docs(compression): document the output-style catalog and its extension point (#10649)

The five output styles (terse-prose, less-code, ponytail, i-have-adhd,
terse-cjk) shipped in Phase 4 but COMPRESSION_GUIDE.md had zero mention of
them. Add the catalog table with per-style language coverage, the injection
contract (catalog order, single marker, shared boundaries once), the config
shape and back-compat note, plus an 'Adding an Output Style' recipe in
EXTENDING_COMPRESSION.md covering the matrix guard and translation floor.

Refs #10426

Co-authored-by: Xiangzhe <bakryun0718@proton.me>

.env.example

@@ -1648,6 +1648,16 @@ APP_LOG_TO_FILE=true
 # Used by: src/shared/constants/featureFlagDefinitions.ts, src/lib/arenaEloSync.ts
 # ARENA_ELO_SYNC_ENABLED=true
 
+# How model ids are prefixed in GET /v1/models. "dual" (default) advertises BOTH the
+# short alias prefix and the canonical provider prefix for each model (cc/claude-sonnet-4-6
+# AND claude/claude-sonnet-4-6) so client configs that hardcoded either form keep working —
+# which roughly doubles the catalog. "alias" emits one id per model; "canonical" emits only
+# the full provider-id prefix (and drops providers whose alias is already canonical).
+# A client can override per request with GET /v1/models?prefix=alias instead.
+# Also configurable from Dashboard > Settings > Feature Flags.
+# Used by: src/shared/constants/featureFlagDefinitions.ts, src/app/api/v1/models/catalog.ts
+# MODELS_CATALOG_PREFIX_MODE=dual
+
 # Sync interval in seconds.  Default: 86400 (24 hours).
 # ARENA_ELO_SYNC_INTERVAL=86400
 

AGENTS.md

@@ -433,6 +433,7 @@ For any non-trivial change, read the matching deep-dive first:
 | Provider catalog (auto-generated)             | `docs/reference/PROVIDER_REFERENCE.md`                  |
 | Tunnels                                       | `docs/ops/TUNNELS_GUIDE.md`                             |
 | Electron desktop app                          | `docs/guides/ELECTRON_GUIDE.md`                         |
+| VS Code Copilot Chat (OmniCopilot extension)  | `docs/guides/VSCODE-COPILOT.md`                         |
 | Release flow                                  | `docs/ops/RELEASE_CHECKLIST.md`                         |
 | Embedded services                             | `docs/frameworks/EMBEDDED-SERVICES.md`                  |
 | Quality gates (~80 scripts, allowlist policy) | `docs/architecture/QUALITY_GATES.md`                    |

README.md

@@ -737,6 +737,8 @@ From inside the editor: open the **Extensions** view, search **"OmniRoute"**, cl
 — works the same way on both stores. Source, issues and the publishing runbook live at
 [diegosouzapw/OmniCopilot](https://github.com/diegosouzapw/OmniCopilot).
 
+<sub>📖 [VS Code Copilot Chat guide](docs/guides/VSCODE-COPILOT.md) — setup, what the picker shows, dashboard-in-a-tab, troubleshooting</sub>
+
 <br/>
 
 <div align="center">

config/quality/file-size-baseline.json

@@ -446,7 +446,8 @@
     "open-sse/vendor/codex-chatgpt-web/bridge.ts": 1387,
     "_rebaseline_2026_08_11_v3850_merge_storm_provider_registry": "DRIFT do merge-storm 2026-08-11 (99 PRs mergeados no release/v3.8.50). AddApiKeyModal.tsx (PR #8949 ChatGPT Web provider) e useProviderConnections.ts/ModelSelectModal.tsx (PRs #9011 combo test-all, #9499 image combos) = UI nova legitima acima do cap; gateways.ts = god-file de catalogo de providers que cresceu com PRs #9009/#9421/#9468/#9594 (qualquer split arriscaria corromper o merge de novo — o proprio PR #9421 quebrou o arquivo); bridge.ts (PR #8949) = ponte Chromium vendored; proxyFetch.ts 1207->1220 = drift herdado de merges. Owner autorizou rebaseline com anotacao (2026-08-11).",
     "src/lib/modelCapabilities.ts": 1006,
-    "src/app/(dashboard)/dashboard/providers/[id]/providerPageHelpers.ts": 1014
+    "src/app/(dashboard)/dashboard/providers/[id]/providerPageHelpers.ts": 1014,
+    "open-sse/config/imageRegistry.ts": 1019
   },
   "_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).",
@@ -610,5 +611,6 @@
   "_rebaseline_2026_08_12_v3850_basereds_round3": "Base-reds round 3 (#9985, 2026-08-12): ModelSelectModal.tsx 1135->1138 = base drift from the #10198 SWR/build repair (flagged as non-blocking drift by Release-Green run 31634993212, rebaselined here so the PR queue's Fast Quality Gates stop failing on inherited drift); gateways.ts 1215->1250 = base drift from the 08-12 merges (#10131 regolo/naga-ac repair, #9210 void-ai+helixmind) plus this PR restoring the chatanywhere metadata entry that round 2 dropped along with its duplicate (wave3 audited entry, +16 lines; same god-file no-split rationale as the 2026-08-11 annotation). Owner-authorized sweep (/sweep-reds).",
   "_rebaseline_2026_08_12_proxyfetch_redaction": "Base-reds round 3 (#9985): proxyFetch.ts 1220->1239 (+19) = redactProxyDetailsInMessage() helper closing the credential leak #10032 reintroduced (raw proxy URL with user:password appended to the propagated error, Hard Rule #12); irreducible security fix at the existing error-surface chokepoint. Covered by tests/unit/tls-proxy-context.test.ts (strengthened leak guards).",
   "_rebaseline_2026_08_12_modelcapabilities_snapshot_routing": "Base-reds round 3 (#9985): modelCapabilities.ts crossed the new-file cap at 1006 (+~10) when the context/max-input-token override lookups were routed through the #9199 bulk snapshot (fixing 323 per-model SQLite reads per catalog prepare — auto-combo-context-advertising guard); cohesive change at the existing resolution chokepoints, not extractable. Covered by tests/unit/auto-combo-context-advertising.test.ts + model-capability-resolution-snapshot-9199.test.ts.",
-  "_rebaseline_2026_08_14_imagetotext_servicekinds": "Image-to-Text category (#10275/#10291): gateways.ts grew 1250→1255 by data lines only — the serviceKinds: [\"llm\", \"imageToText\"] declarations on the openrouter and chutes catalog entries, plus the 3-line comment recording why chutes needs no static dots.ocr entry (passthroughModels discovery). No new logic or branching; the file is a provider catalog of declarative metadata. Splitting a catalog for five lines would be worse than the growth (semantic-families rule)."
+  "_rebaseline_2026_08_14_imagetotext_servicekinds": "Image-to-Text category (#10275/#10291): gateways.ts grew 1250→1255 by data lines only — the serviceKinds: [\"llm\", \"imageToText\"] declarations on the openrouter and chutes catalog entries, plus the 3-line comment recording why chutes needs no static dots.ocr entry (passthroughModels discovery). No new logic or branching; the file is a provider catalog of declarative metadata. Splitting a catalog for five lines would be worse than the growth (semantic-families rule).",
+  "_rebaseline_2026_08_18_imageregistry_merge_train": "merge-train 2026-08-18 (owner-authorized, /merge-prs batch of 84): open-sse/config/imageRegistry.ts crossed the 1000-line new-file cap for the first time purely from combining three independent, already-legitimate provider registrations boarded in the same local merge-train — #10542 (aihorde optional-key image catalog), #10494 (gemini-web image generation), #10594 (freepik/magnific provider rename + validation). 996 on release tip -> 1019 on the train tip. Each PR individually adds a small, additive IMAGE_PROVIDERS registry entry at the existing chokepoint; none crosses the cap alone. Not modularized as part of this train's gate fix (out of scope for a merge reconciliation, not a feature change). Covered by each PR's own focused tests (aihorde-image-catalog/generation, gemini-web image tests, freepik/magnific provider tests)."
 }

