Vendor OpenClaw source as Adolf fork baseline
Some checks failed
ClawSweeper Dispatch / dispatch (push) Has been cancelled
CodeQL / Security High (actions) (push) Has been cancelled
CodeQL / Security High (channel-runtime-boundary) (push) Has been cancelled
CodeQL / Security High (core-auth-secrets) (push) Has been cancelled
CodeQL / Security High (mcp-process-tool-boundary) (push) Has been cancelled
CodeQL / Security High (network-ssrf-boundary) (push) Has been cancelled
CodeQL / Security High (plugin-trust-boundary) (push) Has been cancelled
CodeQL / Security High (process-exec-boundary) (push) Has been cancelled
Docs Sync Publish Repo / sync-publish-repo (push) Has been cancelled
Docs / docs (push) Has been cancelled
OpenClaw Stable Main Closeout / Resolve stable release closeout inputs (push) Has been cancelled
OpenClaw Stable Main Closeout / Verify stable main closeout (push) Has been cancelled
Workflow Sanity / no-tabs (push) Has been cancelled
Workflow Sanity / actionlint (push) Has been cancelled
Workflow Sanity / generated-doc-baselines (push) Has been cancelled
CI / runner-admission (push) Has been cancelled
CI / preflight (push) Has been cancelled
CI / security-fast (push) Has been cancelled
CI / pnpm-store-warmup (push) Has been cancelled
CI / build-artifacts (push) Has been cancelled
CI / native-i18n (push) Has been cancelled
CI / ${{ matrix.check_name }} (push) Has been cancelled
CI / ${{ matrix.checkName }} (push) Has been cancelled
CI / checks-node-compat-node22 (push) Has been cancelled
CI / check-bundled-channel-config-metadata (push) Has been cancelled
CI / check-dependencies (push) Has been cancelled
CI / check-guards (push) Has been cancelled
CI / check-lint (push) Has been cancelled
CI / check-prod-types (push) Has been cancelled
CI / check-shrinkwrap (push) Has been cancelled
CI / check-test-types (push) Has been cancelled
CI / check-additional-boundaries-a (push) Has been cancelled
CI / check-additional-boundaries-bcd (push) Has been cancelled
CI / check-additional-extension-bundled (push) Has been cancelled
CI / check-additional-extension-channels (push) Has been cancelled
CI / check-additional-extension-package-boundary (push) Has been cancelled
CI / check-additional-runtime-topology-architecture (push) Has been cancelled
CI / check-session-accessor-boundary (push) Has been cancelled
CI / check-session-transcript-reader-boundary (push) Has been cancelled
CI / check-docs (push) Has been cancelled
CI / skills-python (push) Has been cancelled
CI / macos-swift (push) Has been cancelled
CI / ios-build (push) Has been cancelled
CI / ci-timings-summary (push) Has been cancelled
Native App Locale Refresh / Refresh native fa (push) Has been cancelled
Native App Locale Refresh / Refresh native fr (push) Has been cancelled
Native App Locale Refresh / Refresh native hi (push) Has been cancelled
Native App Locale Refresh / Refresh native id (push) Has been cancelled
Native App Locale Refresh / Refresh native it (push) Has been cancelled
Native App Locale Refresh / Refresh native ja-JP (push) Has been cancelled
Control UI Locale Refresh / plan (push) Has been cancelled
Control UI Locale Refresh / Refresh ${{ matrix.locale }} (push) Has been cancelled
Control UI Locale Refresh / Commit control UI locale refresh (push) Has been cancelled
Live Media Runner Image / Build live media runner image (push) Has been cancelled
Native App Locale Refresh / Refresh native ar (push) Has been cancelled
Native App Locale Refresh / Refresh native de (push) Has been cancelled
Native App Locale Refresh / Refresh native es (push) Has been cancelled
Native App Locale Refresh / Refresh native ko (push) Has been cancelled
Native App Locale Refresh / Refresh native nl (push) Has been cancelled
Native App Locale Refresh / Refresh native pl (push) Has been cancelled
Native App Locale Refresh / Refresh native pt-BR (push) Has been cancelled
