qca-sdk 0.0.1.dev5__tar.gz → 0.2.0__tar.gz

qca_sdk-0.2.0/Makefile

@@ -0,0 +1,33 @@
+PYTHON ?= python3
+LIVE_ENV_FILE ?= .env.live
+.DEFAULT_GOAL := test
+
+.PHONY: test lint typecheck build docs docs-check test-live test-live-managed test-live-all
+
+test:
+	$(PYTHON) -m pytest -q
+
+docs:
+	uv run --python 3.12 --extra dev --locked python scripts/generate-docs.py
+
+docs-check:
+	uv run --python 3.12 --extra dev --locked python scripts/docs-check.py
+
+lint:
+	$(PYTHON) -m ruff check src tests examples scripts
+	$(PYTHON) -m ruff format --check src tests examples scripts
+
+typecheck:
+	$(PYTHON) -m mypy src/qca scripts
+
+build:
+	$(PYTHON) -m build
+
+test-live:
+	QODER_RUN_LIVE=1 QODER_LIVE_ENV_FILE="$(LIVE_ENV_FILE)" $(PYTHON) -m pytest tests/integration/test_forward.py -m integration -v
+
+test-live-managed:
+	QODER_RUN_LIVE=1 QODER_LIVE_ENV_FILE="$(LIVE_ENV_FILE)" $(PYTHON) -m pytest tests/integration/test_managed.py -m integration -v
+
+test-live-all:
+	QODER_RUN_LIVE=1 QODER_LIVE_ENV_FILE="$(LIVE_ENV_FILE)" $(PYTHON) -m pytest tests/integration -m integration -v

{qca_sdk-0.0.1.dev5 → qca_sdk-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: qca-sdk
-Version: 0.0.1.dev5
+Version: 0.2.0
 Summary: Typed synchronous and asynchronous clients for Qoder Cloud Agents
 Author: Qoder
 License-Expression: MIT
@@ -27,11 +27,16 @@ Requires-Dist: pytest>=8; extra == "dev"
 Requires-Dist: pytest-asyncio>=0.24; extra == "dev"
 Requires-Dist: ruff>=0.11; extra == "dev"
 Requires-Dist: mypy>=1.15; extra == "dev"
-Requires-Dist: build>=1.2; extra == "dev"
+Requires-Dist: build==1.6.1; extra == "dev"
+Requires-Dist: pydoc-markdown<5,>=4; extra == "dev"
+Provides-Extra: release
+Requires-Dist: twine==7.0.0; extra == "release"
 Dynamic: license-file
 
 # Qoder Cloud Agents Python SDK
 
+[Changelog](CHANGELOG.md) · [Releases](https://github.com/QoderAI/qoder-cloud-agents-sdk-python/releases)
+
 [![PyPI version](https://img.shields.io/pypi/v/qca-sdk.svg)](https://pypi.org/project/qca-sdk/)
 
 The Qoder Cloud Agents Python SDK provides access to the Qoder Cloud Agents API from Python 3.10+. It ships synchronous and natively asynchronous clients, typed request parameters and response models, automatic pagination, SSE streaming, and file transfer.
@@ -44,7 +49,7 @@ The API is exposed in two modes, and each has its own client, resources, and typ
 python -m pip install qca-sdk
 ```
 
-The distribution is named `qca-sdk`; the import package is `qca`. The package is still in pre-release, so the command above resolves to the latest `0.0.1.devN` build. To work from a checkout of this repository instead:
+The distribution is named `qca-sdk`; the import package is `qca`. The package is pre-1.0, so the command above resolves to the latest `0.1.x` release. To work from a checkout of this repository instead:
 
 ```bash
 python -m pip install .
@@ -55,6 +60,22 @@ python -m pip install -e '.[dev]'   # development environment
 
 Python 3.10 or newer. The runtime dependencies are `httpx`, `pydantic` v2, `anyio`, and `typing-extensions`; the package is typed and ships `py.typed`.
 