docs/compression/COMPRESSION_GUIDE.md

@@ -446,6 +446,60 @@ Caveman output mode is **opt-in** — set it via the combo config:
 }
 ```
 
+### Output Styles (catalog)
+
+Caveman output mode above is the **legacy single-style path**. Phase 4 generalized it
+into a catalog of composable output styles: `OUTPUT_STYLE_CATALOG` in
+`open-sse/services/compression/outputStyles/catalog.ts`. Each style is a system-prompt
+instruction that makes the model itself produce cheaper output; styles can be enabled
+together and are injected in catalog order.
+
+| Style | `id` | What it does | Instruction languages |
+| --- | --- | --- | --- |
+| Terse prose | `terse-prose` | Drop filler/articles/hedging; keep technical substance exact. Same text as the legacy caveman output mode (referenced, not re-typed). | en, pt-BR, ja, id |
+| Less code | `less-code` | YAGNI ladder: smallest working change, no unrequested abstractions. | en only (backlog: [#10426](https://github.com/diegosouzapw/OmniRoute/issues/10426)) |
+| Ponytail (lazy senior dev) | `ponytail` | "The best code is the code never written": reuse > rewrite, root cause > symptom, shortest working diff. | en, pt-BR, vi, ja, id |
+| I have ADHD (action-first) | `i-have-adhd` | Action first (command/path/snippet before prose), numbered bounded steps, ONE concrete next step, no preamble/recap/closers. Adapted from [ayghri/i-have-adhd](https://github.com/ayghri/i-have-adhd) (MIT). | en, pt-BR, vi, ja, id |
+| Terse CJK (文言) | `terse-cjk` | Classical-Chinese ultra-terse style. | zh (locale-gated: only offered when the detected language is `zh`) |
+
+Every style ships three intensity levels — `lite`, `full`, `ultra` — and every level
+ends with the shared boundaries clause, which keeps code blocks, file paths, commands,
+error strings, URLs and identifiers verbatim.
+
+#### How injection works
+
+`applyOutputStyles()` (`open-sse/services/compression/outputStyles/apply.ts`) resolves
+the selection against the catalog (unknown ids and locale-mismatched styles are
+dropped, never an error), concatenates the selected instructions in catalog order,
+appends the boundaries clause **once**, and front-loads the result into the system
+prompt behind a single idempotency marker (`[OmniRoute Output Styles]`) — re-applying
+is a no-op. When the detected request language has a translation, the localized
+instruction is injected instead of English.
+
+#### How to enable
+
+In the dashboard: **Context → Settings → Compression** — one row per style with an
+on/off toggle and a level selector. Programmatically, the compression config persists
+the selection as:
+
+```json
+{
+  "outputStyles": [
+    { "id": "i-have-adhd", "level": "full" },
+    { "id": "less-code", "level": "lite" }
+  ]
+}
+```
+
+Back-compat: the legacy `outputMode: "caveman"` combo setting still works and maps to
+`terse-prose`, byte-identical to the old injection in all four legacy languages.
+
+The style × language matrix is pinned by
+`tests/unit/compression/output-styles-i18n-matrix.test.ts`: a new style cannot ship
+without at least a pt-BR translation (or an explicit tracked exception), and an
+existing style cannot silently lose a locale. To add a style, see
+[EXTENDING_COMPRESSION.md](./EXTENDING_COMPRESSION.md#adding-an-output-style).
+
 ### Tool Result Compression
 
 The `toolResultCompressor.ts` module provides **5 specialized compression strategies**

docs/compression/EXTENDING_COMPRESSION.md

@@ -568,6 +568,40 @@ gate (`check:compression-budget`).
 
 ---
 
+## Adding an Output Style
+
+Output styles (see the [guide's catalog table](./COMPRESSION_GUIDE.md#output-styles-catalog))
+are the response-side counterpart of the input engines: instead of compressing what you
+send, they instruct the model to produce cheaper output. The registry is
+`OUTPUT_STYLE_CATALOG` in `open-sse/services/compression/outputStyles/catalog.ts`, and
+**one catalog entry is the entire feature**: the injector, the dashboard settings panel,
+persistence and telemetry all enumerate the catalog — there is no other list to update.
+
+1. **Add one entry to `OUTPUT_STYLE_CATALOG`** with `id`, `label`, `description` and the
+   three English `levels` (`lite`, `full`, `ultra`). Every level must end with
+   `${SHARED_BOUNDARIES}` so code, paths, commands, errors and URLs stay verbatim.
+   The instruction text must be **static and deterministic** per
+   `(id, level, language)` — `${SHARED_BOUNDARIES}` is the only interpolation allowed.
+2. **Translate it.** Ship at least a `pt-BR` block under `i18n`; `ponytail` and
+   `i-have-adhd` (en, pt-BR, vi, ja, id) are the reference shape. A deliberately
+   single-language style sets `locale` instead (like `terse-cjk` → `zh`) and is then
+   only offered under that locale.
+3. **Update the matrix guard** — add the style's languages to `BASELINE_LANGUAGES` in
+   `tests/unit/compression/output-styles-i18n-matrix.test.ts`. The gate fails any new
+   non-locale-gated style without the required translations unless it carries an
+   explicit `KNOWN_ENGLISH_ONLY` entry with a tracking issue.
+4. **Add a per-style test** modeled on
+   `tests/unit/compression/i-have-adhd-catalog.test.ts`: catalog shape, boundaries
+   clause per level, and an anchor asserting each translation is written in its own
+   language rather than copied English.
+5. **Attribution**: if the style is adapted from an upstream project, credit it in a
+   source comment on the entry (e.g. `i-have-adhd` → ayghri/i-have-adhd, MIT) — same
+   rule as "Proposing an upstream-inspired improvement" above.
+
+No UI, schema or telemetry change is needed — those surfaces render from the catalog.
+
+---
+
 ## Best Practices
 
 ### Engine Development

docs/guides/CLI-INTEGRATIONS.md

@@ -24,6 +24,8 @@ per-tool deep dives:
 - [Claude Code configuration](./CLAUDE-CODE-CONFIGURATION.md)
 - [Codex CLI configuration](./CODEX-CLI-CONFIGURATION.md)
 - [Remote Mode](./REMOTE-MODE.md) — drive a remote OmniRoute (VPS / Tailnet) from your laptop
+- [VS Code Copilot Chat](./VSCODE-COPILOT.md) — the OmniCopilot extension; it can also run these
+  `setup-*` commands for you from inside the editor
 
 ---
 

docs/guides/VSCODE-COPILOT.md

@@ -0,0 +1,138 @@
+---
+title: "VS Code Copilot Chat — OmniCopilot extension"
+version: 3.8.50
+lastUpdated: 2026-08-18
+---
+
+# VS Code Copilot Chat — OmniCopilot extension
+
+**OmniCopilot** puts every model your OmniRoute serves into the *native* GitHub Copilot Chat
+model picker. No second sidebar, no separate chat UI — Copilot's agent mode, tool calling,
+MCP servers and custom instructions all keep working, just running on the model you pick.
+
+| | |
+| --- | --- |
+| **Install (VS Code)** | [Marketplace → `diegosouzapw.omnicopilot`](https://marketplace.visualstudio.com/items?itemName=diegosouzapw.omnicopilot) |
+| **Install (forks)** | [Open VSX](https://open-vsx.org/extension/diegosouzapw/omnicopilot) — Cursor, Windsurf, VSCodium, Theia, code-server, Gitpod, Antigravity, Kiro |
+| **Source / issues** | [github.com/diegosouzapw/OmniCopilot](https://github.com/diegosouzapw/OmniCopilot) (MIT) |
+| **Requires** | VS Code 1.104+ |
+
+> **No Copilot subscription needed.** Since VS Code 1.122 a language-model provider works
+> without a GitHub sign-in and without any Copilot plan. Inline completions and
+> embeddings-based features stay outside the provider API and still require Copilot.
+
+---
+
+## Setup
+