Native App Locale Refresh / Refresh native ru (push) Has been cancelled
Native App Locale Refresh / Refresh native sv (push) Has been cancelled
Native App Locale Refresh / Refresh native th (push) Has been cancelled
Native App Locale Refresh / Refresh native tr (push) Has been cancelled
Native App Locale Refresh / Refresh native uk (push) Has been cancelled
Native App Locale Refresh / Refresh native vi (push) Has been cancelled
Native App Locale Refresh / Refresh native zh-CN (push) Has been cancelled
Native App Locale Refresh / Refresh native zh-TW (push) Has been cancelled
Native App Locale Refresh / Commit native locale refresh (push) Has been cancelled
Plugin Init Scaffold Validation / Validate provider scaffold (push) Has been cancelled
Plugin NPM Release / preview_plugins_npm (push) Has been cancelled
Plugin NPM Release / Validate release publish approval (push) Has been cancelled
Plugin NPM Release / preview_plugin_pack (push) Has been cancelled
Plugin NPM Release / publish_plugins_npm (push) Has been cancelled
Sandbox Common Smoke / sandbox-common-smoke (push) Has been cancelled
Website Installer Sync / static (push) Has been cancelled
Website Installer Sync / linux-docker (push) Has been cancelled
Website Installer Sync / macos-installer (push) Has been cancelled
Website Installer Sync / windows-installer (push) Has been cancelled
Website Installer Sync / sync-website (push) Has been cancelled
Some checks failed
ClawSweeper Dispatch / dispatch (push) Has been cancelled
CodeQL / Security High (actions) (push) Has been cancelled
CodeQL / Security High (channel-runtime-boundary) (push) Has been cancelled
CodeQL / Security High (core-auth-secrets) (push) Has been cancelled
CodeQL / Security High (mcp-process-tool-boundary) (push) Has been cancelled
CodeQL / Security High (network-ssrf-boundary) (push) Has been cancelled
CodeQL / Security High (plugin-trust-boundary) (push) Has been cancelled
CodeQL / Security High (process-exec-boundary) (push) Has been cancelled
Docs Sync Publish Repo / sync-publish-repo (push) Has been cancelled
Docs / docs (push) Has been cancelled
OpenClaw Stable Main Closeout / Resolve stable release closeout inputs (push) Has been cancelled
OpenClaw Stable Main Closeout / Verify stable main closeout (push) Has been cancelled
Workflow Sanity / no-tabs (push) Has been cancelled
Workflow Sanity / actionlint (push) Has been cancelled
Workflow Sanity / generated-doc-baselines (push) Has been cancelled
CI / runner-admission (push) Has been cancelled
CI / preflight (push) Has been cancelled
CI / security-fast (push) Has been cancelled
CI / pnpm-store-warmup (push) Has been cancelled
CI / build-artifacts (push) Has been cancelled
CI / native-i18n (push) Has been cancelled
CI / ${{ matrix.check_name }} (push) Has been cancelled
CI / ${{ matrix.checkName }} (push) Has been cancelled
CI / checks-node-compat-node22 (push) Has been cancelled
CI / check-bundled-channel-config-metadata (push) Has been cancelled
CI / check-dependencies (push) Has been cancelled
CI / check-guards (push) Has been cancelled
CI / check-lint (push) Has been cancelled
CI / check-prod-types (push) Has been cancelled
CI / check-shrinkwrap (push) Has been cancelled
CI / check-test-types (push) Has been cancelled
CI / check-additional-boundaries-a (push) Has been cancelled
CI / check-additional-boundaries-bcd (push) Has been cancelled
CI / check-additional-extension-bundled (push) Has been cancelled
CI / check-additional-extension-channels (push) Has been cancelled
CI / check-additional-extension-package-boundary (push) Has been cancelled
CI / check-additional-runtime-topology-architecture (push) Has been cancelled
CI / check-session-accessor-boundary (push) Has been cancelled
CI / check-session-transcript-reader-boundary (push) Has been cancelled
CI / check-docs (push) Has been cancelled
