder\n(per-stream instance)"]
+    L --> M["Enqueue to\nclient stream"]
+
+    style A fill:#f9f,stroke:#333
+    style M fill:#9f9,stroke:#333
+```
+
+#### Request Logger Session Structure
+
+```
+logs/
+└── claude_gemini_claude-sonnet_20260208_143045/
+    ├── 1_req_client.json      ← Raw client request
+    ├── 2_req_source.json      ← After initial conversion
+    ├── 3_req_openai.json      ← OpenAI intermediate format
+    ├── 4_req_target.json      ← Final target format
+    ├── 5_res_provider.txt     ← Provider SSE chunks (streaming)
+    ├── 5_res_provider.json    ← Provider response (non-streaming)
+    ├── 6_res_openai.txt       ← OpenAI intermediate chunks
+    ├── 7_res_client.txt       ← Client-facing SSE chunks
+    └── 6_error.json           ← Error details (if any)
+```
+
+---
+
+### 4.7 Application Layer (`src/`)
+
+| Directory     | Purpose                                                                |
+| ------------- | ---------------------------------------------------------------------- |
+| `src/app/`    | Web UI, API routes, Express middleware, OAuth callback handlers        |
+| `src/lib/`    | Database access (`localDb.ts`, `usageDb.ts`), authentication, shared   |
+| `src/mitm/`   | Man-in-the-middle proxy utilities for intercepting provider traffic    |
+| `src/models/` | Database model definitions                                             |
+| `src/shared/` | Wrappers around open-sse functions (provider, stream, error, etc.)     |
+| `src/sse/`    | SSE endpoint handlers that wire the open-sse library to Express routes |
+| `src/store/`  | Application state management                                           |
+
+#### Notable API Routes
+
+| Route                                         | Methods         | Purpose                                                                               |
+| --------------------------------------------- | --------------- | ------------------------------------------------------------------------------------- |
+| `/api/provider-models`                        | GET/POST/DELETE | CRUD for custom models per provider                                                   |
+| `/api/models/catalog`                         | GET             | Aggregated catalog of all models (chat, embedding, image, custom) grouped by provider |
+| `/api/settings/proxy`                         | GET/PUT/DELETE  | Hierarchical outbound proxy configuration (`global/providers/combos/keys`)            |
+| `/api/settings/proxy/test`                    | POST            | Validates proxy connectivity and returns public IP/latency                            |
+| `/v1/providers/[provider]/chat/completions`   | POST            | Dedicated per-provider chat completions with model validation                         |
+| `/v1/providers/[provider]/embeddings`         | POST            | Dedicated per-provider embeddings with model validation                               |
+| `/v1/providers/[provider]/images/generations` | POST            | Dedicated per-provider image generation with model validation                         |
+| `/api/settings/ip-filter`                     | GET/PUT         | IP allowlist/blocklist management                                                     |
+| `/api/settings/thinking-budget`               | GET/PUT         | Reasoning token budget configuration (passthrough/auto/custom/adaptive)               |
+| `/api/settings/system-prompt`                 | GET/PUT         | Global system prompt injection for all requests                                       |
+| `/api/sessions`                               | GET             | Active session tracking and metrics                                                   |
+| `/api/rate-limits`                            | GET             | Per-account rate limit status                                                         |
+
+---
+
+## 5. Key Design Patterns
+
+### 5.1 Hub-and-Spoke Translation
+
+All formats translate through **OpenAI format as the hub**. Adding a new provider only requires writing **one pair** of translators (to/from OpenAI), not N pairs.
+
+### 5.2 Executor Strategy Pattern
+
+Each provider has a dedicated executor class inheriting from `BaseExecutor`. The factory in `executors/index.ts` selects the right one at runtime.
+
+### 5.3 Self-Registering Plugin System
+
+Translator modules register themselves on import via `register()`. Adding a new translator is just creating a file and importing it.
+
+### 5.4 Account Fallback with Exponential Backoff
+
+When a provider returns 429/401/500, the system can switch to the next account, applying exponential cooldowns (1s → 2s → 4s → max 2min).
+
+### 5.5 Combo Model Chains
+
+A "combo" groups multiple `provider/model` strings. If the first fails, fallback to the next automatically.
+
+### 5.6 Stateful Streaming Translation
+
+Response translation maintains state across SSE chunks (thinking block tracking, tool call accumulation, content block indexing) via the `initState()` mechanism.
+
+### 5.7 Usage Safety Buffer
+
+A 2000-token buffer is added to reported usage to prevent clients from hitting context window limits due to overhead from system prompts and format translation.
+
+---
+
+## 6. Supported Formats
+
+| Format                  | Direction       | Identifier         |
+| ----------------------- | --------------- | ------------------ |
+| OpenAI Chat Completions | source + target | `openai`           |
+| OpenAI Responses API    | source + target | `openai-responses` |
+| Anthropic Claude        | source + target | `claude`           |
+| Google Gemini           | source + target | `gemini`           |
+| Antigravity             | source + target | `antigravity`      |
+| AWS Kiro                | target only     | `kiro`             |
+| Cursor                  | target only     | `cursor`           |
+
+---
+
+## 7. Supported Providers
+
+| Provider                 | Auth Method            | Executor    | Key Notes                                     |
+| ------------------------ | ---------------------- | ----------- | --------------------------------------------- |
+| Anthropic Claude         | API key or OAuth       | Default     | Uses `x-api-key` header                       |
+| Google Gemini            | API key or OAuth       | Default     | Uses `x-goog-api-key` header                  |
+| Antigravity              | OAuth                  | Antigravity | Multi-URL fallback, custom retry parsing      |
+| OpenAI                   | API key                | Default     | Standard Bearer auth                          |
+| Codex                    | OAuth                  | Codex       | Injects system instructions, manages thinking |
+| GitHub Copilot           | OAuth + Copilot token  | Github      | Dual token, VSCode header mimicking           |
+| Kiro (AWS)               | AWS SSO OIDC or Social | Kiro        | Binary EventStream parsing                    |
+| Cursor IDE               | Checksum auth          | Cursor      | Protobuf encoding, SHA-256 checksums          |
+| Qwen                     | OAuth                  | Default     | Standard auth                                 |
+| Qoder                    | OAuth (Basic + Bearer) | Default     | Dual auth header                              |
+| OpenRouter               | API key                | Default     | Standard Bearer auth                          |
+| GLM, Kimi, MiniMax       | API key                | Default     | Claude-compatible, use `x-api-key`            |
+| `openai-compatible-*`    | API key                | Default     | Dynamic: any OpenAI-compatible endpoint       |
+| `anthropic-compatible-*` | API key                | Default     | Dynamic: any Claude-compatible endpoint       |
+
+---
+
+## 8. Data Flow Summary
+
+### Streaming Request
+
+```mermaid
+flowchart LR
+    A["Client"] --> B["detectFormat()"]
+    B --> C["translateRequest()\nsource → OpenAI → target"]
+    C --> D["Executor\nbuildUrl + buildHeaders"]
+    D --> E["fetch(providerURL)"]
+    E --> F["createSSEStream()\nTRANSLATE mode"]
+    F --> G["parseSSELine()"]
+    G --> H["translateResponse()\ntarget → OpenAI → source"]
+    H --> I["extractUsage()\n+ addBuffer"]
+    I --> J["formatSSE()"]
+    J --> K["Client receives\ntranslated SSE"]
+    K --> L["logUsage()\nsaveRequestUsage()"]
+```
+
+### Non-Streaming Request
+
+```mermaid
+flowchart LR
+    A["Client"] --> B["detectFormat()"]
+    B --> C["translateRequest()\nsource → OpenAI → target"]
+    C --> D["Executor.execute()"]
+    D --> E["translateResponse()\ntarget → OpenAI → source"]
+    E --> F["Return JSON\nresponse"]
+```
+
+### Bypass Flow (Claude CLI)
+
+```mermaid
+flowchart LR
+    A["Claude CLI request"] --> B{"Match bypass\npattern?"}
+    B -->|"Title/Warmup/Count"| C["Generate fake\nOpenAI response"]
+    B -->|"No match"| D["Normal flow"]
+    C --> E["Translate to\nsource format"]
+    E --> F["Return without\ncalling provider"]
+```