+1. **Run OmniRoute** — `npm install -g omniroute && omniroute` (dashboard on `http://localhost:20128`).
+2. **Install the extension** — search "OmniRoute" in the Extensions view.
+3. **Pick a model** — Copilot Chat → model picker → **Manage Models…** → **OmniRoute**, then tick
+   what you want.
+
+Nothing to configure when OmniRoute runs on the default port. For a remote instance, open the
+**OmniRoute icon in the Activity Bar** (or run `OmniRoute: Manage Connection`) and set:
+
+- **Server URL** — the server root, e.g. `http://192.168.0.15:20128`. The `/v1` suffix is
+  appended by the extension; do not include it.
+- **API key** — only when the server sets `REQUIRE_API_KEY`. Stored in the OS keychain via VS
+  Code SecretStorage, never in `settings.json`.
+
+---
+
+## What the picker will show
+
+The extension does not show the raw `GET /v1/models` payload — it shapes it, and the count you
+see is lower than the catalog size for two deliberate reasons.
+
+### It asks for one id per model
+
+`MODELS_CATALOG_PREFIX_MODE` defaults to **`dual`**, which advertises every model twice — once
+under the short alias prefix and once under the canonical provider prefix — so older client
+configs keep resolving either form:
+
+```
+cc/claude-sonnet-4-6        ← alias prefix
+claude/claude-sonnet-4-6    ← canonical prefix, same model
+```
+
+The extension requests **`GET /v1/models?prefix=alias`** so one id arrives per model, without
+changing the server-wide setting for your other clients. On a reference instance this collapsed
+**2345 entries to 1396 — 949 duplicates, zero models lost.**
+
+If you would rather fix it server-wide for *every* client, set the
+`MODELS_CATALOG_PREFIX_MODE` feature flag to `alias` in the dashboard. See
+[API_REFERENCE → prefix](../reference/API_REFERENCE.md#model-id-prefixes-prefix) for the
+query parameter and the warning about `canonical`.
+
+### It hides models that cannot chat
+
+The catalog also lists image, video, audio, rerank, embedding and moderation models. Those are
+rejected on a chat request anyway:
+
+```
+HTTP 400 — Model '<id>' is an image-generation model and cannot be used on
+/v1/chat/completions. Use POST /v1/images/generations instead.
+```
+
+so they are filtered out by their `type` field before reaching the picker. **Responses-API
+models are kept** — every Codex / GPT-5.x entry advertises `supported_endpoints: ["responses"]`,
+and OmniRoute translates those for `/v1/chat/completions`, so they are perfectly usable.
+
+### Providers you never configured
+
+The catalog lists models from providers with an **active connection** *plus* every **noAuth**
+provider — the keyless ones that make up much of the free tier. That is intentional. To hide
+them, add them to `blockedProviders` in the dashboard settings; nothing changes in the
+extension.
+
+---
+
+## Dashboard inside a VS Code tab
+
+`omnicopilot.dashboardOpen: "editor"` renders the OmniRoute dashboard in an editor tab via the
+Simple Browser instead of an external browser. Embedding is **opt-in on the server**: start
+OmniRoute with
+
+```bash
+DASHBOARD_ALLOW_EMBED=vscode omniroute
+```
+
+which serves the HTML pages with `frame-ancestors 'self' vscode-webview:` instead of the default
+`frame-ancestors 'none'` + `X-Frame-Options: DENY`. The API surface (`/api`, `/v1`, `/v1beta`,
+`/a2a`, `/healthz`) keeps the strict headers either way. Without the variable the page refuses to
+frame and the extension falls back to the external browser — nothing breaks. See
+[`ENVIRONMENT.md`](../reference/ENVIRONMENT.md) and issue
+[#10273](https://github.com/diegosouzapw/OmniRoute/issues/10273).
+
+---
+
+## Configuring your other tools from inside VS Code
+
+**`OmniRoute: Configure Coding CLI`** drives the `omniroute` CLI to write ready-to-use profiles
+for Codex CLI, Claude Code, Cline, Continue, Cursor, Aider, OpenCode, Goose, Crush, Qwen Code,
+Kilo and Roo — the same configs described in
+[`CLI-INTEGRATIONS.md`](CLI-INTEGRATIONS.md). The API key is handed to the CLI through the
+`OMNIROUTE_API_KEY` environment variable, never on the command line.
+
+---
+
+## Troubleshooting
+
+| Symptom | Cause / fix |
+| --- | --- |
+| No OmniRoute models in the picker | Server unreachable. The status-bar dot goes grey; run `OmniRoute: Check Connection`. Discovery is silent by design and contributes no models rather than prompting. |
+| Every model appears twice | You are on an OmniCopilot older than 1.0.1 — update. The extension now requests `?prefix=alias`. |
+| An image/audio model used to be listed and is gone | Intentional since 1.0.1 — it could never answer a chat request. |
+| Panel missing from the Activity Bar | VS Code moves extra view containers into the **"…"** overflow at the bottom of the Activity Bar, and a container hidden via right-click stays hidden. Right-click the Activity Bar → tick **OmniRoute**, or open it with `OmniRoute: Manage Connection`. |
+| Dashboard opens in the browser despite `editor` mode | The server is not started with `DASHBOARD_ALLOW_EMBED=vscode` (see above). The fallback is deliberate. |
+| Models list is stale after changing providers | `OmniRoute: Refresh Models`, or the ↻ link in the panel. |
+
+---
+
+## See also
+
+- [`CLI-INTEGRATIONS.md`](CLI-INTEGRATIONS.md) — every other coding tool
+- [`REMOTE-MODE.md`](REMOTE-MODE.md) — driving a remote OmniRoute
+- [`../reference/API_REFERENCE.md`](../reference/API_REFERENCE.md) — the `/v1/models` contract
+- [`docs/CATALOG.md`](https://github.com/diegosouzapw/OmniCopilot/blob/main/docs/CATALOG.md) — the extension's own catalog notes

docs/guides/meta.json

@@ -16,6 +16,7 @@
     "CLAUDE-CODE-CONFIGURATION",
     "CODEX-CLI-CONFIGURATION",
     "CLI-INTEGRATIONS",
+    "VSCODE-COPILOT",
     "MANAGEMENT-AUTH",
     "REMOTE-MODE",
     "PWA_GUIDE",

docs/i18n/pl/docs/providers/ALIBABA-QWEN-PROVIDER-FAMILIES.md

@@ -32,7 +32,7 @@ innych rodzin endpointów, więc wszystkie cztery produkty pozostają osobnymi I
 | Rodzina providera       | `global-sg`                                                              | `china-beijing`                                                      | Format wire |
 | ----------------------- | ------------------------------------------------------------------------ | -------------------------------------------------------------------- | ----------- |
 | `alibaba`               | `https://dashscope-intl.aliyuncs.com/compatible-mode/v1`                 | `https://dashscope.aliyuncs.com/compatible-mode/v1`                  | OpenAI      |
-| `bailian-coding-plan`   | `https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1`           | `https://coding.dashscope.aliyuncs.com/apps/anthropic/v1`            | Anthropic   |
+| `bailian-coding-plan`   | `https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1`  | `https://token-plan.cn-beijing.maas.aliyuncs.com/apps/anthropic/v1`  | Anthropic   |
 | `qwen-cloud`            | `https://dashscope-intl.aliyuncs.com/compatible-mode/v1`                 | `https://dashscope.aliyuncs.com/compatible-mode/v1`                  | OpenAI      |
 | `qwen-cloud-token-plan` | `https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1` | `https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1` | OpenAI      |
 

docs/reference/API_REFERENCE.md

@@ -270,6 +270,31 @@ Authorization: Bearer your-api-key
 → Returns all chat, embedding, and image models + combos in OpenAI format
 ```
 
