refactor(agent): remove duplicate progress streaming path

nanobot/agent/runner.py

@@ -46,13 +46,11 @@ from nanobot.runtime_context import (
 from nanobot.session.history_visibility import is_hidden_history_message
 from nanobot.session.recovery import PENDING_FOLLOWUP_ID_KEY
 from nanobot.utils.helpers import (
-    IncrementalThinkExtractor,
     build_assistant_message,
     estimate_message_tokens,
     estimate_prompt_tokens_chain,
     extract_reasoning,
     strip_reasoning_tags,
-    strip_think,
 )
 from nanobot.utils.llm_runtime import LLMRuntime
 from nanobot.utils.prompt_templates import render_template
@@ -67,7 +65,6 @@ from nanobot.utils.runtime import (
 )
 
 ContinuationCallback = Callable[[], str | None]
-ProgressCallback = Callable[[str], Awaitable[None]]
 RetryWaitCallback = Callable[[str], Awaitable[None]]
 CheckpointCallback = Callable[[dict[str, Any]], Awaitable[None]]
 InjectionCallback = Callable[..., Awaitable[Iterable[Any] | None]]
@@ -112,7 +109,6 @@ class AgentRunSpec:
     session_key: str | None = None
     context_block_limit: int | None = None
     provider_retry_mode: str = "standard"
-    progress_callback: ProgressCallback | None = None
     retry_wait_callback: RetryWaitCallback | None = None
     checkpoint_callback: CheckpointCallback | None = None
     injection_callback: InjectionCallback | None = None
@@ -951,14 +947,7 @@ class AgentRunner:
             tools=spec.tools.get_definitions(),
         )
         wants_streaming = hook.wants_streaming()
-        progress_callback = spec.progress_callback
-        wants_progress_streaming = (
-            not wants_streaming
-            and progress_callback is not None
-            and getattr(spec.runtime.provider, "supports_progress_deltas", False) is True
-        )
 
-        progress_state: dict[str, bool] | None = None
         active_hosted_tools: dict[str, dict[str, Any]] = {}
         request_started_at = 0.0
         first_output_at: float | None = None
@@ -1029,40 +1018,6 @@ class AgentRunner:
                 on_tool_call_delta=_provider_tool_event,
                 on_stream_recover=_stream_recover,
             )
-        elif wants_progress_streaming:
-            stream_buf = ""
-            think_extractor = IncrementalThinkExtractor()
-            progress_state = {"reasoning_open": False}
-
-            async def _stream_progress(delta: str) -> None:
-                nonlocal stream_buf
-                if not delta:
-                    return
-                _generation_delta(delta)
-                prev_clean = strip_think(stream_buf)
-                stream_buf += delta
-                new_clean = strip_think(stream_buf)
-                incremental = new_clean[len(prev_clean):]
-
-                if await think_extractor.feed(stream_buf, hook.emit_reasoning):
-                    context.streamed_reasoning = True
-                    progress_state["reasoning_open"] = True
-
-                if incremental:
-                    if progress_state["reasoning_open"]:
-                        await hook.emit_reasoning_end()
-                        progress_state["reasoning_open"] = False
-                    context.streamed_content = True
-                    callback = progress_callback
-                    if callback is not None:
-                        await callback(incremental)
-
-            coro = spec.runtime.provider.chat_stream_with_retry(
-                **kwargs,
-                provider_context=provider_context,
-                on_content_delta=_stream_progress,
-                on_tool_call_delta=_provider_tool_event,
-            )
         else:
             coro = spec.runtime.provider.chat_with_retry(
                 **kwargs,
@@ -1074,10 +1029,9 @@ class AgentRunner:
         # very slow deltas can still run forever. Use a more generous wall-clock
         # timeout for streaming while preserving NANOBOT_LLM_TIMEOUT_S=0 as an
         # opt-out for all LLM wall-clock timeouts.
-        is_streaming_request = wants_streaming or wants_progress_streaming
         outer_timeout_s = (
             max(300.0, timeout_s * 2)
-            if is_streaming_request and timeout_s is not None
+            if wants_streaming and timeout_s is not None
             else timeout_s
         )
         request_started_at = time.perf_counter()
@@ -1115,8 +1069,6 @@ class AgentRunner:
                     "error": response.content
                     or "Model request failed before the provider-hosted tool completed.",
                 })
-        if progress_state and progress_state.get("reasoning_open"):
-            await hook.emit_reasoning_end()
         dropped, all_dropped, original_finish_reason = (
             self._drop_malformed_tool_calls(response)
         )