docs/i18n/tr/docs/cloudflare-zero-trust-guide.md

@@ -1,103 +1,106 @@
-# Kapsamlı Kılavuz: Cloudflare Tunnel ve Zero Trust (Split-Port) (Türkçe)
+# Guia Completo: Cloudflare Tunnel & Zero Trust (Split-Port) (Türkçe)
 
 🌐 **Languages:** 🇺🇸 [English](../../../../docs/cloudflare-zero-trust-guide.md) · 🇪🇸 [es](../../es/docs/cloudflare-zero-trust-guide.md) · 🇫🇷 [fr](../../fr/docs/cloudflare-zero-trust-guide.md) · 🇩🇪 [de](../../de/docs/cloudflare-zero-trust-guide.md) · 🇮🇹 [it](../../it/docs/cloudflare-zero-trust-guide.md) · 🇷🇺 [ru](../../ru/docs/cloudflare-zero-trust-guide.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/cloudflare-zero-trust-guide.md) · 🇯🇵 [ja](../../ja/docs/cloudflare-zero-trust-guide.md) · 🇰🇷 [ko](../../ko/docs/cloudflare-zero-trust-guide.md) · 🇸🇦 [ar](../../ar/docs/cloudflare-zero-trust-guide.md) · 🇮🇳 [hi](../../hi/docs/cloudflare-zero-trust-guide.md) · 🇮🇳 [in](../../in/docs/cloudflare-zero-trust-guide.md) · 🇹🇭 [th](../../th/docs/cloudflare-zero-trust-guide.md) · 🇻🇳 [vi](../../vi/docs/cloudflare-zero-trust-guide.md) · 🇮🇩 [id](../../id/docs/cloudflare-zero-trust-guide.md) · 🇲🇾 [ms](../../ms/docs/cloudflare-zero-trust-guide.md) · 🇳🇱 [nl](../../nl/docs/cloudflare-zero-trust-guide.md) · 🇵🇱 [pl](../../pl/docs/cloudflare-zero-trust-guide.md) · 🇸🇪 [sv](../../sv/docs/cloudflare-zero-trust-guide.md) · 🇳🇴 [no](../../no/docs/cloudflare-zero-trust-guide.md) · 🇩🇰 [da](../../da/docs/cloudflare-zero-trust-guide.md) · 🇫🇮 [fi](../../fi/docs/cloudflare-zero-trust-guide.md) · 🇵🇹 [pt](../../pt/docs/cloudflare-zero-trust-guide.md) · 🇷🇴 [ro](../../ro/docs/cloudflare-zero-trust-guide.md) · 🇭🇺 [hu](../../hu/docs/cloudflare-zero-trust-guide.md) · 🇧🇬 [bg](../../bg/docs/cloudflare-zero-trust-guide.md) · 🇸🇰 [sk](../../sk/docs/cloudflare-zero-trust-guide.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/cloudflare-zero-trust-guide.md) · 🇮🇱 [he](../../he/docs/cloudflare-zero-trust-guide.md) · 🇵🇭 [phi](../../phi/docs/cloudflare-zero-trust-guide.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/cloudflare-zero-trust-guide.md) · 🇨🇿 [cs](../../cs/docs/cloudflare-zero-trust-guide.md) · 🇹🇷 [tr](../../tr/docs/cloudflare-zero-trust-guide.md)
 
 ---
 
-Bu kılavuz, **OmniRoute**'u korumak ve uygulamanızı **hiçbir gelen bağlantı portu açmadan (Zero Inbound)** internete güvenli bir şekilde sunmak için altın standart ağ altyapısını belgeler.
+Este guia documenta o padrão ouro de infraestrutura de rede para proteger o **OmniRoute** e expor sua aplicação de forma segura para a internet, **sem abrir nenhuma porta (Zero Inbound)**.
 
-## Sanal Makinenizde (VM) Ne Yapıldı?
+## O que foi feito na sua VM?
 