+### Model id prefixes (`?prefix=`)
+
+Most models are advertised under a **provider prefix**. Which prefix you get is controlled by
+the `MODELS_CATALOG_PREFIX_MODE` feature flag, and can be overridden **per request** with a
+query parameter — useful for a client that wants a clean list without changing the server-wide
+setting for everyone else:
+
+```bash
+GET /v1/models?prefix=alias        # one id per model — the short alias prefix
+GET /v1/models?prefix=dual         # both forms (server default)
+GET /v1/models?prefix=canonical    # only the full provider-id prefix
+```
+
+| Mode | Emits | Notes |
+| --- | --- | --- |
+| `dual` | `cc/claude-sonnet-4-6` **and** `claude/claude-sonnet-4-6` | **Default.** Both ids route to the same model; kept so client configs that hardcoded either form keep working. Roughly doubles the catalog. |
+| `alias` | `cc/claude-sonnet-4-6` | One entry per model. Providers without a distinct alias still emit their entry, so nothing is lost. |
+| `canonical` | `claude/claude-sonnet-4-6` | ⚠️ The canonical row is only emitted when the canonical provider id **differs** from the alias, so providers without a distinct alias emit nothing in this mode. Prefer `alias` for a de-duplicated list. |
+
+A `dual`-mode mirror can also be recognised without the query parameter: it carries a `parent`
+field pointing at the primary id.
+
+Clients that render a model picker should request `?prefix=alias` — this is what the
+[OmniCopilot VS Code extension](../guides/VSCODE-COPILOT.md) does.
+
 ### No-thinking model variants
 
 For thinking-capable Claude models, `/v1/models` also advertises a **no-thinking** variant whose id is prefixed with `claude-3-omniroute-no-thinking/`:

docs/reference/ENVIRONMENT.md

@@ -881,6 +881,7 @@ Automatic model pricing data synchronization from external sources.
 | Variable                  | Default       | Source File                                      | Description                                                                                                   |
 | ------------------------- | ------------- | ------------------------------------------------ | ------------------------------------------------------------------------------------------------------------- |
 | `ARENA_ELO_SYNC_ENABLED`  | `true`        | `src/shared/constants/featureFlagDefinitions.ts` | Periodic Arena AI leaderboard ELO sync, configurable from Dashboard Feature Flags or with `false` to opt out. |
+| `MODELS_CATALOG_PREFIX_MODE` | `dual`     | `src/shared/constants/featureFlagDefinitions.ts`, `src/app/api/v1/models/catalog.ts` | Prefix form used for model ids in `GET /v1/models`. `dual` advertises both the short alias prefix and the canonical provider prefix for every model (backward compatibility — roughly doubles the catalog); `alias` emits one id per model; `canonical` emits only the full provider-id prefix and omits providers whose alias already is the canonical id. Clients can override per request with `?prefix=alias`. See [API_REFERENCE](API_REFERENCE.md#model-id-prefixes-prefix). |
 | `ARENA_ELO_SYNC_INTERVAL` | `86400` (24h) | `src/lib/arenaEloSync.ts`                        | Sync interval in seconds.                                                                                     |
 
