ewilliams28/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-08-12 21:53:00 -06:00
Code Issues Packages Projects Releases Wiki Activity

test(codex): stress resume across gateway restarts (#110486)

Browse Source
This commit is contained in:
Peter Steinberger
2026-07-18 07:50:17 +01:00
committed by GitHub
parent 4186691885
commit b5fb47e283
4 changed files with 238 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/help/testing-live.md
+19
View File
@@ -320,14 +320,26 @@ Docker notes:
- Default thinking: `low`
- Model override: `OPENCLAW_LIVE_CODEX_HARNESS_MODEL=openai/<model>`
- Thinking override: `OPENCLAW_LIVE_CODEX_HARNESS_THINKING=<level>`
- Non-default model effort assertion:
`OPENCLAW_LIVE_CODEX_HARNESS_EXPECTED_EFFORT=<level>`
- Matrix override: `OPENCLAW_LIVE_CODEX_HARNESS_TARGETS=<model>=<thinking>,...`
- Auth mode: `OPENCLAW_LIVE_CODEX_HARNESS_AUTH=codex-auth` (default) uses the
copied Codex login; `api-key` uses `OPENAI_API_KEY` through Codex app-server.
- Optional image probe: `OPENCLAW_LIVE_CODEX_HARNESS_IMAGE_PROBE=1`
- Optional MCP/tool probe: `OPENCLAW_LIVE_CODEX_HARNESS_MCP_PROBE=1`
- Optional Guardian probe: `OPENCLAW_LIVE_CODEX_HARNESS_GUARDIAN_PROBE=1`
- Optional resume stress: `OPENCLAW_LIVE_CODEX_HARNESS_RESUME_STRESS=1` adds
four history turns, then closes and restarts the Gateway and Codex app-server
three times while requiring the same native thread id and conversation
history. Override the bounded counts with
`OPENCLAW_LIVE_CODEX_HARNESS_RESUME_STRESS_HISTORY_TURNS` (1-20) and
`OPENCLAW_LIVE_CODEX_HARNESS_RESUME_STRESS_RESTARTS` (1-10).
- Optional loop-relay opt-out probe:
`OPENCLAW_LIVE_CODEX_HARNESS_DISABLE_LOOP_RELAY=1`
- The requested thinking preference may map to the nearest effort advertised
by Codex for that model. For example, Luna maps `minimal` to `low`.
- Known Codex catalog models derive that exact native effort automatically.
Unknown model overrides must state the expected mapped effort.
- The smoke forces provider/model `agentRuntime.id: "codex"` so a broken Codex
harness cannot pass by silently falling back to OpenClaw.
- Auth: Codex app-server auth from the local Codex subscription login, or
@@ -351,6 +363,13 @@ Docker recipe:
pnpm test:docker:live-codex-harness
```
Restart and history stress:
```bash
OPENCLAW_LIVE_CODEX_HARNESS_RESUME_STRESS=1 \
pnpm test:docker:live-codex-harness
```
GPT-5.6 native Codex matrix:
```bash