Commit Graph
12 Commits
Author SHA1 Message Date
chengyongruandXubin Ren 8933da1ec5 fix: harden run-level hook lifecycle
maintainer edit: keep cancellation out of on_error so shutdown paths do not look like run failures, and let the SDK capture hook use the authoritative after_run snapshot.
2026-06-05 01:09:45 +08:00
chengyongruandXubin Ren 2ea226055e feat: add run-level agent hook lifecycle 2026-06-05 01:09:45 +08:00
Xubin RenandCursor 458b4ba235 feat(reasoning): stream reasoning content as a first-class channel
Reasoning now flows as its own stream — symmetric to the answer's
``delta`` / ``stream_end`` pair — instead of being shipped as one
oversized progress message. This lets WebUI render a live "Thinking…"
bubble that updates in place, then auto-collapses when the stream
closes. Other channels remain plugin no-ops by default.

## Protocol

New metadata: ``_reasoning_delta`` (chunk) and ``_reasoning_end``
(close marker). ChannelManager routes both to the dedicated plugin
hooks below; the legacy one-shot ``_reasoning`` is kept for back-compat
and BaseChannel expands it into a single delta + end pair so plugins
only ever implement the streaming primitives.

WebSocket emits two new events:

- ``reasoning_delta`` (event, chat_id, text, optional stream_id)
- ``reasoning_end`` (event, chat_id, optional stream_id)

## BaseChannel surface

- ``send_reasoning_delta(chat_id, delta, metadata)`` — no-op default
- ``send_reasoning_end(chat_id, metadata)`` — no-op default
- ``send_reasoning(msg)`` — back-compat wrapper, base impl forwards
  to the streaming primitives

A channel adds reasoning support by overriding the two streaming
primitives. Telegram / Slack / Discord / Feishu / WeChat / Matrix keep
the base no-ops until their bubble UIs are adapted; reasoning silently
drops at dispatch, never as a stray text message.

## AgentHook

Adds ``emit_reasoning_end`` to the hook lifecycle. ``_LoopHook`` tracks
whether a reasoning segment is open and closes it on:

- the first answer delta arriving (so the UI locks the bubble before
  the answer renders below),
- ``on_stream_end``,
- one-shot ``reasoning_content`` / ``thinking_blocks`` after a single
  non-streaming response.

## WebUI

- ``UIMessage.reasoning`` is now a single accumulated string with a
  companion ``reasoningStreaming`` flag.
- ``useNanobotStream`` consumes ``reasoning_delta`` / ``reasoning_end``;
  legacy ``kind: "reasoning"`` is auto-translated to a delta + end.
- New ``ReasoningBubble``: shimmer header + auto-expanded while
  streaming, collapses to a clickable "Thinking" pill once closed,
  respects ``prefers-reduced-motion``.
- Answer deltas adopt the reasoning placeholder so the bubble and the
  answer share one assistant row.

## Tests

- ``tests/channels/test_channel_manager_reasoning.py`` — manager routes
  delta + end, drops on channel opt-out, expands one-shot back-compat.
- ``tests/channels/test_websocket_channel.py`` — new ``reasoning_delta``
  / ``reasoning_end`` frames, empty-chunk safety, no-subscriber safety,
  back-compat expansion.
- ``tests/agent/test_runner_reasoning.py`` — runner closes the segment
  on streaming answer start and after one-shot reasoning.
- WebUI ``useNanobotStream`` + ``message-bubble`` cover the new
  protocol and the shimmer styling.

## Docs

``docs/configuration.md`` and ``docs/websocket.md`` document the new
events and the plugin contract.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-13 07:13:43 +00:00
Xubin RenandCursor 352aaf0627 refactor(reasoning): unify reasoning extraction across providers
Reasoning surfacing was split across three branches in runner.py plus
two separate streaming buffers (loop hook and runner progress stream),
with three independent display-side gates in the CLI. This collapsed
the policy into one source of truth and fixed two real bugs:

- Structured `reasoning_content` was suppressed whenever the answer was
  streamed, because the runner gated emission on `streamed_content`.
  Providers don't stream `reasoning_content`; it only arrives on the
  final response, so the answer stream and the reasoning channel are
  independent. Added `streamed_reasoning` to `AgentHookContext` to track
  the right bit.
- `channels.showReasoning` was subordinated to `sendProgress`. They are
  orthogonal — turning off progress streaming shouldn't silence
  reasoning. Reworked the CLI gates accordingly.

