will/swarm-zap
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(agent): make WIP canonical implementation state

Browse Source
This commit is contained in:
zap
2026-03-12 20:43:19 +00:00
parent c64042b75a
commit 8a5b736ce7
2 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
AGENTS.md
View File

@@ -172,8 +172,10 @@ For non-trivial implementation work, prefer a fresh isolated session/run instead
Default pattern: Default pattern:
1. use the current session to clarify scope, inspect state, and decide the plan 1. use the current session to clarify scope, inspect state, and decide the plan
2. write or refresh a compact state file (`WIP.md` for the standing plan, plus `HANDOFF.md` for the immediate baton-pass when useful) 2. write or refresh a compact state file (`WIP.md` for the standing plan, plus `HANDOFF.md` for the immediate baton-pass when useful)
3. start a fresh isolated implementation session/run 3. treat `WIP.md` as the canonical implementation state file for non-trivial work
4. have that fresh session execute the plan from the state files rather than inheriting a bloated chat history 4. when a task or sub-task is completed, update `WIP.md` immediately with status, evidence, and the next recommended action
5. start a fresh isolated implementation session/run
6. have that fresh session execute the plan from the state files rather than inheriting a bloated chat history
Context-window rule of thumb: Context-window rule of thumb:
- keep the main session for direction, approvals, and summaries - keep the main session for direction, approvals, and summaries

1
MEMORY.md
View File

@@ -39,6 +39,7 @@
- Brave free-plan search is rate-limited heavily; avoid parallel bursts. - Brave free-plan search is rate-limited heavily; avoid parallel bursts.
- In direct sessions with Will, cron jobs should use the `automation` agent by default unless Will explicitly says otherwise in that session. - In direct sessions with Will, cron jobs should use the `automation` agent by default unless Will explicitly says otherwise in that session.
- Council tiers should use local LiteLLM-backed models for usage monitoring: light = `litellm/gpt-5.3-codex` with low thinking, medium = `litellm/gpt-5.3-codex` with high thinking, heavy = `litellm/gpt-5.4` with high thinking. - Council tiers should use local LiteLLM-backed models for usage monitoring: light = `litellm/gpt-5.3-codex` with low thinking, medium = `litellm/gpt-5.3-codex` with high thinking, heavy = `litellm/gpt-5.4` with high thinking.
- For non-trivial implementation work, treat `WIP.md` as the canonical state file and update it after each completed task/sub-task with status, concrete evidence, and the next recommended action.
## Infrastructure notes worth remembering ## Infrastructure notes worth remembering
- Full `~/.openclaw` backups upload to MinIO bucket `zap` and are scheduled via OS cron every 6 hours. - Full `~/.openclaw` backups upload to MinIO bucket `zap` and are scheduled via OS cron every 6 hours.