-OmniRoute'u PM2 aracılığıyla **Split-Port (Ayrık Port)** modunda etkinleştiriyoruz:
+Nós ativamos o OmniRoute em modo **Split-Port** através do PM2:
 
-- **Port `20128`:** **Yalnızca API** (`/v1`) çalıştırır.
-- **Port `20129`:** **Yalnızca görsel Yönetim Panosunu** çalıştırır.
+- **Porta \`20128\`:** Roda **apenas a API** `/v1`.
+- **Porta \`20129\`:** Roda **apenas o Dashboard** Administrativo visual.
 
-Ayrıca dahili servis `REQUIRE_API_KEY=true` gerektirir; bu da hiçbir ajanın Panonun API Keys sekmesinde oluşturulan geçerli bir "Bearer Token" göndermeden API uç noktalarını tüketemeyeceği anlamına gelir.
+Além disso, o serviço interno exige \`REQUIRE_API_KEY=true\`, o que significa que nenhum agente pode consumir os endpoints da API sem enviar um "Bearer Token" legítimo gerado na aba API Keys do Painel.
 
-Bu yapı ağda tamamen bağımsız iki kural oluşturmamıza olanak tanır. **Cloudflare Tunnel (cloudflared)** burada devreye girer.
+Isso nos permite criar duas regras completamente independentes na rede. É aqui que entra o **Cloudflare Tunnel (cloudflared)**.
 
 ---
 
-## 1. Cloudflare'de Tünel Oluşturma
+## 1. Como Criar o Túnel na Cloudflare
 
-`cloudflared` yardımcı programı makinenizde kuruludur. Bulut adımlarını izleyin:
+O utilitário \`cloudflared\` já está instalado na sua máquina. Siga os passos na nuvem:
 
-1. **Cloudflare Zero Trust** panonuza erişin (one.dash.cloudflare.com).
-2. Sol menüden **Networks > Tunnels** yolunu izleyin.
-3. **Add a Tunnel** seçeneğine tıklayın, **Cloudflared** seçin ve tünele `OmniRoute-VM` adını verin.
-4. Ekranda "Install and run a connector" başlıklı bir komut oluşturulacaktır. **Yalnızca Belirteci (`--token` sonrasındaki uzun dize) kopyalamanız yeterlidir**.
-5. Sanal makinenize SSH ile bağlanın ve çalıştırın:
-   ```bash
-   # Tüneli başlatır ve kalıcı olarak hesabınıza bağlar
-   cloudflared service install BURAYA_UZUN_TOKENINIZI_YAPISTIRIN
-   ```
+1. Acesse seu painel **Cloudflare Zero Trust** (One.dash.cloudflare.com).
+2. No menu à esquerda, vá em **Networks > Tunnels**.
+3. Clique em **Add a Tunnel**, escolha **Cloudflared** e dê o nome \`OmniRoute-VM\`.
+4. Ele vai gerar um comando na tela chamado "Install and run a connector". **Você só precisa copiar o Token (a string longa após `--token`)**.
+5. Logue via SSH na sua máquina virtual (ou Terminal do Proxmox) e execute:
+   \`\`\`bash
+   # Inicia e amarra o túnel permanentemente à sua conta
+   cloudflared service install SEU_TOKEN_GIGANTE_AQUI
+   \`\`\`
 
 ---
 
-## 2. Yönlendirmeyi Yapılandırma (Public Hostnames)
+## 2. Configurando o Roteamento (Public Hostnames)
 
-Yeni oluşturulan Tunnel ekranında **Public Hostnames** sekmesine gidin ve yaptığımız ayrımdan yararlanarak **iki** rotayı ekleyin:
+Ainda na tela do Tunnel recém-criado, vá para a aba **Public Hostnames** e adicione as **duas** rotas, aproveitando a separação que fizemos:
 
-### Rota 1: Güvenli API (Kısıtlı)
+### Rota 1: API Segura (Limitada)
 
-- **Subdomain:** `api`
-- **Domain:** `alanadiniz.com` (kendi gerçek alan adınızı seçin)
-- **Service Type:** `HTTP`
-- **URL:** `127.0.0.1:20128` _(Dahili API portu)_
+- **Subdomain:** \`api\`
+- **Domain:** \`seuglobal.com.br\` (escolha seu domínio real)
+- **Service Type:** \`HTTP\`
+- **URL:** \`127.0.0.1:20128\` _(Porta interna da API)_
 
-### Rota 2: Zero Trust Pano (Kapalı)
+### Rota 2: Painel Zero Trust (Fechado)
 
-- **Subdomain:** `omniroute` veya `panel`
-- **Domain:** `alanadiniz.com`
-- **Service Type:** `HTTP`
-- **URL:** `127.0.0.1:20129` _(Dahili Uygulama/Pano portu)_
+- **Subdomain:** \`omniroute\` ou \`painel\`
+- **Domain:** \`seuglobal.com.br\`
+- **Service Type:** \`HTTP\`
+- **URL:** \`127.0.0.1:20129\` _(Porta interna do App/Visual)_
+
+Neste momento, a conectividade "Física" está resolvida. Agora vamos blindar de verdade.
 
 ---
 
-## 3. Panoyu Zero Trust (Access) ile Güçlendirme
+## 3. Blindando o Painel com Zero Trust (Access)
 
-Hiçbir yerel şifre, panonuzu internete tamamen kapatmaktan daha iyi koruyamaz.
+Nenhuma senha local protege melhor o seu painel do que remover totalmente o acesso a ele da internet aberta.
 
-1. Zero Trust panosunda **Access > Applications > Add an application** seçeneğine gidin.
-2. **Self-hosted** seçin.
-3. **Application name** kısmına `OmniRoute Paneli` yazın.
-4. **Application domain** kısmına `omniroute.alanadiniz.com` ("Rota 2"de belirlediğiniz adres) yazın.
-5. **Next** butonuna tıklayın.
-6. **Rule action** için `Allow` seçin. Kural adına `Yalnızca Yönetici` yazın.
-7. **Include** altında "Selector" olarak `Emails` seçin ve e-posta adresinizi girin (örn. `admin@alanadiniz.com`).
-8. Kaydedin (`Add application`).
+1. No painel Zero Trust, vá em **Access > Applications > Add an application**.
+2. Selecione **Self-hosted**.
+3. Em **Application name**, coloque \`Painel OmniRoute\`.
+4. Em **Application domain**, coloque \`omniroute.seuglobal.com.br\` (O mesmo que você fez na "Rota 2").
+5. Clique em **Next**.
+6. Em **Rule action**, escolha \`Allow\`. Em nome da Rule coloque \`Admin Apenas\`.
+7. Em **Include**, no seletor de "Selector" escolha \`Emails\` e digite o seu email, por exemplo \`admin@spgeo.com.br\`.
+8. Salve (`Add application`).
 