 ---

open-sse/services/modelDeprecation.ts

@@ -40,6 +40,13 @@ const BUILT_IN_ALIASES: Record<string, string> = {
   "fireworks/accounts/fireworks/models/kimi-k2": "moonshotai/Kimi-K2",
   "kimi-k2": "moonshotai/Kimi-K2",
 
+  // Qwen — the model ships only under the `-preview` id (bailian-coding-plan, qoder,
+  // qwen-cloud-token-plan, qwen-web). Without this, the bare id missed MODEL_SPECS and
+  // the context preflight fell back to contextManager's `default: 128000`, rejecting
+  // prompts the model's real 1M window accepts. Drop this line if Alibaba ever ships a
+  // distinct GA `qwen3.8-max` — it would no longer be the same model.
+  "qwen3.8-max": "qwen3.8-max-preview",
+
   // Mistral short aliases
   "mistral-large": "mistral-large-latest",
   "mistral-small": "mistral-small-latest",

scripts/check/check-fabricated-docs.mjs

@@ -114,6 +114,12 @@ const ENV_VAR_ALLOWLIST = new Set([
   "LINUX_GPG_KEY", // electron AppImage signing key, CI/build only (ELECTRON_GUIDE.md)
   "BRANCH_LOCK_TOKEN", // release branch-protection ops token (QUALITY_GATE_PLAYBOOK.md)
   "NEXT_LOCALE", // next-intl locale cookie name (I18N.md)
+  // Feature flags are resolved by key at runtime — `resolveFeatureFlag()` reads
+  // `process.env[key]` (src/shared/utils/featureFlags.ts), never a literal
+  // `process.env.MODELS_CATALOG_PREFIX_MODE`, so this scan cannot see the read.
+  // The flag is real: defined in featureFlagDefinitions.ts, overridable from the
+  // dashboard or the environment. (API_REFERENCE.md, VSCODE-COPILOT.md)
+  "MODELS_CATALOG_PREFIX_MODE",
   // Telegram Mini App integration (proposal TELEGRAM-MINIAPP.md, not yet implemented): env vars named in the feasibility analysis but no code reads them yet.
   "TELEGRAM_WEBHOOK_URL", // proposal-only: Telegram webhook public endpoint (TELEGRAM-MINIAPP.md, future feature)
   "TELEGRAM_WEBHOOK_SECRET", // proposal-only: Telegram webhook HMAC secret (TELEGRAM-MINIAPP.md, future feature)

src/app/(dashboard)/dashboard/providers/[id]/providerPageHelpers.ts

@@ -248,7 +248,7 @@ export const CONFIGURABLE_BASE_URL_PROVIDERS = new Set([
 export const DEFAULT_PROVIDER_BASE_URLS: Record<string, string> = {
   "azure-openai": "https://example-resource.openai.azure.com",
   "azure-ai": "https://example-resource.services.ai.azure.com/openai/v1",
-  "bailian-coding-plan": "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1",
+  "bailian-coding-plan": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1",
   "xiaomi-mimo": "https://token-plan-sgp.xiaomimimo.com/v1",
   siliconflow: "https://api.siliconflow.com/v1",
   "searxng-search": "http://localhost:8888/search",

src/lib/providers/validation/audioMiscProviders.ts

@@ -294,7 +294,9 @@ export async function validateBailianCodingPlanProvider({
         providerSpecificData
       ),
       body: JSON.stringify({
-        model: "qwen3-coder-plus",
+        // qwen3-coder-plus belonged to the retired Coding Plan host and is absent from
+        // BAILIAN_CODING_PLAN_MODELS; probe with a model this plan actually serves.
+        model: providerSpecificData.validationModelId || "qwen3.7-max",
         max_tokens: 1,
         messages: [{ role: "user", content: "test" }],
       }),

src/shared/constants/alibabaProviderRegions.ts

@@ -11,9 +11,14 @@ export const ALIBABA_PROVIDER_ENDPOINTS: Readonly<
     "global-sg": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
     "china-beijing": "https://dashscope.aliyuncs.com/compatible-mode/v1",
   },
+  // The catalog entry is the personal TOKEN Plan (see providers/apikey/regional.ts:
+  // name "Alibaba Token Plan"). The legacy coding-intl/coding hosts serve the separate
+  // Coding Plan product and reject Token Plan keys with 401 invalid_api_key — verified
+  // live 2026-08-18 against the same key that returns 429 (quota) on the host below.
+  // Keeps /apps/anthropic/v1 because the registry entry is format "claude".
   "bailian-coding-plan": {
-    "global-sg": "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1",
-    "china-beijing": "https://coding.dashscope.aliyuncs.com/apps/anthropic/v1",
+    "global-sg": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1",
+    "china-beijing": "https://token-plan.cn-beijing.maas.aliyuncs.com/apps/anthropic/v1",
   },
   "qwen-cloud": {
     "global-sg": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
@@ -74,11 +79,48 @@ function normalizeEndpoint(value: string): string {
     .toLowerCase();
 }
 
