Merge main into the AI driver stack

sse.ts and testUtil.ts keep both sides. The route concurrency gate keeps its CallSlot, which already holds the response's single close listener, and CallSlot imports that helper from its new folder.

.github/CODEOWNERS

@@ -2,7 +2,7 @@
 
 # The last matching rule takes precedence.
 
-- @Salazareo
+* @Salazareo
 
 # GUI
 
@@ -18,7 +18,10 @@
 # Backend AI
 
 /src/backend/controllers/puterai/ @404oops @ProgrammerIn-wonderland @Salazareo
-/src/backend/drivers/ai-\*/ @404oops @ProgrammerIn-wonderland @Salazareo
+/src/backend/drivers/ai/ @404oops @ProgrammerIn-wonderland @Salazareo
+/src/backend/util/aiCostFactor* @404oops @ProgrammerIn-wonderland @Salazareo
+/src/backend/util/aiPrices* @404oops @ProgrammerIn-wonderland @Salazareo
+/src/backend/util/aiProviderKey* @404oops @ProgrammerIn-wonderland @Salazareo
 
 # Backend: AI, hosting, workers, networking, and WebDAV
 
@@ -29,7 +32,7 @@
 /src/backend/drivers/workers/ @ProgrammerIn-wonderland @Salazareo
 /src/backend/services/localworker/ @ProgrammerIn-wonderland @Salazareo
 /src/backend/stores/subdomain/ @ProgrammerIn-wonderland @Salazareo
-/extensions/workerSandbox\* @ProgrammerIn-wonderland @Salazareo
+/extensions/workerSandbox* @ProgrammerIn-wonderland @Salazareo
 /src/worker/ @ProgrammerIn-wonderland @Salazareo
 /src/worker-types/ @ProgrammerIn-wonderland @Salazareo
 /src/backend/controllers/peer/ @ProgrammerIn-wonderland @Salazareo
@@ -42,7 +45,7 @@
 /src/backend/services/permission/ @jfcastro92 @Salazareo
 /src/backend/services/acl/ @jfcastro92 @Salazareo
 /src/backend/services/team/ @jfcastro92 @Salazareo
-/src/backend/services/apps/AppPermissionService\* @jfcastro92 @Salazareo
+/src/backend/services/apps/AppPermissionService* @jfcastro92 @Salazareo
 /src/backend/stores/share/ @jfcastro92 @Salazareo
 /src/backend/stores/permission/ @jfcastro92 @Salazareo
 /src/backend/stores/group/ @jfcastro92 @Salazareo
@@ -59,7 +62,7 @@
 /src/puter-js/tests/api/suites/hosting.suite.ts @ProgrammerIn-wonderland @Salazareo
 /src/puter-js/tests/api/suites/workers.suite.ts @ProgrammerIn-wonderland @Salazareo
 /src/puter-js/tests/api/suites/net.suite.ts @ProgrammerIn-wonderland @Salazareo
-/src/puter-js/src/modules/Peer\* @ProgrammerIn-wonderland @Salazareo
+/src/puter-js/src/modules/Peer* @ProgrammerIn-wonderland @Salazareo
 
 # SDK: sharing and permissions
 

.github/workflows/ai-provider-integration-tests.yaml

@@ -31,10 +31,9 @@ jobs:
               run: npm ci
 
             - name: Run AI provider integration tests
-              # Vitest treats positional args as filename substring filters.
-              # The pattern matches every `*.integration.test.ts` file and
-              # nothing else — the regular backend test suite stays out.
-              run: npm run test:backend -- integration.test
+              # Only the provider tests: the other `*.integration.test.ts`
+              # files need no credentials and run with the backend suite.
+              run: npm run test:backend -- $(git ls-files 'src/backend/drivers/ai/**/*.integration.test.ts')
               env:
                   CI: 'true'
                   PUTER_TEST_AI_CLAUDE_API_KEY: ${{ secrets.PUTER_TEST_AI_CLAUDE_API_KEY }}
@@ -49,6 +48,15 @@ jobs:
                   PUTER_TEST_AI_MOONSHOT_API_KEY: ${{ secrets.PUTER_TEST_AI_MOONSHOT_API_KEY }}
                   PUTER_TEST_AI_ZAI_API_KEY: ${{ secrets.PUTER_TEST_AI_ZAI_API_KEY }}
                   PUTER_TEST_AI_ELEVENLABS_API_KEY: ${{ secrets.PUTER_TEST_AI_ELEVENLABS_API_KEY }}
+                  PUTER_TEST_AI_ALIBABA_API_KEY: ${{ secrets.PUTER_TEST_AI_ALIBABA_API_KEY }}
+                  PUTER_TEST_AI_AZURE_OPENAI_API_KEY: ${{ secrets.PUTER_TEST_AI_AZURE_OPENAI_API_KEY }}
+                  PUTER_TEST_AI_AZURE_OPENAI_API_URL: ${{ secrets.PUTER_TEST_AI_AZURE_OPENAI_API_URL }}
+                  PUTER_TEST_AI_BYTEPLUS_API_KEY: ${{ secrets.PUTER_TEST_AI_BYTEPLUS_API_KEY }}
+                  PUTER_TEST_AI_HOONIFY_API_KEY: ${{ secrets.PUTER_TEST_AI_HOONIFY_API_KEY }}
+                  PUTER_TEST_AI_INFRON_API_KEY: ${{ secrets.PUTER_TEST_AI_INFRON_API_KEY }}
+                  PUTER_TEST_AI_KLING_API_KEY: ${{ secrets.PUTER_TEST_AI_KLING_API_KEY }}
+                  PUTER_TEST_AI_META_API_KEY: ${{ secrets.PUTER_TEST_AI_META_API_KEY }}
+                  PUTER_TEST_AI_MINIMAX_API_KEY: ${{ secrets.PUTER_TEST_AI_MINIMAX_API_KEY }}
 
             # Realtime conversations through the SDK against live OpenAI. Builds
             # the SDK bundle these tests load itself, so it runs even when the

AGENTS.md

@@ -9,6 +9,7 @@ Use these as the source of truth before exploring further:
 - [README.md](README.md) — project overview and quickstart.
 - [doc/architecture.md](doc/architecture.md) — backend layered stack (controllers → drivers → services → stores → clients), `PuterServer` wiring, `Context` (ALS), actors, and extensions.
 - [doc/contributing-apis.md](doc/contributing-apis.md) — adding and maintaining public APIs end to end (backend surface → puter.js → types → docs → tests). Follow it for any API work.
+- [doc/ai-drivers.md](doc/ai-drivers.md) — where AI driver code lives (interfaces, providers, protocols, shared), the import rules between those folders, and how to add a provider or an AI interface.
 - [doc/pagination.md](doc/pagination.md) — the one pagination convention for list APIs (limit/cursor/offset/includeTotal, envelope shape, cursor semantics).
 - [doc/alarms.md](doc/alarms.md) — raising alarms and picking a severity (what pages, what only gets recorded), plus the config that routes them.
 - [doc/self-hosting.md](doc/self-hosting.md) — running Puter outside hosted infra.
@@ -70,7 +71,7 @@ Commit messages and PR descriptions never credit anyone or mention a bug report.
 - **Test new behavior.** Every new function, endpoint, driver method, or logic branch gets a test; every bug fix gets a regression test that fails before the fix. If something is genuinely hard to test, skip it but say so in the PR.
 - **Boy Scout Rule, proportional to the change.** In files you're already touching, fix the typo, the dead import, the missing test, the bit you had to read twice. Don't ride a refactor along with a bug fix.
 - **Understand what you commit.** AI assistance is fine; shipping code you couldn't have written, debugged, or defended in review is not.
-- **A limit change is not done until the docs change with it.** Every rate limit, concurrency cap, quota, and allowance in the code is published in [src/docs/src/rate-limits-and-quotas.md](src/docs/src/rate-limits-and-quotas.md) — an undisclosed limit is one developers discover as a service failure. If a PR moves any of these numbers, the same PR updates that page. The numbers live in `src/backend/controllers/fs/limits.ts` (filesystem), `src/backend/drivers/util/aiLimits.ts` (all AI drivers), per-driver `rateLimit`/`concurrent` configs, and `src/backend/data/subPolicies/` (free-tier allowances).
+- **A limit change is not done until the docs change with it.** Every rate limit, concurrency cap, quota, and allowance in the code is published in [src/docs/src/rate-limits-and-quotas.md](src/docs/src/rate-limits-and-quotas.md) — an undisclosed limit is one developers discover as a service failure. If a PR moves any of these numbers, the same PR updates that page. The numbers live in `src/backend/controllers/fs/limits.ts` (filesystem), `src/backend/drivers/ai/shared/aiLimits.ts` (all AI drivers), per-driver `rateLimit`/`concurrent` configs, and `src/backend/data/subPolicies/` (free-tier allowances).
 
 ---
 
@@ -97,6 +98,10 @@ Layer rules:
 - **Drivers and controllers stay thin.** Domain rules a second entry point needs (signup, app CRUD, worker deploy, AI routing/billing) live in a service, not in the first driver or controller that needed them.
 - **Prefer explicit arguments over [`Context`](src/backend/core/context.ts) (ALS).** Use it only for request-scoped values that would otherwise thread through many layers; today that's mostly `actor` and `req`.
 
+### AI drivers
+
+AI drivers live in [src/backend/drivers/ai/](src/backend/drivers/ai/): `interfaces/` holds the Puter-facing drivers, `providers/<vendor>/<interface>/` holds vendor code, `protocols/` holds wire protocols several vendors speak, and `shared/` holds helpers more than one interface uses. Follow [doc/ai-drivers.md](doc/ai-drivers.md) when adding or moving AI code.
+
 ### Extensions
 
 [extensions/](extensions/) is for **non-crucial parts of the system**: Puter must still work with the extension removed. If core needs to call it, it belongs in core ([whoami](extensions/whoami.ts) is the cautionary example). Inside an extension, follow the same layered structure, unless it only needs a few route handlers, in which case the `extension.get/post/...` helpers are enough on their own. The `extension` API is in [doc/architecture.md](doc/architecture.md#extension-api).

doc/ai-drivers.md

@@ -0,0 +1,153 @@
+# AI Drivers
+
+Where the AI driver code lives under [src/backend/drivers/ai/](../src/backend/drivers/ai/), what each folder owns, and how to add a provider or a new AI interface. The general layer rules are in [architecture.md](architecture.md) and [AGENTS.md](../AGENTS.md#backend). This page covers what is specific to AI.
+
+## Layout
+
+```text
+src/backend/drivers/ai/
+├── interfaces/    Puter-facing drivers, one folder per AI interface
+├── providers/     Vendor code, as providers/<vendor>/<interface>/
+├── protocols/     Wire protocols that several vendors speak
+└── shared/        Helpers that more than one interface uses
+```
+
+| Folder | Owns | Example |
+| --- | --- | --- |
+| `interfaces/<interface>/` | The driver class, the interface's contracts in `types.ts`, its provider base class where one exists, and the helpers and tests that apply to every provider of that interface. | [interfaces/chat/ChatCompletionDriver.ts](../src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.ts) |
+| `providers/<vendor>/<interface>/` | One vendor's implementation of one interface: the adapter, its model catalog and prices, its fixtures, and its tests. | [providers/gemini/video/](../src/backend/drivers/ai/providers/gemini/video/) |
+| `providers/<vendor>/` | Helpers that several of that vendor's interfaces use. | [providers/gemini/geminiRest.ts](../src/backend/drivers/ai/providers/gemini/geminiRest.ts) |
+| `protocols/openaiCompatible/` | The OpenAI wire protocol: the base provider class, message and usage conversion, and parameter mapping for Chat Completions and Responses. | [protocols/openaiCompatible/OpenAICompatProvider.ts](../src/backend/drivers/ai/protocols/openaiCompatible/OpenAICompatProvider.ts) |
+| `shared/` | Helpers that more than one interface uses: limits, the provider registry, the remote catalog cache, job polling, streamed charging, and media input. | [shared/aiLimits.ts](../src/backend/drivers/ai/shared/aiLimits.ts) |
+
+Helpers that non-AI code also uses stay in [src/backend/drivers/util/](../src/backend/drivers/util/): file input, data URIs, upstream error mapping, and stream piping.
+
+AI code that a service also needs lives in [src/backend/util/](../src/backend/util/), because a service can't import from the driver layer. The realtime relay in `services/realtime/` bills through the same cost factor as the drivers, so these three files are there:
+
+| File | Holds |
+| --- | --- |
+| [aiCostFactor.ts](../src/backend/util/aiCostFactor.ts) | `withAiCostFactor`, the metering view every AI driver and the realtime relay record usage through, and `withAiCreditHold`. |
+| [aiProviderKey.ts](../src/backend/util/aiProviderKey.ts) | `readProviderKey`, which reads an API key from `config.providers` blocks. |
+| [aiPrices.ts](../src/backend/util/aiPrices.ts) | Vendor prices that a driver and a service both bill. |
+
+### Interfaces
+
+| Folder | Driver | `driverInterface` | `driverName` | Key in `puterDrivers` |
+| --- | --- | --- | --- | --- |
+| `interfaces/chat/` | `ChatCompletionDriver` | `puter-chat-completion` | `ai-chat` | `aiChat` |
+| `interfaces/image/` | `ImageGenerationDriver` | `puter-image-generation` | `ai-image` | `aiImage` |
+| `interfaces/video/` | `VideoGenerationDriver` | `puter-video-generation` | `ai-video` | `aiVideo` |
+| `interfaces/textToSpeech/` | `TTSDriver` | `puter-tts` | `ai-tts` | `aiTts` |
+| `interfaces/speechToText/` | `SpeechToTextDriver` | `puter-speech2txt` | `ai-speech2txt` | `aiSpeech2Txt` |
+| `interfaces/speechToSpeech/` | `VoiceChangerDriver` | `puter-speech2speech` | `ai-speech2speech` | `aiSpeech2Speech` |
+| `interfaces/ocr/` | `OCRDriver` | `puter-ocr` | `ai-ocr` | `aiOcr` |
+
+Folder names are not runtime identifiers. `driverInterface`, `driverName`, driver aliases, the keys under `providers` in config, provider ids, model ids, and usage keys are public contracts. Moving or renaming a file never changes them.
+
+## Request flow
+
+A call goes from the interface to a provider, and from there to a shared protocol when the vendor speaks one:
+
+```text
+interfaces/chat/ChatCompletionDriver.ts
+    validates the call, picks the model and provider, holds credits
+  → providers/deepseek/chat/DeepSeekProvider.ts
+        DeepSeek's catalog, endpoint, and request differences
+    → protocols/openaiCompatible/OpenAICompatProvider.ts
+          the OpenAI-compatible request, response, and stream handling
+```
+
+A provider whose vendor has its own API, such as `ClaudeProvider` or `ElevenLabsTTSProvider`, implements the interface's contract directly and uses no protocol.
+
+## Import rules
+
+- `shared/` imports nothing from `interfaces/`, `providers/`, or `protocols/`.
+- Nothing in `services/`, `stores/`, or `clients/` imports from `drivers/ai/`. Code that a service and a driver both need goes in `src/backend/util/`.
+- `providers/` and `protocols/` import an interface's `types.ts` and helpers. They never import a driver class. Their tests can, to drive a provider through the real driver.
+- Only an interface's driver file imports providers, to register them. The interface's helpers don't.
+- An interface doesn't import another interface. When a second interface needs a helper, move the helper to `shared/`, or to `providers/<vendor>/` when it belongs to one vendor.
+- A vendor folder imports another vendor's folder only when it serves that vendor's models. `providers/azure/` reads the OpenAI and xAI catalogs for that reason.
+
+## Where a file goes
+
+| The code is | It goes in |
+| --- | --- |
+| Input validation, gates, routing, credit holds, or anything else every provider of the interface gets | `interfaces/<interface>/` |
+| A request or response contract that providers implement | `interfaces/<interface>/types.ts` |
+| A vendor's endpoint, request shape, catalog, prices, or quirks | `providers/<vendor>/<interface>/` |
+| A vendor's auth, REST plumbing, or constants that two of its interfaces use | `providers/<vendor>/` |
+| Behavior of a wire protocol that several vendors speak | `protocols/<protocol>/` |
+| A helper that two or more interfaces use and that belongs to no vendor | `shared/` |
+| A helper that non-AI drivers or controllers also use | `src/backend/drivers/util/` |
+| AI code that a service also uses | `src/backend/util/`, in a file named `ai<Something>.ts` |
+
+Keep a helper next to its only consumer. Move it up when a second consumer appears, not before.
+
+When one Puter option becomes a different request shape per vendor, the interface reads the option and each dialect maps it. The chat `compaction` option is read in `interfaces/chat/utils/compaction.js`, mapped for OpenAI by `toOpenAiContextManagement` in `protocols/openaiCompatible/openaiParams.ts`, and mapped for Anthropic by `toAnthropicContextManagement` in `providers/claude/chat/contextManagement.ts`. Tools work the same way: `normalize_tools_object` in the interface, then `toolsToWire` for OpenAI and `claudeToolPolicy` for Anthropic.
+
+Tests sit next to the code they test. Fixtures go in a `fixtures/` folder next to the test that reads them.
+
+## Adding a provider
+
+1. Create `providers/<vendor>/<interface>/`. Use the vendor's existing folder if it has one, so all of a vendor's interfaces stay together.
+2. Implement the interface's contract from `interfaces/<interface>/types.ts`:
+
+    | Interface | Contract | Base class |
+    | --- | --- | --- |
+    | chat | `IChatProvider` | `OpenAICompatProvider` for an OpenAI-compatible vendor |
+    | image | `IImageProvider` | none |
+    | video | `IVideoProvider` | `VideoProvider` |
+    | textToSpeech | `ITTSProvider` | none |
+    | speechToText | `ISpeechToTextProvider` | `SpeechToTextProvider` |
+    | ocr | `IOcrProvider` | none |
+
+    Speech to speech has one provider, so `VoiceChangerDriver` uses `ElevenLabsSpeechToSpeechProvider` directly. Add a contract to its `types.ts` when a second provider needs one.
+
+3. Put the model catalog and prices in the same folder, as `models.ts` or `costs.ts`. A provider that loads its catalog from the vendor wraps the fetch in `cachedRemoteCatalog` from `shared/`.
+4. Register the provider in the interface's driver: in `#registerProviders()`, or in `onServerStart()` for OCR and speech to speech. A chat provider built from an API key and an optional base URL is one row in `KEYED_PROVIDERS` instead. Text to speech and speech to text also list the provider id and its aliases in `providerAliases.ts`.
+5. Read credentials from `config.providers[<key>]`. The key is part of the self-hosting config contract, so reuse the vendor's existing key when it has one.
+6. Add tests next to the provider. Mock the vendor SDK or `fetch` at the network boundary and drive the provider through the real driver where you can. A live test is a `*.integration.test.ts` file that skips itself, with `skipUnlessEnv` from [testEnv.ts](../src/backend/testEnv.ts), unless its `PUTER_TEST_AI_*` variable is set. Helpers for provider tests are in [shared/integrationTestUtil.ts](../src/backend/drivers/ai/shared/integrationTestUtil.ts).
+7. For a chat provider, add its static catalog to `CATALOGS` in [modelCatalogs.test.ts](../src/backend/drivers/ai/interfaces/chat/modelCatalogs.test.ts) and the provider to [providerConsistency.test.ts](../src/backend/drivers/ai/interfaces/chat/providerConsistency.test.ts). The catalog test fails when a `providers/*/chat/` file with "model" in its name exports a catalog that isn't listed.
+8. Add the provider's config key to the `providers` config of the interface's [fuzz suite](#fuzz-tests), and its id to the list of providers the suite expects.
+9. Update the published docs for the models and limits the provider adds, following [contributing-apis.md](contributing-apis.md).
+
+### OpenAI-compatible vendors
+
+A vendor that speaks the OpenAI Chat Completions protocol extends `OpenAICompatProvider` and overrides only what differs. It still gets its own `providers/<vendor>/chat/` folder.
+
+Vendors share one constants-only folder only when at least six of them differ in nothing but base URL and model catalog. Each then becomes one data file under `providers/openaiCompatible/providers/`, read by a single implementation. No vendor qualifies today, because every subclass overrides request, catalog, or billing behavior.
+
+## Fuzz tests
+
+Two seeded suites send malformed input through the real drivers and providers. They run with the rest of the backend tests.
+
+| Suite | Covers |
+| --- | --- |
+| [interfaces/chat/ChatCompletionDriver.fuzz.test.ts](../src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.fuzz.test.ts) | Chat requests with a few values changed, and valid requests against wrong statuses, bodies of the wrong shape, and broken event streams. |
+| [interfaces/mediaDrivers.fuzz.test.ts](../src/backend/drivers/ai/interfaces/mediaDrivers.fuzz.test.ts) | Image, video, speech and OCR requests with a few values changed. Every vendor refuses the request. |
+
+What the suites assert:
+
+- A malformed request never fails with an error that has no status, which `/drivers/call` would report as an unclassified 500.
+- For chat, with the vendors answering, a malformed request also never fails with a 5xx and never marks a route unhealthy.
+- When the upstream misbehaves, chat ends with an answer or an `HttpError`. A stream only has to end: the error line a stream carries isn't checked, so a malformed event can still end one with a 500.
+- Requests reach the vendors, and with the vendors answering some chat requests are answered, so a suite that stops exercising the providers fails.
+
+The vendors are played at the HTTP boundary by `upstream` in [shared/fuzzTestUtil.ts](../src/backend/drivers/ai/shared/fuzzTestUtil.ts), which stands in for global `fetch`, undici `fetch` and axios, and makes `https.request` throw so an SDK with its own client fails the suite. The vendors' SDKs run, except Groq's, which is swapped for the OpenAI SDK, and the AWS clients, whose `send` is stubbed. The media suite calls the drivers as a user with unlimited metering, so a request gets past file input and the credit hold to the vendor. A provider that loads its catalog from the vendor registers no models there, so the suites skip it.
+
+A failure lists each distinct finding with its case number and input. Each case is generated from the seed and its own number, so the same case fails again on the next run. Routes are picked by rendezvous hashing: a model added to a catalog takes only the cases it wins, and every other case keeps its route. To search further, raise the case count:
+
+```sh
+PUTER_FUZZ_CASES=100000 npx vitest run --config src/backend/vitest.config.ts src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.fuzz.test.ts
+```
+
+When a suite finds a crash, validate the value where the request enters, in the driver or in `normalize_single_message`, so every provider is covered. Reject only what crashed: a value a provider ignored or refused before must still reach it. An option a driver reads as text, a number or a flag goes in the driver's `SCALAR_OPTIONS`, and `assertScalarOptions` from `shared/scalarOptions.ts` answers 400 for a value there that can't be converted to text. Add a unit test for the case next to the fix.
+
+## Adding an interface
+
+1. Create `interfaces/<interface>/` with the driver class and a `types.ts` for the contracts providers implement.
+2. Register the driver in [src/backend/drivers/index.ts](../src/backend/drivers/index.ts).
+3. Use `AI_RATE_LIMIT` and `AI_CONCURRENT` from `shared/aiLimits.ts`, and publish any new limit in [rate-limits-and-quotas.md](../src/docs/src/rate-limits-and-quotas.md).
+4. Meter through `withAiCostFactor` from `src/backend/util/aiCostFactor.ts`, and route between providers with `ProviderRegistry` from `shared/providerRegistry.ts`.
+5. List the options the providers read as text, a number or a flag in a `SCALAR_OPTIONS` array, and call `assertScalarOptions` from `shared/scalarOptions.ts` first in each method. Add the driver to [mediaDrivers.fuzz.test.ts](../src/backend/drivers/ai/interfaces/mediaDrivers.fuzz.test.ts).
+6. Follow [contributing-apis.md](contributing-apis.md) for the puter.js method, types, docs, and tests.

doc/architecture.md

@@ -42,6 +42,19 @@ block-beta
 
 Extensions sit alongside this stack and can register into any layer; see [Extensions](#extensions).
 
+### AI drivers
+
+The AI drivers have their own layout under [src/backend/drivers/ai/](../src/backend/drivers/ai/):
+
+| Folder | Holds |
+| --- | --- |
+| `interfaces/` | The Puter-facing drivers, one folder per AI interface (chat, image, video, text to speech, speech to text, speech to speech, OCR). |
+| `providers/` | Vendor code, as `providers/<vendor>/<interface>/`. |
+| `protocols/` | Wire protocols that several vendors speak, such as the OpenAI-compatible one. |
+| `shared/` | Helpers that more than one interface uses. |
+
+A call goes from an interface's driver to a provider, and from there to a shared protocol when the vendor speaks one. [ai-drivers.md](ai-drivers.md) has the ownership rules, the import rules, and the steps for adding a provider.
+
 ## Entry point: `PuterServer`
 
 `PuterServer` is the bootstrap. It:

src/backend/controllers/drivers/DriverController.concurrent.test.ts

@@ -324,7 +324,7 @@ describe('DriverController — concurrent acquire/release', () => {
         const driver = {
             ...makeSyntheticDriver(),
             ping: async () => {
-                Context.get('keepDriverSlot')?.(
+                Context.get('keepConcurrencySlot')?.(
                     new Promise<void>((resolve) => {
                         settleWork = resolve;
                     }),

src/backend/controllers/drivers/DriverController.ts

@@ -51,7 +51,7 @@ import { PermissionUtil } from '../../services/permission/permissionUtil.js';
 import type { WithLifecycle } from '../../types';
 import { withSpan } from '../../util/span.js';
 import { PuterController } from '../types.js';
-import { CallSlot } from './callSlot.js';
+import { CallSlot } from '../../core/http/callSlot.js';
 
 type DriverInstance = WithLifecycle & Record<string, unknown>;
 
@@ -446,7 +446,7 @@ export class DriverController extends PuterController {
                 });
             }
             slot.attach(handle, res);
-            Context.set('keepDriverSlot', (work) => slot.keep(work));
+            Context.set('keepConcurrencySlot', (work) => slot.keep(work));
         }
 
         // Stash the requested driver name in Context so multi-provider

src/backend/controllers/puterai/PuterAIController.shapes.test.ts

@@ -44,7 +44,7 @@ import {
 } from 'vitest';
 
 import type { Actor } from '../../core/actor.js';
-import type { ChatCompletionDriver } from '../../drivers/ai-chat/ChatCompletionDriver.js';
+import type { ChatCompletionDriver } from '../../drivers/ai/interfaces/chat/ChatCompletionDriver.js';
 import { PuterServer } from '../../server.js';
 import { inRequestScope, setupTestServer } from '../../testUtil.js';
 import { PuterAIController } from './PuterAIController.js';

src/backend/controllers/puterai/PuterAIController.test.ts

@@ -49,8 +49,8 @@ import type { RouteOptions } from '../../core/http/index.js';
 import {
     COUNT_TOKENS,
     type ChatCompletionDriver,
-} from '../../drivers/ai-chat/ChatCompletionDriver.js';
-import { AI_CONCURRENT, AI_RATE_LIMIT } from '../../drivers/util/aiLimits.js';
+} from '../../drivers/ai/interfaces/chat/ChatCompletionDriver.js';
+import { AI_CONCURRENT, AI_RATE_LIMIT } from '../../drivers/ai/shared/aiLimits.js';
 import { PuterServer } from '../../server.js';
 import { inRequestScope, setupTestServer } from '../../testUtil.js';
 import { PuterAIController } from './PuterAIController.js';

src/backend/controllers/puterai/PuterAIController.ts

@@ -30,25 +30,28 @@ import type { PuterRouter } from '../../core/http/PuterRouter.js';
 import {
     COUNT_TOKENS,
     type ChatCompletionDriver,
-} from '../../drivers/ai-chat/ChatCompletionDriver.js';
+} from '../../drivers/ai/interfaces/chat/ChatCompletionDriver.js';
 import type {
     IChatCompleteResult,
     IChatMessageResult,
     IChatModel,
     ICompleteArguments,
     UsageDetails,
-} from '../../drivers/ai-chat/types.js';
+} from '../../drivers/ai/interfaces/chat/types.js';
 import {
     outputFormatFromResponseFormat,
     rejectStatefulResponsesFields,
     toolChoiceFromWire,
-} from '../../drivers/ai-chat/utils/openaiParams.js';
+} from '../../drivers/ai/protocols/openaiCompatible/openaiParams.js';
 import {
     promoteStopForToolCalls,
     toFinishReason,
-} from '../../drivers/ai-chat/utils/stopReason.js';
+} from '../../drivers/ai/interfaces/chat/utils/stopReason.js';
 import { isDriverStreamResult } from '../../drivers/meta.js';
-import { AI_CONCURRENT, AI_RATE_LIMIT } from '../../drivers/util/aiLimits.js';
+import {
+    AI_CONCURRENT,
+    AI_RATE_LIMIT,
+} from '../../drivers/ai/shared/aiLimits.js';
 import { PuterController } from '../types.js';
 import { parseAnthropicRequest, toAnthropicMessage } from './anthropicWire.js';
 import { pipeNdjsonStream } from './ndjsonStream.js';
@@ -1301,13 +1304,18 @@ export class PuterAIController extends PuterController {
         return driver;
     }
 
-    /** A completion that stops, and stops billing, when the caller hangs up. */
+    /**
+     * A completion whose caller may hang up. It runs on to its usage report
+     * either way, so it holds the route's concurrency slot until it settles.
+     */
     #complete(
         res: Response,
         args: ICompleteArguments,
     ): Promise<IChatCompleteResult> {
         Context.set('abortSignal', abortOnDisconnect(res));
-        return this.#driver().complete(args);
+        const completion = this.#driver().complete(args);
+        Context.get('keepConcurrencySlot')?.(completion);
+        return completion;
     }
 }
 

src/backend/controllers/puterai/anthropicWire.test.ts

@@ -18,7 +18,7 @@
  */
 
 import { describe, expect, it } from 'vitest';
-import type { IChatMessageResult } from '../../drivers/ai-chat/types.js';
+import type { IChatMessageResult } from '../../drivers/ai/interfaces/chat/types.js';
 import {
     anthropicUsage,
     parseAnthropicRequest,

src/backend/controllers/puterai/anthropicWire.ts

@@ -32,7 +32,7 @@
 
 import type { IncomingHttpHeaders } from 'node:http';
 import { HttpError } from '../../core/http/HttpError.js';
-import { sanitizeCacheControl } from '../../drivers/ai-chat/providers/claude/anthropicPolicy.js';
+import { sanitizeCacheControl } from '../../drivers/ai/providers/claude/chat/anthropicPolicy.js';
 import type {
     ICompleteArguments,
     IChatMessageResult,
@@ -42,9 +42,9 @@ import type {
     ThinkingConfig,
     ToolChoice,
     UsageDetails,
-} from '../../drivers/ai-chat/types.js';
-import { needsOpenAICoercion } from '../../drivers/ai-chat/utils/normalizeToOpenAI.js';
-import { fromFinishReason } from '../../drivers/ai-chat/utils/stopReason.js';
+} from '../../drivers/ai/interfaces/chat/types.js';
+import { needsOpenAICoercion } from '../../drivers/ai/interfaces/chat/utils/normalizeToOpenAI.js';
+import { fromFinishReason } from '../../drivers/ai/interfaces/chat/utils/stopReason.js';
 
 const toStringOrEmpty = (v: unknown): string =>
     typeof v === 'string' ? v : '';

src/backend/controllers/puterai/sse.ts

@@ -20,15 +20,15 @@
 /**
  * SSE transport (`startSse`) plus the Anthropic `/v1/messages` streaming writer
  * (`AnthropicSseWriter`), which turns the driver's NDJSON chunk protocol
- * (`drivers/ai-chat/utils/Streaming.js`) into the exact Anthropic event
- * sequence: `message_start` → `content_block_start/delta/stop`* →
+ * (`drivers/ai/interfaces/chat/utils/Streaming.js`) into the exact Anthropic
+ * event sequence: `message_start` → `content_block_start/delta/stop`* →
  * `message_delta` → `message_stop`.
  */
 
 import type { Response } from 'express';
 import { onResponseClose } from '../../core/http/onResponseClose.js';
-import type { UsageDetails } from '../../drivers/ai-chat/types.js';
-import { promoteStopForToolCalls } from '../../drivers/ai-chat/utils/stopReason.js';
+import type { UsageDetails } from '../../drivers/ai/interfaces/chat/types.js';
+import { promoteStopForToolCalls } from '../../drivers/ai/interfaces/chat/utils/stopReason.js';
 import { anthropicUsage } from './anthropicWire.js';
 
 // -- SSE transport ------------------------------------------------------------

src/backend/core/context.ts

@@ -69,11 +69,11 @@ export interface KnownContextFields {
      */
     abortSignal: AbortSignal;
     /**
-     * Keeps the call's concurrency slot until `work` settles (set by
-     * DriverController when the method is capped), for work that outlives the
-     * response.
+     * Keeps the request's concurrency slot until `work` settles, for work that
+     * outlives the response. Set by DriverController for a capped method and by
+     * the route concurrency gate.
      */
-    keepDriverSlot: (work: Promise<unknown>) => void;
+    keepConcurrencySlot: (work: Promise<unknown>) => void;
     /**
      * Aborts the chat driver's upstream request. A client disconnect doesn't
      * fire it: the upstream bills a request it has accepted either way, so the
@@ -102,7 +102,7 @@ const KNOWN_KEY_FLAGS: Record<keyof KnownContextFields, true> = {
     requestId: true,
     driverName: true,
     abortSignal: true,
-    keepDriverSlot: true,
+    keepConcurrencySlot: true,
     upstreamSignal: true,
     strictUpstreamErrors: true,
     platformWrite: true,

src/backend/core/http/callSlot.ts

@@ -18,7 +18,7 @@
  */
 
 import type { Response } from 'express';
-import { onResponseClose } from '../../core/http/onResponseClose.js';
+import { onResponseClose } from './onResponseClose.js';
 
 // Under the concurrency store's one-hour orphan TTL.
 const SLOT_RENEW_MS = 10 * 60 * 1000;
@@ -29,9 +29,9 @@ interface SlotHandle {
 }
 
 /**
- * A driver call's concurrency slot, held until the response is done and the
- * call's work has settled, including work a driver carries on after the caller
- * hung up or was answered.
+ * A request's concurrency slot, held until the response is done and the work
+ * registered with `keep` has settled, including work that carries on after the
+ * caller hung up or was answered.
  */
 export class CallSlot {
     #handle?: SlotHandle;

src/backend/core/http/middleware/rateLimit.js

@@ -20,8 +20,9 @@
 
 import crypto from 'node:crypto';
 import { withSpan } from '../../../util/span.js';
+import { Context } from '../../context.js';
+import { CallSlot } from '../callSlot.js';
 import { HttpError } from '../HttpError.js';
-import { onResponseClose } from '../onResponseClose.js';
 import { subscriptionOverride } from '../../../services/metering/consts.js';
 
 /**
@@ -413,8 +414,8 @@ async function peekKv(kv, key, limit) {
 //
 // Lifecycle is the wedge between rate and concurrent limits: rate just
 // records a tick, concurrent has to track "still in flight" → "done"
-// across a request boundary. The route middleware hooks `res.finish` /
-// `res.close`; the driver helper wraps the invocation in `try/finally`.
+// across a request boundary. The route middleware and the driver controller
+// both hold the slot in a `CallSlot`.
 
