Stop false stale-send guard after tool-call turns

[iplay88keys]

Description

The chat send guard falsely blocked the next message with "New messages loaded — please review before sending" on essentially every turn after the first — sending twice was needed each time. It surfaced first on a tool-call turn, but the root cause affects every agent response.

Root cause

A2A marks per-message contextId/taskId as optional — the Task is the canonical carrier, so persisted history messages routinely store them as empty strings. After a turn completes the UI keeps the locally-streamed message copies (it does not reload from the backend), and those carry the task's real contextId/taskId, so the send guard keys them as ["task", contextId, taskId, contentSignature]. The backend-extracted copies, with empty ids, fall back to ["message", <id>] instead — and for converted tool messages that id is even regenerated (uuidv4) on every extraction. So a persisted agent message never matches its locally-streamed counterpart, the guard counts the backend as ahead of the local view, and blocks the send. Every turn has an agent response, so every send after the first tripped it.

Fix

Carry contextId/taskId on agent messages so the streamed and persisted copies key identically. Two layers:

• UI (ui/src/lib/messageHandlers.ts): when flattening task.history, backfill contextId/taskId from the task for every extracted agent message (text and tool), treating "" as absent (||, not ??). This is the complete fix on its own — it repairs already-persisted sessions and works regardless of which runtime produced them.
• Runtime (source, defense-in-depth, helps new sessions): stamp contextId/taskId onto agent messages at emission time, in both producers — Python kagent-adk (convert_event_to_a2a_message) and the Go ADK executor, now the default declarative runtime (go/adk/pkg/a2a/executor.go, via a newAgentStatusEvent seam). A2A allows omission, and remote agents are out of our control, so the UI backfill stays regardless.

Scope is limited to agent messages; user messages are keyed by messageId and already match.

Reproduction

1. Send a message that triggers a tool call.
2. Send another message → blocked by the stale-send banner with no actual change.

[chromatic-com]

Warning

Testing paused

Monthly snapshot limit reached. Update your plan for additional snapshots and to resume testing.

[Copilot]

Pull request overview

Fixes a false-positive “stale-send” guard in the chat UI by ensuring agent messages extracted from persisted task.history key identically to their locally-streamed counterparts (especially after tool-call turns), preventing the next send from being incorrectly blocked.

Changes:

• UI: backfills contextId/taskId for extracted agent messages (treating "" as absent) so send-guard keys match between streamed and persisted messages.
• UI tests: adds regression coverage for same-tab tool-call and text turns persisted with empty agent ids.
• Runtimes (defense-in-depth): stamps task_id/context_id onto emitted agent messages in both the Python ADK converter and the Go ADK executor, with accompanying unit tests.

Reviewed changes

Copilot reviewed 6 out of 6 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
ui/src/lib/messageHandlers.ts	Backfills agent contextId/taskId when extracting persisted history so send-guard keys align with streamed messages.
ui/src/components/chat/tests/ChatInterface.sendGuard.test.tsx	Adds regression tests covering the previously-failing same-tab persisted tool-call and text scenarios.
python/packages/kagent-adk/src/kagent/adk/converters/event_converter.py	Stamps task_id/context_id onto converted agent messages at emission time.
python/packages/kagent-adk/tests/unittests/converters/test_event_converter.py	Verifies converted messages carry task_id/context_id.
go/adk/pkg/a2a/executor.go	Centralizes agent message creation to stamp request ContextID/TaskID on emitted agent messages.
go/adk/pkg/a2a/executor_test.go	Tests that the new Go executor seam stamps context/task ids onto agent messages and working status events.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.