Single-helper consolidation:

- `extract_reasoning(reasoning_content, thinking_blocks, content)`
  returns `(reasoning_text, cleaned_content)` with a defined fallback
  order: dedicated field → Anthropic thinking_blocks → inline
  `<think>`/`<thought>` tags. Models that expose none of these
  short-circuit to `(None, content)` — zero overhead.
- `IncrementalThinkExtractor` replaces the ad-hoc `emit_incremental_think`
  function and its hand-rolled "emitted cursor" state in both the loop
  hook and the runner progress stream.

Also documented the new `showReasoning` channel option in
docs/configuration.md and noted its independence from sendProgress.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-12 17:14:19 +00:00
Flinn XieandClaude Opus 4.7 3a27af0018 feat(cli): display model reasoning content during streaming
Add show_reasoning config (default: False) to display model
thinking/reasoning content in the TUI during streaming.  Reasoning
is emitted via a new emit_reasoning hook on AgentHook, gated by the
channels config.  Display uses ✻ prefix with dim italic styling.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-11 01:02:49 +08:00
chengyongruandXubin Ren d97e177981 refactor(sdk): move SDKCaptureHook to agent/hook.py
Colocate the capture hook with the rest of the hook infrastructure
instead of inlining it in the top-level facade module.
2026-05-05 23:23:29 +08:00
hanyuanlingandXubin Ren ae14142a87 fix(codex): stream progress deltas to channels 2026-04-27 18:48:05 +08:00
Xubin RenandXubin Ren 6bf101c79b fix(hook): keep composite hooks backward compatible
Avoid AttributeError regressions when hooks define their own __init__ or when a CompositeHook wraps another composite.

Made-with: Cursor
2026-04-08 23:41:31 +08:00
Lingao MengandXubin Ren d88be08bfd refactor(hook): add reraise flag to AgentHook and remove _LoopHookChain
Add reraise parameter to AgentHook so hooks can opt out of exception
swallowing in CompositeHook._for_each_hook_safe. _LoopHook sets
reraise=True to let its exceptions propagate. _LoopHookChain is removed
and replaced with CompositeHook([loop_hook] + extra_hooks).

Signed-off-by: Lingao Meng <menglingao@xiaomi.com>
2026-04-08 23:41:31 +08:00
Jack LuandXubin Ren bcb8352235 refactor(agent): streamline hook method calls and enhance error logging
- Introduced a helper method `_for_each_hook_safe` to reduce code duplication in hook method implementations.
- Updated error logging to include the method name for better traceability.
- Improved the `SkillsLoader` class by adding a new method `_skill_entries_from_dir` to simplify skill listing logic.
- Enhanced skill loading and filtering logic, ensuring workspace skills take precedence over built-in ones.
- Added comprehensive tests for `SkillsLoader` to validate functionality and edge cases.
2026-04-06 02:51:10 +08:00
sontianyeandXubin Ren f08de72f18 feat(agent): add CompositeHook for composable lifecycle hooks
Introduce a CompositeHook that fans out lifecycle callbacks to an
ordered list of AgentHook instances with per-hook error isolation.
Extract the nested _LoopHook and _SubagentHook to module scope as
public LoopHook / SubagentHook so downstream users can subclass or
compose them.  Add `hooks` parameter to AgentLoop.__init__ for
registering custom hooks at construction time.

Closes #2603
2026-03-31 02:19:29 +08:00
Xubin RenandXubin Ren 5bf0f6fe7d refactor: unify agent runner lifecycle hooks 2026-03-27 12:41:17 +08:00