CI / skills-python (push) Has been cancelled
CI / macos-swift (push) Has been cancelled
CI / ios-build (push) Has been cancelled
CI / ci-timings-summary (push) Has been cancelled
Native App Locale Refresh / Refresh native fa (push) Has been cancelled
Native App Locale Refresh / Refresh native fr (push) Has been cancelled
Native App Locale Refresh / Refresh native hi (push) Has been cancelled
Native App Locale Refresh / Refresh native id (push) Has been cancelled
Native App Locale Refresh / Refresh native it (push) Has been cancelled
Native App Locale Refresh / Refresh native ja-JP (push) Has been cancelled
Control UI Locale Refresh / plan (push) Has been cancelled
Control UI Locale Refresh / Refresh ${{ matrix.locale }} (push) Has been cancelled
Control UI Locale Refresh / Commit control UI locale refresh (push) Has been cancelled
Live Media Runner Image / Build live media runner image (push) Has been cancelled
Native App Locale Refresh / Refresh native ar (push) Has been cancelled
Native App Locale Refresh / Refresh native de (push) Has been cancelled
Native App Locale Refresh / Refresh native es (push) Has been cancelled
Native App Locale Refresh / Refresh native ko (push) Has been cancelled
Native App Locale Refresh / Refresh native nl (push) Has been cancelled
Native App Locale Refresh / Refresh native pl (push) Has been cancelled
Native App Locale Refresh / Refresh native pt-BR (push) Has been cancelled
Native App Locale Refresh / Refresh native ru (push) Has been cancelled
Native App Locale Refresh / Refresh native sv (push) Has been cancelled
Native App Locale Refresh / Refresh native th (push) Has been cancelled
Native App Locale Refresh / Refresh native tr (push) Has been cancelled
Native App Locale Refresh / Refresh native uk (push) Has been cancelled
Native App Locale Refresh / Refresh native vi (push) Has been cancelled
Native App Locale Refresh / Refresh native zh-CN (push) Has been cancelled
Native App Locale Refresh / Refresh native zh-TW (push) Has been cancelled
Native App Locale Refresh / Commit native locale refresh (push) Has been cancelled
Plugin Init Scaffold Validation / Validate provider scaffold (push) Has been cancelled
Plugin NPM Release / preview_plugins_npm (push) Has been cancelled
Plugin NPM Release / Validate release publish approval (push) Has been cancelled
Plugin NPM Release / preview_plugin_pack (push) Has been cancelled
Plugin NPM Release / publish_plugins_npm (push) Has been cancelled
Sandbox Common Smoke / sandbox-common-smoke (push) Has been cancelled
Website Installer Sync / static (push) Has been cancelled
Website Installer Sync / linux-docker (push) Has been cancelled
Website Installer Sync / macos-installer (push) Has been cancelled
Website Installer Sync / windows-installer (push) Has been cancelled
Website Installer Sync / sync-website (push) Has been cancelled
Adolf is a fork/vendored clone of github.com/openclaw/openclaw (v2026.6.11), free to diverge. Tree copied sans upstream .git; upstream remote added for future syncs. Node pinned to 24 (.nvmrc); engines already require >=22.19. Preserves docs/ARCHITECTURE.md. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01LeqyaxJF2nbRXJtae2kNB2
This commit is contained in:
143
qa/scenarios/agents/instruction-followthrough-repo-contract.yaml
Normal file
143
qa/scenarios/agents/instruction-followthrough-repo-contract.yaml
Normal file
@@ -0,0 +1,143 @@
|
||||
title: Instruction followthrough repo contract
|
||||
|
||||
scenario:
|
||||
id: instruction-followthrough-repo-contract
|
||||
surface: repo-contract
|
||||
coverage:
|
||||
primary:
|
||||
- agents.instructions
|
||||
secondary:
|
||||
- runtime.first-action
|
||||
objective: Verify the agent reads repo instruction files first, follows the required tool order, and completes the first feasible action instead of stopping at a plan.