-> **Bu ne sağladı:** Artık `omniroute.alanadiniz.com` adresini açtığınızda doğrudan uygulamanıza düşmez! Cloudflare'in e-posta isteyen şık bir giriş ekranı çıkar. Yalnızca belirttiğiniz e-posta girildiğinde, gelen kutunuza `20129` portuna tüneli açan tek kullanımlık 6 haneli bir kod gönderilir.
+> **O que isso fez:** Se você tentar abrir \`omniroute.seuglobal.com.br\`, não cai mais na sua aplicação OmniRoute! Cai numa tela elegante da Cloudflare pedindo para digitar seu email. Somente se você (ou o email que você botou) for digitado lá, ele recebe no Outlook/Gmail um código de 6 dígitos temporário que libera o túnel até a porta \`20129\`.
 
 ---
 
-## 4. API'yi Hız Sınırı (WAF) ile Korumak
+## 4. Limitando e Protegendo a API com Rate Limit (WAF)
 
-Zero Trust Panosu API rotasına (`api.alanadiniz.com`) uygulanmaz; çünkü bu tarayıcısız, otomatik araçlar (ajanlar) aracılığıyla yapılan programatik bir erişimdir. Bunun için Cloudflare'in ana Güvenlik Duvarını (WAF) kullanacağız.
+O Dashboard do Zero Trust não se aplica à rota da API (\`api.seuglobal.com.br\`), porque é um acesso programático via ferramentas automatizadas (agentes) sem navegador. Para ele, usaremos o Firewall principal (WAF) da Cloudflare.
 
-1. Cloudflare **Normal Panosuna** (dash.cloudflare.com) erişin ve Alan Adınıza girin.
-2. Sol menüden **Security > WAF > Rate limiting rules** yolunu izleyin.
-3. **Create rule** butonuna tıklayın.
-4. **Name:** `OmniRoute API Kötüye Kullanım Önleme`
+1. Acesse o **Painel Normal** da Cloudflare (dash.cloudflare.com) e entre no seu Domínio.
+2. No menu esquerdo, vá em **Security > WAF > Rate limiting rules**.
+3. Clique em **Create rule**.
+4. **Name:** \`Anti-Abuso OmniRoute API\`
 5. **If incoming requests match...**
-   - Field: `Hostname`
-   - Operator: `equals`
-   - Value: `api.alanadiniz.com`
-6. **With the same characteristics:** `IP` olarak bırakın.
-7. Sınırlar (Limit):
-   - **When requests exceed:** `50`
-   - **Period:** `1 minute`
-8. **Action:** `Block` seçin ve engelleme süresini belirleyin (1 dakika veya 1 saat).
+   - Escolha em Field: \`Hostname\`
+   - Operator: \`equals\`
+   - Value: \`api.seuglobal.com.br\`
+6. Em **With the same characteristics:** Mantenha \`IP\`.
+7. Nos limites (Limit):
+   - **When requests exceed:** \`50\`
+   - **Period:** \`1 minute\`
+8. No final, em **Action**: \`Block\` (Bloquear) e decida se o bloqueio dura por 1 minuto ou 1 hora.
 9. **Deploy**.
 
-> **Bu ne sağladı:** Hiç kimse API URL'nize 60 saniyelik bir süre içinde 50'den fazla istek gönderemez. Bu, trafiğin tünelden sunucunuza inmesine gerek kalmadan ağın kenarında (Edge Layer) sunucunuzu aşırı yükten korur.
+> **O que isso fez:** Ninguém pode mandar mais de 50 requisições num período de 60 segundos na sua URL de API. Como você roda vários agentes e os consumos por trás já batem rate limit e já rastreiam tokens, isso é apenas uma medida na Borda da Internet (Edge Layer) que protege sua Instância On-Premises de cair por estresse térmico antes mesmo do tráfego descer pelo túnel.
 
 ---
 
-## Özet
+## Finalização
 
-1. Sanal makinenizde güvenlik duvarında (`/etc/ufw`) **hiçbir açık gelen port bulunmaz**.
-2. OmniRoute yalnızca giden HTTPS (`cloudflared`) trafiğiyle haberleşir ve dünyadan doğrudan TCP bağlantısı almaz.
-3. Yönetim web panonuz e-posta tabanlı İki Faktörlü Doğrulama (2FA) ile korunur.
-4. API'niz Cloudflare tarafından sınırlandırılmıştır ve yalnızca Bearer Token'lar kabul edilir.
+1. A sua VM **não possui nenhuma porta exposta** em `/etc/ufw`.
+2. O OmniRoute só conversa HTTPS saindo (\`cloudflared\`) e não recebendo TCP direto do mundo.
+3. Seus requets pro OpenAI são ofuscados porque configuramos eles globalmente pra passar em um Proxy SOCKS5 (A nuvem não liga pro SOCKS5 porque ela vem Inbound).
+4. Seu painel web tem 2-Factor com Email.
+5. Sua API está ratelimitada na borda pela Cloudflare e só trafega Bearer Tokens.

docs/i18n/tr/docs/features/context-relay.md

@@ -4,54 +4,62 @@
 
 ---
 
-`context-relay`, konuşma tamamlanmadan önce aktif hesap değiştiğinde (rotasyon) oturum sürekliliğini koruyan bir kombo stratejisidir.
+`context-relay` is a combo strategy that keeps session continuity when the active account
+rotates before the conversation is finished.
 
