Skip to content

feat(agent-server): Conversation reactions, the first experimental feature - #6609

Merged
enyst merged 31 commits into
mainfrom
claude/project-thread-hb0du7
Nov 12, 2026
Merged

enyst merged 31 commits into
mainfrom
claude/project-thread-hb0du7

Conversation

@enyst

@enyst enyst commented Nov 7, 2026 •

Copy link
Copy Markdown
Member

HUMAN:

wait, i didnt mean to answer that react/unreact question. i meant to answer differently to should every OH agent get react and unreact tools: i think it would be nice to make a feature flag system, and add there our first feature under yes/no from the user: Conversation reactions.

then maybe we get to merge that before the full Projects.

and it would be on all conversations


AGENT:

Why

Conversation reactions is the first experimental feature a user can turn on: the agent can put an emoji on a message (for example 👀 when the work comes before the answer), and the person can react to the agent's messages. The switches themselves were merged in #6759; this PR is reactions on top of them, and nothing else.

Summary

  • The feature (conversation_reactions, off by default), registered in openhands.agent_server.experimental_features. While it is on, every new OpenHands-agent conversation gets react/unreact through finalize(experimental_feature_tools=...). ACP agents are left as they are. While it is off, POST /api/conversations/{id}/reactions answers 409. Turning it off does not take the tools from conversations started while it was on.
  • Reactions themselves: the ReactionEvent (target_event_id, emoji, removed, source), the react/unreact tools in openhands.tools.reaction, the Observation.follow_up_events() hook, LocalConversation.react, and the REST route. The agent sees the person's reactions on its next turn, as one line naming the emoji and the end of the message; its own reactions are not repeated to it.
  • Docker runtime: the host passes its switches to each container in OH_RUNTIME_EXPERIMENTAL_FEATURES and checks the reactions route itself before forwarding.
  • TypeScript client: ReactionEvent, isReactionEvent, ConversationClient.react.

Changes after a fresh review (2026-11-11)

  • Fixed: a reaction during a pending tool call. A person's reaction posted while a tool call waited for confirmation sat between the call and its result. LLM APIs reject that history: live with deepseek-flash the provider refused it, the SDK condensed to recover, and the agent ran an earlier command again. The conversation now holds such a reaction back (in memory) and emits it once every open call has its result, so the event log itself is always in a valid order and View reorders nothing. The route still answers 200 with the event at once; a server restart during the wait drops a held reaction.
  • react and unreact are no longer offered as selectable tools in agent settings (user_selectable = False); the feature gives them.
  • execute_tool is back to what it is on main: it returns the observation and records nothing. The deferral queue this PR had added to the run loop had no caller.
  • A ReactionEvent's source must be the agent or the user.
  • The feature shape follows feat(agent-server): experimental features the user can turn on or off #6759: a plain string key and no default field.

REST API contract changes

Compared with base OpenAPI 56d559f66ac0 for public /api/** paths.