 // Orphan TTL safety nets — used when the process dies between acquire
 // and release. Memory backend doesn't need one (the process is also
@@ -1138,8 +1139,9 @@ async function resolveSubscriptionLimit(req, opts) {
  * bySubscription: { user_free: 2, unlimited: 50 } } } { concurrent: { limit:
  * 10, backend: 'redis', scope: 'expensive-op' } }
  *
- * On accept, schedules release on `res.finish` / `res.close` so even aborted
- * requests give their slot back. On reject, 429 with the same
+ * On accept, holds the slot until the response is done and any work the handler
+ * registered through `keepConcurrencySlot` has settled, so work that outlives a
+ * caller who hung up still counts. On reject, 429 with the same
  * `too_many_requests` legacyCode as the rate gate (clients already handle that
  * branch). Fails open on backend error.
  */
@@ -1165,13 +1167,11 @@ export function concurrencyGate(opts) {
             return;
         }
 
-        // `finish` (response sent) and `close` (connection closed, possibly
-        // aborted before finish) can both fire; the guard releases once.
-        const { release } = guardSlot(slot, '[concurrent]');
-        const onDone = () => void release();
-        res.once('finish', onDone);
-        onResponseClose(res, onDone);
-        if (res.destroyed || res.writableFinished) onDone();
+        const held = new CallSlot();
+        held.attach(guardSlot(slot, '[concurrent]'), res);
+        if (Context.current()) {
+            Context.set('keepConcurrencySlot', (work) => held.keep(work));
+        }
         next();
     };
 }

src/backend/core/http/middleware/rateLimit.test.js

@@ -29,6 +29,7 @@ import {
     vi,
 } from 'vitest';
 import { EventEmitter } from 'node:events';
+import { Context, runWithContext } from '../../context.js';
 import { isHttpError } from '../HttpError.js';
 import { setupTestServer } from '../../../testUtil.ts';
 import {
@@ -977,6 +978,27 @@ describe('concurrencyGate — memory backend', () => {
         expect(isHttpError(third.err)).toBe(true);
     });
 
+    it('holds the slot past the response for work the handler keeps', async () => {
+        const opts = { limit: 1, key: 'ip', scope: 'cg-kept-work' };
+        let finishWork;
+        const work = new Promise((resolve) => {
+            finishWork = resolve;
+        });
+        const res = makeRes();
+        await runWithContext({}, async () => {
+            await concurrencyGate(opts)(baseReq(), res, () => {
+                Context.get('keepConcurrencySlot')(work);
+            });
+        });
+        res.emit('close');
+        await new Promise((r) => setImmediate(r));
+        expect((await runGate(opts, baseReq())).err?.statusCode).toBe(429);
+
+        finishWork();
+        await new Promise((r) => setImmediate(r));
+        expect((await runGate(opts, baseReq())).err).toBeUndefined();
+    });
+
     it('different keys do not share slots', async () => {
         const opts = { limit: 1, key: 'ip', scope: 'cg-keyed' };
         const a = await runGate(opts, baseReq({ ip: '1.1.1.1' }));

src/backend/core/http/types.ts

@@ -263,10 +263,10 @@ export interface RouteOptions {
     rateLimit?: RouteRateLimit | RouteRateLimit[];
 
     /**
-     * Cap simultaneous in-flight requests per key; slots are released on
-     * response finish or close. `bySubscription` overrides `limit` per
-     * `SubscriptionPolicy.id` when metering is wired in. `key`, `scope`,
-     * `backend` as in `rateLimit`.
+     * Cap simultaneous in-flight requests per key; a slot is released once the
+     * response is done and any work the handler kept it for has settled.
+     * `bySubscription` overrides `limit` per `SubscriptionPolicy.id` when
+     * metering is wired in. `key`, `scope`, `backend` as in `rateLimit`.
      */
     concurrent?: {
         limit: number;

src/backend/drivers/ai-chat/utils/compaction.test.ts

@@ -1,132 +0,0 @@
-/*
- * Copyright (C) 2024-present Puter Technologies Inc.
- *
- * This file is part of Puter.
- *
- * Puter is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published
- * by the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Affero General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with this program.  If not, see <https://www.gnu.org/licenses/>.
- */
-
-import { describe, expect, it } from 'vitest';
-import {
-    messagesHaveCompaction,
-    toAnthropicContextManagement,
-    toOpenAiContextManagement,
-    wantsCompaction,
-} from './compaction.js';
-
-describe('toOpenAiContextManagement', () => {
-    it('returns undefined when compaction is off', () => {
-        expect(toOpenAiContextManagement({})).toBeUndefined();
-        expect(
-            toOpenAiContextManagement({ compaction: false }),
-        ).toBeUndefined();
-    });
-
-    it('builds a compaction entry from `true`', () => {
-        expect(toOpenAiContextManagement({ compaction: true })).toEqual([
-            { type: 'compaction' },
-        ]);
-    });
-
-    it('maps trigger_tokens to compact_threshold', () => {
-        expect(
-            toOpenAiContextManagement({ compaction: { trigger_tokens: 1000 } }),
-        ).toEqual([{ type: 'compaction', compact_threshold: 1000 }]);
-    });
-
-    it('passes a raw context_management payload through verbatim', () => {
-        const raw = [{ type: 'compaction', compact_threshold: 5 }];
-        expect(
-            toOpenAiContextManagement({
-                compaction: true,
-                context_management: raw,
-            }),
-        ).toBe(raw);
-    });
-});
-
-describe('toAnthropicContextManagement', () => {
-    it('returns undefined when compaction is off', () => {
-        expect(toAnthropicContextManagement({})).toBeUndefined();
-    });
-
-    it('builds a compact_20260112 edit from `true`', () => {
-        expect(toAnthropicContextManagement({ compaction: true })).toEqual({
-            edits: [{ type: 'compact_20260112' }],
-        });
-    });
-
-    it('maps trigger_tokens to an input_tokens trigger', () => {
-        expect(
-            toAnthropicContextManagement({
-                compaction: { trigger_tokens: 2000 },
-            }),
-        ).toEqual({
-            edits: [
-                {
-                    type: 'compact_20260112',
-                    trigger: { type: 'input_tokens', value: 2000 },
-                },
-            ],
-        });
-    });
-
-    it('passes a raw context_management payload through verbatim', () => {
-        const raw = { edits: [{ type: 'compact_20260112' }] };
-        expect(
-            toAnthropicContextManagement({ context_management: raw }),
-        ).toBe(raw);
-    });
-});
-
-describe('wantsCompaction', () => {
-    it('is false without opt-in', () => {
-        expect(wantsCompaction({})).toBe(false);
-        expect(wantsCompaction({ compaction: false })).toBe(false);
-    });
-
-    it('is true for the neutral opt-in or a raw passthrough', () => {
-        expect(wantsCompaction({ compaction: true })).toBe(true);
-        expect(wantsCompaction({ compaction: { trigger_tokens: 1 } })).toBe(
-            true,
-        );
-        expect(wantsCompaction({ context_management: [] })).toBe(true);
-    });
-});
-
-describe('messagesHaveCompaction', () => {
-    it('detects a round-tripped compaction content block', () => {
-        expect(
-            messagesHaveCompaction([
-                { role: 'user', content: [{ type: 'text', text: 'hi' }] },
-                {
-                    role: 'assistant',
-                    content: [
-                        { type: 'compaction', encrypted_content: 'ENC' },
-                    ],
-                },
-            ]),
-        ).toBe(true);
-    });
-
-    it('is false for ordinary messages or non-arrays', () => {
-        expect(
-            messagesHaveCompaction([
-                { role: 'user', content: [{ type: 'text', text: 'hi' }] },
-            ]),
-        ).toBe(false);
-        expect(messagesHaveCompaction(undefined)).toBe(false);
-        expect(messagesHaveCompaction('nope')).toBe(false);
-    });
-});

src/backend/drivers/ai-ocr/OCRDriver.ts

@@ -1,718 +0,0 @@
-/*
- * Copyright (C) 2024-present Puter Technologies Inc.
- *
- * This file is part of Puter.
- *
- * Puter is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published
- * by the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Affero General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with this program.  If not, see <https://www.gnu.org/licenses/>.
- */
-
-import {
-    DetectDocumentTextCommand,
-    InvalidS3ObjectException,
-    TextractClient,
-    UnsupportedDocumentException,
-} from '@aws-sdk/client-textract';
-import { Mistral } from '@mistralai/mistralai';
-import { Actor } from '../../core/actor.js';
-import { Context } from '../../core/context.js';
-import { HttpError } from '../../core/http/HttpError.js';
-import {
-    awsCredentialsFrom,
-    type AwsCredentials,
-} from '../../util/awsCredentials.js';
-import { mimeFromName } from '../../util/fileSigning.js';
-import {
-    assertActorHasCredits,
-    insufficientCreditsError,
-} from '../../services/metering/enforcement.js';
-import type { CreditHold } from '../../services/metering/types.js';
-import { PuterDriver } from '../types.js';
-import {
-    type AiMeteringService,
-    withAiCostFactor,
-} from '../util/aiCostFactor.js';
-import { AI_CONCURRENT, AI_RATE_LIMIT } from '../util/aiLimits.js';
-import {
-    type LoadedFile,
-    type ResolvedFileInput,
-    resolveFileInput,
-} from '../util/fileInput.js';
-import {
-    type ProviderCatalog,
-    ProviderRegistry,
-    readProviderKey,
-} from '../util/providerRegistry.js';
-import { OCR_COSTS } from './costs.js';
-import {
-    DEFAULT_OCR_MODEL,
-    findOcrModel,
-    OCR_MAX_INPUT_BYTES,
-    OCR_MAX_PAGES,
-    RETIRED_OCR_MODELS,
-    type OcrModel,
-    type OcrProviderId,
-} from './models.js';
-import { countPdfPages } from './pdfPages.js';
-import { textractRates } from './textractPricing.js';
-
-/**
- * Driver implementing `puter-ocr` — document OCR. Two providers: •
- * `aws-textract` — AWS Textract (region-aware clients; direct S3 source when
- * available) • `mistral` — Mistral OCR (URL/data-URL based)
- */
-interface RecognizeArgs {
-    source?: unknown;
-    file?: unknown;
-    provider?: string;
-    model?: string;
-    // Mistral-specific options — ignored by Textract.
-    pages?: number[];
-    includeImageBase64?: boolean;
-    imageLimit?: number;
-    imageMinSize?: number;
-    bboxAnnotationFormat?: unknown;
-    documentAnnotationFormat?: unknown;
-    documentAnnotationPrompt?: string;
-    tableFormat?: string;
-    extractHeader?: boolean;
-    extractFooter?: boolean;
-    test_mode?: boolean;
-}
-
-/** One recognized line, in the same shape for every provider. */
-interface OcrBlock {
-    type: string;
-    text: string;
-    confidence?: number;
-    page: number;
-}
-
-interface TextractBlock {
-    BlockType?: string;
-    Confidence?: number;
-    Text?: string;
-}
-
-interface MistralOcrResponse {
-    model?: string;
-    pages?: Array<{
-        index?: number;
-        markdown?: string;
-        images?: unknown[];
-        dimensions?: unknown;
-    }>;
-    documentAnnotation?: string | null;
-    usageInfo?: { pagesProcessed?: number };
-}
-
-interface MistralOcrClient {
-    ocr: {
-        process: (
-            payload: Record<string, unknown>,
-        ) => Promise<MistralOcrResponse>;
-    };
-}
-
-// Aliases callers may use in place of a canonical provider id. Resolved here
-// rather than in the SDK so a new alias reaches every caller at once.
-const OCR_CATALOG: ProviderCatalog = {
-    label: 'OCR',
-    ids: ['aws-textract', 'mistral'],
-    defaultId: 'aws-textract',
-    aliases: {
-        aws: 'aws-textract',
-        'aws-textract': 'aws-textract',
-        textract: 'aws-textract',
-        mistral: 'mistral',
-        'mistral-ocr': 'mistral',
-    },
-};
-
-/** Recognizes one input with one provider's model. */
-type OcrRecognizer = (
-    input: ResolvedFileInput,
-    args: RecognizeArgs,
-    model: OcrModel,
-    actor: Actor,
-) => Promise<unknown>;
-
-const NOT_CONFIGURED: Record<OcrProviderId, string> = {
-    'aws-textract': 'AWS credentials not configured',
-    mistral: 'Mistral OCR not configured',
-};
-
-const TABLE_FORMATS = new Set(['markdown', 'html']);
-
-const DEFAULT_TEXTRACT_REGION = 'us-west-2';
-const TEXTRACT_PAGE_USAGE_TYPE = 'aws-textract:detect-document-text:page';
-
-const badRequest = (message: string) =>
-    new HttpError(400, message, { legacyCode: 'bad_request' });
-
-/**
- * Accept a Mistral annotation format in the REST spelling
- * (`json_schema.schema`) or the SDK spelling (`jsonSchema.schemaDefinition`)
- * and return the SDK shape.
- */
-const toMistralResponseFormat = (
-    name: string,
-    value: unknown,
-): Record<string, unknown> => {
-    const format = value as Record<string, unknown> | null;
-    const jsonSchema = (format?.jsonSchema ?? format?.json_schema) as
-        Record<string, unknown> | undefined;
-    const schema = jsonSchema?.schemaDefinition ?? jsonSchema?.schema;
-    if (
-        !format ||
-        typeof format !== 'object' ||
-        (format.type !== undefined && format.type !== 'json_schema') ||
-        !schema ||
-        typeof schema !== 'object'
-    ) {
-        throw badRequest(
-            `\`${name}\` must be { type: 'json_schema', json_schema: { name, schema } }`,
-        );
-    }
-    return {
-        type: 'json_schema',
-        jsonSchema: {
-            name:
-                typeof jsonSchema?.name === 'string'
-                    ? jsonSchema.name
-                    : 'annotation',
-            schemaDefinition: schema,
-            ...(typeof jsonSchema?.description === 'string' && {
-                description: jsonSchema.description,
-            }),
-            ...(typeof jsonSchema?.strict === 'boolean' && {
-                strict: jsonSchema.strict,
-            }),
-        },
-    };
-};
-
-const inputMimeType = (loaded: LoadedFile): string =>
-    loaded.mimeType ??
-    mimeFromName(loaded.filename) ??
-    'application/octet-stream';
-
-/**
- * Declared documents (PDF, DOCX, PPTX, ...) and PDF bytes are documents; images
- * and untyped bytes are read as a single image.
- */
-const isDocumentInput = (loaded: LoadedFile): boolean => {
-    const mime = inputMimeType(loaded);
-    return (
-        loaded.buffer.subarray(0, 4).toString('latin1') === '%PDF' ||
-        loaded.filename.toLowerCase().endsWith('.pdf') ||
-        (!mime.startsWith('image/') && mime !== 'application/octet-stream')
-    );
-};
-
-/**
- * The most pages a call can bill, known before the provider runs: a PDF's page
- * count, or a size-based guess for other documents, capped by a `pages`
- * selection and by what the provider reads in one call. Reads the input only
- * for a provider that takes more than one page.
- */
-const estimateOcrPages = async (
-    input: ResolvedFileInput,
-    provider: OcrProviderId,
-    selection?: unknown,
-): Promise<number> => {
-    const maxPages = OCR_MAX_PAGES[provider];
-    if (maxPages <= 1) return 1;
-    const loaded = await input.load();
-    if (!isDocumentInput(loaded)) return 1;
-    // A document we can't count is billed in proportion to its size, reaching
-    // the provider's page limit at its size limit (20 pages per MB for
-    // Mistral). Small files stay cheap; a large one can't pass as one page.
-    const documentPages =
-        (await countPdfPages(loaded.buffer, maxPages)) ??
-        Math.ceil(
-            (loaded.buffer.length * maxPages) / OCR_MAX_INPUT_BYTES[provider],
-        );
-    const selected = Array.isArray(selection)
-        ? new Set(
-              selection.filter(
-                  (page) => Number.isInteger(page) && (page as number) >= 0,
-              ),
-          ).size
-        : 0;
-    return Math.max(1, Math.min(documentPages, maxPages, selected || Infinity));
-};
-
-export class OCRDriver extends PuterDriver {
-    readonly driverInterface = 'puter-ocr';
-    readonly driverName = 'ai-ocr';
-
-    // Shared AI policy — see `drivers/util/aiLimits.ts` for the tier table.
-    readonly rateLimit = AI_RATE_LIMIT;
-    readonly concurrent = AI_CONCURRENT;
-
-    /** Metering scoped to this driver. Lazy: services wire up after drivers. */
-    get #aiMetering(): AiMeteringService {
-        return withAiCostFactor(
-            this.services.metering,
-            this.clients.event,
-            this.driverName,
-        );
-    }
-
-    /**
-     * Textract is reported at the configured region's first-tier rate. A call
-     * that reads its file from a bucket in another region is billed at that
-     * region's rate instead, which this per-usage-type report can't show.
-     */
-    override getReportedCosts() {
-        const textractRegion =
-            this.#awsConfig?.region ?? DEFAULT_TEXTRACT_REGION;
-        return Object.entries(OCR_COSTS).map(([usageType, ucentsPerUnit]) => ({
-            usageType,
-            ucentsPerUnit:
-                usageType === TEXTRACT_PAGE_USAGE_TYPE
-                    ? this.#textractRates.peek(textractRegion)
-                    : ucentsPerUnit,
-            unit: 'page',
-            source: 'driver:aiOcr',
-        }));
-    }
-
-    // Older SDK bundles name the provider in the driver slot instead of
-    // passing `{ provider }`; `#resolveModel` reads the requested alias
-    // back off the Context.
-    readonly driverAliases = [...OCR_CATALOG.ids];
-    readonly isDefault = true;
-
-    // Textract state — one client per region.
-    #textractClients: Record<string, TextractClient> = {};
-    #awsConfig: { credentials: AwsCredentials; region: string } | null = null;
-    /** DetectDocumentText rates per region, from AWS's public price list. */
-    #textractRates = textractRates(OCR_COSTS[TEXTRACT_PAGE_USAGE_TYPE]);
-
-    // Mistral state.
-    #mistral: MistralOcrClient | null = null;
-
-    /** Configured providers, each a recognizer bound to its state above. */
-    #providers = new ProviderRegistry<OcrRecognizer>(OCR_CATALOG);
-
-    override onServerStart() {
-        const providers = this.config.providers ?? {};
-
-        const textract = providers['aws-textract'] as
-            Record<string, unknown> | undefined;
-        const textractAws = (textract?.aws ?? textract) as
-            Record<string, unknown> | undefined;
-        const textractCredentials = awsCredentialsFrom(textractAws);
-        const textractRegion =
-            (textractAws?.region as string | undefined) ??
-            (textract?.region as string | undefined) ??
-            DEFAULT_TEXTRACT_REGION;
-        if (textractCredentials) {
-            this.#awsConfig = {
-                credentials: textractCredentials,
-                region: textractRegion,
-            };
-            // Warm the configured region so the cost report has its rate.
-            void this.#textractRates.rate(textractRegion);
-            this.#providers.register(
-                'aws-textract',
-                (input, _args, model, actor) =>
-                    this.#textractRecognize(input, model, actor),
-            );
-        }
-
-        const mistralKey = readProviderKey(providers['mistral-ocr']);
-        if (mistralKey) {
-            try {
-                this.#mistral = new Mistral({
-                    apiKey: mistralKey,
-                }) as unknown as MistralOcrClient;
-                this.#providers.register(
-                    'mistral',
-                    (input, args, model, actor) =>
-                        this.#mistralRecognize(input, args, model, actor),
-                );
-            } catch (e) {
-                console.warn(
-                    '[OCRDriver] Failed to init Mistral:',
-                    (e as Error).message,
-                );
-            }
-        }
-    }
-
-    async recognize(args: RecognizeArgs) {
-        if (args.test_mode) return sampleResponse();
-
-        const model = this.#resolveModel(args);
-
-        const actor = Context.get('actor');
-        if (!actor)
-            throw new HttpError(401, 'Authentication required', {
-                legacyCode: 'unauthorized',
-            });
-
-        const input = args.source ?? args.file;
-        if (!input) throw badRequest('`source` is required');
-
-        const recognize = this.#providers.get(model.provider);
-        if (!recognize)
-            throw new HttpError(500, NOT_CONFIGURED[model.provider], {
-                legacyCode: 'internal_error',
-            });
-
-        // Cheap, cached check: reject a zero-balance actor before paying for
-        // the file load and page estimate, which a real credit check would
-        // reject anyway once it runs.
-        await assertActorHasCredits(this.services.metering, actor, this.config);
-
-        // A Puter file is resolved and access-checked here but read only if
-        // the provider needs its bytes; Textract reads it straight from S3.
-        const resolved = await resolveFileInput(
-            this.stores,
-            this.services.fs,
-            actor,
-            input,
-            {
-                acceptWebInput: true,
-                maxBytes: OCR_MAX_INPUT_BYTES[model.provider],
-            },
-        );
-
-        return recognize(resolved, args, model, actor);
-    }
-
-    /**
-     * Decide which model handles a call. A `model` picks its own provider; an
-     * explicit `provider`, then the legacy driver alias the caller dispatched
-     * through, then whichever provider is configured pick that provider's
-     * default model.
-     */
-    #resolveModel(args: RecognizeArgs): OcrModel {
-        const provider = args.provider
-            ? (this.#providers.resolve(args.provider) as OcrProviderId)
-            : undefined;
-
-        if (args.model !== undefined) {
-            if (typeof args.model !== 'string' || !args.model.trim())
-                throw badRequest('`model` must be a non-empty string');
-            const retired = RETIRED_OCR_MODELS[args.model.trim().toLowerCase()];
-            if (retired)
-                throw badRequest(
-                    `${args.model} is no longer available: ${retired}`,
-                );
-            const model = findOcrModel(args.model);
-            if (!model) throw badRequest(`Unknown OCR model: ${args.model}`);
-            if (provider && model.provider !== provider)
-                throw badRequest(
-                    `OCR model ${args.model} is not served by provider ${args.provider}`,
-                );
-            return model;
-        }
-
-        const hinted =
-            provider ?? this.#providers.normalize(Context.get('driverName'));
-        if (!hinted && this.#providers.names().length === 0)
-            throw new HttpError(500, 'No OCR provider configured', {
-                legacyCode: 'internal_error',
-            });
-        const chosen = (hinted ?? this.#providers.defaultId()) as OcrProviderId;
-        return findOcrModel(DEFAULT_OCR_MODEL[chosen])!;
-    }
-
-    /**
-     * Refuse a call the balance can't cover, and hold its cost while the
-     * provider runs so the account's concurrent calls see it. Usage is still
-     * metered from the pages the provider reports.
-     */
-    async #holdCredits(
-        actor: Actor,
-        usageType: string,
-        cost: number,
-    ): Promise<CreditHold> {
-        // Priced at the cost factor usage is recorded at.
-        const hold = await this.#aiMetering.reserveAiCredits(
-            actor,
-            usageType,
-            cost,
-        );
-        if (!hold) throw insufficientCreditsError();
-        return hold;
-    }
-
-    // -- AWS Textract -------------------------------------------------
-
-    #textractClientFor(region: string): TextractClient {
-        const cached = this.#textractClients[region];
-        if (cached) return cached;
-        const client = new TextractClient({
-            credentials: this.#awsConfig!.credentials,
-            region,
-        });
-        this.#textractClients[region] = client;
-        return client;
-    }
-
-    async #textractRecognize(
-        input: ResolvedFileInput,
-        model: OcrModel,
-        actor: Actor,
-    ) {
-        // Prefer S3 direct source if the file is FS-backed; fall back to raw bytes.
-        const { fsEntry } = input;
-        const s3Info =
-            fsEntry && fsEntry.bucket && fsEntry.bucketRegion
-                ? {
-                      bucket: fsEntry.bucket,
-                      bucketRegion: fsEntry.bucketRegion,
-                      key: fsEntry.uuid,
-                  }
-                : null;
-
-        const configuredRegion =
-            this.#awsConfig!.region ?? DEFAULT_TEXTRACT_REGION;
-
-        // Both regions the call may run in are priced up front, so the hold
-        // covers either and a refresh mid-call can't change the charge.
-        const [configuredRate, s3Rate] = await Promise.all([
-            this.#textractRates.rate(configuredRegion),
-            s3Info ? this.#textractRates.rate(s3Info.bucketRegion) : undefined,
-        ]);
-
-        const tryRun = async (useS3: boolean) => {
-            const region =
-                s3Info && useS3 ? s3Info.bucketRegion : configuredRegion;
-            const client = this.#textractClientFor(region);
-            const document =
-                s3Info && useS3
-                    ? { S3Object: { Bucket: s3Info.bucket, Name: s3Info.key } }
-                    : { Bytes: (await input.load()).buffer };
-            return client.send(
-                new DetectDocumentTextCommand({ Document: document }),
-            );
-        };
-
-        const hold = await this.#holdCredits(
-            actor,
-            model.pageUsageType,
-            Math.max(configuredRate, s3Rate ?? 0) *
-                (await estimateOcrPages(input, model.provider)),
-        );
-        try {
-            let response;
-            let costPerPage: number;
-            try {
-                try {
-                    response = await tryRun(Boolean(s3Info));
-                    costPerPage = s3Rate ?? configuredRate;
-                } catch (err) {
-                    if (!(s3Info && err instanceof InvalidS3ObjectException))
-                        throw err;
-                    response = await tryRun(false);
-                    costPerPage = configuredRate;
-                }
-            } catch (err) {
-                if (err instanceof UnsupportedDocumentException)
-                    throw badRequest(
-                        'AWS Textract reads JPEG, PNG, TIFF and single-page PDF documents; use a Mistral OCR model for multi-page PDFs and other formats',
-                    );
-                throw err;
-            }
-
-            const blocks: OcrBlock[] = [];
-            let pageCount = 0;
-            for (const block of (response.Blocks ?? []) as TextractBlock[]) {
-                if (block.BlockType === 'PAGE') {
-                    pageCount += 1;
-                    continue;
-                }
-                if (block.BlockType !== 'LINE' || !block.Text) continue;
-                blocks.push({
-                    type: 'text/textract:LINE',
-                    text: block.Text,
-                    confidence: Number(block.Confidence ?? 0),
-                    page: Math.max(pageCount - 1, 0),
-                });
-            }
-
-            const pages = pageCount || 1;
-            this.#aiMetering.incrementUsage(
-                actor,
-                model.pageUsageType,
-                pages,
-                costPerPage * pages,
-            );
-            return {
-                model: model.id,
-                blocks,
-                text: blocks.map((b) => b.text).join('\n'),
-            };
-        } finally {
-            await hold.release();
-        }
-    }
-
-    // -- Mistral OCR --------------------------------------------------
-
-    async #mistralRecognize(
-        input: ResolvedFileInput,
-        args: RecognizeArgs,
-        model: OcrModel,
-        actor: Actor,
-    ) {
-        const loaded = await input.load();
-        const payload: Record<string, unknown> = {
-            model: model.id,
-            document: this.#mistralBuildChunk(loaded),
-        };
-        if (args.pages) payload.pages = args.pages;
-        if (args.includeImageBase64 !== undefined)
-            payload.includeImageBase64 = args.includeImageBase64;
-        if (typeof args.imageLimit === 'number')
-            payload.imageLimit = args.imageLimit;
-        if (typeof args.imageMinSize === 'number')
-            payload.imageMinSize = args.imageMinSize;
-        if (args.bboxAnnotationFormat !== undefined)
-            payload.bboxAnnotationFormat = toMistralResponseFormat(
-                'bboxAnnotationFormat',
-                args.bboxAnnotationFormat,
-            );
-        if (args.documentAnnotationFormat !== undefined)
-            payload.documentAnnotationFormat = toMistralResponseFormat(
-                'documentAnnotationFormat',
-                args.documentAnnotationFormat,
-            );
-        if (typeof args.documentAnnotationPrompt === 'string')
-            payload.documentAnnotationPrompt = args.documentAnnotationPrompt;
-        if (args.tableFormat !== undefined) {
-            if (!TABLE_FORMATS.has(args.tableFormat))
-                throw badRequest("`tableFormat` must be 'markdown' or 'html'");
-            payload.tableFormat = args.tableFormat;
-        }
-        if (typeof args.extractHeader === 'boolean')
-            payload.extractHeader = args.extractHeader;
-        if (typeof args.extractFooter === 'boolean')
-            payload.extractFooter = args.extractFooter;
-
-        const annotations =
-            payload.documentAnnotationFormat !== undefined ||
-            payload.bboxAnnotationFormat !== undefined;
-        const costPerPage =
-            OCR_COSTS[model.pageUsageType] +
-            (annotations && model.annotationUsageType
-                ? OCR_COSTS[model.annotationUsageType]
-                : 0);
-        const hold = await this.#holdCredits(
-            actor,
-            model.pageUsageType,
-            costPerPage *
-                (await estimateOcrPages(input, model.provider, args.pages)),
-        );
-
-        try {
-            const response = await this.#mistral!.ocr.process(payload);
-            this.#recordMistralUsage(response, model, actor, annotations);
-            return this.#normalizeMistralResponse(response, model);
-        } finally {
-            await hold.release();
-        }
-    }
-
-    #mistralBuildChunk(loaded: LoadedFile): Record<string, unknown> {
-        const mime = inputMimeType(loaded);
-        const dataUrl = `data:${mime};base64,${loaded.buffer.toString('base64')}`;
-        if (isDocumentInput(loaded)) {
-            return {
-                type: 'document_url',
-                documentUrl: dataUrl,
-                documentName: loaded.filename,
-            };
-        }
-        return { type: 'image_url', imageUrl: { url: dataUrl } };
-    }
-
-    #normalizeMistralResponse(response: MistralOcrResponse, model: OcrModel) {
-        const pages = response?.pages ?? [];
-        const blocks: OcrBlock[] = [];
-        for (const [position, page] of pages.entries()) {
-            if (typeof page?.markdown !== 'string') continue;
-            const lines = page.markdown
-                .split('\n')
-                .map((l) => l.trim())
-                .filter(Boolean);
-            for (const line of lines) {
-                blocks.push({
-                    type: 'text/mistral:LINE',
-                    text: line,
-                    page: page.index ?? position,
-                });
-            }
-        }
-        return {
-            model: response?.model ?? model.id,
-            pages,
-            usage_info: response?.usageInfo,
-            ...(typeof response?.documentAnnotation === 'string' && {
-                document_annotation: response.documentAnnotation,
-            }),
-            blocks,
-            text: blocks.map((b) => b.text).join('\n'),
-        };
-    }
-
-    #recordMistralUsage(
-        response: MistralOcrResponse,
-        model: OcrModel,
-        actor: Actor,
-        annotations: boolean,
-    ) {
-        try {
-            const pagesProcessed =
-                response?.usageInfo?.pagesProcessed ??
-                (Array.isArray(response?.pages) ? response.pages.length : 1);
-            this.#aiMetering.incrementUsage(
-                actor,
-                model.pageUsageType,
-                pagesProcessed,
-                OCR_COSTS[model.pageUsageType] * pagesProcessed,
-            );
-            if (annotations && model.annotationUsageType) {
-                this.#aiMetering.incrementUsage(
-                    actor,
-                    model.annotationUsageType,
-                    pagesProcessed,
-                    OCR_COSTS[model.annotationUsageType] * pagesProcessed,
-                );
-            }
-        } catch {
-            // Non-critical.
-        }
-    }
-}
-
-function sampleResponse() {
-    return {
-        model: 'test-mode',
-        blocks: [
-            {
-                type: 'text/puter:sample-output',
-                confidence: 1,
-                text: 'test_mode is enabled; this is a sample OCR response.',
-                page: 0,
-            },
-        ],
-        text: 'test_mode is enabled; this is a sample OCR response.',
-    };
-}