+## Generating documentation
+
+The API reference under `docs/api/` is generated from the public source and
+committed. Regenerate and verify it with:
+
+```bash
+make docs          # regenerate docs/api/ from src/qca
+make docs-check    # regenerate + drift/link/snippet checks (offline)
+```
+
+Under the hood these run `pydoc-markdown` via `uv` on a pinned Python 3.12:
+
+```bash
+uv run --python 3.12 --extra dev --locked pydoc-markdown pydoc-markdown.yml
+```
+
 ## Usage
 
 ```python
@@ -86,7 +107,7 @@ Explicit arguments take precedence over environment variables. The clients never
 
 ```python
 client = Forward(
-    access_token="your-access-token",
+    pat="your-access-token",
     base_url="https://api.qoder.com.cn/api/v1/forward",
     timeout=30.0,
     max_retries=2,
@@ -190,26 +211,34 @@ Reuse one `session_id` for the whole conversation, and reuse one idempotency key
 
 ## Resuming a stream
 
-The SDK does not reconnect a dropped stream on its own. Persist `stream.last_event_id` and pass it back as `last_event_id` on the next call; the server replays from there, so you never have to resend a message it already accepted.
+The low-level `stream()` method exposes `stream.last_event_id` but does not reconnect. Use the handwritten `resumable_stream()` helper to reconnect automatically after EOF, timeouts, transient transport failures, and retryable HTTP statuses. It checkpoints only complete events and sends the latest checkpoint as `Last-Event-ID`; close it with a context manager when finished.
 
 ```python
-from qca import APIConnectionError
+with client.sessions.events.resumable_stream(
+    session_id,
+    last_event_id=saved_event_id,
+    event_deltas=["agent.message"],
+) as stream:
+    for event in stream:
+        saved_event_id = stream.last_event_id
+        print(event.type)
+```
 
-last_event_id = None
-try:
-    with client.sessions.events.stream(session_id, last_event_id=last_event_id) as stream:
-        for event in stream:
-            last_event_id = stream.last_event_id
-            print(event.type)
-except APIConnectionError:
-    pass  # reconnect with the last_event_id recorded above
+The async form is a native async iterator and context manager; unlike `stream()`, constructing it does not require `await`:
+
+```python
+async with client.sessions.events.resumable_stream(session_id) as stream:
+    async for event in stream:
+        print(event.type)
 ```
 
+The helper retries until closed, cancelled, or it receives `session.status_terminated` / `session.deleted`. It uses jittered exponential backoff and the same HTTP retry classification as the client (in particular, `409` is not retried). It does not query event history, discard an invalid cursor, or deduplicate event IDs because multiple preview deltas may share one ID.
+
 Events are also readable after the fact through `client.sessions.events.list(session_id)`, which paginates like any other list method.
 
