diff --git a/changelog.d/fixes/12732-basereds-orphans-v3851.md b/changelog.d/fixes/12732-basereds-orphans-v3851.md
index 59989f8e95..35c230cd1b 100644
--- a/changelog.d/fixes/12732-basereds-orphans-v3851.md
+++ b/changelog.d/fixes/12732-basereds-orphans-v3851.md
@@ -1,5 +1,4 @@
-- **fix(sse):** the non-streaming leg stopped refreshing credentials after a `401`, dropped the body-derived rate-limit lock, and discarded the upstream error `code`/`type` — all lost when the provider execution pipeline was extracted. A Copilot token was never retried, `Please retry after 20s` never drained the runtime reservoir, and a config-class `422` (Antigravity missing project) degraded into a generic account cooldown ([#12732](https://github.com/diegosouzapw/OmniRoute/issues/12732))
+- **fix(sse):** the provider execution pipeline keeps the upstream error `code`/`type` again — both were lost when the non-streaming leg was extracted, so a config-class `422` (Antigravity missing project) degraded into a generic account cooldown instead of reaching the gate that recognises it ([#12732](https://github.com/diegosouzapw/OmniRoute/issues/12732))
 - **fix(db):** a legacy `call_logs` table no longer aborts startup — the provider-stats index is created after the column healing runs, not before it, so an install predating `request_type` opens instead of failing with `no such column` ([#12732](https://github.com/diegosouzapw/OmniRoute/issues/12732))
-- **fix(catalog):** a malformed row in the operator-writable custom-models blob no longer kills every `auto/*` pool, and operator custom models no longer leak into the live-sync reader and shadow a registry model with a parentless duplicate ([#12732](https://github.com/diegosouzapw/OmniRoute/issues/12732))
-- **fix(sse):** codex image generation no longer crashes reading fields off an upstream error body that error-boundary hardening had already sanitized ([#12732](https://github.com/diegosouzapw/OmniRoute/issues/12732))
-- **fix(tests):** realign four guards that the same day's merges left asserting the old behavior — the provider-count and reserved-prefix totals after GreenPT and EURouter, the GLM stream buffer slot that `#12925` turned from a dropped extra argument into a declared parameter, and the injection scan bound that `#13104` reshaped from a head-only window into head-plus-tail. Every guard keeps the invariant it was written to protect ([#12732](https://github.com/diegosouzapw/OmniRoute/issues/12732))
+- **fix(catalog):** a malformed row in the operator-writable custom-models blob no longer kills every `auto/*` pool ([#12732](https://github.com/diegosouzapw/OmniRoute/issues/12732))
+- **fix(tests):** realign the guards that the same day's merges left asserting the old behavior — the provider-count total after GreenPT and EURouter, the GLM stream buffer slot that `#12925` turned into a declared parameter, and the injection scan bound that `#13104` reshaped from a head-only window into head-plus-tail ([#12732](https://github.com/diegosouzapw/OmniRoute/issues/12732))
diff --git a/config/quality/file-size-baseline.json b/config/quality/file-size-baseline.json
index 2b322262dc..e5ac089c0e 100644
--- a/config/quality/file-size-baseline.json
+++ b/config/quality/file-size-baseline.json
@@ -1,4 +1,5 @@
 {
+  "_rebaseline_2026_09_14_13349_virtualfactory_custom_models_guard": "PR #13349 own growth: open-sse/services/autoCombo/virtualFactory.ts 1219->1230 (+11). The customModels key_value blob is operator-writable raw JSON, so a null or non-object row null-derefed every read and no auto/* pool could materialize; the builder now filters rows the same way catalog.ts already does. Irreducible at the read site. Covered by tests/unit/combo-auto-pool-visible-only.test.ts.",
   "_rebaseline_2026_09_11_12732_catalog_timeout_pin": "+1 in tests/unit/models-catalog-route.test.ts (1652->1653) for a single line: process.env.CATALOG_BUILD_TIMEOUT_MS. #12627 bounds a cold catalog build at 8s; beforeEach resets the catalog cache so every case in this file pays a cold build, and a tsx runner needs 10-13s under load — the file returned catalog_build_timeout instead of rows and oscillated between 1 and 10 failures per run, reddening the whole PR queue (base-red #12732). The bound itself stays covered by tests/unit/12627-catalog-inflight-timeout.test.ts. The file is already at its frozen ceiling, so the pin cannot be absorbed; structural shrink tracked in #3501.",
   "_rebaseline_2026_09_11_12945_image_only_model_guard": "PR #12945 own growth: open-sse/handlers/imageGeneration.ts 3259->3293 (+35/-1). The image-only-model guard the PR adds to clear its base-red: the handler now recognises a model that only serves image generation and answers before the chat path can mis-route it. Irreducible at this call site; the predicate itself lives outside the file. Landed as its own PR rather than on #12945 because that branch has a live worktree in another session and pushing to it would pull the branch out from under whoever is working it. Covered by the batch run: 203/208 with the 5 remaining failures reproducing on the pure tip.",
   "_rebaseline_2026_09_11_mergebatch_v3851_diego": "/merge-batch 2026-09-11 (v3.8.51), owner batch. open-sse/handlers/chatCore.ts 6144->6146 (+2): #13278 requires a Responses-shaped body before the native OpenAI-compatible passthrough (+1) and #13276 stops the reactive-compaction log from claiming a compaction when compression is disabled (+2/-1). Both are guard conditions at existing call sites, no new branching structure. open-sse/utils/stream.ts is deliberately NOT rebaselined: already 3115 > 3098 on the pure tip with zero contribution from this batch (base-red #12732, owned by /sweep-reds). Covered by 256 assertions across the batch's test files (246 node:test + 10 vitest).",
@@ -478,7 +479,7 @@
     "src/sse/services/auth.ts": 3542,
     "tests/unit/account-fallback-service.test.ts": 2453,
     "tests/unit/provider-validation-specialty.test.ts": 4656,
-    "open-sse/services/autoCombo/virtualFactory.ts": 1219,
+    "open-sse/services/autoCombo/virtualFactory.ts": 1230,
     "open-sse/services/combo/roundRobinCombo.ts": 1205
   },
   "_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.",
diff --git a/docs/i18n/km/llm.txt b/docs/i18n/km/llm.txt
index 708c2c2b03..52a6a31fc9 100644
--- a/docs/i18n/km/llm.txt
+++ b/docs/i18n/km/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 356 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 358 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
 
