Release Notes — Week of July 27 to August 3, 2026

Highlights

61 commits across 4 themes landed this week (v1.121.0 → v1.126.0). The headline: you can now steer a running task mid-flight, every OpenRouter consumer routes through one configurable gateway, and the operator surface gets its own configuration page.

Steer a running agent task mid-flight

Long-running agent tasks are no longer fire-and-forget. You can now redirect, correct, or queue instructions to a running task across every harness provider — pi, claude, opencode, and codex — without killing and restarting it. Codex queue steering delivers guidance at the next tool-call boundary via harness-side lifecycle hooks, and the runner now reliably returns the agent's true final message as task output.

What this means in practice: a task that takes a wrong turn can be corrected in real time rather than discarded. Tasks are now a collaborative conversation, not a commit-and-pray.

See #1014, #1036, #1039, #1042, and #1054.

Single OpenRouter gateway for all consumers

OPENROUTER_BASE_URL now routes every OpenRouter consumer — summarizers, raters, raw-llm workflow nodes, all provider adapters — through one configurable endpoint. Point your stack at a proxy or self-hosted endpoint once instead of patching each consumer individually.

See #1010.

Operator configuration page at /settings/configuration

All swarm configuration now lives in one place. Grouped cards with editable rows replace env-file hunting. The page surfaces every config key the operator needs to touch, with immediate save and validation.

See #1017.

Honest MCP tool results

A new SwarmToolResult contract surfaces real success and error state from tool calls instead of opaque wrappers. Scripts can finally branch on what actually happened — a tool that returned an error produces a structured error result, not a silent failure. Oversized results are bounded and spilled to KV to protect context windows.

See #1023, #1027, and #1032.

Live model catalog + dynamic UI picker

A live endpoint now serves the current model catalog, driving a dynamic model picker in the UI that always reflects what's actually available. No more stale dropdowns.

See #1022.

Mature memory retrieval on by default

Graph-expansion and mature retrieval flags are enabled out of the box. New installs get richer recall without additional configuration.

See #1002.

Improvements

• Codex queue steering via harness lifecycle hooks — Steering extends to codex by delivering queued guidance at the next tool-call boundary through harness hooks. See #1036.

• Script-workflow agent-task steps wait for terminal status — ctx.step.agentTask now blocks until the task reaches a terminal state, removing flaky early-returns from script workflows. See #1059.

• Workflow definition lifecycle tracking — Workflow definitions are now versioned and lifecycle-tracked alongside their runs. See #1040.

• Searchable Lucide avatar picker — Agent avatars get an expanded, searchable Lucide icon picker with normalized search and result caps. See #1011.

• Activation-funnel telemetry — Previously blind spots in the install-to-activation funnel are now instrumented. See #1024.

• Persistent Slack thread tree — Ephemeral Slack task relays are replaced with a durable, navigable thread tree. See #1056.

• worker-slim Docker target — A slimmer worker image with npx-skills installs and archil removal. See #1021.

• gh-stack extension preinstalled — Workers ship with the official gh-stack extension. See #1055.

• Boot gated on control-plane readiness — Workers wait for the control-plane API before booting, eliminating cold-start races. See #1060.

• 65% faster CI root tests — Root test wall time cut by 65%. See #1062.

• Third-party Actions pinned to commit SHAs — Supply-chain safety through SHA pinning. See #1048.

Bug Fixes

• Runner returns the agent's true final message — Final output is delivered as task output; buffered output is scrubbed to prevent stale residue from leaking across runs. See #1042 and #1054.

• MCP: bound oversized results + preserve full SDK responses — Oversized tool results are bounded and spilled to KV; full SDK responses are preserved by the tool layer. See #1032 and #1037.

• Script safety: KV CRUD + unknown args — KV CRUD operations are safe from scripts; unknown top-level ctx.api args and repeated array params are rejected. See #1043 and #1049.

• Slack thread tree hardening — Truncated tree delivered before cleanup, v2 historical backfill prevented, v2 thread rendering finalized, card-link unfurls suppressed. See #1020, #1063, #1065, and #1070.

• Devin health-check moved to v3 — Points the Devin health-check at v3 instead of the deprecated v1 API. See #1016.

• Workflow run list bounded — Run list no longer returns unbounded rows. See #1028.

• Skills: baked vs seeded de-collision — Baked and seeded skills no longer collide; bundled files are seeded correctly. See #1044.

• Production agent IDs removed from examples — Real agent IDs scrubbed from example docs and configs. See #1041.

• GitHub: self-authored PR reviews ignored — Self-authored reviews no longer counted toward review coverage. See #1058.

• Bun timeout flakes attributable — Flaky Bun timeouts now produce attributable diagnostics. See #1033.

Migration Notes

• SwarmToolResult contract — If you author custom scripts that consume tool results, move to the SwarmToolResult shape. Old opaque wrappers are superseded but not a runtime break — update proactively to stay current.

• archil removal — The archil tooling is removed from the worker image. Operators with archil-dependent workflows should move to the worker-slim target and npx-skills installs before upgrading.