-Mevcut çalışma zamanı model seçimi için öncelikli (priority) yönlendirme gibi davranır, ardından üzerine bir devir (handoff) katmanı ekler:
+The current runtime behaves like priority routing for model selection, then adds a
+handoff layer on top:
 
-- Aktif hesap tükenmeden önce OmniRoute kompakt ve yapılandırılmış bir özet üretir
-- Kimlik doğrulama aynı oturum için farklı bir hesap seçtikten sonra, OmniRoute bu özeti sonraki isteğe bir sistem mesajı olarak enjekte eder
-- Devir başarıyla tüketildiğinde depodan silinir
+- before the active account is exhausted, OmniRoute generates a compact structured summary
+- after authentication selects a different account for the same session, OmniRoute injects
+  that summary as a system message into the next request
+- once the handoff is consumed successfully, it is removed from storage
 
-## Ne Zaman Kullanılmalı
+## When To Use It
 
-Aşağıdakilerin tümü doğru olduğunda `context-relay` kullanın:
+Use `context-relay` when all of the following are true:
 
-- Kombonun aynı sağlayıcının birden çok hesabı arasında geçiş yapması bekleniyorsa
-- Kısa vadeli konuşma sürekliliğini kaybetmek görev kalitesine zarar verecekse
-- Sağlayıcı yaklaşan bir hesap sınırını tahmin etmek için yeterli kota bilgisi sunuyorsa
+- the combo is expected to rotate between multiple accounts of the same provider
+- losing short-term conversational continuity would hurt task quality
+- the provider exposes enough quota information to predict an approaching account limit
 
-Bu özellik, tek bir hesap penceresinden daha uzun sürebilecek uzun kodlama veya araştırma oturumları için son derece kullanışlıdır.
+This is most useful for long-running coding or research sessions that may outlive a single
+account window.
 
-## Çalışma Zamanı Akışı
+## Runtime Flow
 
-Mevcut davranış kasıtlı olarak iki çalışma zamanı katmanına ayrılmıştır.
+The current behavior is intentionally split across two runtime layers.
 
-### %0 ila %84 Kota Kullanımı
+### 0% to 84% quota used
 
-Hiçbir devir özeti üretilmez. İstekler normal öncelik yönlendirmesi gibi davranır.
+No handoff is generated. Requests behave like normal priority routing.
 
-### %85 ila %94 Kota Kullanımı
+### 85% to 94% quota used
 
-Aktif sağlayıcı `handoffProviders` içinde etkinleştirilmişse, OmniRoute hesap tamamen tükenmeden önce arka planda yapılandırılmış bir devir özeti üretir.
+If the active provider is enabled in `handoffProviders`, OmniRoute generates a structured
+handoff summary in the background before the account is fully exhausted.
 
-Önemli detaylar:
+Important details:
 
-- Varsayılan uyarı eşiği `0.85`'tir
-- Üretim için kesin durma noktası `0.95`'tir
-- `sessionId + comboName` başına yalnızca bir devam eden devir üretimine izin verilir
-- Bu oturum/kombo için zaten etkin bir devir varsa, mükerrer özet üretilmez
+- the default warning threshold is `0.85`
+- the hard stop for generation is `0.95`
+- only one in-flight handoff generation is allowed per `sessionId + comboName`
+- if an active handoff already exists for that session/combo, no duplicate summary is generated
 
-### %95 veya Daha Fazla Kota Kullanımı
+### 95% or more quota used
 
-Yeni bir devir üretilmez. Bu noktada sistem zaten tükenme sınırındadır veya tükenmiştir; çalışma zamanı başka bir özet isteği zamanlamaktan kaçınır.
+No new handoff is generated. At this point the system is already in or near exhaustion and
+the runtime avoids scheduling another summary request.
 
-### Hesap Rotasyonundan Sonra
+### After account rotation
 
-Aynı oturum için bir sonraki istek farklı bir kimliği doğrulanmış hesaba çözümlendiğinde, OmniRoute saklanan devir özetini bir sistem mesajı olarak başa ekler. Enjeksiyon yalnızca gerçek hesap değişikliği bilindikten sonra gerçekleşir.
+When the next request for the same session resolves to a different authenticated account,
+OmniRoute prepends the stored handoff as a system message. Injection happens only after the
+real account switch is known.
 
-## Devir Yükü (Handoff Payload)
+## Handoff Payload
 
-Kalıcı devir yükü `context_handoffs` tablosunda saklanır ve şunları içerir:
+The persisted handoff payload is stored in `context_handoffs` and includes:
 
 - `sessionId`
 - `comboName`
@@ -66,49 +74,57 @@ Kalıcı devir yükü `context_handoffs` tablosunda saklanır ve şunları içer
 - `generatedAt`
 - `expiresAt`
 
-Özet modeline şu yapıda bir JSON nesnesi döndürmesi talimatı verilir:
+The summary model is instructed to return a JSON object with this structure:
 
 ```json
 {
-  "summary": "Süreklilik için önemli olan konuların yoğun özeti",
-  "keyDecisions": ["Karar 1", "Karar 2"],
-  "taskProgress": "Ne yapıldı, ne bekliyor ve bir sonraki adım",
-  "activeEntities": ["dosyaA.ts", "özellik X", "sağlayıcı Y"]
+  "summary": "Dense summary of what matters for continuity",
+  "keyDecisions": ["Decision 1", "Decision 2"],
+  "taskProgress": "What is done, what is pending, and the next step",
+  "activeEntities": ["fileA.ts", "feature X", "provider Y"]
 }
 ```
 
-Enjeksiyon anında OmniRoute bu yükü bir `<context_handoff>` sistem mesajına dönüştürür; böylece sonraki hesap doğru yerel bağlamla devam edebilir.
+At injection time, OmniRoute converts that payload into a `<context_handoff>` system
+message so the next account can continue with the correct local context.
 
 ## Yapılandırma
 
-`context-relay` şu yapılandırma alanlarını destekler:
+`context-relay` supports these config fields:
 
-- `handoffThreshold`: Özet üretimi için uyarı eşiği, varsayılan `0.85`
-- `handoffModel`: Yalnızca özet üretimi için kullanılan isteğe bağlı model geçersiz kılma
-- `handoffProviders`: Devir üretimini tetiklemesine izin verilen sağlayıcıların izin listesi
+- `handoffThreshold`: warning threshold for summary generation, default `0.85`
+- `handoffModel`: optional model override used only for summary generation
+- `handoffProviders`: allowlist of providers allowed to trigger handoff generation
 
-Genel varsayılanlar Ayarlar sayfasında yapılandırılabilir ve kombo bazlı değerler bunları Kombolar sayfasında geçersiz kılabilir.
+Global defaults can be configured in Settings, and combo-specific values can override them
+in the Combos page.
 