src/backend/drivers/ai-speech2speech/VoiceChangerDriver.ts

@@ -1,511 +0,0 @@
-/*
- * Copyright (C) 2024-present Puter Technologies Inc.
- *
- * This file is part of Puter.
- *
- * Puter is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published
- * by the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Affero General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with this program.  If not, see <https://www.gnu.org/licenses/>.
- */
-
-import { pipeline, Readable, Transform } from 'node:stream';
-import { Context } from '../../core/context.js';
-import { HttpError } from '../../core/http/HttpError.js';
-import type { DriverStreamResult } from '../meta.js';
-import { OUTPUT_FORMATS } from '../ai-tts/providers/elevenlabs/ElevenLabsTTSProvider.js';
-import { PuterDriver } from '../types.js';
-import {
-    type AiMeteringService,
-    withAiCostFactor,
-    withStreamedAiCharge,
-} from '../util/aiCostFactor.js';
-import { AI_CONCURRENT, AI_RATE_LIMIT } from '../util/aiLimits.js';
-import { loadFileInput } from '../util/fileInput.js';
-import {
-    type ProviderCatalog,
-    ProviderRegistry,
-    readProviderKey,
-} from '../util/providerRegistry.js';
-import { SAMPLE_AUDIO_URL } from '../util/testMode.js';
-import { upstreamBodyStream, upstreamFetch } from '../util/upstreamErrors.js';
-import { VOICE_CHANGER_COSTS } from './costs.js';
-
-/**
- * Driver implementing `puter-speech2speech` — voice changer. Currently a single
- * provider (ElevenLabs).
- */
-
-const DEFAULT_MODEL = 'eleven_multilingual_sts_v2';
-const DEFAULT_VOICE_ID = '21m00Tcm4TlvDq8ikWAM';
-const DEFAULT_OUTPUT_FORMAT = 'mp3_44100_128';
-const MAX_AUDIO_FILE_SIZE = 25 * 1024 * 1024;
-// Covers the upload as well as the conversion.
-const CONVERT_TIMEOUT_MS = 10 * 60 * 1000;
-
-const SUPPORTED_MODELS = Object.keys(VOICE_CHANGER_COSTS).map(
-    (key) => key.split(':')[1]!,
-);
-
-const VOICE_CHANGER_CATALOG: ProviderCatalog = {
-    label: 'Speech-to-speech',
-    ids: ['elevenlabs'],
-    defaultId: 'elevenlabs',
-    aliases: { elevenlabs: 'elevenlabs' },
-};
-
-interface ElevenLabsConfig {
-    apiKey: string;
-    baseUrl: string;
-    defaultVoiceId: string;
-    defaultModelId: string;
-}
-
-interface ConvertArgs {
-    audio: unknown;
-    provider?: string;
-    voice?: string;
-    voice_id?: string;
-    voiceId?: string;
-    model?: string;
-    model_id?: string;
-    voice_settings?: unknown;
-    voiceSettings?: unknown;
-    seed?: number;
-    remove_background_noise?: boolean;
-    output_format?: string;
-    file_format?: string;
-    optimize_streaming_latency?: number;
-    enable_logging?: boolean;
-    test_mode?: boolean;
-}
-
-export class VoiceChangerDriver extends PuterDriver {
-    readonly driverInterface = 'puter-speech2speech';
-    readonly driverName = 'ai-speech2speech';
-    // Older SDK bundles name the provider in the driver slot.
-    readonly driverAliases = ['elevenlabs-voice-changer'];
-    readonly isDefault = true;
-
-    // Shared AI policy — see `drivers/util/aiLimits.ts` for the tier table.
-    readonly rateLimit = AI_RATE_LIMIT;
-    readonly concurrent = AI_CONCURRENT;
-
-    /** Metering scoped to this driver. Lazy: services wire up after drivers. */
-    get #aiMetering(): AiMeteringService {
-        return withAiCostFactor(
-            this.services.metering,
-            this.clients.event,
-            this.driverName,
-        );
-    }
-
-    override getReportedCosts(): Record<string, unknown>[] {
-        return Object.entries(VOICE_CHANGER_COSTS).map(
-            ([usageType, ucentsPerUnit]) => ({
-                usageType,
-                ucentsPerUnit,
-                unit: 'second',
-                source: 'driver:aiSpeech2Speech',
-            }),
-        );
-    }
-
-    #providers = new ProviderRegistry<ElevenLabsConfig>(VOICE_CHANGER_CATALOG);
-
-    override onServerStart() {
-        const elevenlabs = this.config.providers?.elevenlabs;
-        const apiKey = readProviderKey(elevenlabs);
-        if (!apiKey) return;
-        this.#providers.register('elevenlabs', {
-            apiKey,
-            baseUrl:
-                (elevenlabs?.apiBaseUrl as string | undefined) ??
-                'https://api.elevenlabs.io',
-            defaultVoiceId:
-                (elevenlabs?.defaultVoiceId as string | undefined) ??
-                DEFAULT_VOICE_ID,
-            defaultModelId:
-                (elevenlabs?.speechToSpeechModelId as string | undefined) ??
-                DEFAULT_MODEL,
-        });
-    }
-
-    async convert(
-        args: ConvertArgs,
-    ): Promise<DriverStreamResult | { url: string; content_type: string }> {
-        // Only one provider exists today, but naming a different one should
-        // fail loudly rather than quietly convert with this one.
-        const providerName = this.#providers.resolve(args.provider);
-
-        if (args.test_mode) {
-            return { url: SAMPLE_AUDIO_URL, content_type: 'audio/mpeg' };
-        }
-
-        const elevenlabs = this.#providers.get(providerName);
-        if (!elevenlabs) {
-            throw new HttpError(500, 'ElevenLabs API key not configured', {
-                legacyCode: 'internal_error',
-            });
-        }
-
-        const actor = Context.get('actor');
-        if (!actor)
-            throw new HttpError(401, 'Authentication required', {
-                legacyCode: 'unauthorized',
-            });
-
-        if (!args.audio) {
-            throw new HttpError(400, '`audio` is required', {
-                legacyCode: 'bad_request',
-            });
-        }
-
-        const modelId =
-            args.model_id || args.model || elevenlabs.defaultModelId;
-        const voiceId =
-            args.voice_id ||
-            args.voiceId ||
-            args.voice ||
-            elevenlabs.defaultVoiceId;
-        if (!voiceId)
-            throw new HttpError(400, '`voice` is required', {
-                legacyCode: 'bad_request',
-            });
-        // `voiceId` lands in the request URL path, which carries our API key,
-        // so anything outside ElevenLabs' `[A-Za-z0-9_-]+` id shape could
-        // steer the request at a different endpoint.
-        if (!/^[A-Za-z0-9_-]+$/.test(voiceId))
-            throw new HttpError(400, '`voice` must be alphanumeric', {
-                legacyCode: 'bad_request',
-            });
-
-        // Gate on the cost table: an id we can't price is one we can't bill
-        // for, and ElevenLabs bills us for it either way. This also keeps
-        // anything but a known id out of the multipart `model_id` field.
-        const usageKey = `elevenlabs:${modelId}:second`;
-        if (!Object.hasOwn(VOICE_CHANGER_COSTS, usageKey)) {
-            throw new HttpError(
-                400,
-                `Invalid model: ${modelId}. Expected: ${SUPPORTED_MODELS.join(', ')}`,
-                {
-                    legacyCode: 'field_invalid',
-                    fields: {
-                        key: 'model',
-                        expected: SUPPORTED_MODELS,
-                        got: modelId,
-                    },
-                },
-            );
-        }
-        const ucentsPerSecond = VOICE_CHANGER_COSTS[usageKey]!;
-
-        const loaded = await loadFileInput(
-            this.stores,
-            this.services.fs,
-            actor,
-            args.audio,
-            { maxBytes: MAX_AUDIO_FILE_SIZE, acceptWebInput: true },
-        );
-
-        // The hold estimates seconds from the input at 128 kbps: compact audio
-        // is under-held rather than refused. Usage is metered from the length
-        // of the audio that comes back.
-        const estimatedSeconds = Math.max(
-            1,
-            Math.ceil(loaded.buffer.byteLength / 16000),
-        );
-        const estimatedCost = ucentsPerSecond * estimatedSeconds;
-
-        const formData = new FormData();
-        const blob = new Blob([loaded.buffer as BlobPart], {
-            type: loaded.mimeType ?? 'application/octet-stream',
-        });
-        formData.append('audio', blob, loaded.filename);
-        formData.append('model_id', modelId);
-
-        const settings = args.voice_settings ?? args.voiceSettings;
-        if (settings !== undefined && settings !== null) {
-            formData.append(
-                'voice_settings',
-                typeof settings === 'string'
-                    ? settings
-                    : JSON.stringify(settings),
-            );
-        }
-        if (args.seed !== undefined && args.seed !== null) {
-            formData.append('seed', String(args.seed));
-        }
-        if (typeof args.remove_background_noise === 'boolean') {
-            formData.append(
-                'remove_background_noise',
-                String(args.remove_background_noise),
-            );
-        }
-        if (args.file_format) {
-            formData.append('file_format', args.file_format);
-        }
-
-        const searchParams = new URLSearchParams();
-        const outputFormat = args.output_format || DEFAULT_OUTPUT_FORMAT;
-        if (outputFormat) searchParams.set('output_format', outputFormat);
-        if (
-            args.optimize_streaming_latency !== undefined &&
-            args.optimize_streaming_latency !== null
-        ) {
-            searchParams.set(
-                'optimize_streaming_latency',
-                String(args.optimize_streaming_latency),
-            );
-        }
-        if (args.enable_logging !== undefined && args.enable_logging !== null) {
-            searchParams.set('enable_logging', String(args.enable_logging));
-        }
-
-        const url = new URL(
-            `/v1/speech-to-speech/${voiceId}`,
-            elevenlabs.baseUrl,
-        );
-        const search = searchParams.toString();
-        if (search) url.search = search;
-
-        const metering = this.#aiMetering;
-        const output = measuredOutput(
-            outputBytesPerSecond(outputFormat),
-            outputFormat,
-        );
-        return withStreamedAiCharge(
-            metering,
-            actor,
-            usageKey,
-            estimatedCost,
-            async (): Promise<DriverStreamResult> => {
-                const response = await upstreamFetch(
-                    'elevenlabs',
-                    url,
-                    {
-                        method: 'POST',
-                        headers: { 'xi-api-key': elevenlabs.apiKey },
-                        body: formData,
-                    },
-                    {
-                        providerLabel: 'ElevenLabs',
-                        timeoutMs: CONVERT_TIMEOUT_MS,
-                        stream: true,
-                    },
-                );
-                return {
-                    dataType: 'stream',
-                    content_type:
-                        response.headers.get('content-type') ?? 'audio/mpeg',
-                    stream: output.measure(upstreamBodyStream(response)),
-                };
-            },
-            async () => {
-                const measured = await output.seconds;
-                // A stream cut short was still converted in full upstream.
-                const seconds =
-                    measured.complete && measured.seconds
-                        ? measured.seconds
-                        : Math.max(measured.seconds ?? 0, estimatedSeconds);
-                return metering.incrementUsage(
-                    actor,
-                    usageKey,
-                    seconds,
-                    ucentsPerSecond * seconds,
-                );
-            },
-        );
-    }
-}
-
-/**
- * Bytes per second of an ElevenLabs `output_format`. A format outside the
- * documented set is sized as the default, so a made-up bitrate can't shrink the
- * bill.
- */
-export function outputBytesPerSecond(format: string): number {
-    const known = OUTPUT_FORMATS.has(format) ? format : DEFAULT_OUTPUT_FORMAT;
-    const [codec, rate, kbps] = known.split('_');
-    if (codec === 'mp3' || codec === 'opus') return Number(kbps) * 125;
-    if (codec === 'ulaw' || codec === 'alaw') return Number(rate);
-    // pcm and wav: 16-bit mono.
-    return Number(rate) * 2;
-}
-
-// Past this, a WAV whose data chunk hasn't started is billed by raw length.
-const WAV_HEADER_MAX_BYTES = 64 * 1024;
-
-/**
- * Where the samples of a RIFF/WAVE stream start, once `head` reaches its `data`
- * chunk; undefined until then, or if `head` isn't a WAV.
- */
-export function wavDataOffset(head: Buffer): number | undefined {
-    if (head.length < 12) return undefined;
-    if (
-        head.toString('ascii', 0, 4) !== 'RIFF' ||
-        head.toString('ascii', 8, 12) !== 'WAVE'
-    )
-        return undefined;
-    let offset = 12;
-    while (offset + 8 <= head.length) {
-        if (head.toString('ascii', offset, offset + 4) === 'data')
-            return offset + 8;
-        const size = head.readUInt32LE(offset + 4);
-        offset += 8 + size + (size & 1);
-    }
-    return undefined;
-}
-
-const OGG_HEADER_BYTES = 27;
-const NO_GRANULE = 2n ** 64n - 1n;
-
-/**
- * Walks an Ogg Opus stream page by page as it arrives. Opus is variable
- * bitrate, so its length comes from the last page's granule position (48 kHz
- * samples, less the stream's pre-skip) rather than its byte count.
- */
-export class OggOpusClock {
-    #header = Buffer.alloc(0);
-    #skip = 0;
-    #firstBody: Buffer | undefined = Buffer.alloc(0);
-    #firstBodyBytes = 0;
-    #granule: bigint | undefined;
-    #preSkip = 0;
-    #broken = false;
-
-    push(chunk: Buffer): void {
-        let offset = 0;
-        while (!this.#broken && offset < chunk.length) {
-            if (this.#skip > 0) {
-                const n = Math.min(this.#skip, chunk.length - offset);
-                if (this.#firstBody && this.#firstBody.length < 19) {
-                    this.#firstBody = Buffer.concat([
-                        this.#firstBody,
-                        chunk.subarray(offset, offset + n),
-                    ]);
-                }
-                this.#skip -= n;
-                offset += n;
-                if (this.#skip === 0 && this.#firstBody) this.#readOpusHead();
-                continue;
-            }
-            const want =
-                this.#header.length < OGG_HEADER_BYTES
-                    ? OGG_HEADER_BYTES
-                    : OGG_HEADER_BYTES + this.#header[26]!;
-            const n = Math.min(
-                want - this.#header.length,
-                chunk.length - offset,
-            );
-            this.#header = Buffer.concat([
-                this.#header,
-                chunk.subarray(offset, offset + n),
-            ]);
-            offset += n;
-            if (this.#header.length < want) continue;
-            if (this.#header.toString('ascii', 0, 4) !== 'OggS') {
-                this.#broken = true;
-                return;
-            }
-            if (want === OGG_HEADER_BYTES && this.#header[26]! > 0) continue;
-            const granule = this.#header.readBigUInt64LE(6);
-            if (granule !== NO_GRANULE) this.#granule = granule;
-            let body = 0;
-            for (const lacing of this.#header.subarray(OGG_HEADER_BYTES)) {
-                body += lacing;
-            }
-            this.#header = Buffer.alloc(0);
-            this.#skip = body;
-            if (this.#firstBody) this.#firstBodyBytes = body;
-        }
-    }
-
-    /** Whole seconds so far, once the stream has proven to be Ogg Opus. */
-    get seconds(): number | undefined {
-        if (this.#broken || this.#granule === undefined) return undefined;
-        const samples = Number(this.#granule) - this.#preSkip;
-        return samples > 0
-            ? Math.max(1, Math.ceil(samples / 48_000))
-            : undefined;
-    }
-
-    #readOpusHead(): void {
-        const head = this.#firstBody!;
-        this.#firstBody = undefined;
-        if (
-            this.#firstBodyBytes < 19 ||
-            head.toString('ascii', 0, 8) !== 'OpusHead'
-        ) {
-            this.#broken = true;
-            return;
-        }
-        this.#preSkip = head.readUInt16LE(10);
-    }
-}
-
-/**
- * Counts the bytes of a converted stream. `seconds` settles when the stream
- * ends or closes: its length in whole seconds (undefined when nothing came
- * back), and whether the upstream sent all of it. A WAV's header isn't audio,
- * so it isn't counted; Opus is timed by its pages.
- */
-function measuredOutput(bytesPerSecond: number, format: string) {
-    let bytes = 0;
-    let head: Buffer | undefined = format.startsWith('wav_')
-        ? Buffer.alloc(0)
-        : undefined;
-    const opus = format.startsWith('opus_') ? new OggOpusClock() : undefined;
-    let headerBytes = 0;
-    let settle!: (measured: { seconds?: number; complete: boolean }) => void;
-    const seconds = new Promise<{ seconds?: number; complete: boolean }>(
-        (resolve) => {
-            settle = resolve;
-        },
-    );
-    const lengthOf = () => {
-        const timed = opus?.seconds;
-        if (timed !== undefined) return timed;
-        const audio = bytes - headerBytes;
-        return audio > 0
-            ? Math.max(1, Math.ceil(audio / bytesPerSecond))
-            : undefined;
-    };
-    const measure = (source: Readable): Readable => {
-        const counter = new Transform({
-            transform(chunk: Buffer, _encoding, callback) {
-                bytes += chunk.length;
-                opus?.push(chunk);
-                if (head) {
-                    head = Buffer.concat([head, chunk]);
-                    const offset = wavDataOffset(head);
-                    if (offset !== undefined) headerBytes = offset;
-                    if (
-                        offset !== undefined ||
-                        head.length >= WAV_HEADER_MAX_BYTES
-                    )
-                        head = undefined;
-                }
-                callback(null, chunk);
-            },
-            flush(callback) {
-                settle({ seconds: lengthOf(), complete: true });
-                callback();
-            },
-        });
-        counter.once('close', () =>
-            settle({ seconds: lengthOf(), complete: false }),
-        );
-        pipeline(source, counter, () => {});
-        return counter;
-    };
-    return { measure, seconds };
-}

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.availability.http.test.ts

@@ -19,9 +19,9 @@
 
 import { createServer, type Server } from 'node:http';
 import { afterAll, beforeAll, beforeEach, describe, expect, it } from 'vitest';
-import { setupPuterTestEnv, type PuterTestEnv } from '../../testUtil.js';
+import { setupPuterTestEnv, type PuterTestEnv } from '../../../../testUtil.js';
 import { clearUnhealthyRoutes } from './utils/providerHealth.js';
-import { makeActor } from '../../core/actor.js';
+import { makeActor } from '../../../../core/actor.js';
 
 const policyMessage =
     'Policy Violation: this user has been blocked for a previous policy violation. Learn more: https://vendor.test/private';
@@ -129,6 +129,17 @@ describe('model availability through real HTTP', () => {
             meteringEnforcement: { subscriptions: false },
         } as never);
     }, 120000);
+    it('serves qualified chat model names through HTTP', async () => {
+        const response = await fetch(
+            new URL('/puterai/chat/models', env.apiOrigin),
+        );
+        expect(response.status).toBe(200);
+        const { models } = (await response.json()) as { models: string[] };
+        expect(models).toContain('openrouter:vendor/availability-test');
+        expect(models.every((id) => /^[^:/]+:[^/]+\/.+/.test(id))).toBe(true);
+        expect(models).not.toContain('vendor/availability-test');
+    });
+
     afterAll(async () => {
         await env?.shutdown();
         upstream?.closeAllConnections();

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.cancellation.http.test.ts

@@ -19,8 +19,8 @@
 
 import { createServer, type Server, type ServerResponse } from 'node:http';
 import { afterAll, beforeAll, describe, expect, it, vi } from 'vitest';
-import { makeActor, type Actor } from '../../core/actor.js';
-import { setupPuterTestEnv, type PuterTestEnv } from '../../testUtil.js';
+import { makeActor, type Actor } from '../../../../core/actor.js';
+import { setupPuterTestEnv, type PuterTestEnv } from '../../../../testUtil.js';
 
 const routes = [
     '/drivers/call',

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.concurrency.http.test.ts

@@ -0,0 +1,225 @@
+/*
+ * Copyright (C) 2024-present Puter Technologies Inc.
+ *
+ * This file is part of Puter.
+ *
+ * Puter is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+import { createServer, type Server, type ServerResponse } from 'node:http';
+import { afterAll, beforeAll, describe, expect, it, vi } from 'vitest';
+import { setupPuterTestEnv, type PuterTestEnv } from '../../../../testUtil.js';
+
+/**
+ * A completion runs on to its usage report after the caller hangs up, so it
+ * keeps counting against the caller's concurrency cap until it settles.
+ */
+describe('chat concurrency over HTTP after the caller hangs up', () => {
+    let upstream: Server;
+    let env: PuterTestEnv;
+    let onRequest: (res: ServerResponse, body: string) => void;
+
+    beforeAll(async () => {
+        upstream = createServer((req, res) => {
+            if (req.url === '/api/tags') {
+                res.setHeader('Content-Type', 'application/json');
+                res.end(JSON.stringify({ models: [{ name: 'slot-test' }] }));
+                return;
+            }
+            let body = '';
+            req.setEncoding('utf8');
+            req.on('data', (chunk: string) => {
+                body += chunk;
+            });
+            req.once('end', () => onRequest(res, body));
+        });
+        await new Promise<void>((resolve) =>
+            upstream.listen(0, '127.0.0.1', resolve),
+        );
+        const port = (upstream.address() as { port: number }).port;
+        env = await setupPuterTestEnv({
+            providers: {
+                ollama: { apiBaseUrl: `http://127.0.0.1:${port}` },
+            },
+            meteringEnforcement: { subscriptions: false },
+        } as never);
+        await vi.waitFor(async () => {
+            expect(
+                (await env.server.drivers.aiChat.models()).some(
+                    (model) => model.id === 'ollama:ollama/slot-test',
+                ),
+            ).toBe(true);
+        });
+    }, 120_000);
+
+    afterAll(async () => {
+        await env?.shutdown();
+        upstream?.closeAllConnections();
+        if (upstream)
+            await new Promise<void>((resolve) =>
+                upstream.close(() => resolve()),
+            );
+    });
+
+    const call = (route: string, stream: boolean, signal?: AbortSignal) => {
+        const args = {
+            model: 'ollama:ollama/slot-test',
+            stream,
+            messages: [{ role: 'user', content: 'hi' }],
+            max_tokens: 16,
+        };
+        return fetch(new URL(route, env.apiOrigin), {
+            method: 'POST',
+            headers: {
+                'Content-Type': 'application/json',
+                Authorization: `Bearer ${env.users.user.apiToken}`,
+                Origin: env.apiOrigin,
+            },
+            body: JSON.stringify(
+                route === '/drivers/call'
+                    ? {
+                          interface: 'puter-chat-completion',
+                          method: 'complete',
+                          args,
+                      }
+                    : args,
+            ),
+            signal,
+        });
+    };
+
+    const usage = { prompt_tokens: 3, completion_tokens: 5, total_tokens: 8 };
+    const chunk = (delta: object, finish: string | null, extra = {}) =>
+        `data: ${JSON.stringify({
+            id: 'chatcmpl_1',
+            object: 'chat.completion.chunk',
+            choices: [{ index: 0, delta, finish_reason: finish }],
+            ...extra,
+        })}\n\n`;
+
+    const finishAnswer = (res: ServerResponse, body: string) => {
+        if (!(JSON.parse(body) as { stream?: boolean }).stream) {
+            res.setHeader('Content-Type', 'application/json');
+            res.end(
+                JSON.stringify({
+                    id: 'chatcmpl_1',
+                    object: 'chat.completion',
+                    created: 0,
+                    model: 'slot-test',
+                    choices: [
+                        {
+                            index: 0,
+                            message: { role: 'assistant', content: 'done' },
+                            finish_reason: 'stop',
+                        },
+                    ],
+                    usage,
+                }),
+            );
+            return;
+        }
+        if (!res.headersSent)
+            res.setHeader('Content-Type', 'text/event-stream');
+        res.end(
+            `${chunk({ content: 'done' }, 'stop')}data: ${JSON.stringify({
+                id: 'chatcmpl_1',
+                object: 'chat.completion.chunk',
+                choices: [],
+                usage,
+            })}\n\ndata: [DONE]\n\n`,
+        );
+    };
+
+    /** Starts a completion, waits until it is generating, then hangs up. */
+    const abandon = async (route: string, stream: boolean) => {
+        let received!: () => void;
+        const reached = new Promise<void>((resolve) => {
+            received = resolve;
+        });
+        const pending: { res: ServerResponse; body: string }[] = [];
+        onRequest = (res, body) => {
+            pending.push({ res, body });
+            if (stream) {
+                res.setHeader('Content-Type', 'text/event-stream');
+                res.write(chunk({ role: 'assistant', content: 'partial' }, null));
+            }
+            received();
+        };
+        const abort = new AbortController();
+        const request = call(route, stream, abort.signal);
+        const outcome = await Promise.race([
+            reached.then(() => 'generating' as const),
+            request.then((response) => response),
+        ]);
+        if (outcome !== 'generating') {
+            return { refused: outcome, pending };
+        }
+        if (stream) {
+            const response = await request;
+            const reader = response.body!.getReader();
+            let text = '';
+            while (!text.includes('partial')) {
+                const { value, done } = await reader.read();
+                if (done) break;
+                text += new TextDecoder().decode(value);
+            }
+        }
+        abort.abort();
+        await request.catch(() => undefined);
+        return { refused: undefined, pending };
+    };
+
+    it.each([
+        { route: '/drivers/call', stream: true },
+        { route: '/drivers/call', stream: false },
+        { route: '/puterai/openai/v1/chat/completions', stream: true },
+        { route: '/puterai/openai/v1/chat/completions', stream: false },
+        { route: '/puterai/anthropic/v1/messages', stream: true },
+    ])(
+        'counts an abandoned completion until it settles: $route (stream=$stream)',
+        async ({ route, stream }) => {
+            const running: { res: ServerResponse; body: string }[] = [];
+            let refused: Response | undefined;
+            try {
+                for (let i = 0; i < 25 && !refused; i++) {
+                    const attempt = await abandon(route, stream);
+                    running.push(...attempt.pending);
+                    refused = attempt.refused;
+                    // Let the server see the hang-up before the next call.
+                    await new Promise((resolve) => setTimeout(resolve, 50));
+                }
+                expect(refused?.status).toBe(429);
+                expect(await refused!.text()).toContain(
+                    'Too many concurrent requests',
+                );
+                expect(running.length).toBeGreaterThan(0);
+
+                for (const { res, body } of running.splice(0))
+                    finishAnswer(res, body);
+                onRequest = finishAnswer;
+                await expect
+                    .poll(async () => (await call(route, false)).status, {
+                        timeout: 15_000,
+                    })
+                    .toBe(200);
+            } finally {
+                for (const { res, body } of running) finishAnswer(res, body);
+                upstream.closeAllConnections();
+                // The next case starts with a fresh rate-limit window.
+                await new Promise((resolve) => setTimeout(resolve, 10_100));
+            }
+        },
+        60_000,
+    );
+});

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.edges.test.ts

@@ -42,22 +42,22 @@ import {
     vi,
 } from 'vitest';
 
-import { Context } from '../../core/context.js';
-import { HttpError } from '../../core/http/HttpError.js';
-import { PuterServer } from '../../server.js';
-import { setupTestServer } from '../../testUtil.js';
-import { withTestActor } from '../integrationTestUtil.js';
+import { Context } from '../../../../core/context.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import { PuterServer } from '../../../../server.js';
+import { setupTestServer } from '../../../../testUtil.js';
+import { withTestActor } from '../../shared/integrationTestUtil.js';
 import { ChatCompletionDriver } from './ChatCompletionDriver.js';
-import { AzureChatProvider } from './providers/azure/AzureChatProvider.js';
-import { FakeChatProvider } from './providers/FakeChatProvider.js';
-import { InfronProvider } from './providers/infron/InfronProvider.js';
-import { NeuralwattProvider } from './providers/neuralwatt/NeuralwattProvider.js';
-import { OpenAiChatProvider } from './providers/openai/OpenAiChatCompletionsProvider.js';
-import { OpenRouterProvider } from './providers/openrouter/OpenRouterProvider.js';
-import { TogetherAIProvider } from './providers/together/TogetherAIProvider.js';
-import { XAI_CHAT_MODELS } from './providers/xai/catalog.js';
-import { XAIProvider } from './providers/xai/XAIProvider.js';
-import { handle_completion_output } from './utils/OpenAIUtil.js';
+import { AzureChatProvider } from '../../providers/azure/chat/AzureChatProvider.js';
+import { FakeChatProvider } from '../../providers/fake/chat/FakeChatProvider.js';
+import { InfronProvider } from '../../providers/infron/chat/InfronProvider.js';
+import { NeuralwattProvider } from '../../providers/neuralwatt/chat/NeuralwattProvider.js';
+import { OpenAiChatProvider } from '../../providers/openai/chat/OpenAiChatCompletionsProvider.js';
+import { OpenRouterProvider } from '../../providers/openrouter/chat/OpenRouterProvider.js';
+import { TogetherAIProvider } from '../../providers/together/chat/TogetherAIProvider.js';
+import { XAI_CHAT_MODELS } from '../../providers/xai/chat/catalog.js';
+import { XAIProvider } from '../../providers/xai/chat/XAIProvider.js';
+import { handle_completion_output } from '../../protocols/openaiCompatible/OpenAIUtil.js';
 import { clearUnhealthyRoutes, isRouteUnhealthy } from './utils/providerHealth.js';
 
 let server: PuterServer;
@@ -1231,4 +1231,41 @@ describe('ChatCompletionDriver streaming failure handling', () => {
         expect(events).toContainEqual({ type: 'text', text: 'hello' });
         expect(cleanup).toHaveBeenCalledTimes(1);
     });
+
+    it('frees the concurrency slot before the provider cleanup hook finishes', async () => {
+        let finishCleanup!: () => void;
+        const cleanup = vi.fn(
+            () =>
+                new Promise<void>((resolve) => {
+                    finishCleanup = resolve;
+                }),
+        );
+        vi.spyOn(FakeChatProvider.prototype, 'complete').mockResolvedValue({
+            stream: true,
+            init_chat_stream: async ({
+                chatStream,
+            }: {
+                chatStream: { end: (usage?: Record<string, number>) => void };
+            }) => {
+                chatStream.end({ input_tokens: 1, output_tokens: 1 });
+            },
+            finally_fn: cleanup,
+        } as never);
+
+        const kept: Promise<unknown>[] = [];
+        const result = (await withTestActor(() => {
+            Context.set('keepConcurrencySlot', (work) => kept.push(work));
+            return fakeOnlyDriver.complete({
+                model: 'fake',
+                messages: [{ role: 'user', content: 'hi' }],
+                stream: true,
+            } as never);
+        })) as unknown as { stream: Readable };
+        await collect(result.stream);
+
+        expect(kept).toHaveLength(1);
+        await kept[0];
+        await vi.waitFor(() => expect(cleanup).toHaveBeenCalledTimes(1));
+        finishCleanup();
+    });
 });