+/**
+ * Preset hosts this family used to ship. They must keep counting as presets: a connection
+ * saved while a preset was current carries that URL in providerSpecificData.baseUrl, and if
+ * a retired preset were mistaken for a deliberate custom URL the connection would stay
+ * pinned to a host that no longer accepts its key, deaf to the region selector.
+ */
+const LEGACY_FAMILY_PRESETS: Readonly<Record<AlibabaProviderFamily, readonly string[]>> = {
+  alibaba: [],
+  // Retired 2026-08-18 — Coding Plan hosts, wrong product for this Token Plan entry.
+  "bailian-coding-plan": [
+    "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1",
+    "https://coding.dashscope.aliyuncs.com/apps/anthropic/v1",
+  ],
+  "qwen-cloud": [],
+  "qwen-cloud-token-plan": [],
+};
+
+/**
+ * Media (AIGC) roots, when they differ from the chat root.
+ *
+ * Only bailian-coding-plan diverges: its CHAT traffic moved to the Token Plan host
+ * (2026-08), but image/video generation keeps running on the DashScope AIGC service
+ * (`/api/v1/services/aigc/…`) — see imageRegistry.ts / videoRegistry.ts, which pin those
+ * hosts literally. Deriving media from the chat root would have silently repointed every
+ * Bailian image/video call at a host that does not serve AIGC.
+ */
+const ALIBABA_PROVIDER_MEDIA_OVERRIDES: Partial<
+  Record<AlibabaProviderFamily, Readonly<Record<AlibabaProviderRegion, string>>>
+> = {
+  "bailian-coding-plan": {
+    "global-sg": "https://coding-intl.dashscope.aliyuncs.com/api/v1",
+    "china-beijing": "https://coding.dashscope.aliyuncs.com/api/v1",
+  },
+};
+
 function isFamilyPresetUrl(family: AlibabaProviderFamily, value: string): boolean {
   const normalized = normalizeEndpoint(value);
-  return ALIBABA_PROVIDER_REGION_VALUES.some(
+  const isCurrentPreset = ALIBABA_PROVIDER_REGION_VALUES.some(
     (region) => normalizeEndpoint(ALIBABA_PROVIDER_ENDPOINTS[family][region]) === normalized
   );
+  if (isCurrentPreset) return true;
+  return LEGACY_FAMILY_PRESETS[family].some((preset) => normalizeEndpoint(preset) === normalized);
 }
 
 export function isAlibabaRegionalProvider(providerId: string | null | undefined): boolean {
@@ -167,6 +209,22 @@ export function resolveAlibabaProviderMediaBaseUrl(
   providerSpecificData?: unknown,
   fallback = ""
 ): string {
+  const family = canonicalProviderFamily(providerId);
+  const data = asRecord(providerSpecificData);
+  const configuredBaseUrl =
+    typeof data.baseUrl === "string" && data.baseUrl.trim() ? data.baseUrl.trim() : "";
+  const mediaOverride = family ? ALIBABA_PROVIDER_MEDIA_OVERRIDES[family] : undefined;
+
+  // A custom base URL still drives media, as before — the override only replaces the
+  // preset-derived host.
+  if (
+    family &&
+    mediaOverride &&
+    (!configuredBaseUrl || isFamilyPresetUrl(family, configuredBaseUrl))
+  ) {
+    return mediaOverride[resolveAlibabaProviderRegion(providerId, data)];
+  }
+
   return stripTrailingSlashes(
     resolveAlibabaProviderBaseUrl(providerId, providerSpecificData, fallback).trim()
   )

src/shared/constants/config.ts

@@ -38,7 +38,8 @@ export const PROVIDER_ENDPOINTS = {
   helixmind: "https://helixmind.online/v1/chat/completions",
   glm: "https://api.z.ai/api/anthropic/v1/messages",
   glmt: "https://api.z.ai/api/anthropic/v1/messages",
-  "bailian-coding-plan": "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1/messages",
+  "bailian-coding-plan":
+    "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1/messages",
   "qwen-cloud": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions",
   "qwen-cloud-token-plan":
     "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions",

tests/e2e/providers-bailian-coding-plan.spec.ts

@@ -3,7 +3,8 @@ import { gotoDashboardRoute } from "./helpers/dashboardAuth";
 
 // #7882 replaced this provider's free-text Base URL field with a region step:
 // the endpoint is now derived from the choice ("global-sg" ->
-// coding-intl.dashscope.aliyuncs.com, "china-beijing" -> coding.dashscope.aliyuncs.com,
+// token-plan.ap-southeast-1.maas.aliyuncs.com, "china-beijing" ->
+// token-plan.cn-beijing.maas.aliyuncs.com,
 // see src/shared/constants/alibabaProviderRegions.ts), so the modal persists
 // providerSpecificData.region instead of a baseUrl. A per-connection base-URL
 // override still exists, but it moved to Advanced in the edit-connection modal.
@@ -120,7 +121,7 @@ test.describe("Bailian Coding Plan Provider", () => {
   // free-text Base URL field, which #7882 removed for this provider — an invalid
   // URL is no longer reachable from this modal. Replaced with the other half of
   // the region contract: the China-mainland choice must persist as typed, since
-  // that is what selects the coding.dashscope.aliyuncs.com endpoint.
+  // that is what selects the token-plan.cn-beijing.maas.aliyuncs.com endpoint.
   test("region step persists the China-mainland (Beijing) choice", async ({ page }) => {
     const capturedPayloads: { createProvider?: Record<string, unknown> } = {};
 
@@ -222,6 +223,8 @@ test.describe("Bailian Coding Plan Provider", () => {
     expect(capturedPayloads.createProvider).toBeDefined();
     const payload = capturedPayloads.createProvider;
     expect(payload?.providerSpecificData).toBeDefined();
-    expect((payload?.providerSpecificData as Record<string, unknown>)?.region).toBe("china-beijing");
+    expect((payload?.providerSpecificData as Record<string, unknown>)?.region).toBe(
+      "china-beijing"
+    );
   });
 });

tests/unit/alibaba-provider-regions.test.ts

@@ -24,8 +24,8 @@ test("Alibaba-family endpoint matrix keeps product and region boundaries distinc
       "china-beijing": "https://dashscope.aliyuncs.com/compatible-mode/v1",
     },
     "bailian-coding-plan": {
-      "global-sg": "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1",
-      "china-beijing": "https://coding.dashscope.aliyuncs.com/apps/anthropic/v1",
+      "global-sg": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1",
+      "china-beijing": "https://token-plan.cn-beijing.maas.aliyuncs.com/apps/anthropic/v1",
     },
     "qwen-cloud": {
       "global-sg": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
@@ -92,7 +92,7 @@ test("DefaultExecutor applies the regional endpoint to normal requests", () => {
     codingPlan.buildUrl("qwen3.7-plus", true, 0, {
       providerSpecificData: { region: "china-beijing" },
     }),
-    "https://coding.dashscope.aliyuncs.com/apps/anthropic/v1/messages"
+    "https://token-plan.cn-beijing.maas.aliyuncs.com/apps/anthropic/v1/messages"
   );
 
   const qwenCloud = new DefaultExecutor("qwen-cloud");
@@ -133,7 +133,11 @@ test("provider validation probes the selected Coding Plan region", async () => {
       },
     });
     assert.equal(result.valid, true);
-    assert.deepEqual(urls, ["https://coding.dashscope.aliyuncs.com/apps/anthropic/v1/messages"]);
+    // The stored URL is a RETIRED preset, so it must not pin the connection: the
+    // china-beijing selector still wins and routes to the Token Plan CN host.
+    assert.deepEqual(urls, [
+      "https://token-plan.cn-beijing.maas.aliyuncs.com/apps/anthropic/v1/messages",
+    ]);
   } finally {
     globalThis.fetch = originalFetch;
   }

tests/unit/bailian-coding-plan-provider.test.ts

@@ -34,7 +34,7 @@ test("bailian-coding-plan not in OAUTH_PROVIDERS", () => {
 });
 