@@ -18,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.22.2 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 173 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 174 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -128,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 173 versioned SQL migration files
+│   │   │   └── migrations/       # 174 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **356 AI providers** with automatic format translation
+- **358 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 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, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -393,7 +393,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 173 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 174 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -437,7 +437,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 173 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 174 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
diff --git a/docs/i18n/kn/llm.txt b/docs/i18n/kn/llm.txt
index 4cded7a099..a7b779f8e4 100644
--- a/docs/i18n/kn/llm.txt
+++ b/docs/i18n/kn/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 356 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 358 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
 
@@ -18,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.22.2 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 173 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 174 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -128,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 173 versioned SQL migration files
+│   │   │   └── migrations/       # 174 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **356 AI providers** with automatic format translation
+- **358 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 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, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -393,7 +393,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 173 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 174 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -437,7 +437,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 173 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 174 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
diff --git a/docs/i18n/ml/llm.txt b/docs/i18n/ml/llm.txt
index b9a6c5a310..f83599c122 100644
--- a/docs/i18n/ml/llm.txt
+++ b/docs/i18n/ml/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 356 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 358 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
 
@@ -18,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.22.2 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 173 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 174 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -128,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 173 versioned SQL migration files
+│   │   │   └── migrations/       # 174 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **356 AI providers** with automatic format translation
+- **358 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 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, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -393,7 +393,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 173 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 174 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -437,7 +437,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 173 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 174 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
diff --git a/docs/i18n/my/llm.txt b/docs/i18n/my/llm.txt
index a60e2f044d..6356b493ac 100644
--- a/docs/i18n/my/llm.txt
+++ b/docs/i18n/my/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 356 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 358 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
 
