Name the generator we actually run

Our SDKs are generated by openapi-generator on our own CI. The docs said a
hosted third-party service, which we retired: hanzoai/openapi's LLM.md and its
regenerate-sdks.yml both already said so, while its README still called that
service "canonical" and told a reader to fetch an API key for it out of KMS.

Two sources disagreeing is how somebody follows the wrong one, and the wrong one
here sends them looking for a credential that should not exist.

The same claim had spread to what customers and agents read: five pages on
docs.hanzo.ai and six agent skills advertised a vendor we do not use, and
hip-0040 -- the standard for multi-language SDKs -- argued FOR it by name. The
argument survives without the brand, because it was never about the vendor: one
spec beats N hand-written clients. python-sdk's mock script also pulled that
vendor's fork of prism-cli; it takes upstream @stoplight/prism-cli now.

What is deliberately left alone is every occurrence that is not about us: a
filament material in a 3D-printer integration, a browser of that name in three
user-agent parsers, tokenizer vocabulary where the string is a token id, and
citations recording where Mux, Perigon and Stigg publish their own specs.
Renaming any of those breaks something real.

examples/.keep

@@ -1,4 +1,4 @@
-File generated from our OpenAPI spec by Stainless.
+Generated from our OpenAPI spec.
 
-This directory can be used to store example files demonstrating usage of this SDK.
-It is ignored by Stainless code generation and its content (other than this keep file) won't be touched.
+This directory holds example files demonstrating usage of this SDK. Code
+generation ignores it, so nothing here is overwritten by a regeneration.

pkg/hanzo-tasks/README.md

@@ -0,0 +1,101 @@
+# hanzo-tasks
+
+Durable activities on the native Hanzo Tasks engine.
+
+The engine is Hanzo's own (`hanzoai/tasks`), reached over JSON at
+`api.hanzo.ai/v1/tasks`. It speaks no protobuf and no gRPC, and this package
+depends on no workflow runtime — dispatching work and running a worker are both
+plain HTTP over `httpx`.
+
+```bash
+pip install hanzo-tasks
+```
+
+## Dispatch
+
+```python
+from hanzo_tasks import Tasks
+
+async with Tasks.from_env() as tasks:
+    activity = await tasks.dispatch(
+        "render",
+        input={"scene": 3},
+        task_queue="gpu",
+        heartbeat_timeout="60s",
+    )
+    print(activity.id, activity.run_id, activity.status)
+```
+
+`from_env()` reads `HANZO_API_KEY`, `HANZO_TASKS_URL` and
+`HANZO_TASKS_NAMESPACE`. The org is never named in a request: IAM validates the
+bearer token and the edge mints the org from the validated claim, so a caller
+cannot reach another tenant's shard by asking to.
+
+## Run a worker
+
+The worker **polls**. It never accepts a push, so it needs no inbound address
+and runs behind NAT.
+
+```python
+from hanzo_tasks import Tasks, Worker
+
+tasks = Tasks.from_env()
+worker = Worker(tasks, task_queue="gpu")
+
+
+@worker.handler("render")
+async def render(activity):
+    return {"frames": 120}
+
+
+await worker.run()
+```
+
+Return a value to complete the activity; raise to fail it with that cause.
+Handlers may be async or plain functions.
+
+## What the engine does, so you don't
+
+These are properties of the engine, not of this client. There is deliberately
+no second copy of them here, because a second copy can disagree.
+
+- **A dead worker's work comes back.** The engine reaps expired leases before
+  every claim, so an activity whose claimant stopped heartbeating returns to
+  `SCHEDULED` and the next poll picks it up. No client-side timer.
+- **Two workers never claim the same activity.** Claims are serialized per
+  namespace.
+- **The lease is the activity's own heartbeat timeout**, else the worker's
+  `lease_seconds`, else the engine default. `Worker` heartbeats at a third of
+  the window the server actually granted, so a beat can be missed without
+  losing the claim.
+- **An empty queue is not an error.** It is `204`, and `claim()` returns
+  `None`.
+- **Retries are the engine's.** Pass a `RetryPolicy` to `dispatch()`; the
+  engine counts attempts and fails the activity when they are exhausted.
+
+## Reading state
+
+```python
+page = await tasks.activities(page_size=50)
+for activity in page:
+    print(activity.id, activity.status, activity.attempt)
+
+activity = await tasks.describe(id, run_id)
+events, cursor = await tasks.history(id, run_id)
+```
+
+## Errors
+
+The engine reports `{"error": ..., "code": <int>}` — `code` is a number here,
+not the `status` string the rest of the Hanzo API uses.
+
+| Exception | Meaning |
+|---|---|
+| `Denied` | 401/403 — no validated principal, or one carrying no org |
+| `NotFound` | 404 — no such activity in this namespace |
+| `Terminal` | 409 — already completed, failed or canceled |
+| `TasksError` | anything else, carrying `.code` |
+
+## License
+
+MIT

pkg/hanzo-tools-shell/hanzo_tools/shell/shellflow.py

@@ -27,7 +27,7 @@ from __future__ import annotations
 
 import re
 from typing import Any, Dict, List, Final, Tuple, Union
-from functools import lru_cache  # noqa: TID251 - not using Stainless SDK
+from functools import lru_cache  # noqa: TID251 - hand-written package, not the generated client
 
 # Type aliases with full annotations
 ASTDict = Dict[str, Any]

scripts/generate.sh

@@ -2,8 +2,8 @@
 # Regenerate the Hanzo Python client (`hanzoai`) from the unified OpenAPI spec.
 #
 # The ONE way: hanzoai/openapi `hanzo.yaml` is the single source of truth. The
-# `hanzoai` package under pkg/ is generated from it with openapi-generator — no
-# Stainless. Other pkg/hanzo-* packages are hand-written and untouched here.
+# `hanzoai` package under pkg/ is generated from it with openapi-generator, run
+# on our own CI. Other pkg/hanzo-* packages are hand-written and untouched here.
 #
 #   ./scripts/generate.sh                 # pulls spec from hanzoai/openapi@main
 #   SPEC=/path/to/hanzo.yaml ./scripts/generate.sh   # local spec override

scripts/mock

@@ -21,7 +21,7 @@ echo "==> Starting mock server with URL ${URL}"
 
 # Run prism mock on the given spec
 if [ "$1" == "--daemon" ]; then
-  npm exec --package=@stainless-api/[email protected] -- prism mock "$URL" &> .prism.log &
+  npm exec --package=@stoplight/[email protected] -- prism mock "$URL" &> .prism.log &
 
   # Wait for server to come online
   echo -n "Waiting for server"
@@ -37,5 +37,5 @@ if [ "$1" == "--daemon" ]; then
 
   echo
 else
-  npm exec --package=@stainless-api/[email protected] -- prism mock "$URL"
+  npm exec --package=@stoplight/[email protected] -- prism mock "$URL"
 fi