nanobot/providers/base.py

@@ -603,8 +603,6 @@ _SYNTHETIC_USER_CONTENT = "(conversation continued)"
 class LLMProvider(ABC):
     """Base class for LLM providers."""
 
-    supports_progress_deltas = False
-
     _CHAT_RETRY_DELAYS = (1, 2, 4)
     _PERSISTENT_MAX_DELAY = 60
     _PERSISTENT_IDENTICAL_ERROR_LIMIT = 10

nanobot/providers/fallback_provider.py

@@ -157,10 +157,6 @@ class FallbackProvider(LLMProvider):
         super().set_llm_call_observer(observer)
         self._primary.set_llm_call_observer(observer)
 
-    @property
-    def supports_progress_deltas(self) -> bool:
-        return bool(getattr(self._primary, "supports_progress_deltas", False))
-
     def can_resume_conversation_state(
         self,
         state: ProviderConversationState,

nanobot/providers/openai_codex_provider.py

@@ -44,8 +44,6 @@ _COMPACTION_RETAINED_CHAR_BUDGET = 256_000
 class OpenAICodexProvider(LLMProvider):
     """Use Codex OAuth to call the Responses API."""
 
-    supports_progress_deltas = True
-
     def __init__(
         self,
         default_model: str = "openai-codex/gpt-5.6-sol",

nanobot/providers/xai_grok_provider.py

@@ -63,8 +63,6 @@ def _is_named_x_search_tool(value: object) -> bool:
 class XAIGrokProvider(LLMProvider):
     """Call xAI's subscription proxy and expose supported hosted tools."""
 
-    supports_progress_deltas = True
-
     def __init__(
         self,
         default_model: str = DEFAULT_XAI_GROK_MODEL,

tests/agent/test_loop_progress.py

@@ -373,7 +373,6 @@ class TestToolEventProgress:
         """The /goal command rewrites the prompt but must not bypass WebUI file-edit progress."""
         bus = MessageBus()
         provider = MagicMock()
-        provider.supports_progress_deltas = True
         provider.get_default_model.return_value = "test-model"
         call_count = 0
 
@@ -460,7 +459,6 @@ class TestToolEventProgress:
         """Non-streaming channels should get one final reply, not token progress spam."""
         bus = MessageBus()
         provider = MagicMock()
-        provider.supports_progress_deltas = True
         provider.get_default_model.return_value = "openai-codex/gpt-5.5"
         provider.chat_with_retry = AsyncMock(return_value=LLMResponse(content="Hello", tool_calls=[]))
         provider.chat_stream_with_retry = AsyncMock()
@@ -493,7 +491,6 @@ class TestToolEventProgress:
         """Streaming channels still receive provider deltas through stream events."""
         bus = MessageBus()
         provider = MagicMock()
-        provider.supports_progress_deltas = True
         provider.get_default_model.return_value = "openai-codex/gpt-5.5"
 
         async def chat_stream_with_retry(*, on_content_delta, **kwargs):
@@ -544,7 +541,6 @@ class TestToolEventProgress:
     ) -> None:
         bus = MessageBus()
         provider = MagicMock()
-        provider.supports_progress_deltas = True
         provider.get_default_model.return_value = "test-model"
         responses = iter([
             LLMResponse(content="first-", finish_reason="length"),
@@ -590,7 +586,6 @@ class TestToolEventProgress:
     ) -> None:
         bus = MessageBus()
         provider = MagicMock()
-        provider.supports_progress_deltas = True
         provider.get_default_model.return_value = "test-model"
         call_count = 0
 