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.fuzz.test.ts

@@ -0,0 +1,726 @@
+/*
+ * Copyright (C) 2024-present Puter Technologies Inc.
+ *
+ * This file is part of Puter.
+ *
+ * Puter is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Puter is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Puter. If not, see <https://www.gnu.org/licenses/>.
+ */
+
+/**
+ * Seeded fuzzing of `ChatCompletionDriver.complete` through every registered
+ * provider. The vendors are played at the HTTP boundary, so the real SDKs and
+ * the providers' own request and response code run.
+ */
+
+import { afterAll, beforeAll, describe, expect, it, vi } from 'vitest';
+
+import { isHttpError } from '../../../../core/http/HttpError.js';
+import type { PuterServer } from '../../../../server.js';
+import { setupTestServer } from '../../../../testUtil.js';
+import { kv } from '../../../../util/kvSingleton.js';
+import { isDriverStreamResult } from '../../../meta.js';
+import {
+    caseRandom,
+    corruptReply,
+    Findings,
+    fuzzCases,
+    hostileValue,
+    mutate,
+    pick,
+    pickStable,
+    type Random,
+    unclassifiedFailure,
+    upstream,
+    type UpstreamReply,
+    type UpstreamRequest,
+} from '../../shared/fuzzTestUtil.js';
+import {
+    readStreamResult,
+    withTestActor,
+} from '../../shared/integrationTestUtil.js';
+import { ChatCompletionDriver } from './ChatCompletionDriver.js';
+import type { ICompleteArguments } from './types.js';
+import { clearUnhealthyRoutes } from './utils/providerHealth.js';
+
+vi.mock('undici', async (importOriginal) => ({
+    ...(await importOriginal<typeof import('undici')>()),
+    fetch: (input: unknown, init?: RequestInit) => upstream.fetch(input, init),
+}));
+
+// groq-sdk brings its own HTTP client. Groq's API is OpenAI-compatible, so the
+// OpenAI SDK stands in for it and the requests reach the stub like the rest.
+vi.mock('groq-sdk', async () => ({ default: (await import('openai')).OpenAI }));
+
+vi.mock('axios', () => {
+    const request = (config: Parameters<typeof upstream.axios>[0]) =>
+        upstream.axios(config);
+    const get = (url: string, config?: object) =>
+        upstream.axios({ ...config, url, method: 'GET' });
+    return { default: { request, get }, request, get };
+});
+
+// -- The vendors, played at the HTTP boundary --
+
+const TEXT = 'pong';
+const chatUsage = { prompt_tokens: 3, completion_tokens: 5, total_tokens: 8 };
+const chatChunk = (delta: object, finish: string | null) => ({
+    id: 'chatcmpl-1',
+    object: 'chat.completion.chunk',
+    created: 1,
+    model: 'm',
+    choices: [{ index: 0, delta, finish_reason: finish }],
+});
+const responsesMessage = {
+    type: 'message',
+    id: 'msg_1',
+    role: 'assistant',
+    status: 'completed',
+    content: [{ type: 'output_text', text: TEXT, annotations: [] }],
+};
+const responsesBody = {
+    id: 'resp_1',
+    object: 'response',
+    status: 'completed',
+    model: 'm',
+    output: [responsesMessage],
+    usage: {
+        input_tokens: 3,
+        output_tokens: 5,
+        total_tokens: 8,
+        input_tokens_details: { cached_tokens: 0 },
+        output_tokens_details: { reasoning_tokens: 0 },
+    },
+};
+const anthropicUsage = { input_tokens: 3, output_tokens: 5 };
+const geminiBody = {
+    candidates: [
+        {
+            index: 0,
+            content: { role: 'model', parts: [{ text: TEXT }] },
+            finishReason: 'STOP',
+        },
+    ],
+    usageMetadata: {
+        promptTokenCount: 3,
+        candidatesTokenCount: 5,
+        totalTokenCount: 8,
+    },
+};
+
+const anthropicEvents = [
+    {
+        type: 'message_start',
+        message: {
+            id: 'msg_1',
+            type: 'message',
+            role: 'assistant',
+            model: 'm',
+            content: [],
+            stop_reason: null,
+            stop_sequence: null,
+            usage: { input_tokens: 3, output_tokens: 1 },
+        },
+    },
+    {
+        type: 'content_block_start',
+        index: 0,
+        content_block: { type: 'text', text: '' },
+    },
+    {
+        type: 'content_block_delta',
+        index: 0,
+        delta: { type: 'text_delta', text: TEXT },
+    },
+    { type: 'content_block_stop', index: 0 },
+    {
+        type: 'message_delta',
+        delta: { stop_reason: 'end_turn', stop_sequence: null },
+        usage: { output_tokens: 5 },
+    },
+    { type: 'message_stop' },
+];
+
+const responsesEvents = [
+    {
+        type: 'response.created',
+        response: { ...responsesBody, status: 'in_progress', output: [] },
+    },
+    {
+        type: 'response.output_item.added',
+        output_index: 0,
+        item: { ...responsesMessage, status: 'in_progress', content: [] },
+    },
+    {
+        type: 'response.output_text.delta',
+        item_id: 'msg_1',
+        output_index: 0,
+        content_index: 0,
+        delta: TEXT,
+    },
+    {
+        type: 'response.output_item.done',
+        output_index: 0,
+        item: responsesMessage,
+    },
+    { type: 'response.completed', response: responsesBody },
+];
+
+/** A well-formed answer from whichever vendor API the request went to. */
+const healthyUpstream = ({
+    url,
+    json,
+}: UpstreamRequest): UpstreamReply | undefined => {
+    const path = url.pathname;
+    // A caller-supplied media link that leads nowhere.
+    if (url.hostname === 'upstream.test') return { status: 404, body: '' };
+    const streaming = (json as { stream?: unknown } | undefined)?.stream;
+    if (path.endsWith('/chat/completions')) {
+        if (!streaming) {
+            return {
+                body: {
+                    id: 'chatcmpl-1',
+                    object: 'chat.completion',
+                    created: 1,
+                    model: 'm',
+                    choices: [
+                        {
+                            index: 0,
+                            message: { role: 'assistant', content: TEXT },
+                            finish_reason: 'stop',
+                        },
+                    ],
+                    usage: chatUsage,
+                },
+            };
+        }
+        return {
+            sse: [
+                { data: chatChunk({ role: 'assistant', content: TEXT }, null) },
+                { data: chatChunk({}, 'stop') },
+                {
+                    data: {
+                        ...chatChunk({}, null),
+                        choices: [],
+                        usage: chatUsage,
+                    },
+                },
+                { data: '[DONE]' },
+            ],
+        };
+    }
+    if (path.endsWith('/responses')) {
+        return streaming
+            ? {
+                  sse: responsesEvents.map((data) => ({
+                      event: data.type,
+                      data,
+                  })),
+              }
+            : { body: responsesBody };
+    }
+    if (path.endsWith('/messages/count_tokens')) {
+        return { body: { input_tokens: 3 } };
+    }
+    if (path.endsWith('/messages')) {
+        return streaming
+            ? {
+                  sse: anthropicEvents.map((data) => ({
+                      event: data.type,
+                      data,
+                  })),
+              }
+            : {
+                  body: {
+                      id: 'msg_1',
+                      type: 'message',
+                      role: 'assistant',
+                      model: 'm',
+                      content: [{ type: 'text', text: TEXT }],
+                      stop_reason: 'end_turn',
+                      stop_sequence: null,
+                      usage: anthropicUsage,
+                  },
+              };
+    }
+    if (path.endsWith(':generateContent')) return { body: geminiBody };
+    if (path.endsWith(':streamGenerateContent')) {
+        return { sse: [{ data: geminiBody }] };
+    }
+    if (path.endsWith(':countTokens')) return { body: { totalTokens: 3 } };
+    if (path.endsWith('/moderations')) {
+        return {
+            body: {
+                id: 'modr_1',
+                model: 'm',
+                results: [
+                    { flagged: false, categories: {}, category_scores: {} },
+                ],
+            },
+        };
+    }
+    return undefined;
+};
+
+// -- Requests to mutate --
+
+const PNG =
+    'data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8z8BQDwAEhQGAhKmMIQAAAABJRU5ErkJggg==';
+
+const weatherTool = {
+    type: 'function',
+    function: {
+        name: 'get_weather',
+        description: 'Get the weather for a city',
+        parameters: {
+            type: 'object',
+            properties: { city: { type: 'string' } },
+            required: ['city'],
+        },
+    },
+};
+
+const CORPUS: Record<string, unknown>[] = [
+    { messages: [{ role: 'user', content: 'hi' }] },
+    {
+        messages: [
+            { role: 'system', content: 'Be brief.' },
+            {
+                role: 'user',
+                content: [
+                    { type: 'text', text: 'What is this?' },
+                    { type: 'image_url', image_url: { url: PNG } },
+                ],
+            },
+        ],
+        max_tokens: 64,
+        temperature: 0.5,
+        top_p: 0.9,
+        stream: true,
+    },
+    {
+        messages: [
+            { role: 'user', content: 'Weather in Paris?' },
+            {
+                role: 'assistant',
+                content: null,
+                tool_calls: [
+                    {
+                        id: 'call_1',
+                        type: 'function',
+                        function: {
+                            name: 'get_weather',
+                            arguments: '{"city":"Paris"}',
+                        },
+                    },
+                ],
+            },
+            { role: 'tool', tool_call_id: 'call_1', content: 'Sunny' },
+        ],
+        tools: [weatherTool],
+        tool_choice: 'auto',
+        parallel_tool_calls: false,
+    },
+    {
+        messages: [
+            {
+                role: 'user',
+                content: [
+                    {
+                        type: 'text',
+                        text: 'Weather in Paris?',
+                        cache_control: { type: 'ephemeral' },
+                    },
+                ],
+            },
+            {
+                role: 'assistant',
+                content: [
+                    { type: 'text', text: 'Checking.' },
+                    {
+                        type: 'tool_use',
+                        id: 'toolu_1',
+                        name: 'get_weather',
+                        input: { city: 'Paris' },
+                    },
+                ],
+            },
+            {
+                role: 'user',
+                content: [
+                    {
+                        type: 'tool_result',
+                        tool_use_id: 'toolu_1',
+                        content: 'Sunny',
+                    },
+                ],
+            },
+        ],
+        tools: [weatherTool, { type: 'web_search' }],
+        tool_choice: { type: 'function', function: { name: 'get_weather' } },
+        stream: true,
+        streamToolInput: true,
+    },
+    {
+        messages: [{ role: 'user', content: 'Reply in JSON.' }],
+        outputFormat: {
+            type: 'json_schema',
+            schema: { type: 'object', properties: { a: { type: 'string' } } },
+        },
+        reasoning: { effort: 'low' },
+        reasoning_effort: 'low',
+        thinking: { type: 'enabled', budget_tokens: 1024 },
+        text: { verbosity: 'low' },
+        verbosity: 'low',
+        stopSequences: ['END'],
+        topK: 5,
+        normalize: true,
+    },
+    {
+        messages: [{ role: 'user', content: 'hi' }],
+        instructions: 'Be brief.',
+        compaction: { trigger_tokens: 150000 },
+        context_management: { edits: [{ type: 'clear_tool_uses_20250919' }] },
+        cacheControl: { type: 'ephemeral', ttl: '1h' },
+        prompt_cache_key: 'k',
+        prompt_cache_retention: '24h',
+        serviceSpeed: 'fast',
+        service_tier: 'flex',
+        speed: 'fast',
+        metadata: { trace: 't' },
+        include: ['reasoning.encrypted_content'],
+        store: false,
+        truncation: 'auto',
+        taskBudget: { total: 1000, remaining: 500 },
+        safeguards: [{ type: 'prompt_injection' }],
+        anthropicBetas: ['context-management-2025-06-27'],
+        moderation: true,
+        response: { normalize: true },
+        fallback: false,
+    },
+];
+
+CORPUS.push(
+    {
+        messages: [
+            {
+                role: 'user',
+                content: [
+                    { type: 'text', text: 'Describe these.' },
+                    { type: 'image_url', image_url: PNG },
+                    {
+                        type: 'image',
+                        source: {
+                            type: 'base64',
+                            media_type: 'image/png',
+                            data: PNG.split(',')[1],
+                        },
+                    },
+                    {
+                        type: 'video_url',
+                        video_url: { url: 'data:video/mp4;base64,AAAA' },
+                    },
+                    {
+                        type: 'file',
+                        file: {
+                            filename: 'a.pdf',
+                            file_data: 'data:application/pdf;base64,JVBERi0=',
+                        },
+                    },
+                    {
+                        type: 'document',
+                        source: {
+                            type: 'base64',
+                            media_type: 'application/pdf',
+                            data: 'JVBERi0=',
+                        },
+                    },
+                ],
+            },
+        ],
+    },
+    {
+        messages: [
+            {
+                role: 'user',
+                content: [
+                    { type: 'text', text: 'Read it.' },
+                    { puter_path: '~/Documents/a.png' },
+                ],
+            },
+        ],
+    },
+    // Model output sent back, in each vendor's shape.
+    {
+        messages: [
+            { role: 'user', content: 'Think, then search.' },
+            {
+                role: 'assistant',
+                content: [
+                    { type: 'thinking', thinking: 'Hm.', signature: 'sig' },
+                    { type: 'redacted_thinking', data: 'x' },
+                    {
+                        type: 'reasoning',
+                        id: 'rs_1',
+                        summary: [{ type: 'summary_text', text: 'Hm.' }],
+                        encrypted_content: 'enc',
+                    },
+                    { type: 'text', text: 'Searching.' },
+                    {
+                        type: 'server_tool_use',
+                        id: 'srvtoolu_1',
+                        name: 'web_search',
+                        input: { query: 'x' },
+                    },
+                    {
+                        type: 'web_search_tool_result',
+                        tool_use_id: 'srvtoolu_1',
+                        content: [],
+                    },
+                    {
+                        type: 'compaction',
+                        id: 'cmp_1',
+                        encrypted_content: 'enc',
+                    },
+                ],
+                reasoning: 'Hm.',
+                refusal: null,
+            },
+            { type: 'compaction', id: 'cmp_2', encrypted_content: 'enc' },
+            { role: 'user', content: 'Go on.' },
+        ],
+        tools: [
+            { type: 'web_search_20250305', name: 'web_search', max_uses: 3 },
+            {
+                type: 'function',
+                function: {
+                    name: 'strict_tool',
+                    strict: true,
+                    parameters: {
+                        type: 'object',
+                        properties: {},
+                        additionalProperties: false,
+                    },
+                },
+            },
+            {
+                name: 'anthropic_style',
+                description: 'x',
+                input_schema: { type: 'object', properties: {} },
+            },
+        ],
+        tool_choice: 'required',
+        thinking: { type: 'adaptive' },
+        prompt_cache_options: { ttl: '30m' },
+        instructions: [{ role: 'system', content: 'Be brief.' }],
+    },
+);
+
+const OPTION_NAMES = [
+    ...new Set(CORPUS.flatMap((request) => Object.keys(request))),
+    'previous_response_id',
+    'conversation',
+    'prompt',
+    'prompt_cache_options',
+    'background',
+    'custom',
+    'customLimitMessage',
+    'test_mode',
+];
+
+// -- Harness --
+
+const key = { apiKey: 'fuzz-key' };
+const providers = {
+    claude: key,
+    'azure-openai': { ...key, apiURL: 'https://azure.upstream.test/openai' },
+    'openai-completion': key,
+    gemini: key,
+    meta: key,
+    groq: key,
+    deepseek: key,
+    mistral: key,
+    xai: key,
+    moonshot: key,
+    minimax: key,
+    zai: key,
+    alibaba: key,
+    byteplus: key,
+    hoonify: key,
+    ollama: { enabled: false },
+};
+
+let server: PuterServer;
+let driver: ChatCompletionDriver;
+// Every provider gets the same share of cases, whatever its catalog size.
+let routes: Map<string, { provider: string; id: string }[]>;
+
+beforeAll(async () => {
+    upstream.install();
+    server = await setupTestServer();
+    driver = new ChatCompletionDriver(
+        { providers } as never,
+        server.clients,
+        server.stores,
+        server.services,
+    );
+    await driver.onServerStart();
+    routes = new Map();
+    for (const model of await driver.models()) {
+        if (!model.provider || model.provider === 'fake-chat') continue;
+        const route = { provider: model.provider, id: model.id };
+        routes.set(route.provider, [
+            ...(routes.get(route.provider) ?? []),
+            route,
+        ]);
+    }
+}, 120_000);
+
+afterAll(async () => {
+    await server?.shutdown();
+    upstream.uninstall();
+});
+
+const pickRoute = (random: Random) =>
+    pickStable(
+        random,
+        routes.get(pickStable(random, [...routes.keys()], (name) => name))!,
+        (route) => route.id,
+    );
+
+/** Runs one completion to its end, stream included, and returns its failure. */
+const complete = async (args: Record<string, unknown>): Promise<unknown> => {
+    try {
+        const result = await withTestActor(() =>
+            driver.complete(
+                structuredClone(args) as unknown as ICompleteArguments,
+            ),
+        );
+        if (isDriverStreamResult(result)) await readStreamResult(result);
+        return undefined;
+    } catch (error) {
+        return error;
+    }
+};
+
+describe('ChatCompletionDriver seeded fuzzing', () => {
+    it('covers every configured provider', () => {
+        expect([...routes.keys()].sort()).toEqual([
+            'alibaba',
+            'azure-openai',
+            'azure-openai-responses',
+            'byteplus',
+            'claude',
+            'deepseek',
+            'gemini',
+            'groq',
+            'hoonify',
+            'meta',
+            'minimax',
+            'mistral',
+            'moonshotai',
+            'openai-completion',
+            'openai-responses',
+            'xai',
+            'zai',
+        ]);
+    });
+
+    it('answers or rejects a malformed request without failing a healthy route', async () => {
+        upstream.respond = healthyUpstream;
+        upstream.unanswered.clear();
+        clearUnhealthyRoutes();
+        const findings = new Findings();
+        let answered = 0;
+
+        for (let index = 0; index < fuzzCases(3000); index++) {
+            const random = caseRandom(0xc4a7, index);
+            const route = pickRoute(random);
+            const args: Record<string, unknown> = {
+                ...mutate(pick(random, CORPUS), random, OPTION_NAMES),
+                provider: route.provider,
+                model: route.id,
+            };
+            // Now and then the route itself is the malformed part.
+            if (random() < 0.05) {
+                args[pick(random, ['provider', 'model'])] =
+                    hostileValue(random);
+            }
+            const label = `${route.provider}:${route.id}`;
+            const error = await complete(args);
+            if (!error) answered++;
+            const unclassified = error && unclassifiedFailure(error);
+            if (unclassified) findings.add(unclassified, index, label, args);
+            else if (isHttpError(error) && error.statusCode >= 500) {
+                const attempts = (error.fields?.attempts ?? []) as {
+                    status?: number;
+                    error: string;
+                }[];
+                findings.add(
+                    `${error.statusCode} ${error.legacyCode}: ${error.message} [${attempts.map((a) => `${a.status ?? 'no status'} ${a.error}`).join(' | ')}]`,
+                    index,
+                    label,
+                    args,
+                );
+            }
+            // The vendors answered every request, so no route failed.
+            for (const marked of kv.keys('aiChat:unhealthyRoute:*')) {
+                findings.add(`marked unhealthy ${marked}`, index, label, args);
+            }
+            clearUnhealthyRoutes();
+        }
+
+        for (const request of upstream.unanswered) {
+            findings.add(`no upstream fixture for ${request}`, -1, '', {});
+        }
+        findings.assertNone();
+        // A run where nothing is answered has stopped reaching the providers.
+        expect(answered).toBeGreaterThan(0);
+    }, 600_000);
+
+    it('ends every request with an answer or a classified error when the upstream misbehaves', async () => {
+        const findings = new Findings();
+        const askedBefore = upstream.asked;
+
+        for (let index = 0; index < fuzzCases(2000); index++) {
+            const random = caseRandom(0x0b5e, index);
+            const route = pickRoute(random);
+            const replies: unknown[] = [];
+            upstream.respond = (request) => {
+                const healthy = healthyUpstream(request);
+                const reply = healthy && corruptReply(healthy, random);
+                replies.push(reply);
+                return reply;
+            };
+            const error = await complete({
+                messages: [{ role: 'user', content: 'hi' }],
+                provider: route.provider,
+                model: route.id,
+                stream: random() < 0.5,
+                fallback: random() < 0.5,
+            });
+            const unclassified = error && unclassifiedFailure(error);
+            if (unclassified) {
+                findings.add(
+                    unclassified,
+                    index,
+                    `${route.provider}:${route.id}`,
+                    replies,
+                );
+            }
+            clearUnhealthyRoutes();
+        }
+        findings.assertNone();
+        expect(upstream.asked).toBeGreaterThan(askedBefore);
+    }, 600_000);
+});

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.media.test.ts

@@ -38,11 +38,11 @@ import {
     vi,
 } from 'vitest';
 
-import { PuterServer } from '../../server.js';
-import { setupTestServer } from '../../testUtil.js';
-import { withTestActor } from '../integrationTestUtil.js';
+import { PuterServer } from '../../../../server.js';
+import { setupTestServer } from '../../../../testUtil.js';
+import { withTestActor } from '../../shared/integrationTestUtil.js';
 import { ChatCompletionDriver } from './ChatCompletionDriver.js';
-import { FakeChatProvider } from './providers/FakeChatProvider.js';
+import { FakeChatProvider } from '../../providers/fake/chat/FakeChatProvider.js';
 import type { IChatModel, ICompleteArguments } from './types.js';
 
 // The puter_path resolver reads the user's filesystem; stub it and assert on
@@ -51,7 +51,7 @@ const { processPuterPathUploadsMock } = vi.hoisted(() => ({
     processPuterPathUploadsMock: vi.fn(async (_messages: unknown) => {}),
 }));
 
-vi.mock('./providers/openai/fileUpload.js', () => ({
+vi.mock('../../providers/openai/chat/fileUpload.js', () => ({
     processPuterPathUploads: processPuterPathUploadsMock,
     MAX_FILE_SIZE: 5 * 1_000_000,
 }));

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.metering.test.ts

@@ -38,14 +38,14 @@ import {
     vi,
 } from 'vitest';
 
-import { Context } from '../../core/context.js';
-import type { UsageInput } from '../../services/metering/types.js';
-import { PuterServer } from '../../server.js';
-import { setupTestServer } from '../../testUtil.js';
-import { withTestActor } from '../integrationTestUtil.js';
+import { Context } from '../../../../core/context.js';
+import type { UsageInput } from '../../../../services/metering/types.js';
+import { PuterServer } from '../../../../server.js';
+import { setupTestServer } from '../../../../testUtil.js';
+import { withTestActor } from '../../shared/integrationTestUtil.js';
 import { ChatCompletionDriver } from './ChatCompletionDriver.js';
 import { clearUnhealthyRoutes, isRouteUnhealthy } from './utils/providerHealth.js';
-import { FakeChatProvider } from './providers/FakeChatProvider.js';
+import { FakeChatProvider } from '../../providers/fake/chat/FakeChatProvider.js';
 import type { IChatCompleteResult } from './types.js';
 import { SDK_TIMEOUT_MS } from './utils/sdkClient.js';
 import type { AIChatStream } from './utils/Streaming.js';

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.routing.test.ts

@@ -44,21 +44,21 @@ import type { Request } from 'express';
 import {
     renderAnthropicError,
     renderOpenAIError,
-} from '../../controllers/puterai/wireErrors.js';
-import { Context } from '../../core/context.js';
-import { HttpError } from '../../core/http/HttpError.js';
-import { PuterServer } from '../../server.js';
-import { setupTestServer } from '../../testUtil.js';
-import { withTestActor } from '../integrationTestUtil.js';
+} from '../../../../controllers/puterai/wireErrors.js';
+import { Context } from '../../../../core/context.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import { PuterServer } from '../../../../server.js';
+import { setupTestServer } from '../../../../testUtil.js';
+import { withTestActor } from '../../shared/integrationTestUtil.js';
 import { ChatCompletionDriver } from './ChatCompletionDriver.js';
-import { OPEN_AI_MODELS } from './providers/openai/models.js';
+import { OPEN_AI_MODELS } from '../../providers/openai/chat/models.js';
 import {
     clearUnhealthyRoutes,
     isRouteUnhealthy,
     markRouteUnhealthy,
 } from './utils/providerHealth.js';
-import { InfronProvider } from './providers/infron/InfronProvider.js';
-import { UpstreamDeadlineError } from '../util/upstreamErrors.js';
+import { InfronProvider } from '../../providers/infron/chat/InfronProvider.js';
+import { UpstreamDeadlineError } from '../../../util/upstreamErrors.js';
 
 // -- OpenAI SDK mock ------------------------------------------------
 // Gemini reaches Google through `new openai.OpenAI()` (default export) and

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.test.ts

@@ -44,17 +44,17 @@ import {
     vi,
 } from 'vitest';
 
-import { Context } from '../../core/context.js';
-import { HttpError } from '../../core/http/HttpError.js';
-import { PuterServer } from '../../server.js';
-import { setupTestServer } from '../../testUtil.js';
-import { withTestActor } from '../integrationTestUtil.js';
+import { Context } from '../../../../core/context.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import { PuterServer } from '../../../../server.js';
+import { setupTestServer } from '../../../../testUtil.js';
+import { withTestActor } from '../../shared/integrationTestUtil.js';
 import { COUNT_TOKENS, ChatCompletionDriver } from './ChatCompletionDriver.js';
-import { ClaudeProvider } from './providers/claude/ClaudeProvider.js';
-import { FakeChatProvider } from './providers/FakeChatProvider.js';
-import { OllamaChatProvider } from './providers/ollama/OllamaProvider.js';
-import { XAI_CHAT_MODELS } from './providers/xai/catalog.js';
-import { XAIProvider } from './providers/xai/XAIProvider.js';
+import { ClaudeProvider } from '../../providers/claude/chat/ClaudeProvider.js';
+import { FakeChatProvider } from '../../providers/fake/chat/FakeChatProvider.js';
+import { OllamaChatProvider } from '../../providers/ollama/chat/OllamaProvider.js';
+import { XAI_CHAT_MODELS } from '../../providers/xai/chat/catalog.js';
+import { XAIProvider } from '../../providers/xai/chat/XAIProvider.js';
 import type {
     IChatCompleteResult,
     IChatProvider,
@@ -207,6 +207,50 @@ describe('ChatCompletionDriver model map', () => {
         d.onServerShutdown();
     });
 
+    it('lists qualified model ids without publishing aliases as models', async () => {
+        const ids = [
+            'kimi/kimi-3',
+            'ollama:plain-model',
+            'ollama:vendor/qualified',
+            'vendor/tagged:free',
+        ];
+        vi.spyOn(OllamaChatProvider.prototype, 'models').mockResolvedValue(
+            ids.map((id) => ({
+                id,
+                aliases: ['legacy-' + id],
+                costs_currency: 'usd-cents',
+                costs: {},
+                max_tokens: 8192,
+            })),
+        );
+        const d = newDriver({ ollama: {} });
+        await d.onServerStart();
+        try {
+            expect(
+                (await d.list()).filter(
+                    (id) => !['abuse', 'costly', 'fake'].includes(id),
+                ),
+            ).toEqual([
+                'ollama:kimi/kimi-3',
+                'ollama:ollama/plain-model',
+                'ollama:vendor/qualified',
+                'ollama:vendor/tagged:free',
+            ]);
+            const models = (await d.models()).filter(
+                (model) => model.provider === 'ollama',
+            );
+            expect(models.map((model) => model.id).sort()).toEqual(
+                [...ids].sort(),
+            );
+            for (const model of models) {
+                expect(model.aliases).toContain(model.puterId);
+                expect(model.aliases).toContain('legacy-' + model.id);
+            }
+        } finally {
+            d.onServerShutdown();
+        }
+    });
+
     it('lists the catalog to a caller that asks while it is still loading', async () => {
         const d = newDriver({ ollama: { enabled: false } });
         d.onServerStart();
@@ -2396,3 +2440,97 @@ describe('ChatCompletionDriver service speed', () => {
         },
     );
 });
+
+describe('ChatCompletionDriver.complete option shapes', () => {
+    const hi = [{ role: 'user', content: 'hi' }];
+
+    it.each(['model', 'provider', 'service_tier'])(
+        'rejects a value that cannot be text as `%s`',
+        async (name) => {
+            const args = { model: 'fake', messages: hi, [name]: { toString: null } };
+            await expect(
+                withTestActor(() => driver.complete(args as never)),
+            ).rejects.toMatchObject({
+                statusCode: 400,
+                legacyCode: 'bad_request',
+                message: `\`${name}\` is not a usable value`,
+            });
+            await expect(
+                withTestActor(() => driver[COUNT_TOKENS](args as never)),
+            ).rejects.toMatchObject({ statusCode: 400 });
+        },
+    );
+
+    it('routes by the model when `provider` is an object, as it did before', async () => {
+        const completeSpy = vi.spyOn(FakeChatProvider.prototype, 'complete');
+        await withTestActor(() =>
+            driver.complete({
+                model: 'fake',
+                messages: hi,
+                provider: { order: ['Anthropic'] },
+            } as never),
+        );
+        expect(completeSpy).toHaveBeenCalledTimes(1);
+    });
+
+    it.each([false, 0, '', null])(
+        'treats `tools: %j` as no tools when counting tokens',
+        async (tools) => {
+            const countTokens = vi.fn(async (_args: object) => 1);
+            const fake = FakeChatProvider.prototype as {
+                countTokens?: typeof countTokens;
+            };
+            fake.countTokens = countTokens;
+            try {
+                await withTestActor(() =>
+                    driver[COUNT_TOKENS]({
+                        model: 'fake',
+                        messages: hi,
+                        tools,
+                    } as never),
+                );
+            } finally {
+                delete fake.countTokens;
+            }
+            expect(countTokens.mock.calls[0]![0]).not.toHaveProperty('tools');
+        },
+    );
+
+    it.each([false, 0, '', null])(
+        'treats `tools: %j` as no tools',
+        async (tools) => {
+            const completeSpy = vi.spyOn(FakeChatProvider.prototype, 'complete');
+            await withTestActor(() =>
+                driver.complete({ model: 'fake', messages: hi, tools } as never),
+            );
+            expect(completeSpy.mock.calls[0]![0]).not.toHaveProperty('tools');
+        },
+    );
+
+    it('reports zero tokens in the cost event for a usage count that is not a number', async () => {
+        vi.spyOn(FakeChatProvider.prototype, 'models').mockResolvedValueOnce([
+            {
+                id: 'priced',
+                aliases: [],
+                costs_currency: 'usd-cents',
+                costs: { input_tokens: 1000, output_tokens: 2000 },
+                max_tokens: 8192,
+            },
+        ]);
+        const d = await makeDriver();
+        const costEvents = captureEvent('ai.prompt.cost-calculated');
+        vi.spyOn(FakeChatProvider.prototype, 'complete').mockResolvedValueOnce({
+            message: { role: 'assistant', content: [{ type: 'text', text: 'ok' }] },
+            usage: { input_tokens: 10, output_tokens: { toString: null } },
+            finish_reason: 'stop',
+        } as never);
+
+        await withTestActor(() => d.complete({ model: 'priced', messages: hi }));
+
+        expect(costEvents[0]![1]).toMatchObject({
+            input_tokens: 10,
+            output_tokens: 0,
+            total_ucents: 10 * 1000,
+        });
+    });
+});

src/backend/drivers/ai/interfaces/chat/ChatCompletionDriver.ts

@@ -19,56 +19,56 @@
 
 import crypto from 'node:crypto';
 import { PassThrough } from 'node:stream';
-import { EventMap } from '../../clients/event/types.js';
-import type { Actor } from '../../core/actor.js';
-import { Context } from '../../core/context.js';
-import { HttpError, isHttpError } from '../../core/http/HttpError.js';
-import { insufficientCreditsError } from '../../services/metering/enforcement.js';
-import { isFreeSubscription } from '../../services/metering/consts.js';
-import type { MeteringService } from '../../services/metering/MeteringService.js';
-import type { CreditHold } from '../../services/metering/types.js';
-import { NO_CREDIT_HOLD } from '../../services/metering/types.js';
-import type { DriverStreamResult } from '../meta.js';
-import { PuterDriver } from '../types.js';
+import { EventMap } from '../../../../clients/event/types.js';
+import type { Actor } from '../../../../core/actor.js';
+import { Context } from '../../../../core/context.js';
+import { HttpError, isHttpError } from '../../../../core/http/HttpError.js';
+import { insufficientCreditsError } from '../../../../services/metering/enforcement.js';
+import { isFreeSubscription } from '../../../../services/metering/consts.js';
+import type { MeteringService } from '../../../../services/metering/MeteringService.js';
+import type { CreditHold } from '../../../../services/metering/types.js';
+import { NO_CREDIT_HOLD } from '../../../../services/metering/types.js';
+import type { DriverStreamResult } from '../../../meta.js';
+import { PuterDriver } from '../../../types.js';
 import {
     type AiMeteringService,
     factoredTotal,
     requestAiCosts,
     withAiCostFactor,
-} from '../util/aiCostFactor.js';
-import { AI_CONCURRENT, AI_RATE_LIMIT } from '../util/aiLimits.js';
+} from '../../../../util/aiCostFactor.js';
+import { AI_CONCURRENT, AI_RATE_LIMIT } from '../../shared/aiLimits.js';
 import {
     isCreditExhaustion as isUpstreamCreditExhaustion,
     isUpstreamConnectionError,
     isUpstreamTimeoutError,
     sanitizeUpstreamMessage,
     UpstreamDeadlineError,
-} from '../util/upstreamErrors.js';
-import { AlibabaProvider } from './providers/alibaba/AlibabaProvider.js';
-import { AzureChatProvider } from './providers/azure/AzureChatProvider.js';
-import { AzureResponsesProvider } from './providers/azure/AzureResponsesProvider.js';
-import { BytePlusProvider } from './providers/byteplus/BytePlusProvider.js';
-import { ClaudeProvider } from './providers/claude/ClaudeProvider.js';
-import { DeepSeekProvider } from './providers/deepseek/DeepSeekProvider.js';
-import { FakeChatProvider } from './providers/FakeChatProvider.js';
-import { GeminiChatProvider } from './providers/gemini/GeminiChatProvider.js';
-import { GroqAIProvider } from './providers/groq/GroqAIProvider.js';
-import { HoonifyProvider } from './providers/hoonify/HoonifyProvider.js';
-import { InfronProvider } from './providers/infron/InfronProvider.js';
-import { MetaProvider } from './providers/meta/MetaProvider.js';
-import { MiniMaxProvider } from './providers/minimax/MiniMaxProvider.js';
-import { MistralAIProvider } from './providers/mistral/MistralAiProvider.js';
-import { MoonshotProvider } from './providers/moonshot/MoonshotProvider.js';
-import { NeuralwattProvider } from './providers/neuralwatt/NeuralwattProvider.js';
-import { OllamaChatProvider } from './providers/ollama/OllamaProvider.js';
-import type { ChatProviderConfig } from './providers/OpenAICompatProvider.js';
-import { processPuterPathUploads } from './providers/openai/fileUpload.js';
-import { OpenAiChatProvider } from './providers/openai/OpenAiChatCompletionsProvider.js';
-import { OpenAiResponsesChatProvider } from './providers/openai/OpenAiChatResponsesProvider.js';
-import { OpenRouterProvider } from './providers/openrouter/OpenRouterProvider.js';
-import { TogetherAIProvider } from './providers/together/TogetherAIProvider.js';
-import { XAIProvider } from './providers/xai/XAIProvider.js';
-import { ZAIProvider } from './providers/zai/ZAIProvider.js';
+} from '../../../util/upstreamErrors.js';
+import { AlibabaProvider } from '../../providers/alibaba/chat/AlibabaProvider.js';
+import { AzureChatProvider } from '../../providers/azure/chat/AzureChatProvider.js';
+import { AzureResponsesProvider } from '../../providers/azure/chat/AzureResponsesProvider.js';
+import { BytePlusProvider } from '../../providers/byteplus/chat/BytePlusProvider.js';
+import { ClaudeProvider } from '../../providers/claude/chat/ClaudeProvider.js';
+import { DeepSeekProvider } from '../../providers/deepseek/chat/DeepSeekProvider.js';
+import { FakeChatProvider } from '../../providers/fake/chat/FakeChatProvider.js';
+import { GeminiChatProvider } from '../../providers/gemini/chat/GeminiChatProvider.js';
+import { GroqAIProvider } from '../../providers/groq/chat/GroqAIProvider.js';
+import { HoonifyProvider } from '../../providers/hoonify/chat/HoonifyProvider.js';
+import { InfronProvider } from '../../providers/infron/chat/InfronProvider.js';
+import { MetaProvider } from '../../providers/meta/chat/MetaProvider.js';
+import { MiniMaxProvider } from '../../providers/minimax/chat/MiniMaxProvider.js';
+import { MistralAIProvider } from '../../providers/mistral/chat/MistralAiProvider.js';
+import { MoonshotProvider } from '../../providers/moonshot/chat/MoonshotProvider.js';
+import { NeuralwattProvider } from '../../providers/neuralwatt/chat/NeuralwattProvider.js';
+import { OllamaChatProvider } from '../../providers/ollama/chat/OllamaProvider.js';
+import type { ChatProviderConfig } from '../../protocols/openaiCompatible/OpenAICompatProvider.js';
+import { processPuterPathUploads } from '../../providers/openai/chat/fileUpload.js';
+import { OpenAiChatProvider } from '../../providers/openai/chat/OpenAiChatCompletionsProvider.js';
+import { OpenAiResponsesChatProvider } from '../../providers/openai/chat/OpenAiChatResponsesProvider.js';
+import { OpenRouterProvider } from '../../providers/openrouter/chat/OpenRouterProvider.js';
+import { TogetherAIProvider } from '../../providers/together/chat/TogetherAIProvider.js';
+import { XAIProvider } from '../../providers/xai/chat/XAIProvider.js';
+import { ZAIProvider } from '../../providers/zai/chat/ZAIProvider.js';
 import type {
     IChatCompleteResult,
     IChatMessageResult,
@@ -103,9 +103,13 @@ import {
     normalizeResultToOpenAI,
     shouldPresentAsOpenAI,
 } from './utils/normalizeToOpenAI.js';
-import { isToolChoice, toolChoiceFromWire } from './utils/openaiParams.js';
 import {
-    catalogPrice,
+    isToolChoice,
+    toolChoiceFromWire,
+} from '../../protocols/openaiCompatible/openaiParams.js';
+import { assertScalarOptions } from '../../shared/scalarOptions.js';
+import { catalogPrice } from '../../shared/catalogPrice.js';
+import {
     costKeys,
     costsForRequest,
     isFreeModel,
@@ -121,7 +125,7 @@ import {
     TRANSIENT_UNHEALTHY_TTL_SEC,
     UNHEALTHY_TTL_SEC,
 } from './utils/providerHealth.js';
-import { CATALOG_TTL_MS } from './utils/cachedRemoteCatalog.js';
+import { CATALOG_TTL_MS } from '../../shared/cachedRemoteCatalog.js';
 import { SDK_TIMEOUT_MS } from './utils/sdkClient.js';
 import { fromFinishReason } from './utils/stopReason.js';
 import { AIChatStream } from './utils/Streaming.js';
@@ -178,6 +182,9 @@ export const COUNT_TOKENS = Symbol('aiChat.countTokens');
  */
 const HOLD_RENEW_INTERVAL_MS = 5 * 60 * 1000;
 