-## Mimari Not
+## Architectural Note
 
-Mevcut uygulama bağımsız bir `handleContextRelayCombo` işleyicisi kullanmaz.
+The current implementation does not use a standalone `handleContextRelayCombo` handler.
 
-Bunun yerine:
+Instead:
 
-- `open-sse/services/combo.ts` başarılı bir turun devir üretip üretmeyeceğine karar verir
-- `src/sse/handlers/chat.ts` devir özetini yalnızca kimlik doğrulama istek için kullanılan gerçek hesabı belirledikten sonra enjekte eder
+- `open-sse/services/combo.ts` decides whether a successful turn should generate a handoff
+- `src/sse/handlers/chat.ts` injects the handoff only after authentication resolves the
+  actual account used for the request
 
-## Sınırlamalar
+This split is intentional in the current codebase because the combo loop alone does not know
+whether the request stayed on the same account or actually switched accounts.
 
-- Etkili çalışma zamanı desteği şu anda `codex` kota rotasyonu üzerinde yoğunlaşmıştır.
-- `handoffProviders` bir yapılandırma yüzeyi olarak modellenmiştir ancak gerçek devir üretimi hala sağlayıcıya özel kota altyapısına bağlıdır.
-- Özet kasıtlı olarak kompakt ve yakın geçmişe dayalıdır; tam bir konuşma geçmişi tekrar oynatma mekanizması değildir.
-- Devirler `sessionId + comboName` ile kapsama alınır ve otomatik olarak sona erer.
-- Oturum hesap değiştirmezse, saklanan devir enjekte edilmez.
+## Limitations
 
-## Önerilen Kullanım Modeli
+- Effective runtime support is currently centered on `codex` quota rotation.
+- `handoffProviders` is already modeled as a config surface, but real handoff generation
+  still depends on provider-specific quota plumbing.
+- The summary is intentionally compact and recent-history based; it is not a full transcript
+  replay mechanism.
+- Handoffs are scoped by `sessionId + comboName` and expire automatically.
+- If the session does not switch accounts, the stored handoff is not injected.
 
-- Aynı sağlayıcıdan birden fazla hesap kullanın
-- Oturum boyunca kararlı `sessionId` değerleri koruyun
-- Arka plan özet isteğine yer bırakmak için `handoffThreshold` değerini yeterince erken bir seviyeye ayarlayın
-- Bu özelliği kalıcı belleğin yerine geçen bir mekanizma olarak değil, bir süreklilik desteği olarak değerlendirin
+## Recommended Usage Pattern
+
+- use multiple accounts from the same provider
+- keep stable `sessionId` values across the session
+- set `handoffThreshold` early enough to leave room for the background summary request
+- treat the feature as continuity assistance, not as a replacement for persistent memory

docs/i18n/tr/docs/frameworks/A2A-SERVER.md

@@ -1,55 +1,38 @@
----
-title: "OmniRoute A2A Sunucu Dokümantasyonu"
-version: 3.8.50
-lastUpdated: 2026-08-23
----
+# OmniRoute A2A Server Documentation (Türkçe)
 