 ## Handling errors
 
-`APIConnectionError` is raised when the request never reached the API; `APITimeoutError` is its timeout subclass. A non-2xx status raises an `APIStatusError` subclass, and a response that cannot be decoded into its declared type raises `APIResponseValidationError`. All of them derive from `qca.APIError`.
+`APIConnectionError` is raised when the request never reached the API; `APITimeoutError` is its timeout subclass. A non-2xx status raises an `APIStatusError` subclass. Invalid JSON, invalid download URLs, and response schema mismatches when strict response validation is enabled raise `APIResponseValidationError`. All of them derive from `qca.APIError`.
 
 ```python
 from qca import APIConnectionError, APIStatusError, APITimeoutError
@@ -231,13 +260,29 @@ except APIStatusError as exc:
 | 403 | `PermissionDeniedError` |
 | 404 | `NotFoundError` |
 | 409 | `ConflictError` |
+| 413 | `RequestTooLargeError` |
 | 422 | `UnprocessableEntityError` |
 | 429 | `RateLimitError` |
-| 5xx | `InternalServerError` |
+| 529 | `OverloadedError` |
+| other 5xx | `InternalServerError` |
 | other | `APIStatusError` |
 
 `code` and `type` are read from the error body and are `None` when the server omits them, so log `message` and `request_id` as well. A non-JSON error body is kept verbatim in `.body`.
 
+`RequestTooLargeError` and `OverloadedError` inherit directly from `APIStatusError`, matching Anthropic. Code that previously caught `InternalServerError` for status 529 should now catch `OverloadedError` as well, or catch `APIStatusError` for all HTTP errors.
+
+## Response validation
+
+By default, responses are constructed into models without requiring every field to match the declared schema, matching Anthropic's Python SDK. Nested objects are still converted to models and unknown fields are retained. Unexpected field values may keep their original type, so type annotations describe the expected API schema rather than guaranteeing the runtime value.
+
+To require Pydantic response validation and raise `APIResponseValidationError` on a schema mismatch, enable the constructor option:
+
+```python
+client = Forward(_strict_response_validation=True)
+```
+
+The option is available on `Forward`, `Managed`, `AsyncForward`, and `AsyncManaged`, and is preserved by `with_options`, raw and streaming response views, pagination, and SSE parsing. Invalid JSON and invalid download URLs still raise `APIResponseValidationError` in either mode. Direct construction or validation of model classes continues to use Pydantic validation.
+
 ## Request IDs
 
 Every response model carries the `x-request-id` of the call that produced it, and errors expose the same value. Include it when reporting a problem.
@@ -251,6 +296,8 @@ print(identity._request_id)
 
 Certain errors are retried twice by default with exponential backoff. GET and HEAD requests, and any request carrying an idempotency key, are retried on connection errors, 408, 429, and 5xx; other requests are retried on 429 only. A 409 is never retried automatically, and an SSE stream that has already been established is never retried. Within those rules the SDK honors `x-should-retry` and a valid `Retry-After-Ms` or `Retry-After`.
 
+Positive server-requested delays, including values over 60 seconds, are honored up to 4,294,967 seconds, matching Anthropic's Python SDK. A numeric `Retry-After-Ms` takes precedence over `Retry-After`, which accepts seconds or an HTTP date. Zero, negative, or invalid delays fall back to exponential backoff. A server-requested wait can therefore exceed the timeout configured for an individual HTTP attempt.
+
 ```python
 client = Forward(max_retries=0)  # disable for all requests
 client.with_options(max_retries=5).sessions.list()  # or override per call site
@@ -260,7 +307,7 @@ client.with_options(max_retries=5).sessions.list()  # or override per call site
 
 ## Timeouts
 
-The default timeout is 10 seconds to connect and 60 seconds for each subsequent phase. Pass a float of seconds, an `httpx.Timeout`, or `None` to disable.
+The default timeout is 5 seconds to connect and 600 seconds each for reading data, writing data, and acquiring a connection from the pool, matching Anthropic's Python SDK. These are phase timeouts, not a total request deadline. Pass a float of seconds, an `httpx.Timeout`, or `None` to disable.
 
 ```python
 client = Forward(timeout=30.0)
@@ -390,11 +437,11 @@ For tokens that expire, pass a credential provider instead of a static token. It
 client = Forward(credential=my_credential)
 ```
 
-A static `access_token` takes precedence over a provider, and an explicit `Authorization` header takes precedence over both.
+A static `pat` takes precedence over a provider, and an explicit `Authorization` header takes precedence over both.
 
 ## Versioning
 
-This project follows [Semantic Versioning](https://semver.org). It is pre-1.0 and currently published as `0.0.1.devN`, so the public surface may still change between releases. Anything prefixed with an underscore is internal and may change at any time.
+This project follows [Semantic Versioning](https://semver.org). It is pre-1.0, so the public surface may still change between releases. Anything prefixed with an underscore is internal and may change at any time.
 
 ```python
 import qca

{qca_sdk-0.0.1.dev5 → qca_sdk-0.2.0}/README.md

@@ -1,5 +1,7 @@
 # Qoder Cloud Agents Python SDK
 
+[Changelog](CHANGELOG.md) · [Releases](https://github.com/QoderAI/qoder-cloud-agents-sdk-python/releases)
+
 [![PyPI version](https://img.shields.io/pypi/v/qca-sdk.svg)](https://pypi.org/project/qca-sdk/)
 
 The Qoder Cloud Agents Python SDK provides access to the Qoder Cloud Agents API from Python 3.10+. It ships synchronous and natively asynchronous clients, typed request parameters and response models, automatic pagination, SSE streaming, and file transfer.
@@ -12,7 +14,7 @@ The API is exposed in two modes, and each has its own client, resources, and typ
 python -m pip install qca-sdk
 ```
 