@@ -637,7 +632,6 @@ class TestToolEventProgress:
     ) -> None:
         bus = MessageBus()
         provider = MagicMock()
-        provider.supports_progress_deltas = True
         provider.get_default_model.return_value = "test-model"
 
         async def chat_stream_with_retry(*, on_content_delta, **kwargs):
@@ -728,7 +722,6 @@ class TestToolEventProgress:
         """A no-tools finalization must not be dropped after empty stream retries."""
         bus = MessageBus()
         provider = MagicMock()
-        provider.supports_progress_deltas = True
         provider.get_default_model.return_value = "openai-codex/gpt-5.5"
         provider.chat_stream_with_retry = AsyncMock(side_effect=[
             LLMResponse(content=None, tool_calls=[]),
@@ -776,7 +769,6 @@ class TestToolEventProgress:
     ) -> None:
         bus = MessageBus()
         provider = MagicMock()
-        provider.supports_progress_deltas = True
         provider.get_default_model.return_value = "openai-codex/gpt-5.5"
         first_request_started = asyncio.Event()
         release_first_request = asyncio.Event()
@@ -935,7 +927,6 @@ class TestToolEventProgress:
         """Recovered streaming output should use a new stream segment."""
         bus = MessageBus()
         provider = MagicMock()
-        provider.supports_progress_deltas = True
         provider.get_default_model.return_value = "openai-codex/gpt-5.5"
 
         async def chat_stream_with_retry(*, on_content_delta, on_stream_recover, **kwargs):
@@ -988,13 +979,12 @@ class TestToolEventProgress:
         provider.chat_with_retry.assert_not_awaited()
 
     @pytest.mark.asyncio
-    async def test_streamed_progress_is_not_repeated_before_tool_execution(
+    async def test_streamed_content_is_not_repeated_before_tool_execution(
         self,
         tmp_path: Path,
     ) -> None:
-        """If content was already streamed as progress, tool setup should not repeat it."""
+        """If content was already streamed, tool setup should not repeat it."""
         loop = _make_loop(tmp_path)
-        loop.provider.supports_progress_deltas = True
         tool_call = ToolCallRequest(id="call1", name="custom_tool", arguments={"path": "foo.txt"})
         calls = iter([
             LLMResponse(content="I will inspect it.", tool_calls=[tool_call]),

tests/agent/test_runner_core.py

@@ -798,64 +798,6 @@ async def test_runner_times_out_never_ending_streaming_request():
     provider.chat_with_retry.assert_not_awaited()
 
 
-@pytest.mark.asyncio
-async def test_runner_closes_progress_reasoning_on_streaming_wall_timeout():
-    from nanobot.agent.hook import AgentHook
-    from nanobot.agent.runner import AgentRunner
-
-    provider = MagicMock(spec=LLMProvider)
-    provider.supports_progress_deltas = True
-    events: list[tuple[str, str | None]] = []
-
-    async def chat_stream_with_retry(*, on_content_delta, **kwargs):
-        try:
-            await on_content_delta("<think>working...</think>")
-            await asyncio.sleep(3600)
-        finally:
-            events.append(("provider_cancelled", None))
-
-    provider.chat_stream_with_retry = chat_stream_with_retry
-    provider.chat_with_retry = AsyncMock()
-    tools = MagicMock()
-    tools.get_definitions.return_value = []
-
-    class ProgressReasoningHook(AgentHook):
-        async def emit_reasoning(self, reasoning_content: str | None) -> None:
-            if reasoning_content:
-                events.append(("reasoning", reasoning_content))
-
-        async def emit_reasoning_end(self) -> None:
-            events.append(("reasoning_end", None))
-
-    real_wait_for = asyncio.wait_for
-
-    async def fake_wait_for(coro, *, timeout):
-        assert timeout == 300.0
-        return await real_wait_for(coro, timeout=0.01)
-
-    runner = AgentRunner()
-    with patch("nanobot.agent.runner.asyncio.wait_for", fake_wait_for):
-        result = await runner.run(make_run_spec(provider,
-            initial_messages=[{"role": "user", "content": "think forever"}],
-            tools=tools,
-            model="test-model",
-            max_iterations=1,
-            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-            hook=ProgressReasoningHook(),
-            progress_callback=AsyncMock(),
-            llm_timeout_s=1,
-        ))
-
-    assert result.stop_reason == "error"
-    assert result.final_content == "Error calling LLM: timed out after 300s"
-    assert events == [
-        ("reasoning", "working..."),
-        ("provider_cancelled", None),
-        ("reasoning_end", None),
-    ]
-    provider.chat_with_retry.assert_not_awaited()
-
-
 @pytest.mark.asyncio
 async def test_runner_replaces_empty_tool_result_with_marker():
     from nanobot.agent.runner import AgentRunner
@@ -1285,13 +1227,8 @@ async def test_runner_accumulates_usage_and_preserves_cache_reads():
 