-# OmniRoute A2A Sunucu Dokümantasyonu (Türkçe)
-
-🌐 **Languages:** 🇺🇸 [English](../../../../docs/frameworks/A2A-SERVER.md) · 🇸🇦 [ar](../../ar/docs/frameworks/A2A-SERVER.md) · 🇧🇬 [bg](../../bg/docs/frameworks/A2A-SERVER.md) · 🇧🇩 [bn](../../bn/docs/frameworks/A2A-SERVER.md) · 🇨🇿 [cs](../../cs/docs/frameworks/A2A-SERVER.md) · 🇩🇰 [da](../../da/docs/frameworks/A2A-SERVER.md) · 🇩🇪 [de](../../de/docs/frameworks/A2A-SERVER.md) · 🇪🇸 [es](../../es/docs/frameworks/A2A-SERVER.md) · 🇮🇷 [fa](../../fa/docs/frameworks/A2A-SERVER.md) · 🇫🇮 [fi](../../fi/docs/frameworks/A2A-SERVER.md) · 🇫🇷 [fr](../../fr/docs/frameworks/A2A-SERVER.md) · 🇮🇳 [gu](../../gu/docs/frameworks/A2A-SERVER.md) · 🇮🇱 [he](../../he/docs/frameworks/A2A-SERVER.md) · 🇮🇳 [hi](../../hi/docs/frameworks/A2A-SERVER.md) · 🇭🇺 [hu](../../hu/docs/frameworks/A2A-SERVER.md) · 🇮🇩 [id](../../id/docs/frameworks/A2A-SERVER.md) · 🇮🇹 [it](../../it/docs/frameworks/A2A-SERVER.md) · 🇯🇵 [ja](../../ja/docs/frameworks/A2A-SERVER.md) · 🇰🇷 [ko](../../ko/docs/frameworks/A2A-SERVER.md) · 🇮🇳 [mr](../../mr/docs/frameworks/A2A-SERVER.md) · 🇲🇾 [ms](../../ms/docs/frameworks/A2A-SERVER.md) · 🇳🇱 [nl](../../nl/docs/frameworks/A2A-SERVER.md) · 🇳🇴 [no](../../no/docs/frameworks/A2A-SERVER.md) · 🇵🇭 [phi](../../phi/docs/frameworks/A2A-SERVER.md) · 🇵🇱 [pl](../../pl/docs/frameworks/A2A-SERVER.md) · 🇵🇹 [pt](../../pt/docs/frameworks/A2A-SERVER.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/frameworks/A2A-SERVER.md) · 🇷🇴 [ro](../../ro/docs/frameworks/A2A-SERVER.md) · 🇷🇺 [ru](../../ru/docs/frameworks/A2A-SERVER.md) · 🇸🇰 [sk](../../sk/docs/frameworks/A2A-SERVER.md) · 🇸🇪 [sv](../../sv/docs/frameworks/A2A-SERVER.md) · 🇰🇪 [sw](../../sw/docs/frameworks/A2A-SERVER.md) · 🇮🇳 [ta](../../ta/docs/frameworks/A2A-SERVER.md) · 🇮🇳 [te](../../te/docs/frameworks/A2A-SERVER.md) · 🇹🇭 [th](../../th/docs/frameworks/A2A-SERVER.md) · 🇹🇷 [tr](../../tr/docs/frameworks/A2A-SERVER.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/frameworks/A2A-SERVER.md) · 🇵🇰 [ur](../../ur/docs/frameworks/A2A-SERVER.md) · 🇻🇳 [vi](../../vi/docs/frameworks/A2A-SERVER.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/frameworks/A2A-SERVER.md)
+🌐 **Languages:** 🇺🇸 [English](../../../../docs/A2A-SERVER.md) · 🇸🇦 [ar](../../ar/docs/A2A-SERVER.md) · 🇧🇬 [bg](../../bg/docs/A2A-SERVER.md) · 🇧🇩 [bn](../../bn/docs/A2A-SERVER.md) · 🇨🇿 [cs](../../cs/docs/A2A-SERVER.md) · 🇩🇰 [da](../../da/docs/A2A-SERVER.md) · 🇩🇪 [de](../../de/docs/A2A-SERVER.md) · 🇪🇸 [es](../../es/docs/A2A-SERVER.md) · 🇮🇷 [fa](../../fa/docs/A2A-SERVER.md) · 🇫🇮 [fi](../../fi/docs/A2A-SERVER.md) · 🇫🇷 [fr](../../fr/docs/A2A-SERVER.md) · 🇮🇳 [gu](../../gu/docs/A2A-SERVER.md) · 🇮🇱 [he](../../he/docs/A2A-SERVER.md) · 🇮🇳 [hi](../../hi/docs/A2A-SERVER.md) · 🇭🇺 [hu](../../hu/docs/A2A-SERVER.md) · 🇮🇩 [id](../../id/docs/A2A-SERVER.md) · 🇮🇹 [it](../../it/docs/A2A-SERVER.md) · 🇯🇵 [ja](../../ja/docs/A2A-SERVER.md) · 🇰🇷 [ko](../../ko/docs/A2A-SERVER.md) · 🇮🇳 [mr](../../mr/docs/A2A-SERVER.md) · 🇲🇾 [ms](../../ms/docs/A2A-SERVER.md) · 🇳🇱 [nl](../../nl/docs/A2A-SERVER.md) · 🇳🇴 [no](../../no/docs/A2A-SERVER.md) · 🇵🇭 [phi](../../phi/docs/A2A-SERVER.md) · 🇵🇱 [pl](../../pl/docs/A2A-SERVER.md) · 🇵🇹 [pt](../../pt/docs/A2A-SERVER.md) · 🇧🇷 [pt-BR](../../pt-BR/docs/A2A-SERVER.md) · 🇷🇴 [ro](../../ro/docs/A2A-SERVER.md) · 🇷🇺 [ru](../../ru/docs/A2A-SERVER.md) · 🇸🇰 [sk](../../sk/docs/A2A-SERVER.md) · 🇸🇪 [sv](../../sv/docs/A2A-SERVER.md) · 🇰🇪 [sw](../../sw/docs/A2A-SERVER.md) · 🇮🇳 [ta](../../ta/docs/A2A-SERVER.md) · 🇮🇳 [te](../../te/docs/A2A-SERVER.md) · 🇹🇭 [th](../../th/docs/A2A-SERVER.md) · 🇹🇷 [tr](../../tr/docs/A2A-SERVER.md) · 🇺🇦 [uk-UA](../../uk-UA/docs/A2A-SERVER.md) · 🇵🇰 [ur](../../ur/docs/A2A-SERVER.md) · 🇻🇳 [vi](../../vi/docs/A2A-SERVER.md) · 🇨🇳 [zh-CN](../../zh-CN/docs/A2A-SERVER.md)
 
 ---
 
-> Agent-to-Agent Protokolü v0.3 — Akıllı bir yönlendirme ajanı olarak OmniRoute
+> Agent-to-Agent Protocol v0.3 — OmniRoute as an intelligent routing agent
 
-A2A yüzeyinin iki arayüzü vardır:
-
-- `POST /a2a` adresinde **JSON-RPC 2.0** (kurallı giriş noktası, `src/app/a2a/route.ts` içinde tanımlı).
-- Panolar ve araçlar için `/api/a2a/*` altında **REST** (durum, görev listesi, iptal).
-
-Görevler `A2ATaskManager` (`src/lib/a2a/taskManager.ts`, varsayılan 5 dakikalık TTL) tarafından izlenir. Yetenekler `src/lib/a2a/taskExecution.ts` içindeki `A2A_SKILL_HANDLERS` aracılığıyla dağıtılır.
-
-## Ajan Keşfi (Agent Discovery)
+## Agent Discovery
 
 ```bash
 curl http://localhost:20128/.well-known/agent.json
 ```
 
-OmniRoute'un yeteneklerini, becerilerini ve kimlik doğrulama gereksinimlerini açıklayan Ajan Kartını (Agent Card) döndürür.
+Returns the Agent Card describing OmniRoute's capabilities, skills, and authentication requirements.
 
 ---
 
-## Kimlik Doğrulama
+## Authentication
 
-Tüm `/a2a` istekleri `Authorization` başlığı aracılığıyla bir API anahtarı gerektirir:
+All `/a2a` requests require an API key via the `Authorization` header:
 
 ```
-Authorization: Bearer SIZIN_OMNIROUTE_API_ANAHTARINIZ
+Authorization: Bearer YOUR_OMNIROUTE_API_KEY
 ```
 
-Sunucuda hiçbir API anahtarı yapılandırılmamışsa, kimlik doğrulama atlanır.
-
-## Etkinleştirme
-
-A2A, **Uç Noktalar → A2A** anahtarıyla kontrol edilir ve varsayılan olarak devre dışıdır. Devre dışıyken, `GET /api/a2a/status` `status: "disabled"` ve `online: false` bildirir; `POST /a2a` çağrıları `-32000` JSON-RPC hata koduyla HTTP 503 döndürür.
+If no API key is configured on the server, authentication is bypassed.
 