--- base public OpenAPI
+++ head public OpenAPI
@@ -130,0 +131 @@
+operation POST /api/conversations/{conversation_id}/reactions operationId=react_to_message_api_conversations__conversation_id__reactions_post
@@ -352,0 +354 @@
+parameter POST /api/conversations/{conversation_id}/reactions path:conversation_id required=true schema=type="string" format="uuid"
@@ -411,0 +414 @@
+requestBody POST /api/conversations/{conversation_id}/reactions application/json required=true schema=ReactionRequest
@@ -737,0 +741,5 @@
+response POST /api/conversations/{conversation_id}/reactions 200 application/json schema=ReactionEvent
+response POST /api/conversations/{conversation_id}/reactions 400 no-content
+response POST /api/conversations/{conversation_id}/reactions 404 no-content
+response POST /api/conversations/{conversation_id}/reactions 409 no-content
+response POST /api/conversations/{conversation_id}/reactions 422 application/json schema=HTTPValidationError
@@ -1013 +1021 @@
-schema Action oneOf=[MCPToolAction,ClassifyAndSwitchLLMAction,FinishAction,InvokeSkillAction,SwitchLLMAction,ThinkAction,VisionInspectAction,AskOracleAction,BrowserAction,BrowserClickAction,BrowserCloseTabAction,BrowserGetContentAction,BrowserGetStateAction,BrowserGetStorageAction,BrowserGoBackAction,BrowserListTabsAction,BrowserNavigateAction,BrowserScrollAction,BrowserSetStorageAction,BrowserStartRecordingAction,BrowserStopRecordingAction,BrowserSwitchTabAction,BrowserTypeAction,StartChildConversationAction,DelegateAction,FileEditorAction,EditAction,ListDirectoryAction,ReadFileAction,WriteFileAction,GlobAction,GrepAction,PlanningFileEditorAction,TaskAction,TaskTrackerAction,TerminalAction,WorkflowAction]
+schema Action oneOf=[MCPToolAction,ClassifyAndSwitchLLMAction,FinishAction,InvokeSkillAction,SwitchLLMAction,ThinkAction,VisionInspectAction,AskOracleAction,BrowserAction,BrowserClickAction,BrowserCloseTabAction,BrowserGetContentAction,BrowserGetStateAction,BrowserGetStorageAction,BrowserGoBackAction,BrowserListTabsAction,BrowserNavigateAction,BrowserScrollAction,BrowserSetStorageAction,BrowserStartRecordingAction,BrowserStopRecordingAction,BrowserSwitchTabAction,BrowserTypeAction,StartChildConversationAction,DelegateAction,FileEditorAction,EditAction,ListDirectoryAction,ReadFileAction,WriteFileAction,GlobAction,GrepAction,PlanningFileEditorAction,ReactAction,UnreactAction,TaskAction,TaskTrackerAction,TerminalAction,WorkflowAction]
@@ -1707 +1715 @@
-schema Event oneOf=[ServerErrorEvent,ACPToolCallEvent,Condensation,CondensationRequest,CondensationSummaryEvent,ConversationErrorEvent,ConversationStateUpdateEvent,HookExecutionEvent,LLMCompletionLogEvent,ActionEvent,MessageEvent,AgentErrorEvent,ObservationEvent,UserRejectObservation,SystemPromptEvent,SecurityAnalysisEvent,StreamingDeltaEvent,TokenEvent,InterruptEvent,PauseEvent]
+schema Event oneOf=[ServerErrorEvent,ACPToolCallEvent,Condensation,CondensationRequest,CondensationSummaryEvent,ConversationErrorEvent,ConversationStateUpdateEvent,HookExecutionEvent,LLMCompletionLogEvent,ActionEvent,MessageEvent,AgentErrorEvent,ObservationEvent,UserRejectObservation,SystemPromptEvent,ReactionEvent,SecurityAnalysisEvent,StreamingDeltaEvent,TokenEvent,InterruptEvent,PauseEvent]
@@ -2544 +2552 @@
-schema Observation oneOf=[MCPToolObservation,ClassifyAndSwitchLLMObservation,FinishObservation,InvokeSkillObservation,SwitchLLMObservation,ThinkObservation,VisionInspectObservation,ClientToolObservation,AskOracleObservation,BrowserObservation,StartChildConversationObservation,DelegateObservation,FileEditorObservation,EditObservation,ListDirectoryObservation,ReadFileObservation,WriteFileObservation,GlobObservation,GrepObservation,PlanningFileEditorObservation,TaskObservation,TaskTrackerObservation,TerminalObservation,WorkflowObservation]
+schema Observation oneOf=[MCPToolObservation,ClassifyAndSwitchLLMObservation,FinishObservation,InvokeSkillObservation,SwitchLLMObservation,ThinkObservation,VisionInspectObservation,ClientToolObservation,AskOracleObservation,BrowserObservation,StartChildConversationObservation,DelegateObservation,FileEditorObservation,EditObservation,ListDirectoryObservation,ReadFileObservation,WriteFileObservation,GlobObservation,GrepObservation,PlanningFileEditorObservation,ReactionObservation,TaskObservation,TaskTrackerObservation,TerminalObservation,WorkflowObservation]
@@ -2711,0 +2720,34 @@
+schema ReactAction property emoji required schema=type="string" enum=["eyes","+1","white_check_mark","tada","thinking_face","heart"]
+schema ReactAction property kind required schema=type="string" const="ReactAction"
+schema ReactAction property message_id optional schema=anyOf=[type="string",type="null"]
+schema ReactAction type="object" additionalProperties=false
+schema ReactTool property action_type required schema=type="string"
+schema ReactTool property annotations optional schema=anyOf=[openhands__sdk__tool__tool__ToolAnnotations,type="null"]
+schema ReactTool property description required schema=type="string"
+schema ReactTool property kind required schema=type="string" const="ReactTool"
+schema ReactTool property meta optional schema=anyOf=[type="object" additionalProperties=true,type="null"]
+schema ReactTool property observation_type optional schema=anyOf=[type="string",type="null"]
+schema ReactTool property title required schema=type="string"
+schema ReactTool type="object"
+schema ReactionEvent property emoji required schema=type="string" enum=["eyes","+1","white_check_mark","tada","thinking_face","heart"]
+schema ReactionEvent property id optional schema=type="string"
+schema ReactionEvent property kind required schema=type="string" const="ReactionEvent"
+schema ReactionEvent property parent_id optional schema=anyOf=[type="string",type="null"]
+schema ReactionEvent property removed optional schema=type="boolean" default=false
+schema ReactionEvent property source optional schema=type="string" enum=["agent","user","environment","hook"] default="user"
+schema ReactionEvent property target_event_id required schema=type="string"
+schema ReactionEvent property target_text_clipped optional schema=type="boolean" default=false
+schema ReactionEvent property target_text_ending optional schema=anyOf=[type="string",type="null"]
+schema ReactionEvent property timestamp optional schema=type="string"
+schema ReactionEvent type="object" additionalProperties=false
+schema ReactionObservation property content optional schema=type="array" items=anyOf=[TextContent,ImageContent]
+schema ReactionObservation property emoji optional schema=anyOf=[type="string" enum=["eyes","+1","white_check_mark","tada","thinking_face","heart"],type="null"]
+schema ReactionObservation property is_error optional schema=type="boolean" default=false
+schema ReactionObservation property kind required schema=type="string" const="ReactionObservation"
+schema ReactionObservation property removed optional schema=type="boolean" default=false
+schema ReactionObservation property target_event_id optional schema=anyOf=[type="string",type="null"]
+schema ReactionObservation type="object" additionalProperties=false
+schema ReactionRequest property emoji required schema=type="string" enum=["eyes","+1","white_check_mark","tada","thinking_face","heart"]
+schema ReactionRequest property removed optional schema=type="boolean" default=false
+schema ReactionRequest property target_event_id optional schema=anyOf=[type="string",type="null"]
+schema ReactionRequest type="object"
@@ -3242 +3284 @@
-schema ToolDefinition oneOf=[MCPToolDefinition,ClassifyAndSwitchLLMTool,FinishTool,InvokeSkillTool,SwitchLLMTool,ThinkTool,VisionInspectTool,ClientTool,AskOracleTool,BrowserClickTool,BrowserCloseTabTool,BrowserGetContentTool,BrowserGetStateTool,BrowserGetStorageTool,BrowserGoBackTool,BrowserListTabsTool,BrowserNavigateTool,BrowserScrollTool,BrowserSetStorageTool,BrowserStartRecordingTool,BrowserStopRecordingTool,BrowserSwitchTabTool,BrowserToolSet,BrowserTypeTool,StartChildConversationTool,FileEditorTool,EditTool,ListDirectoryTool,ReadFileTool,WriteFileTool,GlobTool,GrepTool,PlanningFileEditorTool,TaskTool,TaskToolSet,TaskTrackerTool,TerminalTool,WorkflowTool,WorkflowToolSet]
+schema ToolDefinition oneOf=[MCPToolDefinition,ClassifyAndSwitchLLMTool,FinishTool,InvokeSkillTool,SwitchLLMTool,ThinkTool,VisionInspectTool,ClientTool,AskOracleTool,BrowserClickTool,BrowserCloseTabTool,BrowserGetContentTool,BrowserGetStateTool,BrowserGetStorageTool,BrowserGoBackTool,BrowserListTabsTool,BrowserNavigateTool,BrowserScrollTool,BrowserSetStorageTool,BrowserStartRecordingTool,BrowserStopRecordingTool,BrowserSwitchTabTool,BrowserToolSet,BrowserTypeTool,StartChildConversationTool,FileEditorTool,EditTool,ListDirectoryTool,ReadFileTool,WriteFileTool,GlobTool,GrepTool,PlanningFileEditorTool,ReactTool,UnreactTool,TaskTool,TaskToolSet,TaskTrackerTool,TerminalTool,WorkflowTool,WorkflowToolSet]
@@ -3264,0 +3307,12 @@
+schema UnreactAction property emoji required schema=type="string" enum=["eyes","+1","white_check_mark","tada","thinking_face","heart"]
+schema UnreactAction property kind required schema=type="string" const="UnreactAction"
+schema UnreactAction property message_id optional schema=anyOf=[type="string",type="null"]
+schema UnreactAction type="object" additionalProperties=false
+schema UnreactTool property action_type required schema=type="string"
+schema UnreactTool property annotations optional schema=anyOf=[openhands__sdk__tool__tool__ToolAnnotations,type="null"]
+schema UnreactTool property description required schema=type="string"
+schema UnreactTool property kind required schema=type="string" const="UnreactTool"
+schema UnreactTool property meta optional schema=anyOf=[type="object" additionalProperties=true,type="null"]
+schema UnreactTool property observation_type optional schema=anyOf=[type="string",type="null"]
+schema UnreactTool property title required schema=type="string"
+schema UnreactTool type="object"