@@ -18,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.22.2 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 173 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 174 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -128,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 173 versioned SQL migration files
+│   │   │   └── migrations/       # 174 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **356 AI providers** with automatic format translation
+- **358 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 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, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -393,7 +393,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 173 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 174 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -437,7 +437,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 173 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 174 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
diff --git a/docs/i18n/ne/llm.txt b/docs/i18n/ne/llm.txt
index a3c223785c..906e6e00a9 100644
--- a/docs/i18n/ne/llm.txt
+++ b/docs/i18n/ne/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 356 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 358 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
 
@@ -18,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.22.2 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 173 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 174 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -128,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 173 versioned SQL migration files
+│   │   │   └── migrations/       # 174 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **356 AI providers** with automatic format translation
+- **358 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 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, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -393,7 +393,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 173 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 174 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -437,7 +437,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 173 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 174 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
diff --git a/docs/i18n/or/llm.txt b/docs/i18n/or/llm.txt
index 82b705e87b..6e9ada54ad 100644
--- a/docs/i18n/or/llm.txt
+++ b/docs/i18n/or/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 356 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 358 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
 
@@ -18,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.22.2 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 173 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 174 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -128,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 173 versioned SQL migration files
+│   │   │   └── migrations/       # 174 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **356 AI providers** with automatic format translation
+- **358 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 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, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -393,7 +393,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 173 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 174 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -437,7 +437,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 173 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 174 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
diff --git a/docs/i18n/pa/llm.txt b/docs/i18n/pa/llm.txt
index a5708b380f..f8bb598a43 100644
--- a/docs/i18n/pa/llm.txt
+++ b/docs/i18n/pa/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 356 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 358 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
 
@@ -18,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.22.2 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 173 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 174 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -128,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 173 versioned SQL migration files
+│   │   │   └── migrations/       # 174 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **356 AI providers** with automatic format translation
+- **358 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 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, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -393,7 +393,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 173 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 174 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -437,7 +437,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 173 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 174 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
diff --git a/docs/i18n/si/llm.txt b/docs/i18n/si/llm.txt
index 0adc9ddd4e..89e681459d 100644
--- a/docs/i18n/si/llm.txt
+++ b/docs/i18n/si/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 356 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 358 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
 
@@ -18,7 +18,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 
 - **Runtime:** Node.js `>=22.22.2 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
 - **Framework:** Next.js 16 (App Router) with TypeScript 6
-- **Database:** SQLite via better-sqlite3 (local, zero-config, 173 migrations)
+- **Database:** SQLite via better-sqlite3 (local, zero-config, 174 migrations)
 - **State management:** Zustand (client), SQLite (server persistence)
 - **UI:** React 19, Tailwind CSS 4, Recharts for analytics, @lobehub/icons for 130+ provider SVG icons
 - **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
@@ -128,7 +128,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   ├── secrets.ts        # Secrets management
 │   │   │   ├── stateReset.ts     # State reset utilities
 │   │   │   ├── migrationRunner.ts # Schema migration runner
-│   │   │   └── migrations/       # 173 versioned SQL migration files
+│   │   │   └── migrations/       # 174 versioned SQL migration files
 │   │   ├── evals/                # Eval runner and scheduler
 │   │   ├── memory/               # Persistent conversational memory
 │   │   │   ├── extraction.ts     # Memory extraction from conversations
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **356 AI providers** with automatic format translation
+- **358 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 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, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -393,7 +393,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 8. **ProviderIcon component:** Unified icon system using `@lobehub/icons` (130+ SVG) with PNG fallback and generic icon fallback chain. Used on providers, dashboard, and agents pages.
 
-9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 173 SQL migrations.
+9. **DB architecture:** `localDb.ts` is a re-export layer only — real logic lives in 122 `src/lib/db/` modules with 174 SQL migrations.
 
 10. **Upstream headers:** Custom headers merged in executors after default auth; same header name replaces executor value. Forbidden header names in `src/shared/constants/upstreamHeaders.ts`.
 
@@ -437,7 +437,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
 
 4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
 
-5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 173 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
+5. **Database layer:** Operations go through `src/lib/db/` modules (122 domain-specific files, 174 migrations). `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module.
 