 // Schema validation tests for providerSpecificData.baseUrl
-const VALID_BAILIAN_URL = "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1";
+const VALID_BAILIAN_URL = "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1";
 
 test("createProviderSchema accepts valid baseUrl in providerSpecificData", () => {
   const validation = validateBody(createProviderSchema, {
@@ -427,7 +427,7 @@ test("validateProviderApiKey returns invalid for 401 response (bailian-coding-pl
       provider: "bailian-coding-plan",
       apiKey: "invalid-key",
       providerSpecificData: {
-        baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1",
+        baseUrl: "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1",
       },
     });
 
@@ -452,7 +452,7 @@ test("validateProviderApiKey returns invalid for 403 response (bailian-coding-pl
       provider: "bailian-coding-plan",
       apiKey: "forbidden-key",
       providerSpecificData: {
-        baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1",
+        baseUrl: "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1",
       },
     });
 
@@ -479,7 +479,7 @@ test("validateProviderApiKey returns valid for 400 response (bailian-coding-plan
       provider: "bailian-coding-plan",
       apiKey: "valid-key",
       providerSpecificData: {
-        baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1",
+        baseUrl: "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1",
       },
     });
 
@@ -508,7 +508,7 @@ test("validateProviderApiKey returns valid for 200 response (bailian-coding-plan
       provider: "bailian-coding-plan",
       apiKey: "valid-key",
       providerSpecificData: {
-        baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1",
+        baseUrl: "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1",
       },
     });
 
@@ -533,7 +533,7 @@ test("validateProviderApiKey returns invalid for 500 response (bailian-coding-pl
       provider: "bailian-coding-plan",
       apiKey: "bad-key",
       providerSpecificData: {
-        baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1",
+        baseUrl: "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1",
       },
     });
 
@@ -561,7 +561,7 @@ test("validateProviderApiKey avoids double /messages suffix for bailian-coding-p
       provider: "bailian-coding-plan",
       apiKey: "valid-key",
       providerSpecificData: {
-        baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1/messages",
+        baseUrl: "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1/messages",
       },
     });
 
@@ -569,7 +569,7 @@ test("validateProviderApiKey avoids double /messages suffix for bailian-coding-p
     assert.equal(urls.length, 1);
     assert.equal(
       urls[0],
-      "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1/messages",
+      "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1/messages",
       "Should probe exactly one /messages suffix"
     );
   } finally {
@@ -588,7 +588,7 @@ test("POST /api/providers validation: bailian-coding-plan with baseUrl passes sc
     apiKey: "sk-placeholder-key",
     name: "Test Bailian Provider",
     providerSpecificData: {
-      baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1",
+      baseUrl: "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1",
     },
   });
 
@@ -597,7 +597,7 @@ test("POST /api/providers validation: bailian-coding-plan with baseUrl passes sc
     assert.equal(validation.data.provider, "bailian-coding-plan");
     assert.equal(
       validation.data.providerSpecificData?.baseUrl,
-      "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1"
+      "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1"
     );
   }
 });

tests/unit/bailian-token-plan-endpoint-parity.test.ts

@@ -0,0 +1,102 @@
+/**
+ * bailian-coding-plan ("Alibaba Token Plan") pointed inference and validation at two
+ * DIFFERENT hosts.
+ *
+ * #10290 moved the open-sse registry to the Token Plan host, but the dashboard's key
+ * validation resolves its URL through ALIBABA_PROVIDER_REGION_ENDPOINTS, which still held
+ * the legacy Coding Plan host. Verified live 2026-08-18 with a valid Token Plan key:
+ *
+ *   coding-intl.dashscope.aliyuncs.com   → 401 invalid_api_key
+ *   token-plan.ap-southeast-1.maas...    → 429 Throttling.AllocationQuota (auth OK)
+ *
+ * validateBailianCodingPlanProvider maps 401/403 to "Invalid API key", so a perfectly
+ * good key was rejected at add-connection time while the very same key worked for
+ * inference. These tests pin the two paths together.
+ */
+
+import test from "node:test";
+import assert from "node:assert/strict";
+
+import { REGISTRY } from "../../open-sse/config/providers/index.ts";
+import { PROVIDER_ENDPOINTS } from "../../src/shared/constants/config.ts";
+import { DEFAULT_PROVIDER_BASE_URLS } from "../../src/app/(dashboard)/dashboard/providers/[id]/providerPageHelpers.ts";
+import {
+  ALIBABA_PROVIDER_ENDPOINTS,
+  resolveAlibabaProviderBaseUrl,
+} from "../../src/shared/constants/alibabaProviderRegions.ts";
+
+const LEGACY_CODING_PLAN_HOST = "coding-intl.dashscope.aliyuncs.com";
+
+test("validation resolves the same host the inference registry dispatches to", () => {
+  const registryBaseUrl = REGISTRY["bailian-coding-plan"].baseUrl;
+  const resolved = resolveAlibabaProviderBaseUrl("bailian-coding-plan", {
+    region: "global-sg",
+  });
+
+  assert.equal(
+    resolved,
+    registryBaseUrl,
+    "the dashboard would validate the key against a different host than inference uses"
+  );
+});
+
+test("no default endpoint still points at the Coding Plan host", () => {
+  // The catalog entry is a TOKEN Plan; Coding Plan keys are a different product and the
+  // legacy host rejects Token Plan keys outright. Compare parsed hostnames, not URL
+  // substrings (CodeQL js/incomplete-url-substring-sanitization).
+  assert.notEqual(
+    new URL(PROVIDER_ENDPOINTS["bailian-coding-plan"]).hostname,
+    LEGACY_CODING_PLAN_HOST,
+    "PROVIDER_ENDPOINTS still defaults to the legacy Coding Plan host"
+  );
+  assert.notEqual(
+    new URL(DEFAULT_PROVIDER_BASE_URLS["bailian-coding-plan"]).hostname,
+    LEGACY_CODING_PLAN_HOST,
+    "the dashboard base-URL placeholder still shows the legacy Coding Plan host"
+  );
+  for (const region of ["global-sg", "china-beijing"] as const) {
+    assert.notEqual(
+      new URL(ALIBABA_PROVIDER_ENDPOINTS["bailian-coding-plan"][region]).hostname,
+      LEGACY_CODING_PLAN_HOST,
+      `region ${region} still maps to the legacy Coding Plan host`
+    );
+  }
+});
+
+test("both regions keep the Anthropic-compatible path the claude format requires", () => {
+  // format: "claude" + chatPath "/messages" — a compatible-mode URL here would 404.
+  for (const region of ["global-sg", "china-beijing"] as const) {
+    assert.ok(
+      ALIBABA_PROVIDER_ENDPOINTS["bailian-coding-plan"][region].endsWith("/apps/anthropic/v1"),
+      `region ${region} must keep the /apps/anthropic/v1 root`
+    );
+  }
+});
+
+test("a saved legacy preset URL still follows the region selector", () => {
+  // Migration guard: connections created before the fix carry the legacy host in
+  // providerSpecificData.baseUrl. isFamilyPresetUrl must keep recognizing it as a
+  // preset — otherwise it is treated as a deliberate custom URL and the connection
+  // stays pinned to the host that rejects its key, with no way out but manual editing.
+  const legacyPreset = "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1";
+
+  assert.equal(
+    resolveAlibabaProviderBaseUrl("bailian-coding-plan", {
+      region: "global-sg",
+      baseUrl: legacyPreset,
+    }),
+    ALIBABA_PROVIDER_ENDPOINTS["bailian-coding-plan"]["global-sg"],
+    "a stored legacy preset must not pin the connection to the dead host"
+  );
+});
+
+test("a genuinely custom base URL still wins over the region preset", () => {
+  const custom = "https://my-gateway.internal/apps/anthropic/v1";
+  assert.equal(
+    resolveAlibabaProviderBaseUrl("bailian-coding-plan", {
+      region: "global-sg",
+      baseUrl: custom,
+    }),
+    custom
+  );
+});