Issue Number

Closes #6621

How to Test

  • uv run pytest tests/tools/reaction tests/agent_server/test_experimental_features_router.py tests/agent_server/test_reactions_router.py: passes, including test_a_reaction_during_a_pending_tool_call_waits_for_its_result: the reaction stays out of the log while the call is open and follows its result.
  • uv run pytest -n 8 tests/tools/reaction tests/agent_server tests/sdk/context tests/sdk/event tests/sdk/conversation: 4711 passed, 2 failed. test_exited_leader_descendant_does_not_block_recovery[status] also fails on main in this sandbox (process reaping); test_file_legacy_routes_are_removed_from_openapi failed only under -n 8 and passes alone.
  • clients/typescript: 416 tests pass; npm run audit:endpoints passes.
  • Live, real model (deepseek-flash): control-agent-server map run --fresh --file F37: 7/7 pass, twice, including F37.rest-while-confirming (react while a call waits: no ReactionEvent in the log yet; accept; the reaction is saved after the result and the run finishes with exactly the two commands asked for and no condensation).
  • Live with the SDK alone (deepseek-chat, AlwaysConfirm): the held reaction lands as ActionEvent, ObservationEvent, ReactionEvent, the next model call succeeds, and the agent names the 👍 and the message it was on.
  • Upgrade, live on main + this PR: a 1.62.0 user's settings, profiles, secret and conversation load unchanged; the old conversation continues without the tools; with the feature on a new conversation gets them and the agent reacts; the person's ❤️ on the 1.62.0-era conversation is seen by the agent on its next turn; restart, feature off, restart: every conversation restores and keeps working. A new user with no settings does the same.
  • Canvas (feat(settings): Features page for experimental user feature flags, with Conversation reactions OpenHands#19503, Paper theme) over the same upgrade: the Experimental page lists the feature after the upgrade, the switch works, the agent's 👀 and the person's ❤️ show as chips and survive a reload.

Video/Screenshots

API only. Screenshots are in OpenHands/OpenHands#19503.

Type

  • Bug fix
  • Feature
  • Refactor
  • Breaking change
  • Docs / chore

Notes

  • Downgrade: ReactionEvent is a new event kind and react/unreact are new tools. On a server older than this PR a reaction in a conversation reads as an unreadable event, and a conversation started with the feature on opens but cannot continue (its tools are not registered there). An older remote client cannot parse a conversation once it holds a reaction. All of this needs the feature turned on first.
  • A reaction stays on: the agent unreacts only when a reaction no longer fits or the person asks.
  • The react tool description says when each emoji fits, most of all +1 first when the person corrects or changes the plan mid-task. Changing a tool description normally warrants the integration-test label.
  • feat(agent-server): projects API, coordinator tools, board groups and artifacts #6602 keeps a copy of this code and will follow the same changes.

🤖 Generated with Claude Code

https://claude.ai/code/session_013ArwwJ5sQMXhwgSTG2Ztkt


🐳 Agent Server images for this PR — GHCR package, pull/run commands, and all pushed tags (click to expand)

• GHCR package: https://github.com/OpenHands/agent-sdk/pkgs/container/agent-server

Variants & Base Images

Variant Architectures Base Image Docs / Tags
java amd64, arm64 eclipse-temurin:17-jdk Link
python-slim amd64, arm64 python-node-runtime Link
python-minimal amd64, arm64 python-node-runtime Link
python amd64, arm64 python-node-runtime Link
golang amd64, arm64 golang:1.21-bookworm Link

Pull (multi-arch manifest)

# Each variant is a multi-arch manifest supporting both amd64 and arm64
docker pull ghcr.io/openhands/agent-server:82d61a2-python

Run

docker run -it --rm \
  -p 8000:8000 \
  --name agent-server-82d61a2-python \
  ghcr.io/openhands/agent-server:82d61a2-python

