<!-- ephemeral -->
# TeaQL TypeScript Tool API: HTTP

The HTTP provider uses an injected `fetch` implementation and is denied by the default policy.
Only the trusted application composition root may register it and allow `HTTP_TOOL`.

```typescript
import {
  ContextTools, FetchHttpToolProvider, HTTP_TOOL, ToolPolicy, UserContext,
} from '@teaql/teaql';

const ctx = new UserContext();
const tools = ContextTools.builder(ctx)
  .policy(ToolPolicy.builder().allow(HTTP_TOOL).build())
  .provider(new FetchHttpToolProvider(fetch))
  .build();

const body: string = await tools.get(HTTP_TOOL)
  .get('https://example.com/status')
  .purpose('read the external service status')
  .execute();
```

Exact type-state API:

- `HttpTool.get(url)` and `post(url, body)` return `HttpIntentPhase`;
- `purpose(intent)` or `auditAs(intent)` returns `ExecutableHttpTool`;
- `execute()` returns native `Promise<string>` and rejects blank intent or non-2xx status;
- provider absence, unknown token, and denied policy remain explicit errors.

POST bodies are JSON encoded. This version does not expose caller-defined headers, response
status objects, timeout customization, or response JSON decoding. Preserve the native response
shape and reject unknown operations instead of inventing them.


---

## TeaQL seven-language assist contract

Apply the verified Rust semantic ceiling while using only the exact TYPESCRIPT generated and
runtime APIs. Discover APIs through the generated application AGENTS.md and progressive
model-aware Assist. Do not inspect generated domain-library source.

- Do not create plurals by appending `s` or `es`; use the centralized generated plural.
- Human and non-human entities use different generated predicate vocabularies. Preserve
  forms such as “who are active” and “whose email is”; never infer them from English.
- Configure filters, projection, paging, and other query options before `purpose(...)`.
  Comment may appear anywhere in the chain. Purpose enters the executable stage; execution
  requires both values, but comment does not have to immediately precede purpose.
- Every execute/list/stream and every save accepts exactly one context argument:
  `UserContext`. Name that argument `context`, never `runtime`; data services and global
  policy are injected when the context is built. Reserve `runtime` for process-level
  runtime ownership, provider/pool setup, and module assembly.
- Tenant, merchant, identity, permissions, request policy, purpose policy, hard limit,
  and continuous-page cursor policy come only from trusted context, never dynamic JSON or TFP.
- If the required operation is absent after current entity/action and required field
  Assist, stop that path and report MISSING_ASSIST. Do not guess an API or search the
  generated library as a fallback.
- Create each application-owned source file once. After its first compile attempt,
  repair only the smallest block identified by the exact compiler or test diagnostic.
  Preserve unrelated code; do not rewrite the complete file as an error-recovery loop.
- Before a repair that would replace more than 25% of an existing application file,
  stop and report LARGE_REWRITE_REQUEST with the file, exact diagnostic, reason, and
  estimated scope. Initial creation and model-driven regeneration are not repairs.

Capability: `tool-api`.

- Treat generated entity, request, expression, and tool documentation as the API
  source of truth. Compile the produced code and retain the native response shape.
- Reject unknown modules, fields, operations, and policy overrides explicitly.