[release] v0.105.6#5385
Merged
Merged
Conversation
… outside parameters The commit_revision friendly card previews only the parameters tree, but the backend deep-merges the delta onto the whole revision data (url, script, headers, ...). A mixed delta rendered its parameters half and silently hid the rest of the commit. Mirror the backend's test_run delta-scope rule: any set key besides parameters, or any remove path not under parameters., returns null so the ApprovalDock shows the exact payload instead.
Recent Claude models default extended-thinking display to "omitted"
(signature-only, empty text), so claude-agent-acp emits no
agent_thought_chunk and the playground shows no reasoning for Sonnet/Opus
while Haiku works. Request visible ("summarized") adaptive thinking via
_meta.claudeCode.options for the Claude harness only, so reasoning
surfaces for every model without forcing a budget. Pi harness untouched.
Ports open PR #5372 onto the decomposed runner layout: the session-init
insertion now lives in sandbox_agent/environment.ts.
Claude-Session: https://claude.ai/code/session_01DnWRxU3dCJ11hgDidm26vW
… failure When a user denies a gated tool call, the runner replied reject and the harness closed the call as a failed tool result, so the Vercel egress projected the generic tool-output-error frame -- the UI rendered a decline as a breakage. Add a structural denied marker at the runner deny mapping (never string-match the error text): otel.markToolCallDenied flags the gated tool-call id, and the closing failed tool_result carries denied: true. The SDK egress (both projection sites) projects the AI SDK tool-output-denied chunk for a denied result and keeps tool-output-error for a genuine failure. Covers the cold decision-map deny (Claude and Pi gates) and the live keep-alive resume-reject. Design record: D-022 (final-sweep-decisions.md). Claude-Session: https://claude.ai/code/session_01DnWRxU3dCJ11hgDidm26vW
Plan-only workspace for delivering browser-fulfilled client tools to the Claude harness in remote Daytona sandboxes. Reuses the existing file relay (the Pi-on-Daytona pattern); adds no new runner-to-sandbox network path. Plans #5256 and closes the residual mixed-set silent-drop from #4984. Claude-Session: https://claude.ai/code/session_01DnWRxU3dCJ11hgDidm26vW
Advertise browser-fulfilled client tools to the in-sandbox stdio MCP shim and add a paused relay answer so a parked client tool ends the shim's tools/call cleanly while the runner ends the turn. The browser result returns on the cold-replay resume. Deletes the interim #5366 client-only Daytona refusal. Closes #5256; closes the residual mixed-set drop of #4984. The client-tool pause disposition is a closed set (pi-native / cold-acknowledge, with warm-hold reserved) at the client-tool boundary; the relay consumes the derived writePausedAnswer switch. Claude-Session: https://claude.ai/code/session_01DnWRxU3dCJ11hgDidm26vW
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
dosubot
Bot
added
the
size:XS
…rness Package the pre-release agent-QA harness as a tracked, portable skill at .agents/skills/agent-release-gate/ (SKILL.md + resources: the three drivers, a cells-x-journeys coverage matrix, the traps doc, and sanitized regression seeds). The drivers read AGENTA_BASE / AGENTA_PROJECT_ID / AGENTA_API_KEY from the environment first (--env-file fallback) with a clear missing-credentials error, and write runs to ./qa-gate-runs/ in the CWD, so the gate runs against any deployment. A tracked .claude/skills symlink and two .gitignore allowlist entries make it discoverable. Also delete four stale files from the design folder (cleanup-plan.md, regression-skill-DRAFT.md, scripts/warm_daytona_probe.py, scripts/mcp_qa_server.mjs) and add a one-line pointer plus a testing-README subsection. Seed canary tokens are replaced with a fixed placeholder so no gitleaks allowlist change is needed. Claude-Session: https://claude.ai/code/session_019TK4ow9a3dXUNY657djbQr
test(web): fix the active-tab locator that broke five acceptance tests
feat(sdk): emit tool-output-denied so the UI can tell a denial from a failure
dosubot
Bot
added
size:M
feat(runner): client tools on Claude in remote sandboxes
dosubot
Bot
removed
the
size:M
Updated contributor count and added new contributors to the README.
docs(readme): reposition around building and running agents
dosubot
Bot
added
size:XXL
fix(auth): correct exc_infp typo to exc_info in auto-join error logging
|
|
…erabreham docs: add truecallerabreham as a contributor for bug
fix(sdk): use Claude harness model identifiers
…issue [fix] Refresh workflow name after rename
test(sdk): align bare Claude alias test with the curated alias list
test(agent): add the agent release gate — a portable wire-level QA harness
[fix] Enable agent rename on the onboarding playground [AGE-3954]
…view-scope fix(frontend): Show raw payload for commit deltas outside parameters
mmabrouk
approved these changes
Jul 19, 2026
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
5 participants
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.
New version v0.105.6 in