 
 @pytest.mark.asyncio
-async def test_runner_binds_on_retry_wait_to_retry_callback_not_progress():
+async def test_runner_binds_on_retry_wait_callback():
-    """Regression: provider retry heartbeats must route through
+    """Provider retry heartbeats use the explicitly supplied callback."""
-    ``retry_wait_callback``, not ``progress_callback``. Binding them to
-    the progress callback (as an earlier runtime refactor did) caused
-    internal retry diagnostics like "Model request failed, retry in 1s"
-    to leak to end-user channels as normal progress updates.
-    """
     from nanobot.agent.runner import AgentRunner
 
     captured: dict = {}
@@ -1305,7 +1242,6 @@ async def test_runner_binds_on_retry_wait_to_retry_callback_not_progress():
     tools = MagicMock()
     tools.get_definitions.return_value = []
 
-    progress_cb = AsyncMock()
     retry_wait_cb = AsyncMock()
 
     runner = AgentRunner()
@@ -1318,12 +1254,10 @@ async def test_runner_binds_on_retry_wait_to_retry_callback_not_progress():
         model="test-model",
         max_iterations=1,
         max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-        progress_callback=progress_cb,
         retry_wait_callback=retry_wait_cb,
     ))
 
     assert captured["on_retry_wait"] is retry_wait_cb
-    assert captured["on_retry_wait"] is not progress_cb
 
 
 # ---------------------------------------------------------------------------

tests/agent/test_runner_progress_deltas.py

@@ -1,4 +1,4 @@
-"""Tests for provider progress delta routing in the shared runner."""
+"""Tests for runner progress hooks and provider event routing."""
 
 import asyncio
 from unittest.mock import AsyncMock, MagicMock
@@ -6,7 +6,6 @@ from unittest.mock import AsyncMock, MagicMock
 import pytest
 
 from agent.runner_helpers import make_run_spec
-from nanobot.agent.hook import CompositeHook
 from nanobot.agent.hooks import FileEditActivityHook
 from nanobot.agent.progress_hook import AgentProgressHook
 from nanobot.agent.runner import AgentRunner
@@ -17,45 +16,9 @@ from nanobot.providers.base import LLMResponse, ToolCallRequest
 _MAX_TOOL_RESULT_CHARS = AgentDefaults().max_tool_result_chars
 
