Nothing is editorialised. Sources land, the tape prints, every fact keeps its link back to where it came from. The archive is the product.
Cline's Vertex integration stops filtering the model picker to a hardcoded global-endpoint list and lets you type any Vertex model ID, including Fable 5. The Yolo Mode toggle is gone — it was never read by the approval path — and existing Yolo/auto-approve-all setups are migrated to auto-approving every action so unattended runs keep working.
Mostly Agent Manager work: reassigned terminal and navigation shortcuts, repository choice when creating worktrees in multi-project mode, and slash commands inside worktree prompts. Supporting changes cover model search relevance, custom provider configuration, and lower background load from Git polling and file watchers.
The JetBrains plugin now sends editor context — active file, open and visible files, selected text, and shell context — along with prompts, surfaced in the message as clickable attachments. A new JetBrains Context setting turns the automatic collection off if you don't want that content sent.
Adds cline mcp uninstall and lets schedules inherit saved provider settings. The bulk is reliability work inherited from SDK v0.0.72: interrupted turns no longer silently drop queued prompts, a hung MCP server no longer blocks session creation, and LiteLLM traffic moves to Chat Completions so proxy setups work.
Reliability release for the Cline SDK centred on interrupt and restart semantics: prompts queued during a turn survive an abort, session context persists across aborts and hub restarts, and failed queued turns now report run.failed instead of completing silently. A hung or unconfigured MCP server can no longer stall session creation, and LiteLLM traffic moves from the Responses API to Chat Completions.
Maintenance release on the extended-stable line — targeted security and reliability repairs, no new features. Notable for plugin authors: before_agent_start, root openclaw/plugin-sdk imports, providerAuthEnvVars, and channelEnvVars are scheduled for removal. OpenCode Go users get the corrected hy3 model identifier in place of the failing hy3-preview alias.
A 169-PR release dominated by security and reliability repair. Gateway HTTP now rejects disallowed browser origins before unauthenticated handling, external MCP loopback clients get short-lived session-bound grants instead of inheriting mutable child-process authority, Codex app-server commands require a real human or plugin approval, and secrets are redacted from MCP status output and Telegram-adjacent logs. Operators running exposed gateways should treat this as an upgrade release.
Remote MCP servers can be authorized with OAuth from Settings → MCP, including servers that need a pre-registered client ID/secret rather than dynamic registration. Turns that fail — including sending with no model credentials — now show an error in the transcript instead of failing silently, and MCP errors are attributed to the individual server rather than the whole page.
Adds installable portable Agent Plugins with search across local, personal, workspace, and remote catalogs, plus opt-in support for the MCP 2026-07-28 protocol revision (paginated discovery, multi-round requests, non-blocking server startup). The deprecated codex exec --full-auto flag is removed — use --sandbox workspace-write — and Linux bundle archives are no longer published. Unfamiliar local projects now require explicit trust before running.
Adds claude self-hosted-runner, letting Team and Enterprise plans run web, mobile, and desktop sessions on their own machines or containers, plus cross-session SendMessage/ListAgents so sessions on any of your machines can message each other. Also expands sandbox credential masking and changes what the feedback survey uploads.
Reasoning effort now resolves the same way across providers — including Ollama — instead of going through per-provider thinking overrides, and an explicit request to turn reasoning off is honoured everywhere. Also adds meta/muse-spark-1.2-contributor on the Cline provider and fixes error telemetry attribution. Matters if you set reasoning per provider today.
Reasoning effort levels and enable/disable flags now map onto the AI SDK's native reasoning setting across providers, which the notes describe as replacing the previous per-provider thinking overrides; an explicit disable takes priority. Also refreshes the model catalog from models.dev and fixes telemetry model attribution.
Release candidate for the JetBrains plugin adding session resume for Claude and Codex through the bundled Kilo Core runtime, visibility and developer controls over which Kilo Core CLI build is used, and a large batch of diff-rendering and session-stability fixes. Relevant to JetBrains users running Kilo against Claude or Codex.
Significance 4+ across every vertical, sent 07:00 UTC. No summaries of summaries. 393 entries archived and counting.