-The distribution is named `qca-sdk`; the import package is `qca`. The package is still in pre-release, so the command above resolves to the latest `0.0.1.devN` build. To work from a checkout of this repository instead:
+The distribution is named `qca-sdk`; the import package is `qca`. The package is pre-1.0, so the command above resolves to the latest `0.1.x` release. To work from a checkout of this repository instead:
 
 ```bash
 python -m pip install .
@@ -23,6 +25,22 @@ python -m pip install -e '.[dev]'   # development environment
 
 Python 3.10 or newer. The runtime dependencies are `httpx`, `pydantic` v2, `anyio`, and `typing-extensions`; the package is typed and ships `py.typed`.
 
+## Generating documentation
+
+The API reference under `docs/api/` is generated from the public source and
+committed. Regenerate and verify it with:
+
+```bash
+make docs          # regenerate docs/api/ from src/qca
+make docs-check    # regenerate + drift/link/snippet checks (offline)
+```
+
+Under the hood these run `pydoc-markdown` via `uv` on a pinned Python 3.12:
+
+```bash
+uv run --python 3.12 --extra dev --locked pydoc-markdown pydoc-markdown.yml
+```
+
 ## Usage
 
 ```python
@@ -54,7 +72,7 @@ Explicit arguments take precedence over environment variables. The clients never
 
 ```python
 client = Forward(
-    access_token="your-access-token",
+    pat="your-access-token",
     base_url="https://api.qoder.com.cn/api/v1/forward",
     timeout=30.0,
     max_retries=2,
@@ -158,26 +176,34 @@ Reuse one `session_id` for the whole conversation, and reuse one idempotency key
 
 ## Resuming a stream
 
-The SDK does not reconnect a dropped stream on its own. Persist `stream.last_event_id` and pass it back as `last_event_id` on the next call; the server replays from there, so you never have to resend a message it already accepted.
+The low-level `stream()` method exposes `stream.last_event_id` but does not reconnect. Use the handwritten `resumable_stream()` helper to reconnect automatically after EOF, timeouts, transient transport failures, and retryable HTTP statuses. It checkpoints only complete events and sends the latest checkpoint as `Last-Event-ID`; close it with a context manager when finished.
 
 ```python
-from qca import APIConnectionError
+with client.sessions.events.resumable_stream(
+    session_id,
+    last_event_id=saved_event_id,
+    event_deltas=["agent.message"],
+) as stream:
+    for event in stream:
+        saved_event_id = stream.last_event_id
+        print(event.type)
+```
 
-last_event_id = None
-try:
-    with client.sessions.events.stream(session_id, last_event_id=last_event_id) as stream:
-        for event in stream:
-            last_event_id = stream.last_event_id
-            print(event.type)
-except APIConnectionError:
-    pass  # reconnect with the last_event_id recorded above
+The async form is a native async iterator and context manager; unlike `stream()`, constructing it does not require `await`:
+
+```python
+async with client.sessions.events.resumable_stream(session_id) as stream:
+    async for event in stream:
+        print(event.type)
 ```
 
+The helper retries until closed, cancelled, or it receives `session.status_terminated` / `session.deleted`. It uses jittered exponential backoff and the same HTTP retry classification as the client (in particular, `409` is not retried). It does not query event history, discard an invalid cursor, or deduplicate event IDs because multiple preview deltas may share one ID.
+
 Events are also readable after the fact through `client.sessions.events.list(session_id)`, which paginates like any other list method.
 
 ## Handling errors
 
-`APIConnectionError` is raised when the request never reached the API; `APITimeoutError` is its timeout subclass. A non-2xx status raises an `APIStatusError` subclass, and a response that cannot be decoded into its declared type raises `APIResponseValidationError`. All of them derive from `qca.APIError`.
+`APIConnectionError` is raised when the request never reached the API; `APITimeoutError` is its timeout subclass. A non-2xx status raises an `APIStatusError` subclass. Invalid JSON, invalid download URLs, and response schema mismatches when strict response validation is enabled raise `APIResponseValidationError`. All of them derive from `qca.APIError`.
 