 
-@pytest.mark.asyncio
-async def test_runner_streams_provider_progress_deltas_by_default():
-    """Direct runner users keep the existing opt-in provider progress behavior."""
-    provider = MagicMock()
-    provider.supports_progress_deltas = True
-
-    async def chat_stream_with_retry(*, on_content_delta, **kwargs):
-        await on_content_delta("he")
-        await on_content_delta("llo")
-        return LLMResponse(content="hello", tool_calls=[], usage=None)
-
-    provider.chat_stream_with_retry = chat_stream_with_retry
-    provider.chat_with_retry = AsyncMock()
-    tools = MagicMock()
-    tools.get_definitions.return_value = []
-    progress_cb = AsyncMock()
-
-    runner = AgentRunner()
-    result = await runner.run(make_run_spec(provider,
-        initial_messages=[
-            {"role": "system", "content": "system"},
-            {"role": "user", "content": "hi"},
-        ],
-        tools=tools,
-        model="test-model",
-        max_iterations=1,
-        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-        progress_callback=progress_cb,
-    ))
-
-    assert result.final_content == "hello"
-    assert [call.args[0] for call in progress_cb.await_args_list] == ["he", "llo"]
-    provider.chat_with_retry.assert_not_awaited()
-
-
 @pytest.mark.asyncio
 async def test_runner_routes_hosted_tool_events_to_structured_progress():
     provider = MagicMock()
-    provider.supports_progress_deltas = True
 
     async def chat_stream_with_retry(*, on_content_delta, on_tool_call_delta, **kwargs):
         await on_tool_call_delta({
@@ -88,13 +51,17 @@ async def test_runner_routes_hosted_tool_events_to_structured_progress():
     tools.get_definitions.return_value = []
     progress_events: list[dict] = []
     progress_text: list[str] = []
+    streamed_text: list[str] = []
 
     async def progress_cb(content, *, tool_events=None, **kwargs):
         progress_text.append(content)
         if tool_events:
             progress_events.extend(tool_events)
 
-    hook = CompositeHook([AgentProgressHook(on_progress=progress_cb)])
+    async def stream_cb(content: str) -> None:
+        streamed_text.append(content)
+
+    hook = AgentProgressHook(on_progress=progress_cb, on_stream=stream_cb)
     result = await AgentRunner().run(make_run_spec(
         provider,
         initial_messages=[{"role": "user", "content": "search X"}],
@@ -102,7 +69,6 @@ async def test_runner_routes_hosted_tool_events_to_structured_progress():
         model="test-model",
         max_iterations=1,
         max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-        progress_callback=progress_cb,
         hook=hook,
     ))
 
@@ -133,14 +99,14 @@ async def test_runner_routes_hosted_tool_events_to_structured_progress():
             "embeds": [],
         },
     ]
-    assert progress_text == ['search X "nanobot oauth"', "", "done"]
+    assert progress_text == ['search X "nanobot oauth"', ""]
+    assert streamed_text == ["done"]
     provider.chat_with_retry.assert_not_awaited()
 
 
 @pytest.mark.asyncio
 async def test_runner_fails_pending_hosted_tool_when_model_request_fails():
     provider = MagicMock()
-    provider.supports_progress_deltas = True
 
     async def chat_stream_with_retry(*, on_tool_call_delta, **kwargs):
         await on_tool_call_delta({
@@ -166,7 +132,10 @@ async def test_runner_fails_pending_hosted_tool_when_model_request_fails():
         if tool_events:
             progress_events.extend(tool_events)
 
-    hook = CompositeHook([AgentProgressHook(on_progress=progress_cb)])
+    async def stream_cb(_content: str) -> None:
+        pass
+
+    hook = AgentProgressHook(on_progress=progress_cb, on_stream=stream_cb)
     result = await AgentRunner().run(make_run_spec(
         provider,
         initial_messages=[{"role": "user", "content": "search X"}],
@@ -174,7 +143,6 @@ async def test_runner_fails_pending_hosted_tool_when_model_request_fails():
         model="test-model",
         max_iterations=1,
         max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-        progress_callback=progress_cb,
         hook=hook,
     ))
 
@@ -200,7 +168,6 @@ async def test_runner_fails_pending_hosted_tool_when_model_request_fails():
 @pytest.mark.asyncio
 async def test_runner_emits_write_file_diff_from_tool_execution_snapshots(tmp_path):
     provider = MagicMock()
-    provider.supports_progress_deltas = True
     call_count = 0
     progress_events: list[dict] = []
     (tmp_path / "big.txt").write_text("old\n", encoding="utf-8")
@@ -218,7 +185,7 @@ async def test_runner_emits_write_file_diff_from_tool_execution_snapshots(tmp_pa
         def prepare_call(self, name, params):
             return tool, params, None
 