All tags pushed for this build

ghcr.io/openhands/agent-server:82d61a2-golang-amd64
ghcr.io/openhands/agent-server:82d61a25b956145147a1b327045b91743f13b5ac-golang-amd64
ghcr.io/openhands/agent-server:claude-project-thread-hb0du7-golang-amd64
ghcr.io/openhands/agent-server:82d61a2-golang_tag_1.21-bookworm-amd64
ghcr.io/openhands/agent-server:82d61a2-golang-arm64
ghcr.io/openhands/agent-server:82d61a25b956145147a1b327045b91743f13b5ac-golang-arm64
ghcr.io/openhands/agent-server:claude-project-thread-hb0du7-golang-arm64
ghcr.io/openhands/agent-server:82d61a2-golang_tag_1.21-bookworm-arm64
ghcr.io/openhands/agent-server:82d61a2-java-amd64
ghcr.io/openhands/agent-server:82d61a25b956145147a1b327045b91743f13b5ac-java-amd64
ghcr.io/openhands/agent-server:claude-project-thread-hb0du7-java-amd64
ghcr.io/openhands/agent-server:82d61a2-eclipse-temurin_tag_17-jdk-amd64
ghcr.io/openhands/agent-server:82d61a2-java-arm64
ghcr.io/openhands/agent-server:82d61a25b956145147a1b327045b91743f13b5ac-java-arm64
ghcr.io/openhands/agent-server:claude-project-thread-hb0du7-java-arm64
ghcr.io/openhands/agent-server:82d61a2-eclipse-temurin_tag_17-jdk-arm64
ghcr.io/openhands/agent-server:82d61a2-python-amd64
ghcr.io/openhands/agent-server:82d61a25b956145147a1b327045b91743f13b5ac-python-amd64
ghcr.io/openhands/agent-server:claude-project-thread-hb0du7-python-amd64
ghcr.io/openhands/agent-server:82d61a2-python-node-runtime-amd64
ghcr.io/openhands/agent-server:82d61a2-python-arm64
ghcr.io/openhands/agent-server:82d61a25b956145147a1b327045b91743f13b5ac-python-arm64
ghcr.io/openhands/agent-server:claude-project-thread-hb0du7-python-arm64
ghcr.io/openhands/agent-server:82d61a2-python-node-runtime-arm64
ghcr.io/openhands/agent-server:82d61a2-python-minimal-amd64
ghcr.io/openhands/agent-server:82d61a25b956145147a1b327045b91743f13b5ac-python-minimal-amd64
ghcr.io/openhands/agent-server:claude-project-thread-hb0du7-python-minimal-amd64
ghcr.io/openhands/agent-server:82d61a2-python-node-runtime-minimal-amd64
ghcr.io/openhands/agent-server:82d61a2-python-minimal-arm64
ghcr.io/openhands/agent-server:82d61a25b956145147a1b327045b91743f13b5ac-python-minimal-arm64
ghcr.io/openhands/agent-server:claude-project-thread-hb0du7-python-minimal-arm64
ghcr.io/openhands/agent-server:82d61a2-python-node-runtime-minimal-arm64
ghcr.io/openhands/agent-server:82d61a2-python-slim-amd64
ghcr.io/openhands/agent-server:82d61a25b956145147a1b327045b91743f13b5ac-python-slim-amd64
ghcr.io/openhands/agent-server:claude-project-thread-hb0du7-python-slim-amd64
ghcr.io/openhands/agent-server:82d61a2-python-node-runtime-slim-amd64
ghcr.io/openhands/agent-server:82d61a2-python-slim-arm64
ghcr.io/openhands/agent-server:82d61a25b956145147a1b327045b91743f13b5ac-python-slim-arm64
ghcr.io/openhands/agent-server:claude-project-thread-hb0du7-python-slim-arm64
ghcr.io/openhands/agent-server:82d61a2-python-node-runtime-slim-arm64
ghcr.io/openhands/agent-server:82d61a2-golang
ghcr.io/openhands/agent-server:82d61a25b956145147a1b327045b91743f13b5ac-golang
ghcr.io/openhands/agent-server:claude-project-thread-hb0du7-golang
ghcr.io/openhands/agent-server:82d61a2-golang_tag_1.21-bookworm
ghcr.io/openhands/agent-server:82d61a2-java
ghcr.io/openhands/agent-server:82d61a25b956145147a1b327045b91743f13b5ac-java
ghcr.io/openhands/agent-server:claude-project-thread-hb0du7-java
ghcr.io/openhands/agent-server:82d61a2-eclipse-temurin_tag_17-jdk
ghcr.io/openhands/agent-server:82d61a2-python-minimal
ghcr.io/openhands/agent-server:82d61a25b956145147a1b327045b91743f13b5ac-python-minimal
ghcr.io/openhands/agent-server:claude-project-thread-hb0du7-python-minimal
ghcr.io/openhands/agent-server:82d61a2-python-node-runtime-minimal
ghcr.io/openhands/agent-server:82d61a2-python-slim
ghcr.io/openhands/agent-server:82d61a25b956145147a1b327045b91743f13b5ac-python-slim
ghcr.io/openhands/agent-server:claude-project-thread-hb0du7-python-slim
ghcr.io/openhands/agent-server:82d61a2-python-node-runtime-slim
ghcr.io/openhands/agent-server:82d61a2-python
ghcr.io/openhands/agent-server:82d61a25b956145147a1b327045b91743f13b5ac-python
ghcr.io/openhands/agent-server:claude-project-thread-hb0du7-python
ghcr.io/openhands/agent-server:82d61a2-python-node-runtime

About Multi-Architecture Support

  • Each variant tag (e.g., 82d61a2-python) is a multi-arch manifest supporting both amd64 and arm64
  • Docker automatically pulls the correct architecture for your platform
  • Individual architecture tags (e.g., 82d61a2-python-amd64) are also available if needed

A ReactionEvent (target_event_id, emoji, removed, source) records an emoji
on a message; it never reaches the LLM. Agents react with the new react and
unreact tools (openhands.tools.reaction), which default to the person's
latest message. The executor only reads the log: the observation carries
the reaction and the agent records the event right after it on its own
thread, through a new Observation.follow_up_events() hook, so it is safe
with parallel tool calls. People react through
POST /api/conversations/{id}/reactions (LocalConversation.react), which
defaults to the agent's latest message or finish and never runs the agent.
Emoji come from a fixed set of shortcodes. New feature-map family F37.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJH94xGSYwfoyccT4E
… on every tool path

Reaction part of de324a9 from #6602.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJH94xGSYwfoyccT4E
…s the first

A feature flag is a yes/no switch the user sets for themselves, stored in
PersistedSettings.features and read when a conversation starts.
GET /api/settings/features lists the known features with their state, and
PATCH /api/settings/features/{key} {enabled} turns one on or off; unknown
keys are 404. The registry is openhands.agent_server.features.