 ```python
 from qca import APIConnectionError, APIStatusError, APITimeoutError
@@ -199,13 +225,29 @@ except APIStatusError as exc:
 | 403 | `PermissionDeniedError` |
 | 404 | `NotFoundError` |
 | 409 | `ConflictError` |
+| 413 | `RequestTooLargeError` |
 | 422 | `UnprocessableEntityError` |
 | 429 | `RateLimitError` |
-| 5xx | `InternalServerError` |
+| 529 | `OverloadedError` |
+| other 5xx | `InternalServerError` |
 | other | `APIStatusError` |
 
 `code` and `type` are read from the error body and are `None` when the server omits them, so log `message` and `request_id` as well. A non-JSON error body is kept verbatim in `.body`.
 
+`RequestTooLargeError` and `OverloadedError` inherit directly from `APIStatusError`, matching Anthropic. Code that previously caught `InternalServerError` for status 529 should now catch `OverloadedError` as well, or catch `APIStatusError` for all HTTP errors.
+
+## Response validation
+
+By default, responses are constructed into models without requiring every field to match the declared schema, matching Anthropic's Python SDK. Nested objects are still converted to models and unknown fields are retained. Unexpected field values may keep their original type, so type annotations describe the expected API schema rather than guaranteeing the runtime value.
+
+To require Pydantic response validation and raise `APIResponseValidationError` on a schema mismatch, enable the constructor option:
+
+```python
+client = Forward(_strict_response_validation=True)
+```
+
+The option is available on `Forward`, `Managed`, `AsyncForward`, and `AsyncManaged`, and is preserved by `with_options`, raw and streaming response views, pagination, and SSE parsing. Invalid JSON and invalid download URLs still raise `APIResponseValidationError` in either mode. Direct construction or validation of model classes continues to use Pydantic validation.
+
 ## Request IDs
 
 Every response model carries the `x-request-id` of the call that produced it, and errors expose the same value. Include it when reporting a problem.
@@ -219,6 +261,8 @@ print(identity._request_id)
 
 Certain errors are retried twice by default with exponential backoff. GET and HEAD requests, and any request carrying an idempotency key, are retried on connection errors, 408, 429, and 5xx; other requests are retried on 429 only. A 409 is never retried automatically, and an SSE stream that has already been established is never retried. Within those rules the SDK honors `x-should-retry` and a valid `Retry-After-Ms` or `Retry-After`.
 
+Positive server-requested delays, including values over 60 seconds, are honored up to 4,294,967 seconds, matching Anthropic's Python SDK. A numeric `Retry-After-Ms` takes precedence over `Retry-After`, which accepts seconds or an HTTP date. Zero, negative, or invalid delays fall back to exponential backoff. A server-requested wait can therefore exceed the timeout configured for an individual HTTP attempt.
+
 ```python
 client = Forward(max_retries=0)  # disable for all requests
 client.with_options(max_retries=5).sessions.list()  # or override per call site
@@ -228,7 +272,7 @@ client.with_options(max_retries=5).sessions.list()  # or override per call site
 
 ## Timeouts
 
-The default timeout is 10 seconds to connect and 60 seconds for each subsequent phase. Pass a float of seconds, an `httpx.Timeout`, or `None` to disable.
+The default timeout is 5 seconds to connect and 600 seconds each for reading data, writing data, and acquiring a connection from the pool, matching Anthropic's Python SDK. These are phase timeouts, not a total request deadline. Pass a float of seconds, an `httpx.Timeout`, or `None` to disable.
 
 ```python
 client = Forward(timeout=30.0)
@@ -358,11 +402,11 @@ For tokens that expire, pass a credential provider instead of a static token. It
 client = Forward(credential=my_credential)
 ```
 
-A static `access_token` takes precedence over a provider, and an explicit `Authorization` header takes precedence over both.
+A static `pat` takes precedence over a provider, and an explicit `Authorization` header takes precedence over both.
 
 ## Versioning
 
-This project follows [Semantic Versioning](https://semver.org). It is pre-1.0 and currently published as `0.0.1.devN`, so the public surface may still change between releases. Anything prefixed with an underscore is internal and may change at any time.
+This project follows [Semantic Versioning](https://semver.org). It is pre-1.0, so the public surface may still change between releases. Anything prefixed with an underscore is internal and may change at any time.
 