-    async def chat_stream_with_retry(**kwargs):
+    async def chat_with_retry(**kwargs):
         nonlocal call_count
         call_count += 1
         if call_count == 1:
@@ -235,8 +202,7 @@ async def test_runner_emits_write_file_diff_from_tool_execution_snapshots(tmp_pa
             )
         return LLMResponse(content="done", tool_calls=[], usage=None)
 
-    provider.chat_stream_with_retry = chat_stream_with_retry
+    provider.chat_with_retry = chat_with_retry
-    provider.chat_with_retry = AsyncMock()
     tools = Tools()
 
     runner = AgentRunner()
@@ -246,7 +212,6 @@ async def test_runner_emits_write_file_diff_from_tool_execution_snapshots(tmp_pa
         model="test-model",
         max_iterations=2,
         max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-        progress_callback=progress_cb,
         workspace=tmp_path,
         hook=FileEditActivityHook(on_progress=progress_cb, workspace=tmp_path),
     ))
@@ -263,13 +228,11 @@ async def test_runner_emits_write_file_diff_from_tool_execution_snapshots(tmp_pa
         and event["diff"]["format"] == "unified"
         for event in progress_events
     )
-    provider.chat_with_retry.assert_not_awaited()
 
 
 @pytest.mark.asyncio
 async def test_runner_emits_edit_file_diff_from_tool_execution_snapshots(tmp_path):
     provider = MagicMock()
-    provider.supports_progress_deltas = True
     call_count = 0
     progress_events: list[dict] = []
     target = tmp_path / "notes.txt"
@@ -288,7 +251,7 @@ async def test_runner_emits_edit_file_diff_from_tool_execution_snapshots(tmp_pat
         def prepare_call(self, name, params):
             return tool, params, None
 
-    async def chat_stream_with_retry(**kwargs):
+    async def chat_with_retry(**kwargs):
         nonlocal call_count
         call_count += 1
         if call_count == 1:
@@ -309,8 +272,7 @@ async def test_runner_emits_edit_file_diff_from_tool_execution_snapshots(tmp_pat
             )
         return LLMResponse(content="done", tool_calls=[], usage=None)
 
-    provider.chat_stream_with_retry = chat_stream_with_retry
+    provider.chat_with_retry = chat_with_retry
-    provider.chat_with_retry = AsyncMock()
     tools = Tools()
 
     runner = AgentRunner()
@@ -320,7 +282,6 @@ async def test_runner_emits_edit_file_diff_from_tool_execution_snapshots(tmp_pat
         model="test-model",
         max_iterations=2,
         max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-        progress_callback=progress_cb,
         workspace=tmp_path,
         hook=FileEditActivityHook(on_progress=progress_cb, workspace=tmp_path),
     ))
@@ -335,13 +296,11 @@ async def test_runner_emits_edit_file_diff_from_tool_execution_snapshots(tmp_pat
         and event["diff"]["format"] == "unified"
         for event in progress_events
     )
-    provider.chat_with_retry.assert_not_awaited()
 
 
 @pytest.mark.asyncio
 async def test_runner_marks_file_edit_activity_failed_when_tool_errors(tmp_path):
     provider = MagicMock()
-    provider.supports_progress_deltas = True
     call_count = 0
     progress_events: list[dict] = []
 
@@ -358,7 +317,7 @@ async def test_runner_marks_file_edit_activity_failed_when_tool_errors(tmp_path)
         def prepare_call(self, name, params):
             return tool, params, None
 
-    async def chat_stream_with_retry(**kwargs):
+    async def chat_with_retry(**kwargs):
         nonlocal call_count
         call_count += 1
         if call_count == 1:
@@ -375,8 +334,7 @@ async def test_runner_marks_file_edit_activity_failed_when_tool_errors(tmp_path)
             )
         return LLMResponse(content="done", tool_calls=[], usage=None)
 
