feat: gateway reasoning visibility modes#1214
Closed
raulvidis wants to merge 11 commits into
Closed
Conversation
- /reasoning now supports display modes (show/hide/stream) and effort levels (none/minimal/low/medium/high/xhigh) - Telegram inline keyboard shows all options in 3 rows with current status displayed above - "show" mode sends reasoning as a separate message after the response - "stream" mode streams reasoning live and auto-deletes (Telegram only) - "hide" mode enables reasoning at API level but doesn't display it - Effort levels set the reasoning budget without changing display mode - CLI reasoning callback is now a no-op (uses TUI spinner instead) - Fix: /reasoning effort changes no longer overwritten by config reload Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
teknium1
added a commit
that referenced
this pull request
Mar 16, 2026
… providers Stage 1 of streaming support. Adds: - stream_delta_callback parameter on AIAgent.__init__ for real-time token delivery - _interruptible_streaming_api_call() handling chat_completions + anthropic_messages - Enhanced _run_codex_stream() to fire delta callbacks during Codex streaming - _fire_stream_delta() fires both display and TTS callbacks - _fire_reasoning_delta() for reasoning content streaming - Tool-call suppression: callbacks only fire on text-only responses - on_first_delta callback for spinner control on first token - Provider fallback: graceful degradation to non-streaming - _has_stream_consumers() unifies stream_delta_callback and _stream_callback checks - Anthropic streaming returns native Message for downstream compatibility Drawing from PRs #922 (unified streaming), #1312 (gateway consumer), #774 (Telegram streaming), #798 (CLI streaming), #1214 (reasoning modes). Credit: jobless0x, OutThisLife, clicksingh, raulvidis.
4 tasks
teknium1
added a commit
that referenced
this pull request
Mar 16, 2026
…ment The streaming infrastructure already fires reasoning deltas via _fire_reasoning_delta() during streaming. The remaining work is the CLI display layer: a dim reasoning box that opens on first reasoning token, streams live, then transitions to the response box. Reference: PR #1214 (raulvidis) for gateway reasoning visibility.
Author
|
Closing — superseded by merged streaming infrastructure #1538 |
angelburgosrosado
pushed a commit
to angelburgosrosado/hermes-agent
that referenced
this pull request
Apr 27, 2026
… providers Stage 1 of streaming support. Adds: - stream_delta_callback parameter on AIAgent.__init__ for real-time token delivery - _interruptible_streaming_api_call() handling chat_completions + anthropic_messages - Enhanced _run_codex_stream() to fire delta callbacks during Codex streaming - _fire_stream_delta() fires both display and TTS callbacks - _fire_reasoning_delta() for reasoning content streaming - Tool-call suppression: callbacks only fire on text-only responses - on_first_delta callback for spinner control on first token - Provider fallback: graceful degradation to non-streaming - _has_stream_consumers() unifies stream_delta_callback and _stream_callback checks - Anthropic streaming returns native Message for downstream compatibility Drawing from PRs NousResearch#922 (unified streaming), NousResearch#1312 (gateway consumer), NousResearch#774 (Telegram streaming), NousResearch#798 (CLI streaming), NousResearch#1214 (reasoning modes). Credit: jobless0x, OutThisLife, clicksingh, raulvidis.
angelburgosrosado
pushed a commit
to angelburgosrosado/hermes-agent
that referenced
this pull request
Apr 27, 2026
…ment The streaming infrastructure already fires reasoning deltas via _fire_reasoning_delta() during streaming. The remaining work is the CLI display layer: a dim reasoning box that opens on first reasoning token, streams live, then transitions to the response box. Reference: PR NousResearch#1214 (raulvidis) for gateway reasoning visibility.
02356abc
pushed a commit
to 02356abc/hermes-agent
that referenced
this pull request
May 14, 2026
… providers Stage 1 of streaming support. Adds: - stream_delta_callback parameter on AIAgent.__init__ for real-time token delivery - _interruptible_streaming_api_call() handling chat_completions + anthropic_messages - Enhanced _run_codex_stream() to fire delta callbacks during Codex streaming - _fire_stream_delta() fires both display and TTS callbacks - _fire_reasoning_delta() for reasoning content streaming - Tool-call suppression: callbacks only fire on text-only responses - on_first_delta callback for spinner control on first token - Provider fallback: graceful degradation to non-streaming - _has_stream_consumers() unifies stream_delta_callback and _stream_callback checks - Anthropic streaming returns native Message for downstream compatibility Drawing from PRs NousResearch#922 (unified streaming), NousResearch#1312 (gateway consumer), NousResearch#774 (Telegram streaming), NousResearch#798 (CLI streaming), NousResearch#1214 (reasoning modes). Credit: jobless0x, OutThisLife, clicksingh, raulvidis.