The first flag, conversation_reactions (off by default), gives every new
OpenHands-agent conversation the react and unreact tools through a new
finalize(feature_tools=...) parameter (ACP agents are left alone), and
lets POST /api/conversations/{id}/reactions through; while it is off that
route answers 409. Feature map F37 covers both.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJ5sQMXhwgSTG2Ztkt
@enyst enyst self-assigned this Nov 7, 2026
@github-actions

github-actions Bot commented Nov 7, 2026 •

Copy link
Copy Markdown
Contributor

REST API breakage checks (OpenAPI) — ✅ PASSED

Result: ✅ PASSED

Action log

ReactionEvent / ReactionEmoji types with isReactionEvent,
ConversationClient.react(), and SettingsClient.listFeatures() /
updateFeature() with the FeatureFlag type.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJ5sQMXhwgSTG2Ztkt
@datadog-official

This comment has been minimized.

@github-actions

github-actions Bot commented Nov 7, 2026 •

Copy link
Copy Markdown
Contributor

Coverage

Coverage Report •
FileStmtsMissCoverMissing
openhands-agent-server/openhands/agent_server
   conversation_service.py128310092%190–191, 273, 294, 483–484, 650, 657–658, 759, 850, 901–902, 909, 941–942, 958, 989, 993, 1005, 1025, 1046–1047, 1056, 1125, 1135, 1160, 1166–1167, 1171–1172, 1180, 1207, 1213, 1307, 1313, 1318, 1324, 1332–1333, 1342–1345, 1354, 1367, 1385, 1422, 1426–1430, 1453, 1502, 1515, 1523, 1581–1582, 1586, 1800, 1878, 2002, 2005, 2012–2014, 2017–2018, 2024, 2034, 2038, 2067, 2076, 2135–2137, 2168, 2299, 2302, 2329, 2339, 2344–2347, 2361, 2372, 2384–2385, 2417, 2515, 2575, 2633, 2648–2649, 3055, 3108, 3111, 3124
   event_router.py135795%310, 320, 323–324, 373–374, 418
   event_service.py112311090%165, 171–172, 305–306, 436, 440, 445, 472, 479, 514, 517–518, 522–523, 534, 540, 611–612, 618, 674–675, 796, 816, 843, 852, 876–877, 881, 929, 964, 968–969, 1004, 1011, 1017, 1231, 1261, 1264, 1342, 1360, 1374, 1543–1544, 1599, 1633, 1789–1792, 1796, 1839, 1843, 1850, 1864, 1878, 1902, 1949–1951, 2035, 2057, 2060–2061, 2086, 2092, 2094, 2110, 2112, 2119, 2127, 2129–2130, 2134, 2151, 2203, 2209, 2218–2219, 2226, 2241, 2252, 2293–2296, 2376–2377, 2379–2386, 2388–2389, 2399, 2410, 2426–2427, 2438, 2465, 2471, 2477, 2486–2487, 2509, 2519
openhands-agent-server/openhands/agent_server/docker_runtime
   registry.py4197383%96, 101, 104, 117–119, 122, 127, 163, 254, 292, 312–314, 316–317, 320–323, 334, 360–362, 394, 404–408, 414, 418–419, 428, 488, 497–499, 503–507, 521, 556, 560–563, 569, 592, 626–627, 631, 679, 774, 781, 789–791, 794–802, 811–814
   routers.py2767075%62, 70, 77–79, 122–124, 139–140, 142, 171, 179–180, 225, 248, 251–254, 257–261, 294–295, 328, 337, 347, 353–355, 365–367, 376, 379, 389–390, 430, 444–445, 488–490, 511, 513–526, 529–531, 537–540, 551, 560
openhands-sdk/openhands/sdk/agent
   agent.py5173094%334, 490, 494, 843–844, 851–852, 985–987, 989, 1008–1009, 1015, 1020, 1055–1056, 1063–1064, 1109, 1116, 1163–1164, 1448, 1545–1546, 1548, 1578, 1627, 1634
openhands-sdk/openhands/sdk/context/view
   view.py58297%73, 131
openhands-sdk/openhands/sdk/conversation/impl
   local_conversation.py12317194%181, 395, 462, 494–497, 499, 755–756, 867, 1255–1256, 1261, 1276, 1278, 1349, 1453, 1479, 1613, 1618–1623, 1676, 1697–1699, 1748, 2155–2157, 2160–2161, 2169–2170, 2172–2173, 2177–2178, 2449, 2452–2453, 2664, 2700, 2704, 2707, 2726, 2778, 2781, 2813, 2820–2821, 2829, 2833–2835, 2842, 3139–3140, 3158–3159, 3192, 3404, 3408, 3429, 3480, 3487–3488
openhands-sdk/openhands/sdk/conversation/visualizer
   default.py2021792%86, 132–133, 135–140, 142, 171, 191, 198, 205, 316, 410, 449
openhands-sdk/openhands/sdk/event
   reaction.py875043%84–86, 89–92, 94–98, 100–101, 105, 109–110, 113–114, 125–127, 136, 138–139, 142–143, 145–149, 167–179, 183, 193–196
openhands-sdk/openhands/sdk/launch
   finalize.py1231687%107, 113, 152, 211–220, 232, 235, 245
openhands-sdk/openhands/sdk/tool
   schema.py210598%245, 308–309, 470–471
openhands-tools/openhands/tools/reaction
   definition.py551769%40, 51, 66–68, 79–81, 118, 139–141, 143, 166–167, 170, 172
   impl.py161038%31–32, 35–38, 41–44
TOTAL55460871584% 

The react tool told the agent to unreact once it had answered, so a
"react with eyes first, then answer" request left no reaction: the
agent reacted and took it off just before its answer. A reaction now
stays until it no longer fits or the person asks. F37.tool asks in plain
words and checks that the one agent reaction is still on.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJ5sQMXhwgSTG2Ztkt
- execute_tool records a tool's follow-up events without re-taking the
  state lock when the run loop holds it for the step (as switch_llm does,
  #3485), so a react from a tool worker cannot deadlock.
- The reactions route answers 409 with a clear reason when the settings
  file cannot be read, and the feature list reads settings off the event
  loop.
- Docs say what the flag governs: the agent's tools at conversation start,
  the person's reactions at once; child conversations reuse their
  parent's tools. The persisted-settings history notes the new field.
- react/unreact take an EventID and are not idempotent (each call records
  an event).
- TypeScript client: tests for listFeatures, updateFeature, react and
  isReactionEvent; the endpoint audit lists the new client-ahead calls.
- F37: rest-default accepts the agent's finish or its plain-text answer
  as the default target, and the lock gotcha matches the run loop.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJ5sQMXhwgSTG2Ztkt
Since #5796 an MCP entry with neither command nor url is refused when
the config is built, so the invalid-entry case can no longer reach the
runtime. Same one-line change as #6606, so this PR's CI is not red on a
main failure.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJ5sQMXhwgSTG2Ztkt
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJ5sQMXhwgSTG2Ztkt
@enyst
enyst marked this pull request as ready for review November 7, 2026 22:06
@enyst
enyst requested a review from all-hands-bot November 7, 2026 22:06

@all-hands-bot all-hands-bot left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This review was posted by an AI agent (OpenHands).

