fix: apply fallback chat models to background wakeups

[zzz27578]

Summary

• Pass provider_settings into MainAgentBuildConfig for background task result wakeups.
• Keep existing background wakeup streaming behavior while preserving fallback_chat_models and other provider settings.
• Add a unit test covering provider_settings propagation for background task wakeups.

Why

#9054 already fixed the cron/future-task wakeup path. Background task result wakeups still built MainAgentBuildConfig without the full provider_settings, so fallback_chat_models were not available to the main agent runner after a background task completed.

Tests

• uv run ruff format --check .
• uv run ruff check .
• uv run pytest tests\unit\test_astr_agent_tool_exec.py tests\unit\test_cron_manager.py tests\test_tool_loop_agent_runner.py -q

[gemini-code-assist]

Code Review

This pull request updates the background and cron wakeup processes to extract and pass provider_settings to the MainAgentBuildConfig. It also adds corresponding unit tests to verify that these settings, such as fallback chat models, are correctly propagated. The feedback suggests adding defensive guarding when calling ctx.get_config() in astr_agent_tool_exec.py to prevent a potential AttributeError if it returns None.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[gemini-code-assist]

To prevent a potential AttributeError if ctx.get_config() returns None, it is safer to use defensive guarding (e.g., defaulting to an empty dictionary) before calling .get().

        cfg = ctx.get_config(umo=event.unified_msg_origin) or {}
        provider_settings = cfg.get("provider_settings", {})

[sourcery-ai]

Hey - I've found 1 issue, and left some high level feedback:

• In cron.manager._woke_main_agent, streaming_response remains hard-coded to False whereas _wake_main_agent_for_background_result now derives it from provider_settings; consider also honoring provider_settings.get("stream") for cron wakeups for consistency with normal and background flows.
• The _DoneRunner helper is duplicated in both test_astr_agent_tool_exec.py and test_cron_manager.py; consider extracting it into a shared test utility or fixture to avoid duplication and keep behavior in sync.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- In `cron.manager._woke_main_agent`, `streaming_response` remains hard-coded to `False` whereas `_wake_main_agent_for_background_result` now derives it from `provider_settings`; consider also honoring `provider_settings.get("stream")` for cron wakeups for consistency with normal and background flows.
- The `_DoneRunner` helper is duplicated in both `test_astr_agent_tool_exec.py` and `test_cron_manager.py`; consider extracting it into a shared test utility or fixture to avoid duplication and keep behavior in sync.

## Individual Comments

### Comment 1
<location path="tests/unit/test_astr_agent_tool_exec.py" line_range="426-431" />
<code_context>
+        summary_name="BackgroundTask",
+    )
+
+    config = captured["config"]
+    assert config.tool_call_timeout == 456
+    assert config.provider_settings is provider_settings
+    assert config.provider_settings["fallback_chat_models"] == [
+        "fallback-provider"
+    ]
</code_context>
<issue_to_address>
**suggestion (testing):** Add assertions for streaming_response (and possibly other provider_settings-derived fields) to fully verify the new behavior.

Because `_wake_main_agent_for_background_result` now derives `config.streaming_response` from `provider_settings["stream"]`, please add an assertion for that here (e.g. `assert config.streaming_response is False`) so the new wiring is exercised. Likewise, if other fields are expected to propagate from `provider_settings` (e.g. `request_max_retries`), consider asserting them to strengthen this test against regressions.

```suggestion
    config = captured["config"]
    assert config.tool_call_timeout == 456
    assert config.provider_settings is provider_settings
    # streaming_response is derived from provider_settings["stream"]
    assert config.streaming_response == provider_settings["stream"]
    # request_max_retries should also propagate from provider_settings
    assert config.request_max_retries == provider_settings["request_max_retries"]
    assert config.provider_settings["fallback_chat_models"] == [
        "fallback-provider"
    ]
```
</issue_to_address>

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[sourcery-ai]

suggestion (testing): Add assertions for streaming_response (and possibly other provider_settings-derived fields) to fully verify the new behavior.

Because _wake_main_agent_for_background_result now derives config.streaming_response from provider_settings["stream"], please add an assertion for that here (e.g. assert config.streaming_response is False) so the new wiring is exercised. Likewise, if other fields are expected to propagate from provider_settings (e.g. request_max_retries), consider asserting them to strengthen this test against regressions.

Suggested change

	config = captured["config"]
	assert config.tool_call_timeout == 456
	assert config.provider_settings is provider_settings
	assert config.provider_settings["fallback_chat_models"] == [
	"fallback-provider"
	]
	config = captured["config"]
	assert config.tool_call_timeout == 456
	assert config.provider_settings is provider_settings
	# streaming_response is derived from provider_settings["stream"]
	assert config.streaming_response == provider_settings["stream"]
	# request_max_retries should also propagate from provider_settings
	assert config.request_max_retries == provider_settings["request_max_retries"]
	assert config.provider_settings["fallback_chat_models"] == [
	"fallback-provider"
	]