tests/unit/executor-default-base.test.ts

@@ -220,10 +220,10 @@ test("DefaultExecutor.buildUrl normalizes configurable chat-openai-compat base U
   assert.equal(
     bailian.buildUrl("qwen3-coder-plus", true, 0, {
       providerSpecificData: {
-        baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1",
+        baseUrl: "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1",
       },
     }),
-    "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1/messages"
+    "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1/messages"
   );
   assert.equal(
     heroku.buildUrl("claude-4-sonnet", true, 0, {

tests/unit/provider-validation-specialty.test.ts

@@ -1451,7 +1451,9 @@ test("specialty validators cover remaining status branches for Deepgram, Assembl
     if (target.match(/inworld/i)) {
       throw new Error("inworld offline");
     }
-    if (target.match(/dashscope\.aliyuncs\.com/i)) {
+    // Alibaba-family hosts: dashscope.aliyuncs.com (pay-as-you-go / AIGC) and
+    // *.maas.aliyuncs.com (Token Plan).
+    if (target.match(/(?:dashscope|maas)\.aliyuncs\.com/i)) {
       return new Response(JSON.stringify({ error: "server" }), { status: 500 });
     }
     if (target.match(/longcat/i)) {
@@ -1468,7 +1470,7 @@ test("specialty validators cover remaining status branches for Deepgram, Assembl
     provider: "bailian-coding-plan",
     apiKey: "bailian-key",
     providerSpecificData: {
-      baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1/messages",
+      baseUrl: "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1/messages",
     },
   });
   const longcatInvalid = await validateProviderApiKey({ provider: "longcat", apiKey: "lc-key" });

tests/unit/qwen38-max-bare-id-alias.test.ts

@@ -0,0 +1,54 @@
+import assert from "node:assert/strict";
+import { test } from "node:test";
+import { MODEL_SPECS } from "../../src/shared/constants/modelSpecs.ts";
+import { resolveModelAlias } from "../../open-sse/services/modelDeprecation.ts";
+import { resolveLifecycle } from "../../open-sse/handlers/chatCore/modelLifecyclePolicy.ts";
+
+/**
+ * Bare `qwen3.8-max` was an unroutable id: the model ships everywhere as
+ * `qwen3.8-max-preview` (bailian-coding-plan, qoder, qwen-cloud-token-plan, qwen-web),
+ * and nothing in the repo declared the short form. A client sending it therefore
+ *
+ *   1. missed MODEL_SPECS, so `getModelContextLimit()` fell through to the
+ *      `default: 128000` in open-sse/services/contextManager.ts, and the chatCore
+ *      preflight rejected any prompt above 128k with `context_length_exceeded`
+ *      ("Input exceeds context window ... limit 128000") even though the real
+ *      window is 1M; and
+ *   2. would have been dispatched verbatim to the upstream, which only knows the
+ *      `-preview` id.
+ *
+ * Both symptoms have one cause — the missing id — so the fix belongs in the
+ * deprecation/rename alias map (`BUILT_IN_ALIASES`), which `resolveLifecycle()`
+ * applies at open-sse/handlers/chatCore.ts:755, well before both the context
+ * preflight and the upstream dispatch. A MODEL_SPECS `aliases` entry would have
+ * fixed only (1): spec aliases resolve capabilities, never the dispatched id.
+ */
+
+const BARE = "qwen3.8-max";
+const CANONICAL = "qwen3.8-max-preview";
+
+test("bare qwen3.8-max resolves to the canonical -preview id", () => {
+  assert.equal(resolveModelAlias(BARE), CANONICAL);
+});
+
+test("the canonical id is a no-op through the alias map (no double rewrite)", () => {
+  assert.equal(resolveModelAlias(CANONICAL), CANONICAL);
+});
+
+test("the alias target carries the real 1M window, not the 128k fallback", () => {
+  const spec = MODEL_SPECS[CANONICAL];
+  assert.ok(spec, `MODEL_SPECS is missing ${CANONICAL}`);
+  assert.equal(spec.contextWindow, 1_000_000);
+  // The bare id must NOT gain its own spec entry — a second source of truth for the
+  // same model is what lets the two ids drift apart again.
+  assert.equal(MODEL_SPECS[BARE], undefined);
+});
+
+test("chatCore lifecycle resolution rewrites the model before dispatch", () => {
+  for (const provider of ["qwen-cloud-token-plan", "qoder", "bailian-coding-plan", "qwen-web"]) {
+    const [resolvedModel, effectiveModel, lifecycleError] = resolveLifecycle(provider, BARE);
+    assert.equal(resolvedModel, CANONICAL, `resolvedModel for ${provider}`);
+    assert.equal(effectiveModel, CANONICAL, `effectiveModel for ${provider}`);
+    assert.equal(lifecycleError, null, `unexpected lifecycle rejection for ${provider}`);
+  }
+});