Reviewed fresh at head 3a4d2b441df7c20f80ed868ae939f7dd17d0c34b against base 9f9bd444 (origin/main). CI on this head: all test suites green (sdk-tests, agent-server, agent-server-api, tools-tests, workspace, TS client, integration/smoke/ACP); the only red check is "Validate PR description", noted at the end.

Design. A user-scoped feature-flag registry (openhands.agent_server.features) with conversation_reactions as the first flag fits this repo cleanly: the flag state is additive (PersistedSettings.features within schema v7), the REST surface (GET /api/settings/features, PATCH .../features/{key}) refuses unknown keys with 404, and FileSettingsStore.update performs the swap under the existing file lock, so concurrent PATCHes cannot clobber each other.

Tools-at-start vs. live routing. The split behavior is implemented deliberately and correctly: feature_tools(settings.features) is resolved once in _start_conversation (conversation_service.py:1639) and merged into the agent via _with_client_tools (name-deduped), while the reactions REST route re-reads settings and checks is_enabled on every call. ACP agents are correctly excluded in finalize. Child conversations reuse the parent agent, so they inherit the tools chosen at parent start — consistent with the PR's stated semantics.

Reaction data model. ReactionEvent is non-LLM and whitelist-validated (check_reaction_emoji). find_reaction_target only considers the conversation's active branch and only reactable events (MessageEvent, or the agent's finish ActionEvent), and the default-target lookup selects from the opposite side, so a stale or cross-branch target_event_id cannot silently hit the wrong message.

Concurrency. The execute_tool follow-up-emission path (local_conversation.py:3405) reuses the switch_llm (#3485) skip-lock pattern: skip_lock = _step_holds_state_lock and not state.owned(). Verified that _step_holds_state_lock is set around agent.step() in both the sync and async run loops, that the ReactionExecutor itself only reads state (the agent emits the ReactionEvent from the observation on its own thread via follow_up_events()), and that the REST route executes conversation.react through run_in_executor exactly like send_message. The router catches tool ValueErrors → 400 and re-raises inactive_service, matching the existing precedent in event_router.py. The worker-thread test covers the deadlock case this avoids.

Client and docs. The TypeScript client additions (ReactionEvent/isReactionEvent, ConversationClient.react, SettingsClient.listFeatures/updateFeature) match the OpenAPI contract summary in the PR body, and the endpoint-audit config lists the three new endpoints as client-ahead with a tracking PR. Feature-map F37 was added with its F37.tool/F37-fail recipes.

Tests run in the workspace (head, no modifications): tests/tools/reaction, tests/agent_server/test_features_router.py, tests/agent_server/test_reactions_router.py — 24 passed; reaction/feature-selected tests/sdk subset — 262 passed.

One note outside the diff (not attachable inline): the Validate PR description check for this head is failing because the ## Issue Number section says None. while .github/scripts/check_pr_description.py requires a linked issue (Link an issue in the ## Issue Numbersection (e.g.Fixes #123). Newly opened issues must carry the ready-for-dev label.). This is description metadata, not code — adding an issue reference will clear the check before merge.

No material correctness, security, or design issues found on the current head.

✅ APPROVED

The user-facing feature flags are experimental features: list them with
GET /api/settings/experimental and switch one with PATCH
/api/settings/experimental/{key}. The TypeScript client methods become
listExperimentalFeatures and updateExperimentalFeature. This also keeps
clear of the operator-set Canvas feature policy (OpenHands/OpenHands#18843).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJ5sQMXhwgSTG2Ztkt
Modules experimental_features and experimental_features_router, models
ExperimentalFeature / ExperimentalFeatureDefinition /
ExperimentalFeatureUpdate, the persisted field
PersistedSettings.experimental_features, finalize(experimental_feature_tools=...),
and the TypeScript ExperimentalFeature type, so every name says which
flag system it belongs to.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJ5sQMXhwgSTG2Ztkt
A Docker runtime's server had its own empty settings, so its conversations
never got the reaction tools and the person's reactions always answered 409.
The host now passes its switches to each container in
OH_RUNTIME_EXPERIMENTAL_FEATURES, which pick the tools of conversations started
there, and checks the live switch itself before forwarding a reaction.

Also wraps three docstring lines over the line limit, and makes the F37
rest-default recipe fall back cleanly when the agent answered with finish.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJ5sQMXhwgSTG2Ztkt
execute_tool skipped the state lock while a step held it, so two direct
calls on worker threads could write events at once and leave one off the
active branch. Their events now wait for the step to return and are written
by the run loop, the way the step's own parallel tool calls hand theirs back.
Outside a step it takes the state lock like send_message and react.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJ5sQMXhwgSTG2Ztkt
execute_tool decided to defer before taking the queue lock, so a step could
end and drain the queue in between, losing a reaction whose call had
returned success. The decision and the append now happen under the queue
lock, and the run loop clears the step flag and drains under the same lock.
Also types the test worker's emoji as ReactionEmoji for pyright.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJ5sQMXhwgSTG2Ztkt
@enyst enyst changed the title feat(agent-server): user feature flags, with Conversation reactions as the first feat(agent-server): experimental user feature flags, with Conversation reactions as the first Nov 9, 2026
@enyst
enyst requested a review from VascoSch92 November 9, 2026 16:02
enyst pushed a commit that referenced this pull request Nov 9, 2026
Engel wants the Projects PR to carry every split-out PR's code until it
merges, so everything can be tested together. #6609's reactions replace
the earlier copy here: the conversation_reactions experimental feature,
/api/settings/experimental, react/unreact given to conversations (workers
included) when the feature is on, and the run-loop fix for direct tool
calls' events. Also regenerates the TypeScript client contract.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJH94xGSYwfoyccT4E
A person's ReactionEvent now reaches the agent as one line: who reacted,
the emoji, and the message, given as its last 500 characters behind
"<clipped message start, if you need it find the message with the ending
below>" when it is longer. The ending is saved on the event when the person
reacts. Reacting still starts no run. The agent's own reactions stay out of
what it sees, since its react call is already there.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJ5sQMXhwgSTG2Ztkt
@enyst enyst changed the title feat(agent-server): experimental user feature flags, with Conversation reactions as the first feat(agent-server): Conversation reactions, the first experimental feature Nov 11, 2026
enyst pushed a commit that referenced this pull request Nov 11, 2026
Brings #6602's copy of reactions and feature flags in line with
claude/project-thread-hb0du7 (#6609 on top of #6759): reactions placed
before open tool calls, a source validator, no deferred events, tools not
user-selectable, ExperimentalFeature without default, and main. Projects
joins the new registry; tests turn it on by default through is_enabled.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJH94xGSYwfoyccT4E
The merge of main committed conflict markers in four files: the
TypeScript client's endpoint audit config and API client test, and the
verify-agent-server F18 map and README. Each keeps the reactions side,
which already contained the merged flags change. The tree now equals
the branch as it was before the merge.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJKhrR2viNUM9gjr89
@enyst
enyst requested a review from all-hands-bot November 11, 2026 17:50