 6. **Tests** use Node.js built-in test runner + Vitest. Run `npm test`. Vitest for MCP/autoCombo (`npm run test:vitest`). Playwright for E2E (`npm run test:e2e`). Coverage gate: ratchet vs `quality-baseline.json`, absolute floor 60% statements/lines/functions/branches.
 
diff --git a/open-sse/handlers/chatCore/nonStreamingProviderLeg.ts b/open-sse/handlers/chatCore/nonStreamingProviderLeg.ts
index f270ee359d..ba17639af9 100644
--- a/open-sse/handlers/chatCore/nonStreamingProviderLeg.ts
+++ b/open-sse/handlers/chatCore/nonStreamingProviderLeg.ts
@@ -73,20 +73,6 @@ export interface ProviderLegInput {
     model: string;
     translatedBody: Record<string, unknown>;
   }) => Promise<ProviderExecutionOutcome>;
-  /**
-   * Persist the connection/model state a failed provider response implies
-   * (bans, cooldowns, quota lockouts, model lockouts). The streaming leg does
-   * this inline in chatCore; #12867 left the non-streaming leg without it, so
-   * chatCore wires the same routine here. Side effects only — never throws.
-   */
-  persistProviderFailureState?: (failure: {
-    statusCode: number;
-    message: string;
-    retryAfterMs: number | null;
-    upstreamBody: unknown;
-    responseHeaders: Headers;
-    connectionId: string;
-  }) => void | Promise<void>;
   setRequestWireState: (state: {
     translatedBody: Record<string, unknown>;
     effectiveModel: string;
@@ -425,23 +411,6 @@ export async function runNonStreamingProviderLeg(
               outcome.model || currentModel,
               outcome.result.status
             );
-        // The pipeline exhausted account rotation / model fallback, so this is
-        // the final verdict for this connection: persist the state it implies
-        // (ban, cooldown, quota or model lockout) exactly like the streaming leg.
-        if (input.persistProviderFailureState) {
-          try {
-            await input.persistProviderFailureState({
-              statusCode: outcome.result.status,
-              message: outcome.result.rawMessage || raw,
-              retryAfterMs: outcome.result.retryAfterMs ?? null,
-              upstreamBody: outcome.upstreamBody ?? null,
-              responseHeaders: outcome.result.response?.headers ?? new Headers(),
-              connectionId: outcome.connectionId || connectionId,
-            });
-          } catch {
-            // Best-effort state update; the error result must still be returned.
-          }
-        }
         const receipt = buildReceipt(input, {
           httpStatus: outcome.result.status,
           errorType: outcome.result.errorType ?? null,
diff --git a/open-sse/handlers/chatCore/providerExecutionPipeline.ts b/open-sse/handlers/chatCore/providerExecutionPipeline.ts
index 6a5a1c58be..f90a85d5ba 100644
--- a/open-sse/handlers/chatCore/providerExecutionPipeline.ts
+++ b/open-sse/handlers/chatCore/providerExecutionPipeline.ts
@@ -224,14 +224,22 @@ async function toOutcome(
   }
   let message = attempt.response.statusText || "upstream error";
   let body: unknown = attempt.transformedBody;
+  // #12867 dropped the upstream error code/type when this leg moved into the
+  // pipeline. Gates that key on both (isAntigravityMissingProjectError) then
+  // stopped firing, and a config-class 422 degraded into an account cooldown.
+  let upstreamCode: string | undefined;
+  let upstreamType: string | undefined;
   try {
     // clone() is the drain. sendProviderAttempt must not cancel() a streaming
     // non-2xx body before we get here (BYOP 422 / Codex 429 Retry-After).
     const text = await attempt.response.clone().text();
     try {
       body = JSON.parse(text);
-      const err = (body as { error?: { message?: unknown } } | null)?.error;
+      const err = (body as { error?: { message?: unknown; code?: unknown; type?: unknown } } | null)
+        ?.error;
       if (err && typeof err.message === "string" && err.message) message = err.message;
+      if (err && typeof err.code === "string" && err.code) upstreamCode = err.code;
+      if (err && typeof err.type === "string" && err.type) upstreamType = err.type;
     } catch {
       // Non-JSON upstream body (plain-text 429, HTML error page). parseUpstreamError
       // — the pre-pipeline path this replaced — surfaces the raw text as the message;
@@ -250,7 +258,13 @@ async function toOutcome(
     body,
     retryAfterMs: null,
   });
-  const result = createErrorResult(restatement.status, message, restatement.retryAfterMs);
+  const result = createErrorResult(
+    restatement.status,
+    message,
+    restatement.retryAfterMs,
+    upstreamCode,
+    upstreamType
+  );
   return {
     kind: "error",
     result: {
diff --git a/open-sse/handlers/imageGeneration.ts b/open-sse/handlers/imageGeneration.ts
index d0c6b8a434..8c3596e14d 100644
--- a/open-sse/handlers/imageGeneration.ts
+++ b/open-sse/handlers/imageGeneration.ts
@@ -262,31 +262,6 @@ function sanitizeImageProviderError(errorText: string): unknown {
   return sanitizeErrorMessage(errorText);
 }
 