 ```python
 import qca

{qca_sdk-0.0.1.dev5 → qca_sdk-0.2.0}/examples/common/live.py

@@ -3,7 +3,6 @@ from __future__ import annotations
 import argparse
 import json
 import os
-import random
 import re
 import sys
 import time
@@ -56,7 +55,7 @@ def read_env(path: str | Path) -> dict[str, str]:
 @dataclass
 class Config:
     mode: str
-    access_token: str = field(repr=False)
+    pat: str = field(repr=False)
     base_url: str = ""
     model: str = ""
     timeout: float = 300
@@ -89,7 +88,7 @@ class Config:
         return cls(mode, token, str(url), values.get(prefix + "MODEL", ""), timeout)
 
     def client_options(self) -> dict[str, Any]:
-        return dict(access_token=self.access_token, base_url=self.base_url, max_retries=0, timeout=30)
+        return dict(pat=self.pat, base_url=self.base_url, max_retries=0, timeout=30)
 
 
 def safe_error(error: BaseException, token: str = "") -> str:
@@ -163,7 +162,7 @@ class Run:
             try:
                 action()
             except Exception as error:
-                failures.append(f"{kind} {resource_id}: {safe_error(error, self.config.access_token)}")
+                failures.append(f"{kind} {resource_id}: {safe_error(error, self.config.pat)}")
         self.cleanups.clear()
         if failures:
             raise RuntimeError("Cleanup failed:\n" + "\n".join(failures))
@@ -171,89 +170,6 @@ class Run:
             self.output("cleanup", "completed")
 
 
-@dataclass
-class TurnResult:
-    text: str = ""
-    last_id: str = ""
-    tool_used: bool = False
-    complete: bool = False
-
-    def observe(self, event: Any) -> None:
-        if hasattr(event, "to_dict"):
-            event = event.to_dict(mode="json")
-        kind = event.get("type")
-        if event.get("id"):
-            self.last_id = event["id"]
-        if kind in ("session.error", "session.status_terminated"):
-            raise AssertionError(f"Execution failed: {kind}, event_id={self.last_id}")
-        if kind in ("agent.tool_use", "agent.mcp_tool_use"):
-            self.tool_used = True
-        elif kind == "agent.message":
-            # Only the latest completed assistant message can satisfy assertions.
-            self.text = "\n".join(
-                block.get("text", "") for block in event.get("content", []) if block.get("type") == "text"
-            )
-        elif kind == "session.status_idle":
-            reason = event.get("stop_reason")
-            reason = reason.get("type") if isinstance(reason, dict) else reason
-            if reason not in (None, "", "end_turn", "stop_sequence"):
-                raise AssertionError(f"Execution stopped early: {reason}, event_id={self.last_id}")
-            self.complete = bool(self.text)
-
-    def verify(self, expected: list[str], require_tool: bool = False) -> None:
-        if not self.complete:
-            raise AssertionError(f"No idle state after assistant output; last_event_id={self.last_id}")
-        if not all(value in self.text for value in expected):
-            raise AssertionError(f"Assistant output is missing expected values; last_event_id={self.last_id}")
-        if require_tool and not self.tool_used:
-            raise AssertionError(f"No actual tool execution; last_event_id={self.last_id}")
-
-
-def wait_reply(events: Any, run: Run, session_id: str, after: str = "") -> TurnResult:
-    result = TurnResult(last_id=after)
-    while not result.complete:
-        run.remaining()
-        page = events.list(
-            session_id,
-            order="asc",
-            limit=100,
-            extra_query={"after_id": result.last_id or None, "include_tool_calls": True},
-            timeout=min(run.remaining(), 30),
-        )
-        for index, event in enumerate(page):
-            if index >= 2000:
-                raise AssertionError("Event polling exceeded 2000 events")
-            result.observe(event)
-            if result.complete:
-                break
-        if not result.complete:
-            run.pause()
-    run.output("assistant", result.text)
-    return result
-
-
-def turn(
-    events: Any,
-    run: Run,
-    session_id: str,
-    prompt: str,
-    expected: list[str],
-    *,
-    require_tool: bool = False,
-) -> TurnResult:
-    run.output("user", prompt)
-    result = events.send(
-        session_id,
-        events=[{"type": "user.message", "content": [{"type": "text", "text": prompt}]}],
-        extra_headers={"Idempotency-Key": name("event")},
-    )
-    if len(result.data) != 1 or not result.data[0].id:
-        raise AssertionError("Send must return exactly one user event ID")
-    reply = wait_reply(events, run, session_id, result.data[0].id)
-    reply.verify(expected, require_tool)
-    return reply
-
-
 def choose_model(models: Any, requested: str) -> str:
     enabled = [model.id for model in models.data if model.is_enabled and model.id]
     if requested:
@@ -265,29 +181,6 @@ def choose_model(models: Any, requested: str) -> str:
     return "ultimate" if "ultimate" in enabled else sorted(enabled)[0]
 