+// Options that reach error messages and request headers as text.
+const SCALAR_OPTIONS = ['model', 'provider', 'service_tier'];
+
 /**
  * A moderation refusal is a completion that was produced and charged, then
  * withheld — not a route failure. Retrying it on a fallback provider would bill
@@ -585,7 +592,7 @@ export class ChatCompletionDriver extends PuterDriver {
     readonly driverName = 'ai-chat';
     readonly isDefault = true;
 
-    // Shared AI policy — see `drivers/util/aiLimits.ts` for the tier table.
+    // Shared AI policy — see `drivers/ai/shared/aiLimits.ts` for the tier table.
     readonly rateLimit = AI_RATE_LIMIT;
     readonly concurrent = AI_CONCURRENT;
 
@@ -690,6 +697,7 @@ export class ChatCompletionDriver extends PuterDriver {
                 { legacyCode: 'invalid_service_speed' },
             );
         }
+        assertScalarOptions(args, SCALAR_OPTIONS);
         const abortSignal = Context.get('abortSignal');
         abortSignal?.throwIfAborted();
         const actor = Context.get('actor');
@@ -744,6 +752,9 @@ export class ChatCompletionDriver extends PuterDriver {
         args.messages = normalizeMediaParts(normalize_messages(args.messages));
         if (args.tools) {
             normalize_tools_object(args.tools);
+        } else {
+            // `tools: enabled && list` leaves `false` here; it means no tools.
+            delete args.tools;
         }
         // A raw `/drivers/call` caller still sends the OpenAI wire form
         // ('auto'/'none'/'required', {type:'function', function:{name}}) —
@@ -1297,8 +1308,17 @@ export class ChatCompletionDriver extends PuterDriver {
             }, HOLD_RENEW_INTERVAL_MS);
             renewHold.unref?.();
 
-            // Fire-and-forget — the stream writes happen async while the
-            // response is being piped to the client.
+            // The upstream runs on after a caller hangs up, so the request
+            // keeps its concurrency slot until the upstream is done, not until
+            // the cleanup after it.
+            let upstreamDone!: () => void;
+            const upstreamRunning = new Promise<void>((resolve) => {
+                upstreamDone = resolve;
+            });
+            Context.get('keepConcurrencySlot')?.(upstreamRunning);
+
+            // The stream writes happen async while the response is piped to
+            // the client.
             (async () => {
                 try {
                     await init({ chatStream });
@@ -1323,6 +1343,7 @@ export class ChatCompletionDriver extends PuterDriver {
                     }
                     passthrough.end();
                 } finally {
+                    upstreamDone();
                     clearInterval(renewHold);
                     clearTimeout(detachedLimit);
                     abortSignal?.removeEventListener('abort', detachStream);
@@ -1490,6 +1511,7 @@ export class ChatCompletionDriver extends PuterDriver {
     async [COUNT_TOKENS](
         args: ICompleteArguments,
     ): Promise<{ input_tokens: number }> {
+        assertScalarOptions(args, SCALAR_OPTIONS);
         let intendedProvider = args.provider || '';
         if (!args.model && !intendedProvider) {
             intendedProvider = 'azure-openai';
@@ -1515,6 +1537,9 @@ export class ChatCompletionDriver extends PuterDriver {
         args.messages = normalizeMediaParts(normalize_messages(args.messages));
         if (args.tools) {
             normalize_tools_object(args.tools);
+        } else {
+            // `tools: enabled && list` leaves `false` here; it means no tools.
+            delete args.tools;
         }
 
         const provider = this.#providers[model.provider!];
@@ -1848,20 +1873,20 @@ export class ChatCompletionDriver extends PuterDriver {
 
         const cost = usageCost(usage, model, usageCosts, pricingTime);
         const { inputKey, outputKey } = costKeys(model);
+        // The vendor reports usage, and pricing skips a count that is not a
+        // number; so does this.
+        const count = (value: unknown) =>
+            typeof value === 'number' && Number.isFinite(value) ? value : 0;
         const inputTokens = cost
-            ? Number(
-                  usage[inputKey] ??
-                      usage.prompt_tokens ??
-                      usage.input_tokens ??
-                      0,
+            ? count(
+                  usage[inputKey] ?? usage.prompt_tokens ?? usage.input_tokens,
               )
             : 0;
         const outputTokens = cost
-            ? Number(
+            ? count(
                   usage[outputKey] ??
                       usage.completion_tokens ??
-                      usage.output_tokens ??
-                      0,
+                      usage.output_tokens,
               )
             : 0;
         const inputMicroCents = cost?.inputMicroCents ?? 0;
@@ -2061,14 +2086,39 @@ export class ChatCompletionDriver extends PuterDriver {
                 // instance, so they are read and never written: normalizing
                 // the id or appending puterId in place would accumulate across
                 // instantiations. The bucket gets its own copy instead.
-                const aliases =
-                    entry.puterId &&
-                    !(entry.aliases ?? []).includes(entry.puterId)
-                        ? [...(entry.aliases ?? []), entry.puterId]
-                        : entry.aliases;
+                // Keep upstream ids for provider calls and publish a qualified
+                // routing name even when a catalog omits its vendor namespace.
+                const publicId = entry.puterId || entry.id;
+                // A colon after the first slash belongs to the model name, as
+                // in `vendor/model:free`, and names no service.
+                const serviceSeparator = publicId
+                    .split('/', 1)[0]!
+                    .indexOf(':');
+                const service =
+                    serviceSeparator < 0
+                        ? providerName
+                        : publicId.slice(0, serviceSeparator);
+                const modelPath =
+                    serviceSeparator < 0
+                        ? publicId
+                        : publicId.slice(serviceSeparator + 1);
+                const puterId =
+                    providerName === 'fake-chat'
+                        ? entry.puterId
+                        : `${service}:${modelPath.includes('/') ? modelPath : `${service}/${modelPath}`}`;
+                const aliases = puterId
+                    ? [
+                          ...new Set([
+                              ...(entry.aliases ?? []),
+                              ...(entry.puterId ? [entry.puterId] : []),
+                              puterId,
+                          ]),
+                      ]
+                    : entry.aliases;
                 const model = {
                     ...entry,
                     id: normalizeModelKey(entry.id),
+                    ...(puterId ? { puterId } : {}),
                 };
                 // Assigned only when the entry has names to carry: models()
                 // is serialized to the API, and an entry that declared no

src/backend/drivers/ai/interfaces/chat/modelCatalogs.test.ts

@@ -47,29 +47,29 @@
  * on that test.)
  */
 
-import { readdirSync } from 'node:fs';
+import { existsSync, readdirSync } from 'node:fs';
 import { dirname, join } from 'node:path';
 import { fileURLToPath, pathToFileURL } from 'node:url';
 
 import { describe, expect, it } from 'vitest';
 
-import type { IChatModel } from '../types.js';
-import { ALIBABA_MODELS } from './alibaba/models.js';
-import { AZURE_MODELS } from './azure/models.js';
-import { BYTEPLUS_MODELS } from './byteplus/models.js';
-import { CLAUDE_MODELS } from './claude/models.js';
-import { DEEPSEEK_MODELS } from './deepseek/models.js';
-import { GEMINI_MODELS } from './gemini/models.js';
-import { GROQ_MODELS } from './groq/models.js';
-import { HOONIFY_MODELS } from './hoonify/models.js';
-import { META_MODELS } from './meta/models.js';
-import { MINIMAX_MODELS } from './minimax/models.js';
-import { MISTRAL_MODELS } from './mistral/models.js';
-import { MOONSHOT_MODELS } from './moonshot/models.js';
-import { OPEN_AI_MODELS } from './openai/models.js';
-import { OPEN_ROUTER_MODEL_OVERRIDES } from './openrouter/modelOverrides.js';
-import { XAI_MODELS } from './xai/models.js';
-import { ZAI_MODELS } from './zai/models.js';
+import type { IChatModel } from './types.js';
+import { ALIBABA_MODELS } from '../../providers/alibaba/chat/models.js';
+import { AZURE_MODELS } from '../../providers/azure/chat/models.js';
+import { BYTEPLUS_MODELS } from '../../providers/byteplus/chat/models.js';
+import { CLAUDE_MODELS } from '../../providers/claude/chat/models.js';
+import { DEEPSEEK_MODELS } from '../../providers/deepseek/chat/models.js';
+import { GEMINI_MODELS } from '../../providers/gemini/chat/models.js';
+import { GROQ_MODELS } from '../../providers/groq/chat/models.js';
+import { HOONIFY_MODELS } from '../../providers/hoonify/chat/models.js';
+import { META_MODELS } from '../../providers/meta/chat/models.js';
+import { MINIMAX_MODELS } from '../../providers/minimax/chat/models.js';
+import { MISTRAL_MODELS } from '../../providers/mistral/chat/models.js';
+import { MOONSHOT_MODELS } from '../../providers/moonshot/chat/models.js';
+import { OPEN_AI_MODELS } from '../../providers/openai/chat/models.js';
+import { OPEN_ROUTER_MODEL_OVERRIDES } from '../../providers/openrouter/chat/modelOverrides.js';
+import { XAI_MODELS } from '../../providers/xai/chat/models.js';
+import { ZAI_MODELS } from '../../providers/zai/chat/models.js';
 
 // Providers whose catalog is fetched at runtime (OpenRouter, Ollama, Together,
 // Infron, Neuralwatt) have nothing static to check and are absent by design;
@@ -201,28 +201,34 @@ describe('CATALOGS', () => {
     // silent gap these tests are about, so the list is checked against what
     // is actually on disk.
     //
-    // The scan covers every non-test source file under providers/*/ with
-    // "model" in its name — models.ts, but also siblings like openrouter's
-    // modelOverrides.ts. Importing every provider file regardless of name
-    // would drag in SDK modules for a filename sweep, so that naming
-    // convention is the one assumption left unenforced here: a catalog in a
-    // file named without "model" would escape this net.
-    it('lists every static catalog under providers/', async () => {
-        const here = dirname(fileURLToPath(import.meta.url));
+    // The scan covers every non-test source file under providers/*/chat/
+    // with "model" in its name — models.ts, but also siblings like
+    // openrouter's modelOverrides.ts. Importing every provider file
+    // regardless of name would drag in SDK modules for a filename sweep, so
+    // that naming convention is the one assumption left unenforced here: a
+    // catalog in a file named without "model" would escape this net.
+    it('lists every static catalog under providers/*/chat/', async () => {
+        const providersDir = join(
+            dirname(fileURLToPath(import.meta.url)),
+            '../../providers',
+        );
         const registered = new Map(CATALOGS);
+        const found = new Set<string>();
         const problems: string[] = [];
 
-        for (const dir of readdirSync(here, { withFileTypes: true })) {
+        for (const dir of readdirSync(providersDir, { withFileTypes: true })) {
             if (!dir.isDirectory()) continue;
+            const chatDir = join(providersDir, dir.name, 'chat');
+            if (!existsSync(chatDir)) continue;
 
-            for (const file of readdirSync(join(here, dir.name))) {
+            for (const file of readdirSync(chatDir)) {
                 if (!/model/i.test(file)) continue;
                 if (!file.endsWith('.ts') || file.endsWith('.test.ts')) {
                     continue;
                 }
 
                 const module = await import(
-                    pathToFileURL(join(here, dir.name, file)).href
+                    pathToFileURL(join(chatDir, file)).href
                 );
                 for (const [name, value] of Object.entries(module)) {
                     // A catalog is a non-empty array of entries carrying an
@@ -233,16 +239,19 @@ describe('CATALOGS', () => {
                         value.length > 0 &&
                         typeof value[0]?.id === 'string';
                     if (!isCatalog) continue;
+                    found.add(name);
 
                     if (!registered.has(name)) {
-                        problems.push(`${dir.name}/${file} exports ${name}`);
+                        problems.push(
+                            `${dir.name}/chat/${file} exports ${name}`,
+                        );
                     } else if (registered.get(name) !== value) {
                         // The row's label names this export but its value is
                         // a different array — the wrong catalog would be the
                         // one getting checked.
                         problems.push(
                             `the CATALOGS row named ${name} does not hold ` +
-                                `the ${name} that ${dir.name}/${file} exports`,
+                                `the ${name} that ${dir.name}/chat/${file} exports`,
                         );
                     }
                 }
@@ -250,5 +259,7 @@ describe('CATALOGS', () => {
         }
 
         expect(problems, problems.join('\n')).toEqual([]);
+        // A scan pointed at the wrong directory finds nothing and passes.
+        expect([...found].sort()).toEqual([...registered.keys()].sort());
     });
 });

src/backend/drivers/ai/interfaces/chat/providerConsistency.test.ts

@@ -39,41 +39,41 @@
 
 import { describe, expect, it, vi } from 'vitest';
 
-import type { MeteringService } from '../../../services/metering/MeteringService.js';
-import { withTestActor } from '../../integrationTestUtil.js';
+import type { MeteringService } from '../../../../services/metering/MeteringService.js';
+import { withTestActor } from '../../shared/integrationTestUtil.js';
 import type {
     IChatMessageResult,
     IChatModel,
     IChatProvider,
-} from '../types.js';
+} from './types.js';
 import {
     needsOpenAICoercion,
     normalizeResultToOpenAI,
-} from '../utils/normalizeToOpenAI.js';
+} from './utils/normalizeToOpenAI.js';
 
-import { AlibabaProvider } from './alibaba/AlibabaProvider.js';
-import { AzureChatProvider } from './azure/AzureChatProvider.js';
-import { AzureResponsesProvider } from './azure/AzureResponsesProvider.js';
-import { BytePlusProvider } from './byteplus/BytePlusProvider.js';
-import { ClaudeProvider } from './claude/ClaudeProvider.js';
-import { DeepSeekProvider } from './deepseek/DeepSeekProvider.js';
-import { FakeChatProvider } from './FakeChatProvider.js';
-import { GeminiChatProvider } from './gemini/GeminiChatProvider.js';
-import { GroqAIProvider } from './groq/GroqAIProvider.js';
-import { HoonifyProvider } from './hoonify/HoonifyProvider.js';
-import { InfronProvider } from './infron/InfronProvider.js';
-import { MetaProvider } from './meta/MetaProvider.js';
-import { MiniMaxProvider } from './minimax/MiniMaxProvider.js';
-import { MistralAIProvider } from './mistral/MistralAiProvider.js';
-import { MoonshotProvider } from './moonshot/MoonshotProvider.js';
-import { NeuralwattProvider } from './neuralwatt/NeuralwattProvider.js';
-import { OllamaChatProvider } from './ollama/OllamaProvider.js';
-import { OpenAiChatProvider } from './openai/OpenAiChatCompletionsProvider.js';
-import { OpenAiResponsesChatProvider } from './openai/OpenAiChatResponsesProvider.js';
-import { OpenRouterProvider } from './openrouter/OpenRouterProvider.js';
-import { TogetherAIProvider } from './together/TogetherAIProvider.js';
-import { XAIProvider } from './xai/XAIProvider.js';
-import { ZAIProvider } from './zai/ZAIProvider.js';
+import { AlibabaProvider } from '../../providers/alibaba/chat/AlibabaProvider.js';
+import { AzureChatProvider } from '../../providers/azure/chat/AzureChatProvider.js';
+import { AzureResponsesProvider } from '../../providers/azure/chat/AzureResponsesProvider.js';
+import { BytePlusProvider } from '../../providers/byteplus/chat/BytePlusProvider.js';
+import { ClaudeProvider } from '../../providers/claude/chat/ClaudeProvider.js';
+import { DeepSeekProvider } from '../../providers/deepseek/chat/DeepSeekProvider.js';
+import { FakeChatProvider } from '../../providers/fake/chat/FakeChatProvider.js';
+import { GeminiChatProvider } from '../../providers/gemini/chat/GeminiChatProvider.js';
+import { GroqAIProvider } from '../../providers/groq/chat/GroqAIProvider.js';
+import { HoonifyProvider } from '../../providers/hoonify/chat/HoonifyProvider.js';
+import { InfronProvider } from '../../providers/infron/chat/InfronProvider.js';
+import { MetaProvider } from '../../providers/meta/chat/MetaProvider.js';
+import { MiniMaxProvider } from '../../providers/minimax/chat/MiniMaxProvider.js';
+import { MistralAIProvider } from '../../providers/mistral/chat/MistralAiProvider.js';
+import { MoonshotProvider } from '../../providers/moonshot/chat/MoonshotProvider.js';
+import { NeuralwattProvider } from '../../providers/neuralwatt/chat/NeuralwattProvider.js';
+import { OllamaChatProvider } from '../../providers/ollama/chat/OllamaProvider.js';
+import { OpenAiChatProvider } from '../../providers/openai/chat/OpenAiChatCompletionsProvider.js';
+import { OpenAiResponsesChatProvider } from '../../providers/openai/chat/OpenAiChatResponsesProvider.js';
+import { OpenRouterProvider } from '../../providers/openrouter/chat/OpenRouterProvider.js';
+import { TogetherAIProvider } from '../../providers/together/chat/TogetherAIProvider.js';
+import { XAIProvider } from '../../providers/xai/chat/XAIProvider.js';
+import { ZAIProvider } from '../../providers/zai/chat/ZAIProvider.js';
 
 // ── Upstream SDK mocks ──────────────────────────────────────────────
 // One create-mock per wire dialect; every provider speaking that dialect

src/backend/drivers/ai/interfaces/chat/utils/FunctionCalling.js

@@ -18,7 +18,6 @@
  */
 
 import { HttpError } from '@heyputer/backend/src/core/http';
-import { claudeToolPolicy } from '../providers/claude/anthropicPolicy.js';
 
 // Anthropic server/typed tool ids (`web_search_20250305`,
 // `advisor_20260301`, …) and the OpenAI Responses `web_search` tool pass
@@ -124,7 +123,7 @@ export const normalize_tools_object = (tools) => {
         };
 
         // Claude-only extras, carried on the `{type:'function', ...}`
-        // wrapper so `make_claude_tools` can forward them; a top-level
+        // wrapper so `claudeToolPolicy` can forward them; a top-level
         // `strict` (Claude's own convention) moves onto `function.strict`.
         const extras = {};
         if (tool.cache_control !== undefined)
@@ -169,76 +168,3 @@ export const normalize_tools_object = (tools) => {
     }
     return tools;
 };
-
-// OpenAI's own tool conventions pass through untouched.
-const OPENAI_NATIVE_WEB_SEARCH = new Set(['web_search', 'web_search_preview']);
-const ANTHROPIC_WEB_SEARCH_TYPE = (type) =>
-    type === 'web_search_20250305' || /^web_search_2026/.test(type ?? '');
-
-/**
- * Converts a normalized tools object to the format expected by an OpenAI-family
- * dialect: function tools drop their Anthropic-only extras (`cache_control`,
- * `defer_loading`, `eager_input_streaming`, `input_examples`); every other
- * Anthropic typed/server tool (`web_search_20250305`, `advisor_20260301`,
- * `bash_*`, …) is dropped, since none of it is a wire shape OpenAI recognizes.
- * The one exception: an Anthropic web-search tool is translated to OpenAI's own
- * `web_search` tool for the Responses dialect, which supports it natively.
- *
- * @param {any} tools
- * @param {{ dialect?: 'chat' | 'responses' }} [opts]
- * @returns {any[] | undefined}
- */
-export const make_openai_tools = (tools, opts = {}) => {
-    if (!tools) return tools;
-    const dialect = opts.dialect ?? 'chat';
-    const out = [];
-    for (const tool of tools) {
-        if (!tool || typeof tool !== 'object') continue;
-        if (tool.type === 'function') {
-            const stripped = { ...tool };
-            delete stripped.cache_control;
-            delete stripped.defer_loading;
-            delete stripped.eager_input_streaming;
-            delete stripped.input_examples;
-            out.push(stripped);
-            continue;
-        }
-        if (OPENAI_NATIVE_WEB_SEARCH.has(tool.type)) {
-            out.push(tool);
-            continue;
-        }
-        if (dialect === 'responses' && ANTHROPIC_WEB_SEARCH_TYPE(tool.type)) {
-            out.push({
-                type: 'web_search',
-                ...(tool.allowed_domains
-                    ? { filters: { allowed_domains: tool.allowed_domains } }
-                    : {}),
-                ...(tool.user_location
-                    ? { user_location: tool.user_location }
-                    : {}),
-            });
-            continue;
-        }
-        // Any other Anthropic typed/server tool (web_search_* on the chat
-        // dialect, advisor, bash, memory, web_fetch, tool_search, …) has no
-        // OpenAI equivalent — drop it rather than forward an unrecognized type.
-    }
-    return out;
-};
-
-/**
- * This function will convert a normalized tools object to the format expected
- * by Claude: function tools become `{name, description, input_schema, ...}`,
- * and typed/server tools (`web_search`, `web_search_20250305`,
- * `advisor_20260301`, …) go through the allowlist/clamp/reject policy in
- * `claudeToolPolicy` instead of being treated as malformed function
- * definitions.
- *
- * @param {any} tools
- * @param {{ models?: import('../types.js').IChatModel[] }} [opts]
- * @returns {any[] | undefined}
- */
-export const make_claude_tools = (tools, opts = {}) => {
-    if (!tools) return undefined;
-    return claudeToolPolicy(tools, opts.models ?? []).tools;
-};

src/backend/drivers/ai/interfaces/chat/utils/FunctionCalling.test.ts

@@ -20,13 +20,11 @@
 import { describe, expect, it } from 'vitest';
 // @ts-expect-error — sibling JS module without an adjacent .d.ts
 import {
-    make_claude_tools,
-    make_openai_tools,
     normalize_json_schema,
     normalize_tools_object,
 } from './FunctionCalling.js';
 
-// All four exports are pure data transforms — these tests just feed
+// Both exports are pure data transforms — these tests just feed
 // inputs and check the normalized output, no service mocks involved.
 
 // ── normalize_json_schema ───────────────────────────────────────────
@@ -242,159 +240,3 @@ describe('normalize_tools_object', () => {
         expect(out[0].function.parameters.properties).toBe('x');
     });
 });
-
-// ── make_openai_tools ───────────────────────────────────────────────
-
-describe('make_openai_tools', () => {
-    it('keeps a function tool, dropping its Anthropic-only extras', () => {
-        const tools = [
-            {
-                type: 'function',
-                function: { name: 'lookup', parameters: { type: 'object' } },
-                cache_control: { type: 'ephemeral' },
-                defer_loading: true,
-                eager_input_streaming: true,
-                input_examples: [{}],
-            },
-        ];
-        expect(make_openai_tools(tools)).toEqual([
-            {
-                type: 'function',
-                function: { name: 'lookup', parameters: { type: 'object' } },
-            },
-        ]);
-    });
-
-    it('drops an Anthropic web_search tool on the chat dialect', () => {
-        const tools = [{ type: 'web_search_20250305', name: 'web_search' }];
-        expect(make_openai_tools(tools, { dialect: 'chat' })).toEqual([]);
-    });
-
-    it('converts an Anthropic web_search tool to OpenAI web_search on the responses dialect', () => {
-        const tools = [
-            {
-                type: 'web_search_20250305',
-                name: 'web_search',
-                max_uses: 5,
-                allowed_domains: ['example.com'],
-                user_location: { type: 'approximate' },
-            },
-        ];
-        expect(
-            make_openai_tools(tools, { dialect: 'responses' }),
-        ).toEqual([
-            {
-                type: 'web_search',
-                filters: { allowed_domains: ['example.com'] },
-                user_location: { type: 'approximate' },
-            },
-        ]);
-    });
-
-    it('keeps OpenAI web_search/web_search_preview tools verbatim', () => {
-        const tools = [{ type: 'web_search' }, { type: 'web_search_preview' }];
-        expect(make_openai_tools(tools, { dialect: 'responses' })).toEqual(
-            tools,
-        );
-    });
-
-    it('drops other Anthropic typed/server tools (advisor, bash, …)', () => {
-        const tools = [
-            { type: 'advisor_20260301', model: 'claude-haiku-4-5' },
-            { type: 'bash_20250124', name: 'bash' },
-        ];
-        expect(make_openai_tools(tools, { dialect: 'responses' })).toEqual([]);
-    });
-
-    it('passes a falsy tools value through unchanged', () => {
-        expect(make_openai_tools(undefined)).toBeUndefined();
-        expect(make_openai_tools(null)).toBeNull();
-    });
-});
-
-describe('make_claude_tools with a malformed tool', () => {
-    it.each([
-        ['type:function with no function property', { type: 'function' }],
-        ['a null entry', null],
-        ['a bare string entry', 'lookup'],
-    ])('answers 400 for a tool with %s', (_label, tool) => {
-        // A TypeError here has no status, so the retry loop reads it as a
-        // provider failure and marks the route unhealthy for every caller.
-        expect(() => make_claude_tools([tool] as never)).toThrowError(
-            expect.objectContaining({
-                statusCode: 400,
-                legacyCode: 'bad_request',
-            }),
-        );
-    });
-
-    it('answers 400 for an unresolvable advisor model', () => {
-        expect(() =>
-            make_claude_tools([
-                { type: 'advisor_20260301', model: 'not-a-real-model' },
-            ] as never),
-        ).toThrowError(
-            expect.objectContaining({ statusCode: 400, legacyCode: 'bad_request' }),
-        );
-    });
-
-    it('answers 400 for an mcp_toolset tool', () => {
-        expect(() =>
-            make_claude_tools([{ type: 'mcp_toolset' }] as never),
-        ).toThrowError(
-            expect.objectContaining({ statusCode: 400, legacyCode: 'bad_request' }),
-        );
-    });
-});
-
-// ── make_claude_tools ───────────────────────────────────────────────
-
-describe('make_claude_tools', () => {
-    it('returns undefined when tools is undefined', () => {
-        expect(make_claude_tools(undefined)).toBeUndefined();
-    });
-
-    it('returns [] when tools is an empty array', () => {
-        expect(make_claude_tools([])).toEqual([]);
-    });
-
-    it('flattens the OpenAI {function:{...}} wrapper into Claude shape', () => {
-        const out = make_claude_tools([
-            {
-                type: 'function',
-                function: {
-                    name: 'lookup',
-                    description: 'Search the docs',
-                    parameters: {
-                        type: 'object',
-                        properties: { q: { type: 'string' } },
-                    },
-                },
-            },
-        ]);
-        expect(out).toEqual([
-            {
-                name: 'lookup',
-                description: 'Search the docs',
-                input_schema: {
-                    type: 'object',
-                    properties: { q: { type: 'string' } },
-                },
-            },
-        ]);
-    });
-
-    it('maps the OpenAI {type:"web_search"} form to web_search_20250305', () => {
-        const out = make_claude_tools([{ type: 'web_search' }] as never);
-        expect(out).toEqual([
-            { type: 'web_search_20250305', name: 'web_search', max_uses: 10 },
-        ]);
-    });
-
-    it('passes a typed server tool through by its own regexp-matched type', () => {
-        const out = make_claude_tools([
-            { type: 'bash_20250124', name: 'bash' },
-        ] as never);
-        expect(out).toEqual([{ type: 'bash_20250124', name: 'bash' }]);
-    });
-});

src/backend/drivers/ai/interfaces/chat/utils/Messages.js

@@ -18,6 +18,7 @@
  */
 
 import { HttpError } from '@heyputer/backend/src/core/http';
+import { convertsToText } from '../../../shared/scalarOptions.js';
 
 /**
  * Normalizes a single message into a standardized format with role and content
@@ -154,6 +155,39 @@ export const normalize_single_message = (message, params = {}) => {
         }
     }
 
