admin/gbrain
1
0
Fork 0
mirror of https://github.com/garrytan/gbrain.git synced 2026-07-28 06:23:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: reframe v0.16 durability headline around OpenClaw crashes

Browse Source 
"Laptop closed mid-run" framing implied a consumer workflow. Real pain is
OpenClaw subagents dying daily on worker kill, memory blip, or timeout.
Headline + README copy match the body now.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-04-21 20:45:12 -07:00
co-authored by Claude Opus 4.7
parent 5759aa8f73
commit 83beec43af
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+2 -2
View File
@@ -4,8 +4,8 @@ All notable changes to GBrain will be documented in this file.
## [0.16.0] - 2026-04-20
## **Durable agents land. Your LLM loops survive crashes, sleeps, and worker restarts now.**
## **Laptop closed mid-run? Come back, resume where it died.**
## **Durable agents land. Your LLM loops survive crashes, timeouts, and worker restarts now.**
## **OpenClaw died mid-run? Come back, resume from the last committed turn.**
Your OpenClaw crashes daily. Not "sometimes." Daily. An 8-turn OpenClaw subagent fires a tool call, the worker dies on a memory blip, all eight turns of context are gone, and there's nothing to do but start over from turn zero. This release kills that. `gbrain agent run` submits an Anthropic Messages API conversation as a first-class Minion job: every turn persists to `subagent_messages`, every tool call is a two-phase ledger row (`pending` → `complete | failed`), and replay on worker restart picks up from exactly the last committed turn. Crash-safe by construction, not by hope.
README.md
+2 -2
View File
@@ -232,7 +232,7 @@ Moving gateway crons to Minions (deterministic scripts, zero LLM tokens per fire
## Durable agents: `gbrain agent` (v0.15)
Your subagent runs survive crashes now. Laptop closed mid-run? The worker re-claims on wake and replays from the last committed turn. Fan-out across 50 shards, one shard crashes — the aggregator still claims after every child reaches a terminal state and writes a mixed-outcome summary. Tool calls persist as a two-phase ledger (`pending` → `complete | failed`) so replay is safe by construction, not by hope.
Your subagent runs survive crashes now. OpenClaw died mid-run? The worker re-claims on restart and replays from the last committed turn. Fan-out across 50 shards, one shard crashes — the aggregator still claims after every child reaches a terminal state and writes a mixed-outcome summary. Tool calls persist as a two-phase ledger (`pending` → `complete | failed`) so replay is safe by construction, not by hope.
```bash
# Submit a single-subagent run
@@ -247,7 +247,7 @@ gbrain agent run "analyze every page" \
gbrain agent logs 1247 --follow --since 5m
```
Durability is the point: every Anthropic turn commits to `subagent_messages`, every tool call to `subagent_tool_executions`. Worker kills, laptop sleeps, timeouts — all resumable. Host repos (your OpenClaw, etc.) ship their own subagent definitions via `GBRAIN_PLUGIN_PATH` + a `gbrain.plugin.json` manifest: see [`docs/guides/plugin-authors.md`](docs/guides/plugin-authors.md). Requires `ANTHROPIC_API_KEY` on the worker.
Durability is the point: every Anthropic turn commits to `subagent_messages`, every tool call to `subagent_tool_executions`. Worker kills, OpenClaw crashes, timeouts — all resumable. Host repos (your OpenClaw, etc.) ship their own subagent definitions via `GBRAIN_PLUGIN_PATH` + a `gbrain.plugin.json` manifest: see [`docs/guides/plugin-authors.md`](docs/guides/plugin-authors.md). Requires `ANTHROPIC_API_KEY` on the worker.
## Skillify: your skills tree stops being a black box