-    provider.chat_stream_with_retry = chat_stream_with_retry
+    provider.chat_with_retry = chat_with_retry
-    provider.chat_with_retry = AsyncMock()
     tools = Tools()
 
     runner = AgentRunner()
@@ -386,7 +344,6 @@ async def test_runner_marks_file_edit_activity_failed_when_tool_errors(tmp_path)
         model="test-model",
         max_iterations=2,
         max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-        progress_callback=progress_cb,
         workspace=tmp_path,
         hook=FileEditActivityHook(on_progress=progress_cb, workspace=tmp_path),
     ))
@@ -395,13 +352,11 @@ async def test_runner_marks_file_edit_activity_failed_when_tool_errors(tmp_path)
     assert progress_events[-1]["path"] == "aborted.txt"
     assert progress_events[-1]["phase"] == "error"
     assert progress_events[-1]["status"] == "error"
-    provider.chat_with_retry.assert_not_awaited()
 
 
 @pytest.mark.asyncio
 async def test_runner_marks_file_edit_activity_failed_when_cancelled(tmp_path):
     provider = MagicMock()
-    provider.supports_progress_deltas = True
     progress_events: list[dict] = []
     executing = asyncio.Event()
     target = tmp_path / "cancelled.txt"
@@ -426,7 +381,7 @@ async def test_runner_marks_file_edit_activity_failed_when_cancelled(tmp_path):
         def prepare_call(self, name, params):
             return tool, params, None
 
-    async def chat_stream_with_retry(**kwargs):
+    async def chat_with_retry(**kwargs):
         return LLMResponse(
             content=None,
             tool_calls=[
@@ -439,8 +394,7 @@ async def test_runner_marks_file_edit_activity_failed_when_cancelled(tmp_path):
             usage=None,
         )
 
-    provider.chat_stream_with_retry = chat_stream_with_retry
+    provider.chat_with_retry = chat_with_retry
-    provider.chat_with_retry = AsyncMock()
     tools = Tools()
 
     runner = AgentRunner()
@@ -450,7 +404,6 @@ async def test_runner_marks_file_edit_activity_failed_when_cancelled(tmp_path):
         model="test-model",
         max_iterations=2,
         max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-        progress_callback=progress_cb,
         workspace=tmp_path,
         hook=FileEditActivityHook(on_progress=progress_cb, workspace=tmp_path),
     )))
@@ -464,4 +417,3 @@ async def test_runner_marks_file_edit_activity_failed_when_cancelled(tmp_path):
     assert progress_events[-1]["path"] == "cancelled.txt"
     assert progress_events[-1]["status"] == "error"
     assert progress_events[-1]["error"] == "Task interrupted before this tool finished."
-    provider.chat_with_retry.assert_not_awaited()

tests/agent/test_runner_reasoning.py

@@ -15,6 +15,7 @@ import pytest
 
 from agent.runner_helpers import make_run_spec
 from nanobot.agent.hook import AgentHook, AgentHookContext
+from nanobot.agent.progress_hook import AgentProgressHook
 from nanobot.config.schema import AgentDefaults
 from nanobot.providers.base import LLMResponse, LLMUsage, ToolCallRequest
 
@@ -35,6 +36,18 @@ class _RecordingHook(AgentHook):
         self.end_calls += 1
 
 
+class _StreamRecordingHook(_RecordingHook):
+    def __init__(self) -> None:
+        super().__init__()
+        self.streamed: list[str] = []
+
+    def wants_streaming(self) -> bool:
+        return True
+
+    async def on_stream(self, _ctx: AgentHookContext, delta: str) -> None:
+        self.streamed.append(delta)
+
+
 @pytest.mark.asyncio
 async def test_runner_preserves_reasoning_fields_in_assistant_history():
     """Reasoning fields ride along on the persisted assistant message so
@@ -201,7 +214,6 @@ async def test_runner_emits_reasoning_content_even_when_answer_was_streamed():
     from nanobot.agent.runner import AgentRunner
 
     provider = MagicMock()
-    provider.supports_progress_deltas = True
 
     async def chat_stream_with_retry(*, on_content_delta=None, **kwargs):
         if on_content_delta:
@@ -218,12 +230,7 @@ async def test_runner_emits_reasoning_content_even_when_answer_was_streamed():
     tools = MagicMock()
     tools.get_definitions.return_value = []
 