+    // Providers write a block's type and a tool call's id into text, which
+    // throws on a value that can't be converted.
+    for (const block of message.content) {
+        if (!convertsToText(block.type)) {
+            throw new HttpError(
+                400,
+                'each message content item type must be a string',
+                { legacyCode: 'bad_request' },
+            );
+        }
+        const callId =
+            block.type === 'tool_use'
+                ? block.id
+                : block.type === 'tool_result'
+                  ? block.tool_use_id
+                  : undefined;
+        if (!convertsToText(callId)) {
+            throw new HttpError(400, 'a tool call id must be a string', {
+                legacyCode: 'bad_request',
+            });
+        }
+        // A tool's result is text or content blocks; any other object is sent
+        // as its JSON, like the content of a `tool` message above.
+        if (
+            block.type === 'tool_result' &&
+            block.content &&
+            typeof block.content === 'object' &&
+            !Array.isArray(block.content)
+        ) {
+            block.content = JSON.stringify(block.content);
+        }
+    }
+
     // Remove "text" properties from content blocks with type=tool_use
     for (let i = 0; i < message.content.length; i++) {
         if (message.content[i].type !== 'tool_use') {

src/backend/drivers/ai/interfaces/chat/utils/Messages.test.ts

@@ -449,3 +449,106 @@ describe('extract_text', () => {
         ).toThrow(expect.objectContaining({ statusCode: 400 }));
     });
 });
+
+describe('normalize_single_message block validation', () => {
+    it.each([
+        [
+            'an assistant tool call',
+            {
+                role: 'assistant',
+                tool_calls: [
+                    { id: { toString: null }, function: { name: 'f', arguments: '{}' } },
+                ],
+            },
+        ],
+        [
+            'a tool_use block',
+            {
+                role: 'assistant',
+                content: [
+                    {
+                        type: 'tool_use',
+                        id: { toString: null },
+                        name: 'f',
+                        input: {},
+                    },
+                ],
+            },
+        ],
+        [
+            'a tool message',
+            { role: 'tool', tool_call_id: [{ toString: null }], content: 'ok' },
+        ],
+        [
+            'a tool_result block',
+            {
+                role: 'user',
+                content: [
+                    {
+                        type: 'tool_result',
+                        tool_use_id: { toString: null },
+                        content: 'ok',
+                    },
+                ],
+            },
+        ],
+    ])('rejects a tool call id that cannot be text on %s', (_label, message) => {
+        expect(() => normalize_single_message(message)).toThrow(
+            expect.objectContaining({
+                statusCode: 400,
+                message: 'a tool call id must be a string',
+            }),
+        );
+    });
+
+    it('keeps a numeric tool call id as the caller sent it', () => {
+        const message = normalize_single_message({
+            role: 'assistant',
+            content: [{ type: 'tool_use', id: 7, name: 'f', input: {} }],
+        });
+        expect(message.content[0].id).toBe(7);
+    });
+
+    it('keeps a tool call that has no id', () => {
+        const message = normalize_single_message({
+            role: 'assistant',
+            tool_calls: [{ function: { name: 'f', arguments: '{}' } }],
+        });
+        expect(message.content).toEqual([
+            { type: 'tool_use', id: undefined, name: 'f', input: '{}' },
+        ]);
+    });
+
+    it('rejects a content item whose type cannot be text', () => {
+        expect(() =>
+            normalize_single_message({
+                role: 'user',
+                content: [{ type: { toString: null }, text: 'hi' }],
+            }),
+        ).toThrow(
+            expect.objectContaining({
+                statusCode: 400,
+                message: 'each message content item type must be a string',
+            }),
+        );
+    });
+
+    it('sends an object tool result as its JSON', () => {
+        const message = normalize_single_message({
+            role: 'user',
+            content: [
+                { type: 'tool_result', tool_use_id: 't1', content: { temp: 21 } },
+            ],
+        });
+        expect(message.content[0].content).toBe('{"temp":21}');
+    });
+
+    it('keeps a tool result made of content blocks', () => {
+        const blocks = [{ type: 'text', text: 'Sunny' }];
+        const message = normalize_single_message({
+            role: 'user',
+            content: [{ type: 'tool_result', tool_use_id: 't1', content: blocks }],
+        });
+        expect(message.content[0].content).toEqual(blocks);
+    });
+});

src/backend/drivers/ai/interfaces/chat/utils/compaction.js

@@ -18,20 +18,21 @@
  */
 
 /**
- * Inline-compaction translation helpers.
+ * Inline-compaction opt-in helpers.
  *
  * The driver-facing surface exposes a single provider-neutral opt-in
  * (`compaction: boolean | { trigger_tokens }` on `ICompleteArguments`), plus a
  * raw `context_management` escape hatch for callers hitting `/responses` with
- * the OpenAI-native shape. These helpers map that neutral opt-in to each
- * provider's SDK shape so the providers stay free of opt-in-parsing logic.
+ * the OpenAI-native shape. This module reads the opt-in; each dialect maps it
+ * to its own SDK shape (`toOpenAiContextManagement` in the OpenAI protocol,
+ * `toAnthropicContextManagement` in the Claude provider).
  */
 
 /**
  * @param {boolean | { trigger_tokens?: number } | undefined} compaction
  * @returns {{ enabled: boolean; trigger_tokens?: number }}
  */
-const readCompaction = (compaction) => {
+export const readCompaction = (compaction) => {
     if (compaction === true) return { enabled: true };
     if (compaction && typeof compaction === 'object') {
         return {
@@ -44,65 +45,6 @@ const readCompaction = (compaction) => {
     return { enabled: false };
 };
 
-/**
- * Build OpenAI Responses `context_management` from the neutral opt-in. A raw
- * `context_management` passthrough (already in OpenAI shape) wins.
- *
- * @param {{
- *     compaction?: boolean | { trigger_tokens?: number };
- *     context_management?: unknown;
- * }} args
- * @returns {{ type: 'compaction'; compact_threshold?: number }[] | undefined}
- */
-export const toOpenAiContextManagement = (args) => {
-    if (args.context_management !== undefined) {
-        return /** @type {any} */ (args.context_management);
-    }
-    const { enabled, trigger_tokens } = readCompaction(args.compaction);
-    if (!enabled) return undefined;
-    return [
-        {
-            type: 'compaction',
-            ...(trigger_tokens !== undefined
-                ? { compact_threshold: trigger_tokens }
-                : {}),
-        },
-    ];
-};
-
-/**
- * Build Anthropic `context_management` (beta `compact-2026-01-12`) from the
- * neutral opt-in. A raw `context_management` passthrough wins.
- *
- * @param {{
- *     compaction?: boolean | { trigger_tokens?: number };
- *     context_management?: unknown;
- * }} args
- * @returns {{ edits: Record<string, unknown>[] } | undefined}
- */
-export const toAnthropicContextManagement = (args) => {
-    if (args.context_management !== undefined) {
-        return /** @type {any} */ (args.context_management);
-    }
-    const { enabled, trigger_tokens } = readCompaction(args.compaction);
-    if (!enabled) return undefined;
-    return {
-        edits: [
-            {
-                type: 'compact_20260112',
-                ...(trigger_tokens !== undefined
-                    ? {
-                          trigger: {
-                              type: 'input_tokens',
-                              value: trigger_tokens,
-                          },
-                      }
-                    : {}),
-            },
-        ],
-    };
-};
-
 /**
  * Whether the request opted into inline compaction by any route.
  *

src/backend/drivers/ai/interfaces/chat/utils/compaction.test.ts

@@ -0,0 +1,62 @@
+/*
+ * Copyright (C) 2024-present Puter Technologies Inc.
+ *
+ * This file is part of Puter.
+ *
+ * Puter is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+import { describe, expect, it } from 'vitest';
+import { messagesHaveCompaction, wantsCompaction } from './compaction.js';
+
+describe('wantsCompaction', () => {
+    it('is false without opt-in', () => {
+        expect(wantsCompaction({})).toBe(false);
+        expect(wantsCompaction({ compaction: false })).toBe(false);
+    });
+
+    it('is true for the neutral opt-in or a raw passthrough', () => {
+        expect(wantsCompaction({ compaction: true })).toBe(true);
+        expect(wantsCompaction({ compaction: { trigger_tokens: 1 } })).toBe(
+            true,
+        );
+        expect(wantsCompaction({ context_management: [] })).toBe(true);
+    });
+});
+
+describe('messagesHaveCompaction', () => {
+    it('detects a round-tripped compaction content block', () => {
+        expect(
+            messagesHaveCompaction([
+                { role: 'user', content: [{ type: 'text', text: 'hi' }] },
+                {
+                    role: 'assistant',
+                    content: [
+                        { type: 'compaction', encrypted_content: 'ENC' },
+                    ],
+                },
+            ]),
+        ).toBe(true);
+    });
+
+    it('is false for ordinary messages or non-arrays', () => {
+        expect(
+            messagesHaveCompaction([
+                { role: 'user', content: [{ type: 'text', text: 'hi' }] },
+            ]),
+        ).toBe(false);
+        expect(messagesHaveCompaction(undefined)).toBe(false);
+        expect(messagesHaveCompaction('nope')).toBe(false);
+    });
+});

src/backend/drivers/ai/interfaces/chat/utils/mediaParts.ts

@@ -40,7 +40,7 @@ type Part = Record<string, unknown>;
 const isObject = (value: unknown): value is Part =>
     !!value && typeof value === 'object' && !Array.isArray(value);
 
-export { parseDataUri } from '../../util/dataUri.js';
+export { parseDataUri } from '../../../../util/dataUri.js';
 
 /** The URL out of a bare string or an OpenAI-style `{ url }` object. */
 export const mediaUrlOf = (value: unknown): string | undefined => {

src/backend/drivers/ai/interfaces/chat/utils/meterChatUsage.test.ts

@@ -18,19 +18,19 @@
  */
 
 import { describe, expect, it } from 'vitest';
-import type { Actor } from '../../../core/actor.js';
-import { ALIBABA_MODELS } from '../providers/alibaba/models.js';
-import { BYTEPLUS_MODELS } from '../providers/byteplus/models.js';
-import { DEEPSEEK_MODELS } from '../providers/deepseek/models.js';
-import { GROQ_MODELS } from '../providers/groq/models.js';
-import { HOONIFY_MODELS } from '../providers/hoonify/models.js';
-import { MINIMAX_MODELS } from '../providers/minimax/models.js';
-import { MISTRAL_MODELS } from '../providers/mistral/models.js';
-import { MOONSHOT_MODELS } from '../providers/moonshot/models.js';
-import { ZAI_MODELS } from '../providers/zai/models.js';
+import type { Actor } from '../../../../../core/actor.js';
+import { ALIBABA_MODELS } from '../../../providers/alibaba/chat/models.js';
+import { BYTEPLUS_MODELS } from '../../../providers/byteplus/chat/models.js';
+import { DEEPSEEK_MODELS } from '../../../providers/deepseek/chat/models.js';
+import { GROQ_MODELS } from '../../../providers/groq/chat/models.js';
+import { HOONIFY_MODELS } from '../../../providers/hoonify/chat/models.js';
+import { MINIMAX_MODELS } from '../../../providers/minimax/chat/models.js';
+import { MISTRAL_MODELS } from '../../../providers/mistral/chat/models.js';
+import { MOONSHOT_MODELS } from '../../../providers/moonshot/chat/models.js';
+import { ZAI_MODELS } from '../../../providers/zai/chat/models.js';
 import type { IChatModel } from '../types.js';
 import { meterChatUsage } from './meterChatUsage.js';
-import { splitCachedPrompt } from './OpenAIUtil.js';
+import { splitCachedPrompt } from '../../../protocols/openaiCompatible/OpenAIUtil.js';
 import { usageCost } from './pricing.js';
 
 type Recorded = [Record<string, number>, string, Record<string, number>];

src/backend/drivers/ai/interfaces/chat/utils/meterChatUsage.ts

@@ -17,8 +17,8 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-import type { Actor } from '../../../core/actor.js';
-import type { MeteringService } from '../../../services/metering/MeteringService.js';
+import type { Actor } from '../../../../../core/actor.js';
+import type { MeteringService } from '../../../../../services/metering/MeteringService.js';
 import type { IChatModel, ServiceSpeed } from '../types.js';
 import { serviceSpeedBillingModel } from './serviceSpeed.js';
 import { buildCostsOverride } from './pricing.js';

src/backend/drivers/ai/interfaces/chat/utils/modelRouting.test.ts

@@ -19,7 +19,7 @@
  */
 
 import { describe, expect, it } from 'vitest';
-import { GEMINI_MODELS } from '../providers/gemini/models.js';
+import { GEMINI_MODELS } from '../../../providers/gemini/chat/models.js';
 import type { IChatModel } from '../types.js';
 import {
     compareModelPreference,

src/backend/drivers/ai/interfaces/chat/utils/pricing.test.ts

@@ -21,7 +21,6 @@ import { describe, expect, it } from 'vitest';
 import type { IChatModel } from '../types.js';
 import {
     buildCostsOverride,
-    catalogPrice,
     costsForRequest,
     isFreeModel,
     isOutputCostKey,
@@ -480,12 +479,6 @@ it('preserves free classification for legacy hyphenated token keys', () => {
     expect(isFreeModel(model({ 'input-tokens': 0, 'output-tokens': 0 }))).toBe(true);
 });
 
-it('leaves overflowing catalog unit conversions unknown', () => {
-    expect(catalogPrice(1e308, 100)).toBeUndefined();
-    expect(catalogPrice(0, 100)).toBe(0);
-    expect(catalogPrice('0.0000000014', 100_000_000)).toBeCloseTo(0.14);
-});
-
 describe('costsForRequest prompt-size overrides', () => {
     const model = (minPromptTokensInclusive?: boolean): IChatModel => ({
         id: 'tiered',

src/backend/drivers/ai/interfaces/chat/utils/pricing.ts

@@ -23,29 +23,7 @@ import type {
     ModelPricingOverride,
     UsageDetails,
 } from '../types.js';
-
-/**
- * Absent, negative and placeholder prices remain unpriced, including empty
- * strings.
- */
-export const catalogPrice = (
-    value: unknown,
-    multiplier = 1,
-): number | undefined => {
-    if (typeof value !== 'number' && typeof value !== 'string')
-        return undefined;
-    if (
-        typeof value === 'string' &&
-        !/^(?:\d+(?:\.\d*)?|\.\d+)(?:e[+-]?\d+)?$/i.test(value.trim())
-    )
-        return undefined;
-    const price = Number(value);
-    if (!Number.isFinite(price) || price < 0) return undefined;
-    const converted = price * multiplier;
-    return Number.isFinite(converted) && !(price > 0 && converted === 0)
-        ? converted
-        : undefined;
-};
+import { catalogPrice } from '../../../shared/catalogPrice.js';
 
 const CENTS_PER_USD = 100;
 const MTOK = 1_000_000;
@@ -360,7 +338,8 @@ export const buildCostsOverride = (
  * What a usage object costs in µ¢, split into its input and output sides.
  * `recordedCosts` are the per-key costs a provider already metered with and win
  * over the model's rates, so the figure matches the ledger. Null when nothing
- * in the usage could be priced. `now` is the instant the request was priced at.
+ * in the usage could be priced. `now` is the instant the request was priced
+ * at.
  */
 export const usageCost = (
     usage: Record<string, unknown>,

src/backend/drivers/ai/interfaces/chat/utils/providerHealth.test.ts

@@ -19,7 +19,7 @@
  */
 
 import { afterEach, describe, expect, it } from 'vitest';
-import { kv } from '../../../util/kvSingleton.js';
+import { kv } from '../../../../../util/kvSingleton.js';
 import {
     clearUnhealthyRoutes,
     isRouteUnhealthy,

src/backend/drivers/ai/interfaces/chat/utils/providerHealth.ts

@@ -30,7 +30,7 @@
  * blip doesn't hand the model's traffic to a reseller for long.
  */
 
-import { kv } from '../../../util/kvSingleton.js';
+import { kv } from '../../../../../util/kvSingleton.js';
 
 /**
  * How long a route stays marked after a failure that won't heal on its own,

src/backend/drivers/ai/interfaces/chat/utils/serviceSpeed.fuzz.test.ts

@@ -19,21 +19,21 @@
 
 import { describe, expect, it } from 'vitest';
 import type { IChatModel, ServiceSpeed } from '../types.js';
-import { ALIBABA_MODELS } from '../providers/alibaba/models.js';
-import { AZURE_MODELS } from '../providers/azure/models.js';
-import { BYTEPLUS_MODELS } from '../providers/byteplus/models.js';
-import { CLAUDE_MODELS } from '../providers/claude/models.js';
-import { DEEPSEEK_MODELS } from '../providers/deepseek/models.js';
-import { GEMINI_MODELS } from '../providers/gemini/models.js';
-import { GROQ_MODELS } from '../providers/groq/models.js';
-import { HOONIFY_MODELS } from '../providers/hoonify/models.js';
-import { META_MODELS } from '../providers/meta/models.js';
-import { MINIMAX_MODELS } from '../providers/minimax/models.js';
-import { MISTRAL_MODELS } from '../providers/mistral/models.js';
-import { MOONSHOT_MODELS } from '../providers/moonshot/models.js';
-import { OPEN_AI_MODELS } from '../providers/openai/models.js';
-import { XAI_MODELS } from '../providers/xai/models.js';
-import { ZAI_MODELS } from '../providers/zai/models.js';
+import { ALIBABA_MODELS } from '../../../providers/alibaba/chat/models.js';
+import { AZURE_MODELS } from '../../../providers/azure/chat/models.js';
+import { BYTEPLUS_MODELS } from '../../../providers/byteplus/chat/models.js';
+import { CLAUDE_MODELS } from '../../../providers/claude/chat/models.js';
+import { DEEPSEEK_MODELS } from '../../../providers/deepseek/chat/models.js';
+import { GEMINI_MODELS } from '../../../providers/gemini/chat/models.js';
+import { GROQ_MODELS } from '../../../providers/groq/chat/models.js';
+import { HOONIFY_MODELS } from '../../../providers/hoonify/chat/models.js';
+import { META_MODELS } from '../../../providers/meta/chat/models.js';
+import { MINIMAX_MODELS } from '../../../providers/minimax/chat/models.js';
+import { MISTRAL_MODELS } from '../../../providers/mistral/chat/models.js';
+import { MOONSHOT_MODELS } from '../../../providers/moonshot/chat/models.js';
+import { OPEN_AI_MODELS } from '../../../providers/openai/chat/models.js';
+import { XAI_MODELS } from '../../../providers/xai/chat/models.js';
+import { ZAI_MODELS } from '../../../providers/zai/chat/models.js';
 import { shouldPresentAsOpenAI } from './normalizeToOpenAI.js';
 import {
     isServiceSpeedUnavailable,

src/backend/drivers/ai/interfaces/chat/utils/serviceSpeed.integration.test.ts

@@ -20,19 +20,19 @@
 import { describe, expect, it } from 'vitest';
 import {
     makeMeteringStub,
-    optionalEnv,
     withTestActor,
-} from '../../integrationTestUtil.js';
+} from '../../../shared/integrationTestUtil.js';
+import { optionalEnv } from '../../../../../testEnv.js';
 import type {
     IChatMessageResult,
     IChatProvider,
     ICompleteArguments,
 } from '../types.js';
-import { OpenAiResponsesChatProvider } from '../providers/openai/OpenAiChatResponsesProvider.js';
-import { GeminiChatProvider } from '../providers/gemini/GeminiChatProvider.js';
-import { MiniMaxProvider } from '../providers/minimax/MiniMaxProvider.js';
-import { MoonshotProvider } from '../providers/moonshot/MoonshotProvider.js';
-import { MistralAIProvider } from '../providers/mistral/MistralAiProvider.js';
+import { OpenAiResponsesChatProvider } from '../../../providers/openai/chat/OpenAiChatResponsesProvider.js';
+import { GeminiChatProvider } from '../../../providers/gemini/chat/GeminiChatProvider.js';
+import { MiniMaxProvider } from '../../../providers/minimax/chat/MiniMaxProvider.js';
+import { MoonshotProvider } from '../../../providers/moonshot/chat/MoonshotProvider.js';
+import { MistralAIProvider } from '../../../providers/mistral/chat/MistralAiProvider.js';
 import { selectServiceSpeed } from './serviceSpeed.js';
 
 type Case = {

src/backend/drivers/ai/interfaces/chat/utils/serviceSpeed.test.ts

@@ -23,7 +23,7 @@ import { AIChatStream } from './Streaming.js';
 import {
     handle_completion_output,
     handle_completion_output_responses_api,
-} from './OpenAIUtil.js';
+} from '../../../protocols/openaiCompatible/OpenAIUtil.js';
 import type { IChatModel, ServiceSpeed } from '../types.js';
 import {
     requestedServiceSpeed,
@@ -33,10 +33,10 @@ import {
     isServiceSpeedUnavailable,
 } from './serviceSpeed.js';
 import { meterChatUsage } from './meterChatUsage.js';
-import { OPEN_AI_MODELS } from '../providers/openai/models.js';
-import { XAI_MODELS } from '../providers/xai/models.js';
-import { GEMINI_MODELS } from '../providers/gemini/models.js';
-import { CLAUDE_MODELS } from '../providers/claude/models.js';
+import { OPEN_AI_MODELS } from '../../../providers/openai/chat/models.js';
+import { XAI_MODELS } from '../../../providers/xai/chat/models.js';
+import { GEMINI_MODELS } from '../../../providers/gemini/chat/models.js';
+import { CLAUDE_MODELS } from '../../../providers/claude/chat/models.js';
 
 const model = (provider: string, id: string): IChatModel => ({
     provider,

src/backend/drivers/ai/interfaces/chat/utils/usageEstimate.test.ts

@@ -216,6 +216,24 @@ describe('estimatePromptTokens', () => {
     });
 });
 
+describe('estimatePromptTokens compaction blocks', () => {
+    const withCompaction = (encrypted_content: unknown) => [
+        { role: 'assistant', content: [{ type: 'compaction', encrypted_content }] },
+    ];
+
+    it('counts the encrypted content as text', () => {
+        expect(estimatePromptTokens(withCompaction('a'.repeat(400)))).toBe(
+            estimateTextTokens('a'.repeat(400)),
+        );
+    });
+
+    it('counts content that is not a string by its JSON', () => {
+        expect(
+            estimatePromptTokens(withCompaction({ toString: null, blob: 'abcdefgh' })),
+        ).toBe(estimateTextTokens('{"toString":null,"blob":"abcdefgh"}'));
+    });
+});
+
 describe('estimateToolTokens', () => {
     it('is zero for no tools', () => {
         expect(estimateToolTokens(undefined)).toBe(0);

src/backend/drivers/ai/interfaces/chat/utils/usageEstimate.ts

@@ -33,10 +33,10 @@ import {
     createWordScanBudget,
     estimateTextTokens,
     type WordScanBudget,
-} from '../../util/tokenEstimate.js';
+} from '../../../shared/tokenEstimate.js';
 
 // Re-exported so existing consumers keep one import site for all estimators.
-export { estimateTextTokens } from '../../util/tokenEstimate.js';
+export { estimateTextTokens } from '../../../shared/tokenEstimate.js';
 
 /** Tokens per byte of an inline (base64) attachment; see `attachmentTokens`. */
 const ATTACHMENT_BYTES_PER_TOKEN = 150;
@@ -154,7 +154,12 @@ const partTokens = (part: unknown, budget: WordScanBudget): number => {
         );
     }
     if (p.type === 'compaction') {
-        return estimateTextTokens(String(p.encrypted_content ?? ''), budget);
+        return estimateTextTokens(
+            typeof p.encrypted_content === 'string'
+                ? p.encrypted_content
+                : JSON.stringify(p.encrypted_content ?? ''),
+            budget,
+        );
     }
 
     return UNMEASURED_ATTACHMENT_TOKENS;

src/backend/drivers/ai/interfaces/image/ImageGenerationDriver.test.ts

@@ -41,23 +41,22 @@ import {
 } from 'vitest';
 
 import { v4 as uuidv4 } from 'uuid';
-import { runWithContext } from '../../core/context.js';
-import { type Actor, SYSTEM_ACTOR } from '../../core/actor.js';
-import { PuterServer } from '../../server.js';
-import { setupTestServer } from '../../testUtil.js';
-import { withAiCostFactorHook } from '../integrationTestUtil.js';
-import { generateDefaultFsentries } from '../../util/userProvisioning.js';
-import { CLOUDFLARE_IMAGE_GENERATION_MODELS } from './providers/cloudflare/models.js';
-import cloudflareModelSearchFixture from './providers/cloudflare/fixtures/model-search.json';
-import { GEMINI_IMAGE_GENERATION_MODELS } from './providers/gemini/models.js';
-import { OPEN_AI_IMAGE_GENERATION_MODELS } from './providers/openai/models.js';
-import { REPLICATE_IMAGE_GENERATION_MODELS } from './providers/replicate/models.js';
-import { TOGETHER_IMAGE_GENERATION_MODELS } from './providers/together/models.js';
-import { XAI_IMAGE_GENERATION_MODELS } from './providers/xai/models.js';
-import xaiLiveCatalog from './providers/xai/fixtures/image-generation-models.json';
+import { runWithContext } from '../../../../core/context.js';
+import { type Actor, SYSTEM_ACTOR } from '../../../../core/actor.js';
+import { PuterServer } from '../../../../server.js';
+import { setupTestServer, withAiCostFactorHook } from '../../../../testUtil.js';
+import { generateDefaultFsentries } from '../../../../util/userProvisioning.js';
+import { CLOUDFLARE_IMAGE_GENERATION_MODELS } from '../../providers/cloudflare/image/models.js';
+import cloudflareModelSearchFixture from '../../providers/cloudflare/image/fixtures/model-search.json';
+import { GEMINI_IMAGE_GENERATION_MODELS } from '../../providers/gemini/image/models.js';
+import { OPEN_AI_IMAGE_GENERATION_MODELS } from '../../providers/openai/image/models.js';
+import { REPLICATE_IMAGE_GENERATION_MODELS } from '../../providers/replicate/image/models.js';
+import { TOGETHER_IMAGE_GENERATION_MODELS } from '../../providers/together/image/models.js';
+import { XAI_IMAGE_GENERATION_MODELS } from '../../providers/xai/image/models.js';
+import xaiLiveCatalog from '../../providers/xai/image/fixtures/image-generation-models.json';
 import { ImageGenerationDriver } from './ImageGenerationDriver.js';
-import { CATALOG_TTL_MS } from '../ai-chat/utils/cachedRemoteCatalog.js';
-import { ReplicateImageGenerationProvider } from './providers/replicate/ReplicateImageGenerationProvider.js';
+import { CATALOG_TTL_MS } from '../../shared/cachedRemoteCatalog.js';
+import { ReplicateImageGenerationProvider } from '../../providers/replicate/image/ReplicateImageGenerationProvider.js';
 
 // ── SDK mocks ──────────────────────────────────────────────────────
 //
@@ -141,8 +140,8 @@ vi.mock('replicate', () => {
 
 const { secureFetchMock } = vi.hoisted(() => ({ secureFetchMock: vi.fn() }));
 
-vi.mock('../../util/secureHttp.js', async (importOriginal) => ({
-    ...(await importOriginal<typeof import('../../util/secureHttp.js')>()),
+vi.mock('../../../../util/secureHttp.js', async (importOriginal) => ({
+    ...(await importOriginal<typeof import('../../../../util/secureHttp.js')>()),
     secureFetch: secureFetchMock,
 }));
 
@@ -483,6 +482,33 @@ describe('ImageGenerationDriver.generate provider routing', () => {
         },
     );
 
+    it('rejects an input image type that is not a string before any provider runs', async () => {
+        await expect(withActor(() =>
+            driver.generate({
+                model: 'gpt-image-2',
+                prompt: 'make it blue',
+                input_image: 'data:image/png;base64,aGVsbG8=',
+                input_image_mime_type: 5,
+            } as never),
+        )).rejects.toMatchObject({
+            statusCode: 400,
+            message: 'input_image_mime_type must be a string',
+        });
+    });
+
+    it('ignores an input image type that is not a string when there is no input image', async () => {
+        openaiImagesGenerateMock.mockResolvedValueOnce({
+            data: [{ url: 'https://oai/image.png' }],
+        });
+        await expect(withDriverName('ai-image', () =>
+            driver.generate({
+                model: 'gpt-image-2',
+                prompt: 'a landscape',
+                input_image_mime_type: 5,
+            } as never),
+        )).resolves.toBe('https://oai/image.png');
+    });
+
     it('rejects an excluded model regardless of caller casing', async () => {
         await expect(withActor(() =>
             driver.generate({
@@ -1273,7 +1299,7 @@ describe('ImageGenerationDriver.generate audit log', () => {
 // ── puter_output_path ─────────────────────────────────────────────
 
 describe('ImageGenerationDriver.generate puter_output_path', () => {
-    const TEST_ACTOR: import('../../core/actor.js').Actor = {
+    const TEST_ACTOR: import('../../../../core/actor.js').Actor = {
         user: { uuid: 'a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d', id: 42, username: 'testuser' },
     };
 
@@ -1462,7 +1488,7 @@ describe('ImageGenerationDriver.generate puter_output_path', () => {
     });
 
     it('throws 400 when actor has no user ID but puter_output_path is set', async () => {
-        const noIdActor: import('../../core/actor.js').Actor = {
+        const noIdActor: import('../../../../core/actor.js').Actor = {
             user: { uuid: 'f0e1d2c3-b4a5-4968-8777-0a1b2c3d4e5f', username: 'noone' },
         };
         await expect(

src/backend/drivers/ai/interfaces/image/ImageGenerationDriver.ts

@@ -19,32 +19,32 @@
 
 import { assertImagePrompt } from './imageValidation.js';
 import crypto from 'node:crypto';
-import { Context } from '../../core/context.js';
-import { HttpError } from '../../core/http/HttpError.js';
-import type { Actor } from '../../core/actor.js';
-import { PuterDriver } from '../types.js';
+import { Context } from '../../../../core/context.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import type { Actor } from '../../../../core/actor.js';
+import { PuterDriver } from '../../../types.js';
 import {
     type AiMeteringService,
     withAiCostFactor,
-} from '../util/aiCostFactor.js';
-import { AI_CONCURRENT, AI_RATE_LIMIT } from '../util/aiLimits.js';
+} from '../../../../util/aiCostFactor.js';
+import { AI_CONCURRENT, AI_RATE_LIMIT } from '../../shared/aiLimits.js';
 import {
     resolveOutputPath,
     saveGeneratedMediaToFS,
-} from '../util/generatedMedia.js';
-import { readPuterImageInputs } from '../util/mediaInput.js';
-import { ModelCatalog } from '../util/modelCatalog.js';
-import { CATALOG_TTL_MS } from '../ai-chat/utils/cachedRemoteCatalog.js';
-import { readProviderKey } from '../util/providerRegistry.js';
-import { BytePlusImageProvider } from './providers/byteplus/BytePlusImageProvider.js';
-import { CloudflareImageProvider } from './providers/cloudflare/CloudflareImageProvider.js';
-import { GeminiImageProvider } from './providers/gemini/GeminiImageProvider.js';
-import { KlingImageProvider } from './providers/kling/KlingImageProvider.js';
-import { OpenAiImageProvider } from './providers/openai/OpenAiImageProvider.js';
-import { ReplicateImageGenerationProvider } from './providers/replicate/ReplicateImageGenerationProvider.js';
+} from '../../shared/generatedMedia.js';
+import { readPuterImageInputs } from '../../shared/mediaInput.js';
+import { ModelCatalog } from '../../shared/modelCatalog.js';
+import { CATALOG_TTL_MS } from '../../shared/cachedRemoteCatalog.js';
+import { readProviderKey } from '../../../../util/aiProviderKey.js';
+import { BytePlusImageProvider } from '../../providers/byteplus/image/BytePlusImageProvider.js';
+import { CloudflareImageProvider } from '../../providers/cloudflare/image/CloudflareImageProvider.js';
+import { GeminiImageProvider } from '../../providers/gemini/image/GeminiImageProvider.js';
+import { KlingImageProvider } from '../../providers/kling/image/KlingImageProvider.js';
+import { OpenAiImageProvider } from '../../providers/openai/image/OpenAiImageProvider.js';
+import { ReplicateImageGenerationProvider } from '../../providers/replicate/image/ReplicateImageGenerationProvider.js';
 import { resolveImageSize } from './imageDimensions.js';
-import { TogetherImageProvider } from './providers/together/TogetherImageProvider.js';
-import { XAIImageProvider } from './providers/xai/XAIImageProvider.js';
+import { TogetherImageProvider } from '../../providers/together/image/TogetherImageProvider.js';
+import { XAIImageProvider } from '../../providers/xai/image/XAIImageProvider.js';
 import type { IGenerateParams, IImageModel, IImageProvider } from './types.js';
 import { assertInputImagesShape } from './inputImage.js';
 
@@ -78,7 +78,7 @@ export class ImageGenerationDriver extends PuterDriver {
     ];
     readonly isDefault = true;
 
-    // Shared AI policy — see `drivers/util/aiLimits.ts` for the tier table.
+    // Shared AI policy — see `drivers/ai/shared/aiLimits.ts` for the tier table.
     readonly rateLimit = AI_RATE_LIMIT;
     readonly concurrent = AI_CONCURRENT;
 
@@ -177,7 +177,15 @@ export class ImageGenerationDriver extends PuterDriver {
         // settled here — once — before any provider runs.
         assertImagePrompt(args.prompt);
         assertInputImagesShape(args, 'image generation');
-        for (const option of ['quality', 'resolution'] as const) {
+        // The type hint describes an input image, so it is only read, and
+        // only has to be a string, when the request carries one.
+        const hasInputImage =
+            args.input_image != null || (args.input_images?.length ?? 0) > 0;
+        for (const option of [
+            'quality',
+            'resolution',
+            ...(hasInputImage ? (['input_image_mime_type'] as const) : []),
+        ] as const) {
             if (args[option] != null && typeof args[option] !== 'string') {
                 throw new HttpError(400, `${option} must be a string`, {
                     legacyCode: 'bad_request',
@@ -189,6 +197,7 @@ export class ImageGenerationDriver extends PuterDriver {
         // caller's `args` is re-emitted by reference in `.after`/`.error`
         // payloads, so it is never mutated here.
         const { puter_output_path: puterOutputPath, ...request } = args;
+        if (!hasInputImage) delete request.input_image_mime_type;
 
         // Validate the output path early — before spending credits.
         const resolvedOutputPath = puterOutputPath

src/backend/drivers/ai/interfaces/image/imageDimensions.ts

@@ -17,7 +17,7 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-import { HttpError } from '../../core/http/HttpError.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
 import type {
     IGenerateParams,
     IImageModel,

src/backend/drivers/ai/interfaces/image/imageOutput.ts

@@ -17,7 +17,7 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-import { SVG_SNIFF_WINDOW, sniffImageMime } from '../../util/appIcon.js';
+import { SVG_SNIFF_WINDOW, sniffImageMime } from '../../../../util/appIcon.js';
 