@all-hands-bot all-hands-bot left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This review was posted by an AI agent (OpenHands).

Reviewed the reactions portion of this PR (the feature-flag plumbing it builds on was merged separately in #6759 and is in the base main here) against the repository review guide, AGENTS.md, and the package-level guidance.

Scope. In-scope for this repository: SDK event/tool/agent-loop behavior, the Agent Server REST surface, Docker runtime behavior, and the TypeScript client mirror. The linked issue #6621 is open, labeled ready-for-dev and priority:medium, and this PR delivers the agreed first feature (conversation_reactions, off by default) on top of the flag system.

Cross-layer completeness. Traced the change through every public entry point: ReactionEvent (with the agent/user source validator), react/unreact tools in openhands.tools.reaction (user_selectable = False), the Observation.follow_up_events() hook consumed in _execute_action_event and in the rerun path of LocalConversation, the View repositioning of reactions that arrive while tool calls await results, LocalConversation.react for the user path, POST /api/conversations/{id}/reactions with the 409 gate, the Docker runtime host checks plus OH_RUNTIME_EXPERIMENTAL_FEATURES forwarding, and the TypeScript client (ReactionEvent, isReactionEvent, ConversationClient.react) with its endpoint-audit exemption. The ACP path is intentionally left untouched, which finalize() documents and tests confirm.

Concurrency and lifecycle. EventService.react follows the existing send_message pattern (executor thread + conversation FIFO state lock). The View logic keeps the persisted event order intact while presenting the reaction to the LLM before open tool calls, covered by test_a_reaction_during_a_pending_tool_call_stays_out_of_the_call including the rebuild path through View.from_events. My one design note - after the person rejects a pending action, a reaction without target_event_id targets the agent's finish rather than the withdrawn message - is the documented latest-answer semantics, keeps the LLM view valid, and is not a demonstrated defect.

Compatibility. The OpenAPI contract change is additive (new route, new event/tool/observation schemas in unions). New event kind and tool downgrade risks are stated in the PR and gated behind an opt-in feature flag. Persisted settings shape is unchanged from main.

Tests and CI. In the workspace at head 80a69320: tests/tools/reaction, tests/agent_server/test_experimental_features_router.py, tests/agent_server/test_reactions_router.py, docker runtime registry/route tests, test_event_router.py, test_event_service.py, and tests/sdk/{context,event,conversation} all pass. CI on this exact head is green except the Build & Push Java image jobs, which are infrastructure builds unrelated to this diff. The only local failure I could reproduce (test_canvas_extension_backend) fails identically on a clean checkout of the PR head and touches no code this PR changes.

Eval note for the human maintainer: the react tool description guides when the agent reacts (notably +1 on mid-task corrections), which can alter agent behavior. The integration-test workflow passes on this head and the PR includes live model and upgrade evidence, so this does not withhold approval; flagging it for the maintainer's awareness.

No material correctness, security, compatibility, or acceptance-criterion defect found on the current head.

✅ APPROVED

@all-hands-bot all-hands-bot left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This review was posted by an AI agent (OpenHands).

Fresh review at head 80a69320439c3fd991412011863533dfce6e451d against origin/main (56d559f6). Scope gate passed: conversation reactions live where they belong — SDK events/tools, agent-server routing, and the TypeScript client mirror — per AGENTS.md cross-repository boundaries. Linked issue #6621 is open with ready-for-dev / priority:medium.

CI on this head: all functional checks green (sdk-tests, agent-server-tests, cross-tests, integration-test, REST API/OpenAPI, endpoint-audit, security, TS 416 tests, pre-commit). The two failing jobs are Build & Push (java-amd64/arm64): the logs show Docker apt DNS failures (Could not resolve 'ports.ubuntu.com') inside the image build — an environment failure that also fails on unrelated branches, not attributable to this diff.

Workspace verification (no tracked files modified):

  • tests/tools/reaction + test_experimental_features_router.py + test_reactions_router.py: 38 passed, including test_a_reaction_during_a_pending_tool_call_stays_out_of_the_call.
  • tests/agent_server/docker_runtime: 202 passed. tests/sdk/context, tests/sdk/event: 601 passed.
  • clients/typescript: 416 passed.
  • Broader tests/agent_server run had sandbox-environment failures; re-running the identical failing subsets on origin/main reproduced byte-identical failure sets (launch parity, agent launch additions, credential binding — the sandbox injects GITHUB_TOKEN_REVIEW into secret refs — and canvas-extension backend tests). Pre-existing on main, unrelated to this PR.

