Display conversation searches by agent run title

[cephalonaut]

Description

Render conversation-search subagent calls that target agent_run_id with the searched child run title instead of treating the search as the current conversation.

This PR:

• Reads agent_run_id from conversation-search subagent metadata.
• Fetches missing run titles through AgentConversationsModel and re-renders when task data arrives.
• Falls back to agent run <id> when the run title is unavailable.
• Updates warp_multi_agent_api to the branch from Add agent run ID to conversation search metadata warp-proto-apis#311.

Depends on:

• Add agent run ID to conversation search metadata warp-proto-apis#311
• https://github.com/warpdotdev/warp-server/pull/11119

Linked Issue

No linked issue.

Testing

• cargo fmt --check
• cargo check -p warp --lib
• PATH="/tmp/warp-corepack-bin:$PATH" cargo clippy -p warp --lib --all-features --tests -- -D warnings
• I have manually tested my changes locally with ./script/run

Full workspace clippy was attempted with cargo clippy --workspace --all-targets --all-features --tests -- -D warnings; it is currently blocked by an unrelated duplicate DEFAULT_ONNX_MODEL definition in crates/input_classifier/src/bin/evaluate.rs when nld_classifier_v2 is enabled.

Screenshots / Videos

Not captured.

Agent Mode

• Warp Agent Mode - This PR was created via Warp's AI Agent Mode

Plan: https://staging.warp.dev/drive/notebook/xj15fRX70pF0DtEyxohVMj
Conversation: https://staging.warp.dev/conversation/7ce46a9f-3d21-41d9-becb-67d8ab107f23

CHANGELOG-NONE

Co-Authored-By: Oz [email protected]

[oz-for-oss]

@cephalonaut

I'm starting a first review of this pull request.

You can view the conversation on Warp.

I completed the review and no human review was requested for this pull request.

Comment /oz-review on this pull request to retrigger a review (up to 3 times on the same pull request).

Powered by Oz

[oz-for-oss]

Overview

This PR wires agent_run_id through conversation-search subagent metadata, fetches ambient task titles through AgentConversationsModel, and renders conversation search targets as either conversation titles, agent run titles, or a fallback ID. I did not find a code-level correctness or security issue in the changed lines.

Concerns

• This is a user-facing rendering change, but the PR description says screenshots/videos were not captured. For this user-facing change, please include screenshots or a screen recording demonstrating it working end to end.

Verdict

Found: 0 critical, 1 important, 0 suggestions

Request changes

Comment /oz-review on this pull request to retrigger a review (up to 3 times on the same pull request).

Powered by Oz