Highlights
See the complete change list below.
Breaking Changes
No known breaking changes.
Complete Change List
Features
- Adds a Web Shell sidebar activity view for trusted workspace conversations, showing approval/input/error states, unread completions, running work, and bulk read/archive controls. (#16022) by @deggs7
- Adds an "Add to Split View" option to eligible sidebar session menus in web shell, making it easier to open sessions side by side. (#15956) by @4ekuct25
- Adds request success rate, output speed, per-model success indicators, and distinct model colors to the Web Shell token usage panel. (#16108) by @qqqys
- Web Shell composer shows a dismissible Workflow chip that turns Workflow mode off, warns when tools are unavailable, and summarizes the mode in the + menu. (#16107) by @qqqys
- Web Shell Token Usage now plots per-request output speed, first-token latency, and failure details by model, making session performance and errors easier to inspect. (#16111) by @qqqys
- With experimental.unifiedAgentLoop enabled, more ACP turns, including channel prompts and Goal-proposal approvals, run on the shared loop. (#15902) by @qqqys
- Mods can now run prompt.submit hooks in headless runs for -p prompts and stream-json user messages, allowing prompt inspection or rewriting before submission. (#15905) by @qqqys
- Desktop releases now publish Fedora 44 and RHEL 10 x64 RPM installers alongside existing Linux packages. (#16060) by @yiliang114
- feat(web-shell): make GitHub channel configuration usable (#16096) by @wenshao
- feat(verify-pr): inherit --publish consent on same-session re-verification (#16112) by @wenshao
- feat(ci): let the PR review canary cohort carry its own endpoint (#16130) by @yiliang114
Bug Fixes
- OAuth refresh lock cleanup now removes the lock only when the current process owns it, preventing exiting processes from deleting active refresh locks. (#15661) by @2SinceJuly
- MCP tool discovery now skips duplicate tool names but keeps all uniquely named tools, preventing one name collision from hiding an entire server's tools. (#15757) by @2SinceJuly
- The Web Shell Plugins page now shows a back control when the navigation rail is unavailable, letting users return to chat from compact layouts. (#15651) by @2SinceJuly
- LSP code-navigation queries now fail with an explicit reason when no language server is ready instead of returning empty results. (#15946) by @404khai
- The verify report now counts targeted gate test-suite results separately from a round's scripted assertions, making assertion totals reflect only round checks. (#16013) by @wenshao
- Makes long /btw answers scroll in a bounded panel with mouse wheel, Shift+Up/Down, PageUp/PageDown, and a scrollbar, while short answers remain unchanged. (#15982) by @2SinceJuly
- Fixes verify-pr to count each suite run as one assertion and handle skip notices on closed PRs so review rounds are not rejected with zero assertions. (#16050) by @wenshao
- Fixes Kimi K3 generation recognition so supported IDs use the 1,000,000-token context window, while k3-256k keeps its 256K window. (#16048) by @wenshao
- Fixes review command so plain-language re-review requests target the intended PR and do not misread resume flags or file-like tokens. (#15998) by @wenshao
- Installs DejaVu fonts in the sandbox so capture cards use the intended monospace font and render legibly. (#16032) by @yiliang114
- Moves the Workflow mode toggle from the composer toolbar into the composer “+” menu to reduce toolbar clutter while keeping it accessible. (#16047) by @qqqys
- Improves managed-agent recovery accuracy by blocking gap fills without child ledger evidence and clarifying unknown or never-started states. (#16015) by @wenshao
- Fixes managed-agent child result delivery status so consumed child results are no longer marked pending. (#16074) by @wenshao
- Fixes AI attribution notes for loosely spelled git commit --amend commands so they diff against the amended commit, not earlier commits. (#16073) by @yiliang114
- Makes loop-protection reminder delivery and telemetry settle only when the model request carrying the reminder is accepted, preventing premature clearing or logging. (#15559) by @suzhiguo7
- fix(core): don't treat fd duplication (2>&1) as a file write in shell permission checks (#15681) by @Suaroman
- Sanitizes goal approval text and edit-diff file paths in Web Shell by escaping control and bidi characters so displayed approval content cannot carry hidden controls. (#16080) by @yiliang114
- Shows Managed Session list failures as a localized Retry notice with request details and avoids the empty state until loading succeeds. (#16082) by @yiliang114
- Fixes invalid Javadoc left after the module split so the managed-agent release profile can build documentation again. (#16099) by @doudouOUC
- Moves the Web Shell managed session list failure notice below the Sessions / Archived tabs and prevents its request id from being cut off. (#16104) by @yiliang114
