mirror of
https://github.com/hansjone/oclaw.git
synced 2026-10-14 13:43:17 +08:00
重构主控编排与运行时预热链路,统一工作区提示词/专家调度协议并补齐 wiki 记忆注入与写回闭环。
同时收敛启动与运维脚本默认行为(含 wiki worker)、更新 Admin 可观测性与相关测试,降低首轮时延并提高运行稳定性。 Made-with: Cursor
This commit is contained in:
parent
4a23b715a2
commit
dbbe3add6a
14438 changed files with 2693620 additions and 2546 deletions
|
|
@ -0,0 +1,167 @@
|
|||
# Medium game plan Codex harness
|
||||
|
||||
```yaml qa-scenario
|
||||
id: medium-game-plan-codex-harness
|
||||
title: Medium game plan Codex harness
|
||||
surface: workspace
|
||||
coverage:
|
||||
primary:
|
||||
- workspace.planning
|
||||
secondary:
|
||||
- models.codex-cli
|
||||
objective: Verify the Codex app-server harness can plan and build a medium-complex self-contained browser game.
|
||||
successCriteria:
|
||||
- A live-frontier run fails fast unless the selected primary model is codex/gpt-5.4.
|
||||
- The scenario forces the Codex embedded harness and disables PI fallback.
|
||||
- The prompt explicitly asks the agent to enter plan mode before editing.
|
||||
- The agent writes a self-contained HTML game with a canvas loop, controls, scoring, waves, pause, and restart.
|
||||
docsRefs:
|
||||
- docs/plugins/sdk-agent-harness.md
|
||||
- docs/gateway/configuration-reference.md
|
||||
- docs/help/testing.md
|
||||
codeRefs:
|
||||
- extensions/codex/harness.ts
|
||||
- src/agents/harness/selection.ts
|
||||
- extensions/qa-lab/src/suite.ts
|
||||
execution:
|
||||
kind: flow
|
||||
summary: Run with `pnpm openclaw qa suite --provider-mode live-frontier --model codex/gpt-5.4 --alt-model codex/gpt-5.4 --scenario medium-game-plan-codex-harness`.
|
||||
config:
|
||||
requiredProvider: codex
|
||||
requiredModel: gpt-5.4
|
||||
harnessRuntime: codex
|
||||
harnessFallback: none
|
||||
artifactFile: star-garden-defenders-codex.html
|
||||
gameTitle: Star Garden Defenders
|
||||
minBytes: 5000
|
||||
buildPrompt: |-
|
||||
Enter plan mode first and write a short implementation plan before editing.
|
||||
|
||||
Then build a medium-complex, self-contained browser game at ./star-garden-defenders-codex.html.
|
||||
|
||||
Game: Star Garden Defenders.
|
||||
Requirements:
|
||||
- one HTML file only; no external assets, fonts, scripts, or network calls
|
||||
- canvas-based arcade loop with requestAnimationFrame
|
||||
- keyboard controls and mouse or pointer support
|
||||
- player movement, enemy waves, collectibles or power-ups, collision handling
|
||||
- score, lives or health, wave number, pause, restart, and game-over state
|
||||
- polished inline CSS and clear on-screen controls
|
||||
- after writing the file, reply with the filename and the main systems implemented
|
||||
```
|
||||
|
||||
```yaml qa-flow
|
||||
steps:
|
||||
- name: confirms GPT-5.4 Codex harness target
|
||||
actions:
|
||||
- set: selected
|
||||
value:
|
||||
expr: splitModelRef(env.primaryModel)
|
||||
- assert:
|
||||
expr: "env.providerMode !== 'live-frontier' || selected?.provider === config.requiredProvider"
|
||||
message:
|
||||
expr: "`expected live primary provider ${config.requiredProvider}, got ${env.primaryModel}`"
|
||||
- assert:
|
||||
expr: "env.providerMode !== 'live-frontier' || selected?.model === config.requiredModel"
|
||||
message:
|
||||
expr: "`expected live primary model ${config.requiredModel}, got ${env.primaryModel}`"
|
||||
- if:
|
||||
expr: "env.providerMode !== 'live-frontier'"
|
||||
then:
|
||||
- assert: "true"
|
||||
else:
|
||||
- call: patchConfig
|
||||
saveAs: patchResult
|
||||
args:
|
||||
- env:
|
||||
ref: env
|
||||
patch:
|
||||
agents:
|
||||
defaults:
|
||||
embeddedHarness:
|
||||
runtime:
|
||||
expr: config.harnessRuntime
|
||||
fallback:
|
||||
expr: config.harnessFallback