|
||||
successCriteria:
|
||||
- Agent reads the seeded instruction files before writing the requested artifact.
|
||||
- Agent writes the requested artifact in the same run instead of returning only a plan.
|
||||
- Agent does not ask for permission before the first feasible action.
|
||||
- Final reply makes the completed read/write sequence explicit.
|
||||
docsRefs:
|
||||
- docs/help/testing.md
|
||||
- docs/channels/qa-channel.md
|
||||
codeRefs:
|
||||
- src/agents/system-prompt.ts
|
||||
- src/agents/embedded-agent-runner/run/incomplete-turn.ts
|
||||
- extensions/qa-lab/src/mock-openai-server.ts
|
||||
execution:
|
||||
kind: flow
|
||||
summary: Verify the agent reads repo instructions first, then completes the first bounded followthrough task without stalling.
|
||||
config:
|
||||
requiredChannelDriver: qa-channel
|
||||
workspaceFiles:
|
||||
AGENT.md: |-
|
||||
# Repo contract
|
||||
|
||||
Step order:
|
||||
1. Read AGENT.md.
|
||||
2. Read SOUL.md.
|
||||
3. Read FOLLOWTHROUGH_INPUT.md.
|
||||
4. Write ./repo-contract-summary.txt.
|
||||
5. Reply with three labeled lines exactly once: Read, Wrote, Status.
|
||||
|
||||
Do not stop after planning.
|
||||
Do not ask for permission before the first feasible action.
|
||||
SOUL.md: |-
|
||||
# Execution style
|
||||
|
||||
Stay brief, honest, and action-first.
|
||||
If the next tool action is feasible, do it before replying.
|
||||
FOLLOWTHROUGH_INPUT.md: |-
|
||||
Mission: prove you followed the repo contract.
|
||||
Evidence path: AGENT.md -> SOUL.md -> FOLLOWTHROUGH_INPUT.md -> repo-contract-summary.txt
|
||||
prompt: |-
|
||||
Repo contract followthrough check. Read AGENT.md, SOUL.md, and FOLLOWTHROUGH_INPUT.md first.
|
||||
Then follow the repo contract exactly, write ./repo-contract-summary.txt, and reply with
|
||||
three labeled lines: Read, Wrote, Status.
|
||||
Do not stop after planning and do not ask for permission before the first feasible action.
|
||||
expectedReplyAll:
|
||||
- "read:"
|
||||
- "wrote:"
|
||||
- "status:"
|
||||
expectedArtifactAll:
|
||||
- "repo contract"
|
||||
expectedArtifactAny:
|
||||
- "evidence path"
|
||||
- "agent.md"
|
||||
- "followthrough"
|
||||
forbiddenNeedles:
|
||||
- need permission
|
||||
- need your approval
|
||||
- can you approve
|
||||
- i would
|
||||
- i can
|
||||
- next i would
|
||||
|
||||
flow:
|
||||
steps:
|
||||
- name: follows repo instructions instead of stopping at a plan
|
||||
actions:
|
||||
- call: reset
|
||||
- forEach:
|
||||
items:
|
||||
expr: "Object.entries(config.workspaceFiles ?? {})"
|
||||
item: workspaceFile
|
||||
actions:
|
||||
- call: fs.writeFile
|
||||
args:
|
||||
- expr: "path.join(env.gateway.workspaceDir, String(workspaceFile[0]))"
|
||||
- expr: "`${String(workspaceFile[1] ?? '').trimEnd()}\\n`"
|
||||
- utf8
|
||||
- set: artifactPath
|
||||
value:
|
||||
expr: "path.join(env.gateway.workspaceDir, 'repo-contract-summary.txt')"
|
||||
- call: runAgentPrompt
|
||||
args:
|
||||
- ref: env
|
||||
- sessionKey: agent:qa:repo-contract
|
||||
message:
|
||||
expr: config.prompt
|
||||
timeoutMs:
|
||||
expr: liveTurnTimeoutMs(env, 40000)
|
||||
- call: waitForCondition
|
||||
saveAs: artifact
|
||||
args:
|
||||
- lambda:
|
||||
async: true
|
||||