 // Base64 chars needed to recover SVG_SNIFF_WINDOW decoded bytes.
 const SNIFF_BASE64_CHARS = Math.ceil((SVG_SNIFF_WINDOW * 4) / 3);

src/backend/drivers/ai/interfaces/image/imageValidation.ts

@@ -17,7 +17,7 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-import { HttpError } from '../../core/http/HttpError.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
 
 export function assertImagePrompt(prompt: unknown): asserts prompt is string {
     if (typeof prompt !== 'string' || !prompt.trim()) {

src/backend/drivers/ai/interfaces/image/inputImage.test.ts

@@ -37,7 +37,7 @@ import {
 
 const { secureFetchMock } = vi.hoisted(() => ({ secureFetchMock: vi.fn() }));
 
-vi.mock('../../util/secureHttp.js', () => ({ secureFetch: secureFetchMock }));
+vi.mock('../../../../util/secureHttp.js', () => ({ secureFetch: secureFetchMock }));
 
 const fetchResponse = (
     body: Buffer,

src/backend/drivers/ai/interfaces/image/inputImage.ts

@@ -21,12 +21,12 @@
  * Shared helpers for `input_images` (image-to-image) handling across image
  * providers. `input_images` is the canonical, cross-provider field; an entry
  * may be a public URL, a data-URI, or raw base64. The string-level helpers live
- * in `drivers/util/imageInput.ts` so video providers share them; this module
- * re-exports them and adds the `IGenerateParams`-shaped validation.
+ * in `drivers/ai/shared/imageInput.ts` so video providers share them; this
+ * module re-exports them and adds the `IGenerateParams`-shaped validation.
  */
 
-import { HttpError } from '../../core/http/HttpError.js';
-import { assertInputImageString } from '../util/imageInput.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import { assertInputImageString } from '../../shared/imageInput.js';
 import type { IGenerateParams } from './types.js';
 
 /** Most input images one request may carry. */
@@ -41,7 +41,7 @@ export {
     parseDataUri,
     toBase64DataUri,
     toUrlOrDataUri,
-} from '../util/imageInput.js';
+} from '../../shared/imageInput.js';
 
 /**
  * Validate `input_image` / `input_images` once, where the driver call arrives.

src/backend/drivers/ai/interfaces/mediaDrivers.fuzz.test.ts

@@ -0,0 +1,403 @@
+/*
+ * Copyright (C) 2024-present Puter Technologies Inc.
+ *
+ * This file is part of Puter.
+ *
+ * Puter is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Puter is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Puter. If not, see <https://www.gnu.org/licenses/>.
+ */
+
+/**
+ * Seeded fuzzing of the image, video, speech and OCR drivers through every
+ * provider they register. One suite covers the six so the server boots once.
+ * Every vendor refuses the request, so what runs is each driver's validation,
+ * each provider's request building, and the mapping of the refusal.
+ */
+
+import { PollyClient } from '@aws-sdk/client-polly';
+import { TextractClient } from '@aws-sdk/client-textract';
+import { afterAll, beforeAll, describe, expect, it, vi } from 'vitest';
+
+import type { Actor } from '../../../core/actor.js';
+import type { PuterServer } from '../../../server.js';
+import { setupTestServer } from '../../../testUtil.js';
+import { isDriverStreamResult } from '../../meta.js';
+import {
+    fuzzCalls,
+    fuzzCases,
+    hostileValue,
+    pick,
+    pickStable,
+    type Random,
+    upstream,
+} from '../shared/fuzzTestUtil.js';
+import {
+    readStreamResult,
+    withTestActor,
+} from '../shared/integrationTestUtil.js';
+
+vi.mock('undici', async (importOriginal) => ({
+    ...(await importOriginal<typeof import('undici')>()),
+    fetch: (input: unknown, init?: RequestInit) => upstream.fetch(input, init),
+}));
+
+vi.mock('axios', () => {
+    const request = (config: Parameters<typeof upstream.axios>[0]) =>
+        upstream.axios(config);
+    const get = (url: string, config?: object) =>
+        upstream.axios({ ...config, url, method: 'GET' });
+    return { default: { request, get }, request, get };
+});
+
+const PNG =
+    'data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8z8BQDwAEhQGAhKmMIQAAAABJRU5ErkJggg==';
+const AUDIO =
+    'data:audio/wav;base64,UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YQAAAAA=';
+const PDF = 'data:application/pdf;base64,JVBERi0xLjQK';
+
+type Route = { provider: string; model?: string };
+
+interface Target {
+    name: string;
+    driver: string;
+    method: string;
+    /** The providers the suite must reach, so a lost registration fails it. */
+    providers: string[];
+    routes: (driver: Record<string, any>) => Promise<Route[]>;
+    corpus: Record<string, unknown>[];
+}
+
+const modelRoutes = async (driver: Record<string, any>): Promise<Route[]> =>
+    (await driver.models()).map((model: { provider: string; id: string }) => ({
+        provider: model.provider,
+        model: model.id,
+    }));
+
+const providerRoutes = async (driver: Record<string, any>): Promise<Route[]> =>
+    (await driver.list()).map((provider: string) => ({ provider }));
+
+const TARGETS: Target[] = [
+    {
+        name: 'image generation',
+        driver: 'aiImage',
+        method: 'generate',
+        providers: [
+            'byteplus-image-generation',
+            'cloudflare-image-generation',
+            'gemini-image-generation',
+            'kling-image-generation',
+            'openai-image-generation',
+            'replicate-image-generation',
+            'xai-image-generation',
+        ],
+        routes: modelRoutes,
+        corpus: [
+            { prompt: 'a red cube' },
+            {
+                prompt: 'a red cube',
+                ratio: { w: 1024, h: 768 },
+                quality: 'high',
+                seed: 7,
+                negative_prompt: 'blur',
+                steps: 4,
+                guidance: 2,
+                response_format: 'png',
+                output_megapixels: '1',
+                providerOptions: { go_fast: true },
+            },
+            {
+                prompt: 'make it blue',
+                input_image: PNG,
+                input_image_mime_type: 'image/png',
+            },
+            {
+                prompt: 'combine these',
+                input_images: [PNG, PNG],
+                imageSize: '1K',
+                resolution: '1k',
+            },
+        ],
+    },
+    {
+        name: 'video generation',
+        driver: 'aiVideo',
+        method: 'generate',
+        providers: [
+            'byteplus-video-generation',
+            'gemini-video-generation',
+            'kling-video-generation',
+            'minimax-video-generation',
+            'together-video-generation',
+        ],
+        routes: modelRoutes,
+        corpus: [
+            { prompt: 'a red ball' },
+            {
+                prompt: 'a red ball',
+                seconds: 4,
+                resolution: '480p',
+                size: '1280x720',
+                fps: 24,
+                seed: 7,
+                negative_prompt: 'blur',
+                generate_audio: true,
+                output_format: 'mp4',
+            },
+            {
+                prompt: 'animate this',
+                reference_images: [PNG],
+                frame_images: [{ input_image: PNG, frame: 0 }],
+                last_frame: PNG,
+                input_reference: PNG,
+                metadata: { trace: 't' },
+            },
+            {
+                prompt: 'edit this',
+                input_video: 'data:video/mp4;base64,AAAA',
+                duration: '5',
+                width: 1280,
+                height: 720,
+            },
+        ],
+    },
+    {
+        name: 'text to speech',
+        driver: 'aiTts',
+        method: 'synthesize',
+        providers: [
+            'aws-polly',
+            'elevenlabs',
+            'gemini',
+            'kling',
+            'openai',
+            'xai',
+        ],
+        routes: providerRoutes,
+        corpus: [
+            { text: 'Hello.' },
+            {
+                text: 'Hello.',
+                voice: 'Joanna',
+                engine: 'neural',
+                model: 'tts-1',
+                language: 'en-US',
+                response_format: 'mp3',
+                output_format: 'mp3_44100_128',
+                instructions: 'Calm.',
+                voice_settings: { stability: 0.5 },
+            },
+            { text: 'Hello.', ssml: '<speak>Hello.</speak>' },
+        ],
+    },
+    {
+        name: 'speech to text',
+        driver: 'aiSpeech2Txt',
+        method: 'transcribe',
+        providers: ['gemini', 'openai', 'xai'],
+        routes: providerRoutes,
+        corpus: [
+            { file: AUDIO },
+            {
+                file: AUDIO,
+                language: 'en',
+                prompt: 'Names: Ada.',
+                temperature: 0,
+                response_format: 'verbose_json',
+                timestamp_granularities: ['word'],
+                logprobs: true,
+                diarize: true,
+                known_speaker_names: ['Ada'],
+                extra_body: { a: 1 },
+                chunking_strategy: 'auto',
+                format: true,
+                multichannel: false,
+                channels: 1,
+                audio_format: 'wav',
+                sample_rate: 16000,
+            },
+        ],
+    },
+    {
+        name: 'speech to speech',
+        driver: 'aiSpeech2Speech',
+        method: 'convert',
+        providers: ['elevenlabs'],
+        routes: async () => [{ provider: 'elevenlabs' }],
+        corpus: [
+            { audio: AUDIO },
+            {
+                audio: AUDIO,
+                voice: 'v',
+                model: 'eleven_multilingual_sts_v2',
+                voice_settings: { stability: 0.5 },
+                seed: 1,
+                remove_background_noise: true,
+                output_format: 'mp3_44100_128',
+                file_format: 'other',
+                optimize_streaming_latency: 1,
+                enable_logging: false,
+            },
+        ],
+    },
+    {
+        name: 'OCR',
+        driver: 'aiOcr',
+        method: 'recognize',
+        providers: ['aws-textract', 'mistral'],
+        routes: async () => [
+            { provider: 'aws-textract' },
+            { provider: 'mistral' },
+        ],
+        corpus: [
+            { source: PDF },
+            { file: PDF },
+            {
+                source: PNG,
+                pages: [0],
+                includeImageBase64: true,
+                imageLimit: 1,
+                imageMinSize: 10,
+                tableFormat: 'markdown',
+                extractHeader: true,
+                extractFooter: false,
+                documentAnnotationPrompt: 'Summarize.',
+                bboxAnnotationFormat: { type: 'json_schema' },
+                documentAnnotationFormat: { type: 'text' },
+            },
+        ],
+    },
+];
+
+const key = { apiKey: 'fuzz-key' };
+const aws = {
+    aws: { access_key: 'AKIAFUZZ', secret_key: 'x', region: 'us-west-2' },
+};
+const providers = {
+    openai: key,
+    'openai-completion': key,
+    gemini: key,
+    xai: key,
+    mistral: key,
+    'mistral-ocr': key,
+    minimax: key,
+    'together-ai': key,
+    byteplus: key,
+    elevenlabs: key,
+    kling: key,
+    'replicate-image-generation': key,
+    'cloudflare-image-generation': { apiToken: 'fuzz-key', accountId: 'acct' },
+    'aws-polly': aws,
+    'aws-textract': aws,
+    ollama: { enabled: false },
+};
+
+const refused = { status: 400, body: { error: { message: 'refused' } } };
+
+let server: PuterServer;
+// File input needs a user, so the calls run as one, not as the system actor.
+let actor: Actor;
+
+beforeAll(async () => {
+    upstream.install();
+    upstream.respond = () => refused;
+    const refuse = async () => {
+        throw Object.assign(new Error('refused'), {
+            name: 'ValidationException',
+            $metadata: { httpStatusCode: 400 },
+        });
+    };
+    vi.spyOn(PollyClient.prototype, 'send').mockImplementation(refuse);
+    vi.spyOn(TextractClient.prototype, 'send').mockImplementation(refuse);
+    server = await setupTestServer({
+        providers,
+        unlimitedMetering: true,
+    } as never);
+    const user = await server.stores.user.create({
+        username: 'media-fuzz',
+        uuid: '6b1f3c1e-5d0a-4f6e-9c53-0d1f6a2b7c11',
+        password: null,
+        email: '[email protected]',
+        requires_email_confirmation: false,
+    });
+    actor = {
+        user: {
+            id: user.id,
+            uuid: user.uuid,
+            username: user.username,
+            email: user.email ?? null,
+            email_confirmed: true,
+        } as Actor['user'],
+    };
+}, 120_000);
+
+afterAll(async () => {
+    await server?.shutdown();
+    upstream.uninstall();
+    vi.restoreAllMocks();
+});
+
+describe.each(TARGETS)('$name driver seeded fuzzing', (target) => {
+    it('rejects a malformed request with a classified error on every provider', async () => {
+        const driver = (server.drivers as unknown as Record<string, any>)[
+            target.driver
+        ];
+        const routes = await target.routes(driver);
+        const byProvider = new Map<string, Route[]>();
+        for (const route of routes) {
+            byProvider.set(route.provider, [
+                ...(byProvider.get(route.provider) ?? []),
+                route,
+            ]);
+        }
+        expect([...byProvider.keys()].sort()).toEqual(target.providers);
+
+        const pinned = (random: Random) => {
+            const route: Record<string, unknown> = {
+                ...pickStable(
+                    random,
+                    byProvider.get(
+                        pickStable(random, target.providers, (name) => name),
+                    )!,
+                    (candidate) => String(candidate.model),
+                ),
+            };
+            // Now and then the route itself is the malformed part.
+            if (random() < 0.05) {
+                route[pick(random, ['provider', 'model'])] =
+                    hostileValue(random);
+            }
+            return route;
+        };
+        const askedBefore = upstream.asked;
+        const findings = await fuzzCalls({
+            seed: 0x3ed1a,
+            cases: fuzzCases(1000),
+            corpus: target.corpus,
+            optionNames: target.corpus.flatMap((request) =>
+                Object.keys(request),
+            ),
+            pinned,
+            call: async (args) => {
+                const result = await withTestActor(
+                    () => driver[target.method](args),
+                    actor,
+                );
+                if (isDriverStreamResult(result))
+                    await readStreamResult(result);
+            },
+        });
+        findings.assertNone();
+        // Some of the requests have to get as far as a vendor.
+        expect(upstream.asked).toBeGreaterThan(askedBefore);
+    }, 600_000);
+});

src/backend/drivers/ai/interfaces/ocr/OCRDriver.test.ts

@@ -49,16 +49,17 @@ import {
 } from '@aws-sdk/client-textract';
 import { v4 as uuidv4 } from 'uuid';
 
-import type { Actor } from '../../core/actor.js';
-import { runWithContext } from '../../core/context.js';
-import { PuterServer } from '../../server.js';
-import type { MeteringService } from '../../services/metering/MeteringService.js';
-import { buildPdf } from '../../testFixtures/pdf.js';
-import { setupTestServer } from '../../testUtil.js';
-import { generateDefaultFsentries } from '../../util/userProvisioning.js';
+import { SDKValidationError } from '@mistralai/mistralai/models/errors/sdkvalidationerror.js';
+import type { Actor } from '../../../../core/actor.js';
+import { runWithContext } from '../../../../core/context.js';
+import { PuterServer } from '../../../../server.js';
+import type { MeteringService } from '../../../../services/metering/MeteringService.js';
+import { buildPdf } from '../../../../testFixtures/pdf.js';
+import { setupTestServer } from '../../../../testUtil.js';
+import { generateDefaultFsentries } from '../../../../util/userProvisioning.js';
 import type { OCRDriver } from './OCRDriver.js';
 import { OCR_COSTS } from './costs.js';
-import textractUsWest2 from './fixtures/textract-us-west-2.json';
+import textractUsWest2 from '../../providers/awsTextract/ocr/fixtures/textract-us-west-2.json';
 
 // ── SDK mocks ───────────────────────────────────────────────────────
 //
@@ -300,6 +301,19 @@ describe('OCRDriver.recognize argument validation', () => {
         ).rejects.toMatchObject({ statusCode: 401 });
     });
 
+    it('answers 400 for an option value that cannot be text', async () => {
+        await expect(
+            driver.recognize({
+                source: dataUrl(Buffer.from('x'), 'image/png'),
+                imageLimit: { toString: null },
+            } as never),
+        ).rejects.toMatchObject({
+            statusCode: 400,
+            legacyCode: 'bad_request',
+            message: '`imageLimit` is not a usable value',
+        });
+    });
+
     it('throws 400 when neither source nor file is provided', async () => {
         const { actor } = await makeUser();
         await expect(
@@ -986,6 +1000,27 @@ describe('OCRDriver.recognize (mistral)', () => {
         expect(result.text).toBe('Total: 42');
     });
 
+    it('answers 400 when the Mistral SDK refuses the options before sending', async () => {
+        const { actor } = await makeUser();
+        mistralOcrProcessMock.mockRejectedValueOnce(
+            new SDKValidationError('Input validation failed', new Error(), {}),
+        );
+
+        await expect(
+            withActor(actor, () =>
+                driver.recognize({
+                    source: dataUrl(Buffer.from('x'), 'application/pdf'),
+                    provider: 'mistral',
+                    pages: true,
+                } as never),
+            ),
+        ).rejects.toMatchObject({
+            statusCode: 400,
+            legacyCode: 'bad_request',
+        });
+        expect(incrementUsageSpy).not.toHaveBeenCalled();
+    });
+
     it('meters per-page Mistral OCR usage from costs.ts', async () => {
         const { actor } = await makeUser();
         mistralOcrProcessMock.mockResolvedValueOnce({

src/backend/drivers/ai/interfaces/ocr/OCRDriver.ts

@@ -0,0 +1,264 @@
+/*
+ * Copyright (C) 2024-present Puter Technologies Inc.
+ *
+ * This file is part of Puter.
+ *
+ * Puter is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+import { Context } from '../../../../core/context.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import { awsCredentialsFrom } from '../../../../util/awsCredentials.js';
+import { assertActorHasCredits } from '../../../../services/metering/enforcement.js';
+import { PuterDriver } from '../../../types.js';
+import {
+    type AiMeteringService,
+    withAiCostFactor,
+} from '../../../../util/aiCostFactor.js';
+import { AI_CONCURRENT, AI_RATE_LIMIT } from '../../shared/aiLimits.js';
+import { assertScalarOptions } from '../../shared/scalarOptions.js';
+import { resolveFileInput } from '../../../util/fileInput.js';
+import {
+    type ProviderCatalog,
+    ProviderRegistry,
+} from '../../shared/providerRegistry.js';
+import { readProviderKey } from '../../../../util/aiProviderKey.js';
+import {
+    TEXTRACT_PAGE_USAGE_TYPE,
+    TextractOcrProvider,
+} from '../../providers/awsTextract/ocr/TextractOcrProvider.js';
+import { MistralOcrProvider } from '../../providers/mistral/ocr/MistralOcrProvider.js';
+import { badRequest } from './common.js';
+import { OCR_COSTS } from './costs.js';
+import {
+    DEFAULT_OCR_MODEL,
+    findOcrModel,
+    OCR_MAX_INPUT_BYTES,
+    RETIRED_OCR_MODELS,
+    type OcrModel,
+    type OcrProviderId,
+} from './models.js';
+import type { IOcrProvider, RecognizeArgs } from './types.js';
+
+// Aliases callers may use in place of a canonical provider id. Resolved here
+// rather than in the SDK so a new alias reaches every caller at once.
+const OCR_CATALOG: ProviderCatalog = {
+    label: 'OCR',
+    ids: ['aws-textract', 'mistral'],
+    defaultId: 'aws-textract',
+    aliases: {
+        aws: 'aws-textract',
+        'aws-textract': 'aws-textract',
+        textract: 'aws-textract',
+        mistral: 'mistral',
+        'mistral-ocr': 'mistral',
+    },
+};
+
+const NOT_CONFIGURED: Record<OcrProviderId, string> = {
+    'aws-textract': 'AWS credentials not configured',
+    mistral: 'Mistral OCR not configured',
+};
+
+// Options the providers read as text, a number or a flag.
+const SCALAR_OPTIONS = [
+    'provider',
+    'model',
+    'documentAnnotationPrompt',
+    'tableFormat',
+    'imageLimit',
+    'imageMinSize',
+];
+
+/**
+ * Driver implementing `puter-ocr`, document OCR, with two providers:
+ * `aws-textract` and `mistral`.
+ */
+export class OCRDriver extends PuterDriver {
+    readonly driverInterface = 'puter-ocr';
+    readonly driverName = 'ai-ocr';
+
+    // Shared AI policy — see `drivers/ai/shared/aiLimits.ts` for the tier table.
+    readonly rateLimit = AI_RATE_LIMIT;
+    readonly concurrent = AI_CONCURRENT;
+
+    /** Metering scoped to this driver. */
+    get #aiMetering(): AiMeteringService {
+        return withAiCostFactor(
+            this.services.metering,
+            this.clients.event,
+            this.driverName,
+        );
+    }
+
+    /**
+     * Textract is reported at the configured region's first-tier rate. A call
+     * that reads its file from a bucket in another region is billed at that
+     * region's rate instead, which this per-usage-type report can't show.
+     */
+    override getReportedCosts() {
+        return Object.entries(OCR_COSTS).map(([usageType, ucentsPerUnit]) => ({
+            usageType,
+            ucentsPerUnit:
+                usageType === TEXTRACT_PAGE_USAGE_TYPE
+                    ? (this.#textract?.reportedPageRate() ?? ucentsPerUnit)
+                    : ucentsPerUnit,
+            unit: 'page',
+            source: 'driver:aiOcr',
+        }));
+    }
+
+    // Older SDK bundles name the provider in the driver slot instead of
+    // passing `{ provider }`; `#resolveModel` reads the requested alias
+    // back off the Context.
+    readonly driverAliases = [...OCR_CATALOG.ids];
+    readonly isDefault = true;
+
+    /** The registered Textract provider, whose live rate the cost report reads. */
+    #textract: TextractOcrProvider | undefined;
+
+    #providers = new ProviderRegistry<IOcrProvider>(OCR_CATALOG);
+
+    override onServerStart() {
+        const providers = this.config.providers ?? {};
+        const metering = this.#aiMetering;
+
+        const textract = providers['aws-textract'] as
+            | Record<string, unknown>
+            | undefined;
+        const textractAws = (textract?.aws ?? textract) as
+            | Record<string, unknown>
+            | undefined;
+        const textractCredentials = awsCredentialsFrom(textractAws);
+        if (textractCredentials) {
+            this.#textract = new TextractOcrProvider(metering, {
+                credentials: textractCredentials,
+                region:
+                    (textractAws?.region as string | undefined) ??
+                    (textract?.region as string | undefined),
+            });
+            this.#providers.register('aws-textract', this.#textract);
+        }
+
+        const mistralKey = readProviderKey(providers['mistral-ocr']);
+        if (mistralKey) {
+            try {
+                this.#providers.register(
+                    'mistral',
+                    new MistralOcrProvider(metering, { apiKey: mistralKey }),
+                );
+            } catch (e) {
+                console.warn(
+                    '[OCRDriver] Failed to init Mistral:',
+                    (e as Error).message,
+                );
+            }
+        }
+    }
+
+    async recognize(args: RecognizeArgs) {
+        assertScalarOptions(args, SCALAR_OPTIONS);
+        if (args.test_mode) return sampleResponse();
+
+        const model = this.#resolveModel(args);
+
+        const actor = Context.get('actor');
+        if (!actor)
+            throw new HttpError(401, 'Authentication required', {
+                legacyCode: 'unauthorized',
+            });
+
+        const input = args.source ?? args.file;
+        if (!input) throw badRequest('`source` is required');
+
+        const provider = this.#providers.get(model.provider);
+        if (!provider)
+            throw new HttpError(500, NOT_CONFIGURED[model.provider], {
+                legacyCode: 'internal_error',
+            });
+
+        // Cheap, cached check: reject a zero-balance actor before paying for
+        // the file load and page estimate, which a real credit check would
+        // reject anyway once it runs.
+        await assertActorHasCredits(this.services.metering, actor, this.config);
+
+        // A Puter file is resolved and access-checked here but read only if
+        // the provider needs its bytes; Textract reads it straight from S3.
+        const resolved = await resolveFileInput(
+            this.stores,
+            this.services.fs,
+            actor,
+            input,
+            {
+                acceptWebInput: true,
+                maxBytes: OCR_MAX_INPUT_BYTES[model.provider],
+            },
+        );
+
+        return provider.recognize(resolved, args, model, actor);
+    }
+
+    /**
+     * Decide which model handles a call. A `model` picks its own provider; an
+     * explicit `provider`, then the legacy driver alias the caller dispatched
+     * through, then whichever provider is configured pick that provider's
+     * default model.
+     */
+    #resolveModel(args: RecognizeArgs): OcrModel {
+        const provider = args.provider
+            ? (this.#providers.resolve(args.provider) as OcrProviderId)
+            : undefined;
+
+        if (args.model !== undefined) {
+            if (typeof args.model !== 'string' || !args.model.trim())
+                throw badRequest('`model` must be a non-empty string');
+            const retired = RETIRED_OCR_MODELS[args.model.trim().toLowerCase()];
+            if (retired)
+                throw badRequest(
+                    `${args.model} is no longer available: ${retired}`,
+                );
+            const model = findOcrModel(args.model);
+            if (!model) throw badRequest(`Unknown OCR model: ${args.model}`);
+            if (provider && model.provider !== provider)
+                throw badRequest(
+                    `OCR model ${args.model} is not served by provider ${args.provider}`,
+                );
+            return model;
+        }
+
+        const hinted =
+            provider ?? this.#providers.normalize(Context.get('driverName'));
+        if (!hinted && this.#providers.names().length === 0)
+            throw new HttpError(500, 'No OCR provider configured', {
+                legacyCode: 'internal_error',
+            });
+        const chosen = (hinted ?? this.#providers.defaultId()) as OcrProviderId;
+        return findOcrModel(DEFAULT_OCR_MODEL[chosen])!;
+    }
+}
+
+function sampleResponse() {
+    return {
+        model: 'test-mode',
+        blocks: [
+            {
+                type: 'text/puter:sample-output',
+                confidence: 1,
+                text: 'test_mode is enabled; this is a sample OCR response.',
+                page: 0,
+            },
+        ],
+        text: 'test_mode is enabled; this is a sample OCR response.',
+    };
+}

src/backend/drivers/ai/interfaces/ocr/common.ts

@@ -0,0 +1,103 @@
+/*
+ * Copyright (C) 2024-present Puter Technologies Inc.
+ *
+ * This file is part of Puter.
+ *
+ * Puter is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+import type { Actor } from '../../../../core/actor.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import { insufficientCreditsError } from '../../../../services/metering/enforcement.js';
+import type { CreditHold } from '../../../../services/metering/types.js';
+import { mimeFromName } from '../../../../util/fileSigning.js';
+import type { LoadedFile, ResolvedFileInput } from '../../../util/fileInput.js';
+import type { AiMeteringService } from '../../../../util/aiCostFactor.js';
+import {
+    OCR_MAX_INPUT_BYTES,
+    OCR_MAX_PAGES,
+    type OcrProviderId,
+} from './models.js';
+import { countPdfPages } from './pdfPages.js';
+
+export const badRequest = (message: string) =>
+    new HttpError(400, message, { legacyCode: 'bad_request' });
+
+export const inputMimeType = (loaded: LoadedFile): string =>
+    loaded.mimeType ??
+    mimeFromName(loaded.filename) ??
+    'application/octet-stream';
+
+/**
+ * Declared documents (PDF, DOCX, PPTX, ...) and PDF bytes are documents; images
+ * and untyped bytes are read as a single image.
+ */
+export const isDocumentInput = (loaded: LoadedFile): boolean => {
+    const mime = inputMimeType(loaded);
+    return (
+        loaded.buffer.subarray(0, 4).toString('latin1') === '%PDF' ||
+        loaded.filename.toLowerCase().endsWith('.pdf') ||
+        (!mime.startsWith('image/') && mime !== 'application/octet-stream')
+    );
+};
+
+/**
+ * The most pages a call can bill, known before the provider runs: a PDF's page
+ * count, or a size-based guess for other documents, capped by a `pages`
+ * selection and by what the provider reads in one call. Reads the input only
+ * for a provider that takes more than one page.
+ */
+export const estimateOcrPages = async (
+    input: ResolvedFileInput,
+    provider: OcrProviderId,
+    selection?: unknown,
+): Promise<number> => {
+    const maxPages = OCR_MAX_PAGES[provider];
+    if (maxPages <= 1) return 1;
+    const loaded = await input.load();
+    if (!isDocumentInput(loaded)) return 1;
+    // A document we can't count is billed in proportion to its size, reaching
+    // the provider's page limit at its size limit (20 pages per MB for
+    // Mistral). Small files stay cheap; a large one can't pass as one page.
+    const documentPages =
+        (await countPdfPages(loaded.buffer, maxPages)) ??
+        Math.ceil(
+            (loaded.buffer.length * maxPages) / OCR_MAX_INPUT_BYTES[provider],
+        );
+    const selected = Array.isArray(selection)
+        ? new Set(
+              selection.filter(
+                  (page) => Number.isInteger(page) && (page as number) >= 0,
+              ),
+          ).size
+        : 0;
+    return Math.max(1, Math.min(documentPages, maxPages, selected || Infinity));
+};
+
+/**
+ * Refuse a call the balance can't cover, and hold its cost while the provider
+ * runs so the account's concurrent calls see it. Usage is still metered from
+ * the pages the provider reports.
+ */
+export const holdOcrCredits = async (
+    metering: AiMeteringService,
+    actor: Actor,
+    usageType: string,
+    cost: number,
+): Promise<CreditHold> => {
+    // Priced at the cost factor usage is recorded at.
+    const hold = await metering.reserveAiCredits(actor, usageType, cost);
+    if (!hold) throw insufficientCreditsError();
+    return hold;
+};

src/backend/drivers/ai/interfaces/ocr/pdfPages.test.ts

@@ -18,7 +18,7 @@
  */
 
 import { describe, expect, it } from 'vitest';
-import { buildPdf } from '../../testFixtures/pdf.js';
+import { buildPdf } from '../../../../testFixtures/pdf.js';
 import { countPdfPages } from './pdfPages.js';
 
 const pdf = (body: string) => Buffer.from(`%PDF-1.7\n${body}`, 'latin1');

src/backend/drivers/ai/interfaces/ocr/types.ts

@@ -0,0 +1,63 @@
+/*
+ * Copyright (C) 2024-present Puter Technologies Inc.
+ *
+ * This file is part of Puter.
+ *
+ * Puter is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+import type { Actor } from '../../../../core/actor.js';
+import type { ResolvedFileInput } from '../../../util/fileInput.js';
+import type { OcrModel } from './models.js';
+
+export interface RecognizeArgs {
+    source?: unknown;
+    file?: unknown;
+    provider?: string;
+    model?: string;
+    // Mistral-specific options — ignored by Textract.
+    pages?: number[];
+    includeImageBase64?: boolean;
+    imageLimit?: number;
+    imageMinSize?: number;
+    bboxAnnotationFormat?: unknown;
+    documentAnnotationFormat?: unknown;
+    documentAnnotationPrompt?: string;
+    tableFormat?: string;
+    extractHeader?: boolean;
+    extractFooter?: boolean;
+    test_mode?: boolean;
+}
+
+/** One recognized line, in the same shape for every provider. */
+export interface OcrBlock {
+    type: string;
+    text: string;
+    confidence?: number;
+    page: number;
+}
+
+/** One vendor's OCR, bound to the credentials this deployment configured. */
+export interface IOcrProvider {
+    /**
+     * Recognizes one input with one of this provider's models: holds the
+     * estimated cost while the vendor runs, then meters the pages it reports.
+     */
+    recognize(
+        input: ResolvedFileInput,
+        args: RecognizeArgs,
+        model: OcrModel,
+        actor: Actor,
+    ): Promise<unknown>;
+}

src/backend/drivers/ai/interfaces/speechToSpeech/VoiceChangerDriver.test.ts

@@ -41,25 +41,24 @@ import {
 } from 'vitest';
 import { v4 as uuidv4 } from 'uuid';
 
-import type { Actor } from '../../core/actor.js';
-import { runWithContext } from '../../core/context.js';
-import { PuterServer } from '../../server.js';
-import type { MeteringService } from '../../services/metering/MeteringService.js';
-import { setupTestServer } from '../../testUtil.js';
-import { generateDefaultFsentries } from '../../util/userProvisioning.js';
-import type { DriverStreamResult } from '../meta.js';
+import type { Actor } from '../../../../core/actor.js';
+import { runWithContext } from '../../../../core/context.js';
+import { PuterServer } from '../../../../server.js';
+import type { MeteringService } from '../../../../services/metering/MeteringService.js';
+import { setupTestServer, withAiCostFactorHook } from '../../../../testUtil.js';
+import { generateDefaultFsentries } from '../../../../util/userProvisioning.js';
+import type { DriverStreamResult } from '../../../meta.js';
 import {
     OggOpusClock,
     outputBytesPerSecond,
-    type VoiceChangerDriver,
     wavDataOffset,
-} from './VoiceChangerDriver.js';
+} from '../../providers/elevenlabs/speechToSpeech/measuredOutput.js';
+import type { VoiceChangerDriver } from './VoiceChangerDriver.js';
 import {
     callerError,
     readStreamResult,
-    withAiCostFactorHook,
-} from '../integrationTestUtil.js';
-import { VOICE_CHANGER_COSTS } from './costs.js';
+} from '../../shared/integrationTestUtil.js';
+import { VOICE_CHANGER_COSTS } from '../../providers/elevenlabs/speechToSpeech/costs.js';
 
 const { webFetchMock } = vi.hoisted(() => ({ webFetchMock: vi.fn() }));
 vi.mock('undici', async (importOriginal) => ({
@@ -191,6 +190,36 @@ describe('VoiceChangerDriver.convert argument validation', () => {
         ).rejects.toMatchObject({ statusCode: 400 });
     });
 
