From 0d0b7f2369825682334f661571cb734d432aef4b Mon Sep 17 00:00:00 2001 From: dtzp555 Date: Sat, 7 Mar 2026 21:45:44 +1000 Subject: [PATCH] process: require main to forward worker updates to Tao --- MEMORY.md | 3 ++- memory/2026-03-07.md | 1 + skills/execution-agent-dispatch/SKILL.md | 15 +++++++++++++++ 3 files changed, 18 insertions(+), 1 deletion(-) diff --git a/MEMORY.md b/MEMORY.md index 2e3e304..d561124 100644 --- a/MEMORY.md +++ b/MEMORY.md @@ -39,7 +39,8 @@ - Historical temporary preference once was: all subagents **primary** = `openai-codex/gpt-5.2`, **fallback** = `github-copilot/claude-opus-4.6`. - Current important exception / newer rule: **codex_worker** should use **primary** = `openai-codex/gpt-5.4`, prefer high/extra/xhigh thinking when available, and should **not auto-fallback** to another model. If its primary model is unavailable, report to Tao and let Tao decide the replacement model. - Additional long-lived execution agents initialized locally for repeat use: **docs_worker**, **qa_worker**, **ops_worker**. -- Execution-agent system still needs a standardized dispatch/handoff layer: task input template, result format, and blocker/escalation rules. +- Execution-agent system needs a standardized dispatch/handoff layer: task input template, result format, blocker/escalation rules, and a **main-to-Tao forwarding rule**. +- New hard rule: when an execution agent reports acceptance, milestone progress, blocker, or completion, **main must update Tao first before continuing with review/commit/next-step work**. If worker completion is not forwarded, treat that as a main-process failure rather than “still working”. ## 8) Watchdog / automation policy - Tao preference: avoid watchdog-style auto-restart automation. diff --git a/memory/2026-03-07.md b/memory/2026-03-07.md index 1627b03..42d20c9 100644 --- a/memory/2026-03-07.md +++ b/memory/2026-03-07.md @@ -96,3 +96,4 @@ - keep long-lived role-based agents for reuse - delete or archive project-specific temporary agents after the project ends to avoid an “agent graveyard” - Next improvement approved: add a standardized execution-agent dispatch / handoff protocol so workers receive clearer task packets and report blockers/results consistently. +- New hard reporting rule approved: when a worker reports acceptance, milestone, blocker, or completion, main must update Tao before continuing other downstream work. A worker completion that is not forwarded counts as a main-process failure, not “still in progress”. diff --git a/skills/execution-agent-dispatch/SKILL.md b/skills/execution-agent-dispatch/SKILL.md index 6bcc470..beeacf6 100644 --- a/skills/execution-agent-dispatch/SKILL.md +++ b/skills/execution-agent-dispatch/SKILL.md @@ -76,6 +76,21 @@ Default rule: - report at milestone - report immediately on blockers +## Main-to-Tao forwarding rule + +Execution-agent updates are not complete until main forwards the state change upward. + +When a worker reports any of these: +- task accepted +- milestone reached +- blocked +- failed +- completed + +main must update Tao **before** continuing with review, commit, release, or re-delegation work. + +If a worker has already reported completion and main has not forwarded that state, treat it as a **main process failure**, not as "still in progress". + ## Completion rule A task is not complete just because files changed.