|
||||
- call: waitForGatewayHealthy
|
||||
args:
|
||||
- ref: env
|
||||
- 60000
|
||||
- call: waitForQaChannelReady
|
||||
args:
|
||||
- ref: env
|
||||
- 60000
|
||||
- call: readConfigSnapshot
|
||||
saveAs: snapshot
|
||||
args:
|
||||
- ref: env
|
||||
- assert:
|
||||
expr: "snapshot.config.agents?.defaults?.embeddedHarness?.runtime === config.harnessRuntime"
|
||||
message:
|
||||
expr: "`expected embeddedHarness.runtime=${config.harnessRuntime}, got ${JSON.stringify(snapshot.config.agents?.defaults?.embeddedHarness)}`"
|
||||
- assert:
|
||||
expr: "snapshot.config.agents?.defaults?.embeddedHarness?.fallback === config.harnessFallback"
|
||||
message:
|
||||
expr: "`expected embeddedHarness.fallback=${config.harnessFallback}, got ${JSON.stringify(snapshot.config.agents?.defaults?.embeddedHarness)}`"
|
||||
detailsExpr: "env.providerMode === 'live-frontier' ? `provider=${selected?.provider} model=${selected?.model} runtime=${snapshot.config.agents?.defaults?.embeddedHarness?.runtime} fallback=${snapshot.config.agents?.defaults?.embeddedHarness?.fallback}` : `mock mode: parsed ${scenario.id}`"
|
||||
- name: builds the medium game artifact
|
||||
actions:
|
||||
- if:
|
||||
expr: "env.providerMode !== 'live-frontier'"
|
||||
then:
|
||||
- assert: "true"
|
||||
else:
|
||||
- call: reset
|
||||
- call: runAgentPrompt
|
||||
args:
|
||||
- ref: env
|
||||
- sessionKey: agent:qa:medium-game-codex
|
||||
message:
|
||||
expr: config.buildPrompt
|
||||
provider:
|
||||
expr: selected?.provider
|
||||
model:
|
||||
expr: selected?.model
|
||||
timeoutMs:
|
||||
expr: resolveQaLiveTurnTimeoutMs(env, 420000, env.primaryModel)
|
||||
- call: waitForOutboundMessage
|
||||
saveAs: outbound
|
||||
args:
|
||||
- ref: state
|
||||
- lambda:
|
||||
params: [candidate]
|
||||
expr: "candidate.conversation.id === 'qa-operator' && candidate.text.includes(config.artifactFile)"
|
||||
- expr: resolveQaLiveTurnTimeoutMs(env, 60000, env.primaryModel)
|
||||
- set: artifactPath
|
||||
value:
|
||||
expr: "path.join(env.gateway.workspaceDir, config.artifactFile)"
|
||||
- call: waitForCondition
|
||||
saveAs: artifact
|
||||
args:
|
||||
- lambda:
|
||||
async: true
|
||||
expr: "((await fs.readFile(artifactPath, 'utf8').catch(() => '')).includes(config.gameTitle) ? await fs.readFile(artifactPath, 'utf8').catch(() => '') : undefined)"
|
||||
- expr: resolveQaLiveTurnTimeoutMs(env, 60000, env.primaryModel)
|
||||
- 500
|
||||
- set: artifactLower
|
||||
value:
|
||||
expr: normalizeLowercaseStringOrEmpty(artifact)
|
||||
- assert:
|
||||
expr: "artifact.length >= config.minBytes"
|
||||
message:
|
||||
expr: "`expected medium game artifact >= ${config.minBytes} bytes, got ${artifact.length}`"
|
||||
- assert:
|
||||
expr: "artifactLower.includes('star garden defenders') && artifactLower.includes('<canvas') && artifactLower.includes('requestanimationframe')"
|
||||
message: missing title, canvas, or animation loop
|
||||
- assert:
|
||||
expr: "artifactLower.includes('keydown') || artifactLower.includes('keyup')"
|
||||
message: missing keyboard controls
|
||||
- assert:
|
||||
expr: "artifactLower.includes('score') && artifactLower.includes('wave') && artifactLower.includes('pause') && artifactLower.includes('restart')"
|
||||
message: missing score, wave, pause, or restart systems
|
||||
- assert:
|
||||
expr: "outbound.text.includes(config.artifactFile)"
|
||||
message:
|
||||
expr: "`final reply did not mention ${config.artifactFile}: ${outbound.text}`"
|
||||
detailsExpr: "env.providerMode !== 'live-frontier' ? 'mock mode: skipped live medium-game build' : `${config.artifactFile} bytes=${artifact.length}`"
|
||||
```
|
||||
Loading…
Add table
Add a link
Reference in a new issue