+    it('answers 400 for an option value that cannot be text', async () => {
+        await expect(
+            driver.convert({
+                audio: dataUrl(Buffer.from('audio'), 'audio/mpeg'),
+                enable_logging: { toString: null },
+            } as never),
+        ).rejects.toMatchObject({
+            statusCode: 400,
+            legacyCode: 'bad_request',
+            message: '`enable_logging` is not a usable value',
+        });
+        expect(fetchSpy).not.toHaveBeenCalled();
+    });
+
+    it('rejects an output format that is not text before calling ElevenLabs', async () => {
+        const { actor } = await makeUser();
+        await expect(
+            withActor(actor, () =>
+                driver.convert({
+                    audio: dataUrl(Buffer.from('audio'), 'audio/mpeg'),
+                    output_format: -1,
+                } as never),
+            ),
+        ).rejects.toMatchObject({
+            statusCode: 400,
+            legacyCode: 'bad_request',
+        });
+        expect(fetchSpy).not.toHaveBeenCalled();
+    });
+
     it.each([
         ['an unpriced', 'eleven_multilingual_sts_v1'],
         ['a malformed', 'eleven_english_sts_v2&x=1'],

src/backend/drivers/ai/interfaces/speechToSpeech/VoiceChangerDriver.ts

@@ -0,0 +1,155 @@
+/*
+ * Copyright (C) 2024-present Puter Technologies Inc.
+ *
+ * This file is part of Puter.
+ *
+ * Puter is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+import { Context } from '../../../../core/context.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import type { DriverStreamResult } from '../../../meta.js';
+import { ElevenLabsSpeechToSpeechProvider } from '../../providers/elevenlabs/speechToSpeech/ElevenLabsSpeechToSpeechProvider.js';
+import { VOICE_CHANGER_COSTS } from '../../providers/elevenlabs/speechToSpeech/costs.js';
+import { PuterDriver } from '../../../types.js';
+import {
+    type AiMeteringService,
+    withAiCostFactor,
+} from '../../../../util/aiCostFactor.js';
+import { AI_CONCURRENT, AI_RATE_LIMIT } from '../../shared/aiLimits.js';
+import { assertScalarOptions } from '../../shared/scalarOptions.js';
+import {
+    type ProviderCatalog,
+    ProviderRegistry,
+} from '../../shared/providerRegistry.js';
+import { readProviderKey } from '../../../../util/aiProviderKey.js';
+import { SAMPLE_AUDIO_URL } from '../../shared/testMode.js';
+import type { ConvertArgs } from './types.js';
+
+/**
+ * Driver implementing `puter-speech2speech` — voice changer. Currently a single
+ * provider (ElevenLabs).
+ */
+
+const VOICE_CHANGER_CATALOG: ProviderCatalog = {
+    label: 'Speech-to-speech',
+    ids: ['elevenlabs'],
+    defaultId: 'elevenlabs',
+    aliases: { elevenlabs: 'elevenlabs' },
+};
+
+// Options the providers read as text, a number or a flag.
+const SCALAR_OPTIONS = [
+    'provider',
+    'voice',
+    'voice_id',
+    'voiceId',
+    'model',
+    'model_id',
+    'seed',
+    'output_format',
+    'file_format',
+    'optimize_streaming_latency',
+    'enable_logging',
+];
+
+export class VoiceChangerDriver extends PuterDriver {
+    readonly driverInterface = 'puter-speech2speech';
+    readonly driverName = 'ai-speech2speech';
+    // Older SDK bundles name the provider in the driver slot.
+    readonly driverAliases = ['elevenlabs-voice-changer'];
+    readonly isDefault = true;
+
+    // Shared AI policy — see `drivers/ai/shared/aiLimits.ts` for the tier table.
+    readonly rateLimit = AI_RATE_LIMIT;
+    readonly concurrent = AI_CONCURRENT;
+
+    /** Metering scoped to this driver. */
+    get #aiMetering(): AiMeteringService {
+        return withAiCostFactor(
+            this.services.metering,
+            this.clients.event,
+            this.driverName,
+        );
+    }
+
+    override getReportedCosts(): Record<string, unknown>[] {
+        return Object.entries(VOICE_CHANGER_COSTS).map(
+            ([usageType, ucentsPerUnit]) => ({
+                usageType,
+                ucentsPerUnit,
+                unit: 'second',
+                source: 'driver:aiSpeech2Speech',
+            }),
+        );
+    }
+
+    #providers = new ProviderRegistry<ElevenLabsSpeechToSpeechProvider>(
+        VOICE_CHANGER_CATALOG,
+    );
+
+    override onServerStart() {
+        const elevenlabs = this.config.providers?.elevenlabs;
+        const apiKey = readProviderKey(elevenlabs);
+        if (!apiKey) return;
+        this.#providers.register(
+            'elevenlabs',
+            new ElevenLabsSpeechToSpeechProvider(
+                {
+                    stores: this.stores,
+                    fs: this.services.fs,
+                    metering: this.#aiMetering,
+                },
+                {
+                    apiKey,
+                    apiBaseUrl: elevenlabs?.apiBaseUrl as string | undefined,
+                    defaultVoiceId: elevenlabs?.defaultVoiceId as
+                        | string
+                        | undefined,
+                    defaultModelId: elevenlabs?.speechToSpeechModelId as
+                        | string
+                        | undefined,
+                },
+            ),
+        );
+    }
+
+    async convert(
+        args: ConvertArgs,
+    ): Promise<DriverStreamResult | { url: string; content_type: string }> {
+        assertScalarOptions(args, SCALAR_OPTIONS);
+        // Only one provider exists today, but naming a different one should
+        // fail loudly rather than quietly convert with this one.
+        const providerName = this.#providers.resolve(args.provider);
+
+        if (args.test_mode) {
+            return { url: SAMPLE_AUDIO_URL, content_type: 'audio/mpeg' };
+        }
+
+        const elevenlabs = this.#providers.get(providerName);
+        if (!elevenlabs) {
+            throw new HttpError(500, 'ElevenLabs API key not configured', {
+                legacyCode: 'internal_error',
+            });
+        }
+
+        const actor = Context.get('actor');
+        if (!actor)
+            throw new HttpError(401, 'Authentication required', {
+                legacyCode: 'unauthorized',
+            });
+
+        return elevenlabs.convert(args, actor);
+    }
+}

src/backend/drivers/ai/interfaces/speechToSpeech/types.ts

@@ -17,17 +17,23 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-/**
- * Base class for image generation providers.
- *
- * Concrete providers (OpenAI, Gemini, etc.) extend this and implement
- * `generate`, `models`, and `getDefaultModel`.
- */
+/** Types for the `puter-speech2speech` driver interface. */
 
-import type { IImageProvider, IImageModel, IGenerateParams } from '../types.js';
-
-export abstract class ImageProvider implements IImageProvider {
-    abstract generate(params: IGenerateParams): Promise<string>;
-    abstract models(): IImageModel[] | Promise<IImageModel[]>;
-    abstract getDefaultModel(): string;
+export interface ConvertArgs {
+    audio: unknown;
+    provider?: string;
+    voice?: string;
+    voice_id?: string;
+    voiceId?: string;
+    model?: string;
+    model_id?: string;
+    voice_settings?: unknown;
+    voiceSettings?: unknown;
+    seed?: number;
+    remove_background_noise?: boolean;
+    output_format?: string;
+    file_format?: string;
+    optimize_streaming_latency?: number;
+    enable_logging?: boolean;
+    test_mode?: boolean;
 }

src/backend/drivers/ai/interfaces/speechToText/SpeechToTextDriver.test.ts

@@ -43,15 +43,14 @@ import {
 } from 'vitest';
 import { v4 as uuidv4 } from 'uuid';
 
-import type { Actor } from '../../core/actor.js';
-import { runWithContext } from '../../core/context.js';
-import { PuterServer } from '../../server.js';
-import type { MeteringService } from '../../services/metering/MeteringService.js';
-import { setupTestServer } from '../../testUtil.js';
-import { generateDefaultFsentries } from '../../util/userProvisioning.js';
-import { withAiCostFactorHook } from '../integrationTestUtil.js';
+import type { Actor } from '../../../../core/actor.js';
+import { runWithContext } from '../../../../core/context.js';
+import { PuterServer } from '../../../../server.js';
+import type { MeteringService } from '../../../../services/metering/MeteringService.js';
+import { setupTestServer, withAiCostFactorHook } from '../../../../testUtil.js';
+import { generateDefaultFsentries } from '../../../../util/userProvisioning.js';
 import type { SpeechToTextDriver } from './SpeechToTextDriver.js';
-import { SPEECH_TO_TEXT_COSTS } from './costs.js';
+import { SPEECH_TO_TEXT_COSTS } from '../../providers/openai/speechToText/costs.js';
 
 // ── OpenAI SDK mock ─────────────────────────────────────────────────
 //
@@ -270,6 +269,23 @@ describe('SpeechToTextDriver.transcribe test_mode', () => {
 // ── Argument validation ─────────────────────────────────────────────
 
 describe('SpeechToTextDriver argument validation', () => {
+    it.each(['transcribe', 'translate'] as const)(
+        'answers 400 from %s for an option value that cannot be text',
+        async (method) => {
+            await expect(
+                driver[method]({
+                    file: dataUrl(Buffer.from('a'), 'audio/mp3'),
+                    language: { toString: null },
+                } as never),
+            ).rejects.toMatchObject({
+                statusCode: 400,
+                legacyCode: 'bad_request',
+                message: '`language` is not a usable value',
+            });
+            expect(transcriptionsCreateMock).not.toHaveBeenCalled();
+        },
+    );
+
     it('rejects streaming with 400 — not yet supported', async () => {
         const { actor } = await makeUser();
         await expect(
@@ -324,6 +340,22 @@ describe('SpeechToTextDriver argument validation', () => {
         ).rejects.toMatchObject({ statusCode: 400 });
     });
 
+    it('throws 400 when prompt is a list instead of text', async () => {
+        const { actor } = await makeUser();
+        await expect(
+            withActor(actor, () =>
+                driver.transcribe({
+                    file: dataUrl(Buffer.from('a'), 'audio/mp3'),
+                    prompt: [null, 'names'],
+                } as never),
+            ),
+        ).rejects.toMatchObject({
+            statusCode: 400,
+            message: 'prompt must be a string',
+        });
+        expect(transcriptionsCreateMock).not.toHaveBeenCalled();
+    });
+
     it('rejects diarized_json, which gpt-transcribe does not produce', async () => {
         const { actor } = await makeUser();
         await expect(

src/backend/drivers/ai/interfaces/speechToText/SpeechToTextDriver.ts

@@ -17,22 +17,24 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-import { Context } from '../../core/context.js';
-import { HttpError } from '../../core/http/HttpError.js';
-import { PuterDriver } from '../types.js';
+import { Context } from '../../../../core/context.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import { PuterDriver } from '../../../types.js';
 import {
     type AiMeteringService,
     withAiCostFactor,
-} from '../util/aiCostFactor.js';
-import { AI_CONCURRENT, AI_RATE_LIMIT } from '../util/aiLimits.js';
-import { ProviderRegistry, readProviderKey } from '../util/providerRegistry.js';
+} from '../../../../util/aiCostFactor.js';
+import { AI_CONCURRENT, AI_RATE_LIMIT } from '../../shared/aiLimits.js';
+import { assertScalarOptions } from '../../shared/scalarOptions.js';
+import { ProviderRegistry } from '../../shared/providerRegistry.js';
+import { readProviderKey } from '../../../../util/aiProviderKey.js';
 import {
     SPEECH_TO_TEXT_CATALOG,
     SPEECH_TO_TEXT_DRIVER_ALIASES,
 } from './providerAliases.js';
-import { GeminiSpeechToTextProvider } from './providers/gemini/GeminiSpeechToTextProvider.js';
-import { OpenAISpeechToTextProvider } from './providers/openai/OpenAISpeechToTextProvider.js';
-import { XAISpeechToTextProvider } from './providers/xai/XAISpeechToTextProvider.js';
+import { GeminiSpeechToTextProvider } from '../../providers/gemini/speechToText/GeminiSpeechToTextProvider.js';
+import { OpenAISpeechToTextProvider } from '../../providers/openai/speechToText/OpenAISpeechToTextProvider.js';
+import { XAISpeechToTextProvider } from '../../providers/xai/speechToText/XAISpeechToTextProvider.js';
 import type {
     ISpeechToTextDeps,
     ISpeechToTextModel,
@@ -40,6 +42,20 @@ import type {
     ITranscribeArgs,
 } from './types.js';
 
+// Options the providers read as text, a number or a flag.
+const SCALAR_OPTIONS = [
+    'provider',
+    'model',
+    'response_format',
+    'language',
+    'prompt',
+    'temperature',
+    'format',
+    'channels',
+    'audio_format',
+    'sample_rate',
+];
+
 /**
  * Driver implementing the `puter-speech2txt` interface.
  *
@@ -56,7 +72,7 @@ export class SpeechToTextDriver extends PuterDriver {
     readonly driverAliases = [...SPEECH_TO_TEXT_DRIVER_ALIASES];
     readonly isDefault = true;
 
-    // Shared AI policy — see `drivers/util/aiLimits.ts` for the tier table.
+    // Shared AI policy — see `drivers/ai/shared/aiLimits.ts` for the tier table.
     // One bucket covers every provider, keyed by interface+method+user.
     readonly rateLimit = AI_RATE_LIMIT;
     readonly concurrent = AI_CONCURRENT;
@@ -111,10 +127,12 @@ export class SpeechToTextDriver extends PuterDriver {
     }
 
     async transcribe(args: ITranscribeArgs) {
+        assertScalarOptions(args, SCALAR_OPTIONS);
         return this.#provider(args).transcribe(this.#providerArgs(args));
     }
 
     async translate(args: ITranscribeArgs) {
+        assertScalarOptions(args, SCALAR_OPTIONS);
         return this.#provider(args).translate(this.#providerArgs(args));
     }
 

src/backend/drivers/ai/interfaces/speechToText/SpeechToTextProvider.ts

@@ -22,15 +22,15 @@
  * upstream API and exposes the unified `ISpeechToTextProvider` contract.
  */
 
-import { Context } from '../../../core/context.js';
-import { HttpError } from '../../../core/http/HttpError.js';
-import type { Actor } from '../../../core/actor.js';
+import { Context } from '../../../../core/context.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import type { Actor } from '../../../../core/actor.js';
 import type {
     ISpeechToTextDeps,
     ISpeechToTextModel,
     ISpeechToTextProvider,
     ITranscribeArgs,
-} from '../types.js';
+} from './types.js';
 
 export abstract class SpeechToTextProvider implements ISpeechToTextProvider {
     abstract readonly providerName: string;

src/backend/drivers/ai/interfaces/speechToText/providerAliases.ts

@@ -17,7 +17,7 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-import type { ProviderCatalog } from '../util/providerRegistry.js';
+import type { ProviderCatalog } from '../../shared/providerRegistry.js';
 
 /**
  * Canonical `puter-speech2txt` provider ids and the aliases callers may use in

src/backend/drivers/ai/interfaces/speechToText/types.ts

@@ -19,8 +19,8 @@
 
 /** Types for the `puter-speech2txt` driver interface. */
 
-import type { AiMeteringService } from '../util/aiCostFactor.js';
-import type { loadFileInput } from '../util/fileInput.js';
+import type { AiMeteringService } from '../../../../util/aiCostFactor.js';
+import type { loadFileInput } from '../../../util/fileInput.js';
 
 /** The layers a provider needs to read its audio input and meter usage. */
 export interface ISpeechToTextDeps {

src/backend/drivers/ai/interfaces/textToSpeech/TTSDriver.test.ts

@@ -40,16 +40,13 @@ import {
     type MockInstance,
 } from 'vitest';
 
-import { runWithContext } from '../../core/context.js';
-import { SYSTEM_ACTOR } from '../../core/actor.js';
-import { PuterServer } from '../../server.js';
-import { setupTestServer } from '../../testUtil.js';
-import {
-    readStreamResult,
-    withAiCostFactorHook,
-} from '../integrationTestUtil.js';
+import { runWithContext } from '../../../../core/context.js';
+import { SYSTEM_ACTOR } from '../../../../core/actor.js';
+import { PuterServer } from '../../../../server.js';
+import { setupTestServer, withAiCostFactorHook } from '../../../../testUtil.js';
+import { readStreamResult } from '../../shared/integrationTestUtil.js';
 import type { TTSDriver } from './TTSDriver.js';
-import pollyPriceList from './providers/awsPolly/fixtures/us-west-2.json';
+import pollyPriceList from '../../providers/awsPolly/textToSpeech/fixtures/us-west-2.json';
 
 // ── SDK mocks ──────────────────────────────────────────────────────
 //
@@ -221,6 +218,19 @@ describe('TTSDriver.synthesize authentication', () => {
             driver.synthesize({ text: 'hi' } as never),
         ).rejects.toMatchObject({ statusCode: 401 });
     });
+
+    it('answers 400 for an option value that cannot be text', async () => {
+        await expect(
+            driver.synthesize({
+                text: 'hi',
+                language: { toString: null },
+            } as never),
+        ).rejects.toMatchObject({
+            statusCode: 400,
+            legacyCode: 'bad_request',
+            message: '`language` is not a usable value',
+        });
+    });
 });
 
 // ── Provider routing ────────────────────────────────────────────────

src/backend/drivers/ai/interfaces/textToSpeech/TTSDriver.ts

@@ -17,26 +17,28 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-import { Context } from '../../core/context.js';
-import { HttpError } from '../../core/http/HttpError.js';
-import { awsCredentialsFrom } from '../../util/awsCredentials.js';
-import type { DriverStreamResult } from '../meta.js';
-import { PuterDriver } from '../types.js';
+import { Context } from '../../../../core/context.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import { awsCredentialsFrom } from '../../../../util/awsCredentials.js';
+import type { DriverStreamResult } from '../../../meta.js';
+import { PuterDriver } from '../../../types.js';
 import {
     type AiMeteringService,
     withAiCostFactor,
-} from '../util/aiCostFactor.js';
-import { AI_CONCURRENT, AI_RATE_LIMIT } from '../util/aiLimits.js';
-import { usesGoogleGeminiEndpoint } from '../util/geminiRest.js';
-import { ProviderRegistry, readProviderKey } from '../util/providerRegistry.js';
+} from '../../../../util/aiCostFactor.js';
+import { AI_CONCURRENT, AI_RATE_LIMIT } from '../../shared/aiLimits.js';
+import { assertScalarOptions } from '../../shared/scalarOptions.js';
+import { usesGoogleGeminiEndpoint } from '../../providers/gemini/geminiRest.js';
+import { ProviderRegistry } from '../../shared/providerRegistry.js';
+import { readProviderKey } from '../../../../util/aiProviderKey.js';
 import { TTS_CATALOG, TTS_DRIVER_ALIASES } from './providerAliases.js';
-import { AWSPollyTTSProvider } from './providers/awsPolly/AWSPollyTTSProvider.js';
-import { ElevenLabsTTSProvider } from './providers/elevenlabs/ElevenLabsTTSProvider.js';
-import { GeminiTTSProvider } from './providers/gemini/GeminiTTSProvider.js';
-import { KlingTTSProvider } from './providers/kling/KlingTTSProvider.js';
-import { OpenAITTSProvider } from './providers/openai/OpenAITTSProvider.js';
-import { SpeechifyTTSProvider } from './providers/speechify/SpeechifyTTSProvider.js';
-import { XAITTSProvider } from './providers/xai/XAITTSProvider.js';
+import { AWSPollyTTSProvider } from '../../providers/awsPolly/textToSpeech/AWSPollyTTSProvider.js';
+import { ElevenLabsTTSProvider } from '../../providers/elevenlabs/textToSpeech/ElevenLabsTTSProvider.js';
+import { GeminiTTSProvider } from '../../providers/gemini/textToSpeech/GeminiTTSProvider.js';
+import { KlingTTSProvider } from '../../providers/kling/textToSpeech/KlingTTSProvider.js';
+import { OpenAITTSProvider } from '../../providers/openai/textToSpeech/OpenAITTSProvider.js';
+import { SpeechifyTTSProvider } from '../../providers/speechify/textToSpeech/SpeechifyTTSProvider.js';
+import { XAITTSProvider } from '../../providers/xai/textToSpeech/XAITTSProvider.js';
 import type {
     ISynthesizeArgs,
     ITTSEngine,
@@ -44,6 +46,20 @@ import type {
     ITTSVoice,
 } from './types.js';
 
+// Options the providers read as text, a number or a flag.
+const SCALAR_OPTIONS = [
+    'text',
+    'voice',
+    'model',
+    'response_format',
+    'output_format',
+    'instructions',
+    'ssml',
+    'language',
+    'engine',
+    'provider',
+];
+
 /**
  * Driver implementing the `puter-tts` interface.
  *
@@ -63,7 +79,7 @@ export class TTSDriver extends PuterDriver {
     readonly driverAliases = [...TTS_DRIVER_ALIASES];
     readonly isDefault = true;
 
-    // Shared AI policy — see `drivers/util/aiLimits.ts` for the tier table.
+    // Shared AI policy — see `drivers/ai/shared/aiLimits.ts` for the tier table.
     readonly rateLimit = AI_RATE_LIMIT;
     readonly concurrent = AI_CONCURRENT;
 
@@ -132,6 +148,7 @@ export class TTSDriver extends PuterDriver {
     async synthesize(
         args: ISynthesizeArgs,
     ): Promise<DriverStreamResult | { url: string; content_type: string }> {
+        assertScalarOptions(args, SCALAR_OPTIONS);
         const actor = Context.get('actor');
         if (!actor)
             throw new HttpError(401, 'Authentication required', {

src/backend/drivers/ai/interfaces/textToSpeech/common.test.ts

@@ -27,11 +27,11 @@ import {
     it,
     vi,
 } from 'vitest';
-import { makeActor } from '../../../core/actor.js';
-import type { DriverStreamResult } from '../../meta.js';
-import { PuterServer } from '../../../server.js';
-import { setupTestServer } from '../../../testUtil.js';
-import { withAiCostFactor } from '../../util/aiCostFactor.js';
+import { makeActor } from '../../../../core/actor.js';
+import type { DriverStreamResult } from '../../../meta.js';
+import { PuterServer } from '../../../../server.js';
+import { setupTestServer } from '../../../../testUtil.js';
+import { withAiCostFactor } from '../../../../util/aiCostFactor.js';
 import {
     assertMaxChars,
     characterCostReport,

src/backend/drivers/ai/interfaces/textToSpeech/common.ts

@@ -17,13 +17,11 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-import type { Actor } from '../../../core/actor.js';
-import { HttpError } from '../../../core/http/HttpError.js';
-import {
-    type AiMeteringService,
-    withStreamedAiCharge,
-} from '../../util/aiCostFactor.js';
-import type { DriverStreamResult } from '../../meta.js';
+import type { Actor } from '../../../../core/actor.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import { type AiMeteringService } from '../../../../util/aiCostFactor.js';
+import { withStreamedAiCharge } from '../../shared/streamedAiCharge.js';
+import type { DriverStreamResult } from '../../../meta.js';
 
 /**
  * Bounds a synthesis call: the whole reply, or until headers when the audio is

src/backend/drivers/ai/interfaces/textToSpeech/providerAliases.ts

@@ -17,7 +17,7 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-import type { ProviderCatalog } from '../util/providerRegistry.js';
+import type { ProviderCatalog } from '../../shared/providerRegistry.js';
 
 /**
  * Canonical `puter-tts` provider ids and the aliases callers may use in their

src/backend/drivers/ai/interfaces/video/VideoGenerationDriver.test.ts

@@ -41,15 +41,14 @@ import {
 } from 'vitest';
 
 import { v4 as uuidv4 } from 'uuid';
-import { Context, runWithContext } from '../../core/context.js';
-import { HttpError } from '../../core/http/HttpError.js';
-import { type Actor, SYSTEM_ACTOR } from '../../core/actor.js';
-import { PuterServer } from '../../server.js';
-import type { MeteringService } from '../../services/metering/MeteringService.js';
-import { setupTestServer } from '../../testUtil.js';
-import { withAiCostFactorHook } from '../integrationTestUtil.js';
-import { generateDefaultFsentries } from '../../util/userProvisioning.js';
-import { TOGETHER_VIDEO_GENERATION_MODELS } from './providers/together/models.js';
+import { Context, runWithContext } from '../../../../core/context.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import { type Actor, SYSTEM_ACTOR } from '../../../../core/actor.js';
+import { PuterServer } from '../../../../server.js';
+import type { MeteringService } from '../../../../services/metering/MeteringService.js';
+import { setupTestServer, withAiCostFactorHook } from '../../../../testUtil.js';
+import { generateDefaultFsentries } from '../../../../util/userProvisioning.js';
+import { TOGETHER_VIDEO_GENERATION_MODELS } from '../../providers/together/video/models.js';
 import type { VideoGenerationDriver } from './VideoGenerationDriver.js';
 
 const DEFAULT_MODEL = 'togetherai:wan-ai/wan2.7-t2v';
@@ -85,8 +84,8 @@ vi.mock('together-ai', () => {
 
 const { secureFetchMock } = vi.hoisted(() => ({ secureFetchMock: vi.fn() }));
 
-vi.mock('../../util/secureHttp.js', async (importOriginal) => ({
-    ...(await importOriginal<typeof import('../../util/secureHttp.js')>()),
+vi.mock('../../../../util/secureHttp.js', async (importOriginal) => ({
+    ...(await importOriginal<typeof import('../../../../util/secureHttp.js')>()),
     secureFetch: secureFetchMock,
 }));
 
@@ -413,6 +412,48 @@ describe('VideoGenerationDriver.generate provider routing', () => {
         },
     );
 
+    it.each([5, true, { toString: null }, ['wan']])(
+        'rejects the model %j, which is not a name',
+        async (model) => {
+            await expect(
+                withDriverName('ai-video', () =>
+                    driver.generate({ prompt: 'hi', model } as never),
+                ),
+            ).rejects.toMatchObject({
+                statusCode: 400,
+                legacyCode: 'bad_request',
+            });
+            expect(togetherVideosCreateMock).not.toHaveBeenCalled();
+        },
+    );
+
+    it('answers 400 for an option value that cannot be text', async () => {
+        await expect(
+            withActor(() =>
+                driver.generate({
+                    prompt: 'hi',
+                    seed: { toString: null },
+                } as never),
+            ),
+        ).rejects.toMatchObject({
+            statusCode: 400,
+            legacyCode: 'bad_request',
+            message: '`seed` is not a usable value',
+        });
+        expect(togetherVideosCreateMock).not.toHaveBeenCalled();
+    });
+
+    it('falls back to the model default for a size that is an object', async () => {
+        completeTogetherJob();
+        await withActor(() =>
+            driver.generate({
+                prompt: 'hi',
+                size: { width: 1280, height: 720 },
+            } as never),
+        );
+        expect(togetherVideosCreateMock).toHaveBeenCalledTimes(1);
+    });
+
     it.each(['__proto__', 'constructor'])(
         'uses the default for an unknown provider named %s',
         async (provider) => {
@@ -511,6 +552,8 @@ describe('VideoGenerationDriver.generate provider routing', () => {
             'kling-3.0',
             'kling-3.0-omni',
             'kling-3.0-turbo',
+            'kling-4.0',
+            'kling-4.0-flash',
             'kling-o1',
         ]);
     });
@@ -741,7 +784,7 @@ describe('VideoGenerationDriver metering propagation', () => {
 // ── puter_output_path ─────────────────────────────────────────────
 
 describe('VideoGenerationDriver.generate puter_output_path', () => {
-    const TEST_ACTOR: import('../../core/actor.js').Actor = {
+    const TEST_ACTOR: import('../../../../core/actor.js').Actor = {
         user: { uuid: 'a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d', id: 42, username: 'testuser' },
     };
 
@@ -1005,7 +1048,7 @@ describe('VideoGenerationDriver.generate puter_output_path', () => {
     });
 
     it('throws 400 when actor has no user ID but puter_output_path is set', async () => {
-        const noIdActor: import('../../core/actor.js').Actor = {
+        const noIdActor: import('../../../../core/actor.js').Actor = {
             user: { uuid: 'f0e1d2c3-b4a5-4968-8777-0a1b2c3d4e5f', username: 'noone' },
         };
         await expect(

src/backend/drivers/ai/interfaces/video/VideoGenerationDriver.ts

@@ -17,32 +17,33 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-import { Context } from '../../core/context.js';
-import { HttpError } from '../../core/http/HttpError.js';
-import type { Actor } from '../../core/actor.js';
-import { PuterDriver } from '../types.js';
+import { Context } from '../../../../core/context.js';
+import { HttpError } from '../../../../core/http/HttpError.js';
+import type { Actor } from '../../../../core/actor.js';
+import { PuterDriver } from '../../../types.js';
 import {
     type AiMeteringService,
     withAiCostFactor,
-} from '../util/aiCostFactor.js';
-import { AI_CONCURRENT, AI_RATE_LIMIT } from '../util/aiLimits.js';
+} from '../../../../util/aiCostFactor.js';
+import { AI_CONCURRENT, AI_RATE_LIMIT } from '../../shared/aiLimits.js';
+import { assertScalarOptions } from '../../shared/scalarOptions.js';
 import {
     resolveOutputPath,
     saveGeneratedMediaToFS,
-} from '../util/generatedMedia.js';
-import { usesGoogleGeminiEndpoint } from '../util/geminiRest.js';
+} from '../../shared/generatedMedia.js';
+import { usesGoogleGeminiEndpoint } from '../../providers/gemini/geminiRest.js';
 import {
     dataUriByteLength,
     MAX_INLINE_VIDEO_BYTES,
     readPuterImageInputs,
-} from '../util/mediaInput.js';
-import { ModelCatalog } from '../util/modelCatalog.js';
-import { readProviderKey } from '../util/providerRegistry.js';
-import { BytePlusVideoProvider } from './providers/byteplus/BytePlusVideoProvider.js';
-import { GeminiVideoProvider } from './providers/gemini/GeminiVideoProvider.js';
-import { KlingVideoProvider } from './providers/kling/KlingVideoProvider.js';
-import { MiniMaxVideoProvider } from './providers/minimax/MiniMaxVideoProvider.js';
-import { TogetherVideoProvider } from './providers/together/TogetherVideoProvider.js';
+} from '../../shared/mediaInput.js';
+import { ModelCatalog } from '../../shared/modelCatalog.js';
+import { readProviderKey } from '../../../../util/aiProviderKey.js';
+import { BytePlusVideoProvider } from '../../providers/byteplus/video/BytePlusVideoProvider.js';
+import { GeminiVideoProvider } from '../../providers/gemini/video/GeminiVideoProvider.js';
+import { KlingVideoProvider } from '../../providers/kling/video/KlingVideoProvider.js';
+import { MiniMaxVideoProvider } from '../../providers/minimax/video/MiniMaxVideoProvider.js';
+import { TogetherVideoProvider } from '../../providers/together/video/TogetherVideoProvider.js';
 import type {
     IGenerateVideoParams,
     IVideoModel,
@@ -81,6 +82,28 @@ const tierForPixels = (
     return '4k';
 };
 
+// Options the providers read as text, a number or a flag.
+const SCALAR_OPTIONS = [
+    'prompt',
+    'model',
+    'provider',
+    'seconds',
+    'duration',
+    'size',
+    'resolution',
+    'width',
+    'height',
+    'fps',
+    'steps',
+    'guidance_scale',
+    'seed',
+    'output_format',
+    'output_quality',
+    'negative_prompt',
+    'last_frame',
+    'puter_output_path',
+];
+
 /**
  * Driver implementing the `puter-video-generation` interface.
  *
@@ -106,7 +129,7 @@ export class VideoGenerationDriver extends PuterDriver {
     ];
     readonly isDefault = true;
 
-    // Shared AI policy — see `drivers/util/aiLimits.ts` for the tier table.
+    // Shared AI policy — see `drivers/ai/shared/aiLimits.ts` for the tier table.
     readonly rateLimit = AI_RATE_LIMIT;
     readonly concurrent = AI_CONCURRENT;
 
@@ -164,6 +187,7 @@ export class VideoGenerationDriver extends PuterDriver {
     }
 
     async generate(args: IGenerateVideoParams) {
+        assertScalarOptions(args, SCALAR_OPTIONS);
         const actor = Context.get('actor') as Actor | undefined;
         if (!actor)
             throw new HttpError(401, 'Authentication required', {
@@ -179,7 +203,7 @@ export class VideoGenerationDriver extends PuterDriver {
             ? await resolveOutputPath(this.services, actor, puterOutputPath)
             : undefined;
 
-        if (request.model) {
+        if (typeof request.model === 'string') {
             request.model = request.model.trim().toLowerCase();
         }
 
@@ -595,7 +619,10 @@ export class VideoGenerationDriver extends PuterDriver {
     }
 
     #resolveModel(modelId: string, provider?: string): IVideoModel | null {
-        const models = this.#modelIdMap[modelId?.trim().toLowerCase()];
+        const models =
+            typeof modelId === 'string'
+                ? this.#modelIdMap[modelId.trim().toLowerCase()]
+                : undefined;
         if (!models || models.length === 0) return null;
         if (!provider) return models[0];