 ---
 
-## JSON-RPC 2.0 Metotları
+## JSON-RPC 2.0 Methods
 
-### `message/send` — Eşzamanlı Yürütme
+### `message/send` — Synchronous Execution
 
-Bir yeteneğe mesaj gönderir ve tam yanıtı bekler.
+Sends a message to a skill and waits for the complete response.
 
 ```bash
 curl -X POST http://localhost:20128/a2a \
@@ -67,25 +50,151 @@ curl -X POST http://localhost:20128/a2a \
   }'
 ```
 
-### `message/stream` — SSE Akışı
+**Response:**
 
-`message/send` ile aynıdır ancak gerçek zamanlı akış için Server-Sent Events döndürür.
+```json
+{
+  "jsonrpc": "2.0",
+  "id": "1",
+  "result": {
+    "task": { "id": "uuid", "state": "completed" },
+    "artifacts": [{ "type": "text", "content": "..." }],
+    "metadata": {
+      "routing_explanation": "Selected claude-sonnet via provider \"anthropic\" (latency: 1200ms, cost: $0.003)",
+      "cost_envelope": { "estimated": 0.005, "actual": 0.003, "currency": "USD" },
+      "resilience_trace": [
+        { "event": "primary_selected", "provider": "anthropic", "timestamp": "..." }
+      ],
+      "policy_verdict": { "allowed": true, "reason": "within budget and quota limits" }
+    }
+  }
+}
+```
 
-### `tasks/get` — Görev Durumu Alma
+### `message/stream` — SSE Streaming
 
-`params.id` ile bir görevin durumunu, yapıtlarını ve yürütme meta verilerini sorgular.
+Same as `message/send` but returns Server-Sent Events for real-time streaming.
 
-### `tasks/cancel` — Görevi İptal Etme
+```bash
+curl -N -X POST http://localhost:20128/a2a \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer YOUR_KEY" \
+  -d '{
+    "jsonrpc": "2.0",
+    "id": "1",
+    "method": "message/stream",
+    "params": {
+      "skill": "smart-routing",
+      "messages": [{"role": "user", "content": "Explain quantum computing"}]
+    }
+  }'
+```
 
-Çalışan bir görevi iptal eder.
+**SSE Events:**
+
+```
+data: {"jsonrpc":"2.0","method":"message/stream","params":{"task":{"id":"...","state":"working"},"chunk":{"type":"text","content":"..."}}}
+
+: heartbeat 2026-03-03T17:00:00Z
+
+data: {"jsonrpc":"2.0","method":"message/stream","params":{"task":{"id":"...","state":"completed"},"metadata":{...}}}
+```
+
+### `tasks/get` — Query Task Status
+
+```bash
+curl -X POST http://localhost:20128/a2a \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer YOUR_KEY" \
+  -d '{"jsonrpc":"2.0","id":"2","method":"tasks/get","params":{"taskId":"TASK_UUID"}}'
+```
+
+### `tasks/cancel` — Cancel a Task
+
+```bash
+curl -X POST http://localhost:20128/a2a \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer YOUR_KEY" \
+  -d '{"jsonrpc":"2.0","id":"3","method":"tasks/cancel","params":{"taskId":"TASK_UUID"}}'
+```
 
 ---
 
-## Desteklenen A2A Yetenekleri (Skills)
+## Available Skills
 
-1. **`smart-routing`** — Akıllı yönlendirme ve çok sağlayıcılı geri dönüş ile mesaj gönderme.
-2. **`quota-management`** — Tüm bağlı sağlayıcılardaki kota durumunu ve sıfırlanma sürelerini kontrol etme.
-3. **`provider-discovery`** — Uygun sağlayıcıları ve modelleri yeteneklere göre listeleme.
-4. **`cost-analysis`** — Oturum veya zaman dilimi bazında maliyet analiz raporu alma.
-5. **`health-report`** — Sistem çalışma süresi, devre kesiciler ve sağlayıcı sağlık durumu.
-6. **`list-capabilities`** — Desteklenen tüm modelleri, komboları ve stratejileri listeleme.
+| Skill              | Description                                                                                                                     |
+| :----------------- | :------------------------------------------------------------------------------------------------------------------------------ |
+| `smart-routing`    | Routes prompts through OmniRoute's intelligent pipeline. Returns response with routing explanation, cost, and resilience trace. |
+| `quota-management` | Answers natural-language queries about provider quotas, suggests free combos, and provides quota rankings.                      |
+
+---
+
+## Task Lifecycle
+
+```
+submitted → working → completed
+                    → failed
+                    → cancelled
+```
+
+- Tasks expire after 5 minutes (configurable)
+- Terminal states: `completed`, `failed`, `cancelled`
+- Event log tracks every state transition
+
+---
+
+## Error Codes
+
+| Code   | Meaning                        |
+| :----- | :----------------------------- |
+| -32700 | Parse error (invalid JSON)     |
+| -32600 | Invalid request / Unauthorized |
+| -32601 | Method or skill not found      |
+| -32602 | Invalid params                 |
+| -32603 | Internal error                 |
+
+---
+
+## Integration Examples
+
+### Python (requests)
+
+```python
+import requests
+
+resp = requests.post("http://localhost:20128/a2a", json={
+    "jsonrpc": "2.0", "id": "1",
+    "method": "message/send",
+    "params": {
+        "skill": "smart-routing",
+        "messages": [{"role": "user", "content": "Hello"}]
+    }
+}, headers={"Authorization": "Bearer YOUR_KEY"})
+
+result = resp.json()["result"]
+print(result["artifacts"][0]["content"])
+print(result["metadata"]["routing_explanation"])
+```
+
+### TypeScript (fetch)
+
+```typescript
+const resp = await fetch("http://localhost:20128/a2a", {
+  method: "POST",
+  headers: {
+    "Content-Type": "application/json",
+    Authorization: "Bearer YOUR_KEY",
+  },
+  body: JSON.stringify({
+    jsonrpc: "2.0",
+    id: "1",
+    method: "message/send",
+    params: {
+      skill: "smart-routing",
+      messages: [{ role: "user", content: "Hello" }],
+    },
+  }),
+});
+const { result } = await resp.json();
+console.log(result.metadata.routing_explanation);
+```