Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until another agent proves it. Your decisions, judgement and taste are the bar that work must clear. Declare your vision and let agents build it.
JavaScript agentic-codingai-agentsai-governanceautonomous-agentsclaude-codeclicode-reviewcodexcoding-agentsdeveloper-toolsgit-hooksllmlocal-firstmulti-agentsoftware-factoryspec-driven-developmentverificationvibe-coding
docs(changelog): 0.9.2 carries the registered-runner timing fix
Corey Olson54f4938b992c
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex d1c4156e..94214e33 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -45,6 +45,7 @@ Pullboard now turns a failure that keeps coming back into a rule with its proof.- `pullboard next` never tells a seat it holds another seat's claim, and the MCP `board_status` tool answers on a board with held items. (#958, #974)- `pullboard next --verify` no longer reserves a review for a seat of the session that built the item. (#973)- A hung network mount no longer stalls Pullboard. (#912)+- A registered runner's round trip no longer times out under load: each runner call makes 5 git calls instead of about 700, and its timing guards charge each phase only its own time. (#972)- The tour leaves no demo project behind, links nothing to the relay, and finishes when an agent runs it. (#951, #952)- `pullboard land` works in a repo with no remote, and `pullboard status` no longer opens with a refusal there. (#963)- `pullboard init` now prints a short summary and one next step; the details are behind `--verbose`. (#964)