Material findings: none. Cross-layer trace is complete: ReactionEvent with agent/user-only source validation, tool-gated via experimental_feature_tools at finalize (ACP excluded), user_selectable = False so settings don't offer the tools, View correctly moves a person's reaction that arrives during pending tool calls before the open calls (LLM history constraint), follow_up_events() keeps the executor read-only for parallel-tool safety with the rerun path covered, and the Docker dual-path gating is sound: the container trusts OH_RUNTIME_EXPERIMENTAL_FEATURES only for a request the host already gated (tail == "reactions" + POST check in proxy_conversation), verified by test_reactions_follow_the_host_switch_before_reaching_the_runtime. Compatibility is additive (new event kind, new tools, settings field documented as within-v7 with downgrade behavior), and the OpenAPI contract summary in the PR matches the diff. The eval risk of new react tool descriptions is noted for the human maintainer; the integration-test check passed on this head.

✅ APPROVED

A person's reaction that arrives while tool calls are open (a pending
confirmation, a pause) is no longer written between a call and its
result and then moved in the View. The conversation keeps it in memory
and emits it once every open call is answered, so the event log itself
is always in an order a model API accepts. View no longer reorders
anything.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJKhrR2viNUM9gjr89
enyst pushed a commit that referenced this pull request Nov 11, 2026
@enyst
enyst requested a review from all-hands-bot November 11, 2026 23:02

@all-hands-bot all-hands-bot left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This review was posted by an AI agent (OpenHands).

Fresh review at head d5bf5ef91103ff8506e3a192329663d478990631 against origin/main (56d559f6). Scope gate passed: the reactions feature sits where it belongs (SDK events/tools, agent-server routing, TypeScript client mirror) per AGENTS.md ownership boundaries. Linked issue #6621 is open with ready-for-dev / priority:medium.

CI on this head: all 51 checks green — including the Build & Push docker jobs that failed on DNS in the previous run; they pass now. The macOS suite line is a skip, not a failure.

Workspace verification (no tracked files modified):

  • tests/tools/reaction + test_experimental_features_router.py + test_reactions_router.py: 38 passed, including the renamed test_a_reaction_during_a_pending_tool_call_waits_for_its_result.
  • tests/agent_server/docker_runtime + tests/sdk/context + tests/sdk/event: 744 passed, 1 skipped.
  • clients/typescript: 416 passed.

The new hold-back design is sound. The head replaces the previous View reordering with holding a person's reaction in memory while tool calls wait, then emitting it once every open call is answered — so the event log itself is always in a valid order and View no longer special-cases reactions. Verified on the current code:

  • Locking: the run loop holds the conversation state lock across agent.step() (RLock; the #3485 comment marks the step as lock-holding), so _flush_pending_reactions — which fires inside the callback chain when the observation is emitted — is serialized against react(), which appends under with self._state. The reentrant lock makes the flush's recursive _on_event safe.
  • No deadlock while waiting: during WAITING_FOR_CONFIRMATION the run loop breaks out of the with self._state block and returns, releasing the lock, so REST react() cannot block on the run thread.
  • Flush correctness: the flush triggers on any ObservationBaseEvent (covers ObservationEvent and UserRejectObservation) only when get_unmatched_actions is empty; the list swap before iteration prevents re-entrant double-flush; the recursive emission runs the full composed chain, so held reactions are persisted and published.
  • Ordering/id: the restamp at flush time (model_copy(update={"timestamp": ...})) keeps log order = timestamp order while preserving the event id; the test asserts ActionEvent, ObservationEvent, ReactionEvent, ReactionEvent, id stability, and a valid assistant/tool/user message history for the next model call.
  • Edge behavior: reactions held through an error or pause flush on the next observation — consistent with "the agent sees the person's reaction on its next turn". The restart-drops-a-held-reaction trade-off is documented and matches the in-memory design.

The previous View-based special casing was removed cleanly, execute_tool is back to the main shape, and the rest of the feature (feature gating, Docker dual-path, TS client, additive OpenAPI surface) is unchanged from the earlier reviews of this PR and still holds up.

Material findings: none.

✅ APPROVED

claude and others added 2 commits November 12, 2026 00:43
The codebase calls them the user everywhere (source="user"). This
renames the wording in docstrings, comments, test names, the tool
descriptions and the line the agent reads: "[The user reacted ...]".

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJKhrR2viNUM9gjr89
@enyst
enyst enabled auto-merge (squash) November 12, 2026 00:51
@enyst
enyst merged commit 89469eb into main Nov 12, 2026
44 checks passed
@enyst
enyst deleted the claude/project-thread-hb0du7 branch November 12, 2026 01:01
enyst pushed a commit that referenced this pull request Nov 12, 2026
Takes Engel's react tool description edit from main; the rest of the
reactions code here already matched #6609 as merged.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwJH94xGSYwfoyccT4E
enyst added a commit that referenced this pull request Nov 12, 2026
- S16.reactions: the react/unreact tools and ReactionEvent (#6609), scripted
  and live; S16 now owns openhands-tools/reaction.
- S11.task-secrets (known failure #6724) and S17.schema-constraints (known
  failure #6766): open bugs filed since the baseline, reproduced.
- S21: the ask_agent fork-cost and timeout-resend known failures link #6646
  and #6645; the live handshake lists today's adapter versions.
- S14: the tmux pane-pool gotcha states today's behavior (#6752).
- History notes removed from S14, S15 and S17.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013ArwwNZe7p1P7oMgnFNYcy
VascoSch92 added a commit that referenced this pull request Nov 12, 2026
Fifty files conflicted, most of them with #6780 (domain errors), which
rewrote the raises in every router this branch rewrote the lookups of.
Each conflict keeps main's errors, responses and new behaviour and this
branch's injected dependencies.

Code main added since the branch point that used lookups this branch
removed now takes its dependencies like the rest:

- experimental features (#6759): the routes take the settings store
  through Depends(get_settings_store).
- conversation reactions (#6609): require_reactions_enabled takes a
  settings store; the route injects it and the Docker proxy passes the
  registry's.
- pull request status (#6704): get_provider_pull_request takes the
  secrets store.
- trajectory download (#5766): uses the injected config.
- DockerConversationRegistry and the OpenAI gateway read experimental
  features from their own ServerStores.

Code that exists only on this branch raises domain errors too
(dependencies.py, init_router.py, vscode_router.py); a WebSocket that
finds no service still closes with 1013.

Tests main added for these features build their stores per test instead
of reading a process-wide one.
@github-actions github-actions Bot mentioned this pull request Nov 19, 2026
2 of 8 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[Feature]: User feature flags in the Agent Server, starting with Conversation reactions

3 participants