 
-@dataclass
-class ProjectMemory:
-    project: str = field(default_factory=lambda: "青禾订单-" + marker()[:6])
-    release_time: str = field(default_factory=lambda: f"{random.randrange(20, 24):02}:{random.randrange(60):02}")
-    contact: str = field(default_factory=lambda: random.choice(["林岚", "陈朔", "叶澄", "苏棠"]))
-    rollback_version: str = field(
-        default_factory=lambda: f"v2.{random.randrange(100, 1000)}.{random.randrange(100, 1000)}"
-    )
-    path = "projects/release-conventions.md"
-
-    def content(self) -> str:
-        return f"---\nname: release-conventions\ndescription: {self.project} 的项目发布约定\nmetadata:\n  type: project\n---\n\n# {self.project}\n\n- 北京时间 {self.release_time} 开始发布。\n- 发布异常时联系值班负责人{self.contact}。\n- 回滚使用已验证的稳定版本 {self.rollback_version}。\n\nWhy: 在值班窗口发布，并使用验证过的版本恢复服务。\nHow to apply: 为这个项目拟定发布计划时遵循以上约定。\n"
-
-    def index(self) -> str:
-        return f"- [{self.project} 发布约定]({self.path}) — 发布窗口、异常联系人与回滚约定。\n"
-
-    def prompt(self) -> str:
-        return f"请根据你记得的项目约定，为「{self.project}」拟一份简短上线安排，涵盖开始时间、异常联系和回滚处理。不要执行发布；缺少信息时请明确说明。"
-
-    def expected(self) -> list[str]:
-        return [self.release_time, self.contact, self.rollback_version]
-
-
 def run_cli(mode: str, client_type: Any, scenarios: dict[str, Callable[[Any, Run], None]]) -> None:
     parser = argparse.ArgumentParser(description=f"Qoder {mode} SDK examples")
     parser.add_argument("--env", default=".env.live")
@@ -314,9 +207,9 @@ def run_cli(mode: str, client_type: Any, scenarios: dict[str, Callable[[Any, Run
                     try:
                         context.cleanup()
                     except Exception as error:
-                        errors.append(safe_error(error, config.access_token))
+                        errors.append(safe_error(error, config.pat))
         except Exception as error:
-            errors.insert(0, safe_error(error, config.access_token))
+            errors.insert(0, safe_error(error, config.pat))
         results.append({"scenario": scenario, "passed": not errors, "outputs": context.outputs, "errors": errors})
         if args.output == "text":
             print(f"{scenario}: {'FAIL' if errors else 'PASS'}")

{qca_sdk-0.0.1.dev5 → qca_sdk-0.2.0}/examples/forward/__main__.py

@@ -4,19 +4,25 @@ from examples.common.live import run_cli
 from qca import Forward
 
 from .batch import run as batch
+from .conversation import run as conversation
+from .identity_config import run as identity_config
 from .memory import run as memory
 from .models import run as models
 from .resources import run as resources
 from .schedule import run as schedule
 from .session import run as session
+from .streaming_deltas import run as streaming_deltas
 
 SCENARIOS = {
     "models": models,
     "session": session,
+    "conversation": conversation,
     "resources": resources,
+    "identity_config": identity_config,
     "memory": memory,
     "schedule": schedule,
     "batch": batch,
+    "streaming_deltas": streaming_deltas,
 }