-    progress_calls: list[str] = []
+    hook = _StreamRecordingHook()
-
-    async def _progress(content: str, **_kwargs):
-        progress_calls.append(content)
-
-    hook = _RecordingHook()
     runner = AgentRunner()
     result = await runner.run(make_run_spec(provider,
         initial_messages=[{"role": "user", "content": "question"}],
@@ -232,11 +239,10 @@ async def test_runner_emits_reasoning_content_even_when_answer_was_streamed():
         max_iterations=3,
         max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
         hook=hook,
-        progress_callback=_progress,
     ))
 
     assert result.final_content == "The answer."
-    assert progress_calls, "answer should have streamed via progress callback"
+    assert hook.streamed == ["The ", "answer."]
     assert hook.emitted == ["step-by-step deduction"]
 
 
@@ -247,7 +253,6 @@ async def test_runner_does_not_double_emit_when_inline_think_already_streamed():
     from nanobot.agent.runner import AgentRunner
 
     provider = MagicMock()
-    provider.supports_progress_deltas = True
 
     async def chat_stream_with_retry(*, on_content_delta=None, **kwargs):
         if on_content_delta:
@@ -263,10 +268,16 @@ async def test_runner_does_not_double_emit_when_inline_think_already_streamed():
     tools = MagicMock()
     tools.get_definitions.return_value = []
 
-    async def _progress(content: str, **_kwargs):
+    reasoning_events: list[str] = []
+
+    async def _progress(content: str, *, reasoning: bool = False, **_kwargs):
+        if reasoning:
+            reasoning_events.append(content)
+
+    async def _stream(_content: str) -> None:
         pass
 
-    hook = _RecordingHook()
+    hook = AgentProgressHook(on_progress=_progress, on_stream=_stream)
     runner = AgentRunner()
     result = await runner.run(make_run_spec(provider,
         initial_messages=[{"role": "user", "content": "question"}],
@@ -275,12 +286,10 @@ async def test_runner_does_not_double_emit_when_inline_think_already_streamed():
         max_iterations=3,
         max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
         hook=hook,
-        progress_callback=_progress,
     ))
 
     assert result.final_content == "The answer."
-    assert hook.emitted == ["working..."]
+    assert reasoning_events == ["working..."]
-    assert hook.end_calls >= 1, "reasoning stream must be closed once the answer starts"
 
 
 @pytest.mark.asyncio
@@ -320,14 +329,6 @@ async def test_runner_closes_reasoning_stream_after_one_shot_response():
     assert hook.end_calls == 1
 
 
-class _StreamRecordingHook(_RecordingHook):
-    def wants_streaming(self) -> bool:
-        return True
-
-    async def on_stream(self, _ctx: AgentHookContext, delta: str) -> None:
-        pass
-
-
 @pytest.mark.asyncio
 async def test_runner_streams_native_thinking_deltas_without_post_hoc_dup():
     """Anthropic-style ``on_thinking_delta`` should fan out to ``emit_reasoning``;

tests/providers/test_providers_init.py

@@ -63,9 +63,3 @@ def test_explicit_provider_import_still_works(monkeypatch) -> None:
     finally:
         monkeypatch.undo()
         setattr(sys.modules["nanobot"], "providers", original_package)
-
-
-def test_openai_codex_supports_progress_deltas() -> None:
-    from nanobot.providers.openai_codex_provider import OpenAICodexProvider
-
-    assert OpenAICodexProvider.supports_progress_deltas is True