02356abc
pushed a commit
to 02356abc/hermes-agent
that referenced
this pull request
May 14, 2026
…ment The streaming infrastructure already fires reasoning deltas via _fire_reasoning_delta() during streaming. The remaining work is the CLI display layer: a dim reasoning box that opens on first reasoning token, streams live, then transitions to the response box. Reference: PR NousResearch#1214 (raulvidis) for gateway reasoning visibility.
olympus-terminal
pushed a commit
to olympus-terminal/hermes-agent
that referenced
this pull request
May 16, 2026
… providers Stage 1 of streaming support. Adds: - stream_delta_callback parameter on AIAgent.__init__ for real-time token delivery - _interruptible_streaming_api_call() handling chat_completions + anthropic_messages - Enhanced _run_codex_stream() to fire delta callbacks during Codex streaming - _fire_stream_delta() fires both display and TTS callbacks - _fire_reasoning_delta() for reasoning content streaming - Tool-call suppression: callbacks only fire on text-only responses - on_first_delta callback for spinner control on first token - Provider fallback: graceful degradation to non-streaming - _has_stream_consumers() unifies stream_delta_callback and _stream_callback checks - Anthropic streaming returns native Message for downstream compatibility Drawing from PRs NousResearch#922 (unified streaming), NousResearch#1312 (gateway consumer), NousResearch#774 (Telegram streaming), NousResearch#798 (CLI streaming), NousResearch#1214 (reasoning modes). Credit: jobless0x, OutThisLife, clicksingh, raulvidis.
olympus-terminal
pushed a commit
to olympus-terminal/hermes-agent
that referenced
this pull request
May 16, 2026
…ment The streaming infrastructure already fires reasoning deltas via _fire_reasoning_delta() during streaming. The remaining work is the CLI display layer: a dim reasoning box that opens on first reasoning token, streams live, then transitions to the response box. Reference: PR NousResearch#1214 (raulvidis) for gateway reasoning visibility.
Egavasyug
pushed a commit
to Egavasyug/hermes-agent
that referenced
this pull request
Jun 10, 2026
… providers Stage 1 of streaming support. Adds: - stream_delta_callback parameter on AIAgent.__init__ for real-time token delivery - _interruptible_streaming_api_call() handling chat_completions + anthropic_messages - Enhanced _run_codex_stream() to fire delta callbacks during Codex streaming - _fire_stream_delta() fires both display and TTS callbacks - _fire_reasoning_delta() for reasoning content streaming - Tool-call suppression: callbacks only fire on text-only responses - on_first_delta callback for spinner control on first token - Provider fallback: graceful degradation to non-streaming - _has_stream_consumers() unifies stream_delta_callback and _stream_callback checks - Anthropic streaming returns native Message for downstream compatibility Drawing from PRs NousResearch#922 (unified streaming), NousResearch#1312 (gateway consumer), NousResearch#774 (Telegram streaming), NousResearch#798 (CLI streaming), NousResearch#1214 (reasoning modes). Credit: jobless0x, OutThisLife, clicksingh, raulvidis.
Egavasyug
pushed a commit
to Egavasyug/hermes-agent
that referenced
this pull request
Jun 10, 2026
…ment The streaming infrastructure already fires reasoning deltas via _fire_reasoning_delta() during streaming. The remaining work is the CLI display layer: a dim reasoning box that opens on first reasoning token, streams live, then transitions to the response box. Reference: PR NousResearch#1214 (raulvidis) for gateway reasoning visibility.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
/reasoning [off|on|stream]:offdisables reasoning at the provider level,onenables reasoning silently (for future use),streamshows live italicized reasoning previews that auto-delete when the final response arrives./reasoningwith no argument shows an Off / On / Stream button row; callback queries route through the gateway command handler.reasoning_callbackonAIAgentsurfaces reasoning deltas from both chat completions and Codex Responses API streams. Gateway consumes these via an async queue + background task that edits a single preview message.send_typingnow acceptsmetadataso typing indicators go to the correct forum thread.Changed files
run_agent.pyreasoning_callbackparam,_merge_stream_reasoning(),_run_streaming_chat_completion()for reasoning deltas,last_reasoningin result dictgateway/run.py/reasoningcommand handler,_resolve_session_reasoning_config(),send_reasoning_updates()background task,_format_reasoning_preview(),_delete_preview_message()gateway/platforms/telegram.pydelete_message(), inline keyboard for/reasoning,CallbackQueryHandler, "not modified" treated as success inedit_messagegateway/platforms/base.pydelete_message()base method,send_typing(metadata=)signature,_keep_typingmetadata forwardinggateway/session.pyreasoning_modefield onSessionEntry,set_reasoning_mode(), preserved across/resetNew test files
tests/gateway/test_reasoning_command.pytests/gateway/test_session.pytests/gateway/test_telegram_format.pytests/test_run_agent_reasoning_stream.pyTest plan
pytest tests/gateway/test_reasoning_command.py— 8/8 passpytest tests/gateway/test_session.py— 21/21 pass (including 3 new)pytest tests/gateway/test_telegram_format.py— 54/54 pass (including 1 new)pytest tests/test_run_agent_reasoning_stream.py— requires full dep install (firecrawl)/reasoning streamon Telegram shows italic preview that deletes on completion/reasoning offdisables provider-level reasoning🤖 Generated with Claude Code