- Fixes qwen-managed-agent-upgrade start and verify so they reach the control plane and Hosted Harness using the server's resolved endpoint configuration. (#16051) by @wenshao
- Tightens the Web Shell mobile composer layout by aligning workspace controls, truncating long names, and centering the context-usage ring. (#16103) by @ytahdn
- VS Code companion session history now groups This Week by the current calendar week, so earlier sessions are placed in Older instead of incorrectly appearing under This Week. (#16097) by @yiliang114
- The bundled review skill now tells fetch-pr to re-run with both --since and --since-model and removes the retired range model, preventing incomplete anchors. (#16094) by @yiliang114
- The Managed runtime release workflow can now rebuild the missing 0.26.5 runtime from its original tag after repairing the Javadoc issue that blocked the release. (#16114) by @doudouOUC
- Windows installer updates now stop the bundled runtime before replacing files, reducing update failures when node.exe remains locked. (#16071) by @yiliang114
- Channel users can now /approve or /deny their own pending one-time tool permission requests in the current attended turn. (#16087) by @BenGuanRan
- Linux AppImage builds now verify required dynamic libraries are bundled or documented as host-provided, helping prevent missing-library failures. (#16062) by @yiliang114
- Mods that register prompt.paint or ui.place hooks now load successfully, with those unsupported hooks skipped instead of stopping startup. (#16124) by @qqqys
- fix(mcp): warn about disabled tool typos on every discovery path (#16120) by @yiliang114
- fix(managed-agent): Restore profile-owned runtime verification (#16134) by @doudouOUC
- fix(core): attribute background shell notifications to the registering turn (#16125) by @yiliang114
- fix(core): report redirects on cd segments (#16129) by @yiliang114
Documentation
- Updates daemon usage documentation with current deployment, security, authenticated startup, token sidecar lifecycle, and lifecycle-command guidance. (#16056) by @wenshao
- Adds a README quickstart for daemon mode covering qwen serve startup, status/log/stop commands, default loopback binding, and local security warnings. (#16053) by @wenshao
- Updates managed-agent structure-review documentation to reflect the Runtime Broker extraction and newly separated recovery, reconciliation, and cancellation components. (#16109) by @wenshao
- ManagedAgentStore documentation now reflects the completed store conversion and removes outdated setter descriptions. (#16118) by @wenshao
Internal Changes
- Public and WebShell Session event streams now share replay and live delivery while keeping existing payloads, event names, and delivery order. (#15952) by @doudouOUC
- ci: route the classify_pr gate to ECS for every pull request (#16019) by @yiliang114
- Adds an end-to-end test for /autofix-pr watch helpers against real git and a fake gh to improve automated fix reliability. (#16017) by @wenshao
- Adds a managed-agent contract test asserting A3 sibling call binding and approval snapshot consistency, with no production behavior change. (#15995) by @wang1408
- Makes Windows preview installer tests run reliably through cmd.exe so nightly results are reported correctly. (#16028) by @yiliang114
- Improves managed-agent broker reliability by separating runtime execution workflows. (#16029) by @doudouOUC
- Makes managed-agent session store initialization safer by using constructor dependency injection. (#16061) by @doudouOUC
- test(managed-agent): gate the expired-cursor resync answer (#16076) by @wenshao
- Refactors Managed Agent runtime execution to centralize dispatch, cancellation, and completion tracking in an internal dispatcher. (#16084) by @doudouOUC
- Adds a Managed Agent test verifying mcp-release refusal and same-id retry behavior when a session uses two MCP servers. (#16089) by @wenshao
- Adds a managed-agent test verifying detach is refused while a tool result is unknown and the session remains attached. (#16098) by @wenshao
- Reconnects Hosted fault probes to current execution owners so managed-agent tests observe dispatch, cancellation, and delayed replies accurately. (#16101) by @doudouOUC
- Settings documentation now matches the runtime schema, and memory.enableAutoSkill and security.auth.useExternal are correctly shown as false. (#16085) by @yiliang114
- Windows installation PATH persistence is now protected by a contract test, reducing the chance that a fresh install fails to remain on PATH. (#16072) by @yiliang114
- Managed Agent storage was reorganized into Agent and Session stores without changing user-visible behavior. (#16090) by @doudouOUC
- refactor(managed-agent): trim store delegation boilerplate (#16142) by @doudouOUC
New Contributors
- @404khai made their first contribution in #15946
- @wang1408 made their first contribution in #15995
- @suzhiguo7 made their first contribution in #15559
- @Suaroman made their first contribution in #15681
Full Changelog: v0.26.5...v0.26.6