-/**
- * Flatten an arbitrary error payload into a call-log string.
- *
- * `sanitizeUpstreamDetails()` builds its objects with `Object.create(null)`
- * (#12506, prototype-pollution hardening), so a bare `String(value)` on a
- * sanitized upstream body throws `TypeError: Cannot convert object to
- * primitive value`. Serialize objects as JSON — the same shape the provider
- * handlers already log — and keep `String()` for primitives and Errors.
- */
-function stringifyImageErrorForLog(error: unknown): string {
-  if (typeof error === "string") return error;
-  if (error !== null && typeof error === "object" && !(error instanceof Error)) {
-    try {
-      return JSON.stringify(error) ?? "";
-    } catch {
-      return "[unserializable error]";
-    }
-  }
-  try {
-    return String(error);
-  } catch {
-    return "[unserializable error]";
-  }
-}
-
 // #8307 — some ChatGPT accounts can run Codex but lack entitlement for the specific
 // requested image model. Upstream signals this as a 400 with an exact, stable message
 // (not a generic "invalid request"). Classify it so the caller can mark the failure
diff --git a/tests/unit/custom-models-live-catalog-12597.test.ts b/tests/unit/custom-models-live-catalog-12597.test.ts
index b81745aeb9..da30364d76 100644
--- a/tests/unit/custom-models-live-catalog-12597.test.ts
+++ b/tests/unit/custom-models-live-catalog-12597.test.ts
@@ -19,12 +19,8 @@ const {
   replaceSyncedAvailableModelsForConnection,
   getActiveProvidersWithSyncedModel,
 } = await import("../../src/lib/db/models.ts");
-const {
-  getActiveSyncedCatalog,
-  getAllActiveSyncedModels,
-  catalogContainsModel,
-  reconcileProvidersWithActiveSyncedCatalog,
-} = await import("../../src/lib/db/models/activeSyncedCatalog.ts");
+const { getActiveSyncedCatalog, catalogContainsModel, reconcileProvidersWithActiveSyncedCatalog } =
+  await import("../../src/lib/db/models/activeSyncedCatalog.ts");
 
 const PROVIDER = "github";
 const CONNECTION_ID = "github-live-catalog-12597";
@@ -128,21 +124,6 @@ test("#12597 sparse custom overlay does not wipe synced capability fields", asyn
   assert.deepEqual(match?.supportedThinkingEfforts, ["low", "high"]);
 });
 
-test("#12597 the union is dispatch-only — getAllActiveSyncedModels stays live-sync-shaped", async () => {
-  await addCustomModel(PROVIDER, PICKER_MODEL, "DeepSeek R1 via picker");
-
-  const allActive = await getAllActiveSyncedModels();
-  const ids = (allActive[PROVIDER] ?? []).map((model) => model.id);
-
-  assert.deepEqual(
-    ids,
-    [SYNCED_MODEL],
-    "getAllActiveSyncedModels reports what the provider's live sync returned; its consumers (/v1/models' synced loop, /api/models' exclusive-listing suppression, getSyncedAutoAliases) each handle custom rows on their own"
-  );
-  // The dispatch-time readers still see it — that is what #12597 fixed.
-  assert.equal(catalogContainsModel(await getActiveSyncedCatalog(PROVIDER), PICKER_MODEL), true);
-});
-
 test("#12597 without a custom row the picker id is still absent (lock the old contract)", async () => {
   const catalog = await getActiveSyncedCatalog(PROVIDER);
   assert.equal(catalogContainsModel(catalog, PICKER_MODEL), false);