expr: "(() => { const normalize = (value) => normalizeLowercaseStringOrEmpty(value); const matches = (value) => { const normalized = normalize(value); return normalized && config.expectedArtifactAll.every((needle) => normalized.includes(normalize(needle))) && config.expectedArtifactAny.some((needle) => normalized.includes(normalize(needle))); }; return fs.readFile(artifactPath, 'utf8').then((value) => matches(value) ? value : undefined).catch(() => undefined); })()"
|
||||
- expr: liveTurnTimeoutMs(env, 30000)
|
||||
- expr: "env.providerMode === 'mock-openai' ? 100 : 250"
|
||||
- set: normalizedArtifact
|
||||
value:
|
||||
expr: "normalizeLowercaseStringOrEmpty(artifact)"
|
||||
- assert:
|
||||
expr: "config.expectedArtifactAll.every((needle) => normalizedArtifact.includes(normalizeLowercaseStringOrEmpty(needle))) && config.expectedArtifactAny.some((needle) => normalizedArtifact.includes(normalizeLowercaseStringOrEmpty(needle)))"
|
||||
message:
|
||||
expr: "`repo contract artifact missing expected followthrough signals: ${artifact}`"
|
||||
- set: expectedReplyAll
|
||||
value:
|
||||
expr: config.expectedReplyAll.map(normalizeLowercaseStringOrEmpty)
|
||||
- call: waitForCondition
|
||||
saveAs: outbound
|
||||
args:
|
||||
- lambda:
|
||||
expr: "state.getSnapshot().messages.filter((candidate) => candidate.direction === 'outbound' && candidate.conversation.id === 'qa-operator' && expectedReplyAll.every((needle) => normalizeLowercaseStringOrEmpty(candidate.text).includes(needle))).at(-1)"
|
||||
- expr: liveTurnTimeoutMs(env, 30000)
|
||||
- expr: "env.providerMode === 'mock-openai' ? 100 : 250"
|
||||
- assert:
|
||||
expr: "!config.forbiddenNeedles.some((needle) => normalizeLowercaseStringOrEmpty(outbound.text).includes(needle))"
|
||||
message:
|
||||
expr: "`repo contract followthrough bounced for permission or stalled: ${outbound.text}`"
|
||||
- set: followthroughDebugRequests
|
||||
value:
|
||||
expr: "env.mock ? [...(await fetchJson(`${env.mock.baseUrl}/debug/requests`))].filter((request) => /repo contract followthrough check/i.test(String(request.allInputText ?? ''))) : []"
|
||||
- assert:
|
||||
expr: "!env.mock || followthroughDebugRequests.filter((request) => request.plannedToolName === 'read').length >= 3"
|
||||
message:
|
||||
expr: "`expected three read tool calls before write, saw plannedToolNames=${JSON.stringify(followthroughDebugRequests.map((request) => request.plannedToolName ?? null))}`"
|
||||
- assert:
|
||||
expr: "!env.mock || followthroughDebugRequests.some((request) => request.plannedToolName === 'write')"
|
||||
message:
|
||||
expr: "`expected write tool call during repo contract followthrough, saw plannedToolNames=${JSON.stringify(followthroughDebugRequests.map((request) => request.plannedToolName ?? null))}`"
|
||||
- assert:
|
||||
expr: "!env.mock || (() => { const readIndices = followthroughDebugRequests.map((r, i) => r.plannedToolName === 'read' ? i : -1).filter(i => i >= 0); const firstWrite = followthroughDebugRequests.findIndex((r) => r.plannedToolName === 'write'); return readIndices.length >= 3 && firstWrite >= 0 && readIndices[2] < firstWrite; })()"
|
||||
message:
|
||||
expr: "`expected all 3 reads before any write during repo contract followthrough, saw plannedToolNames=${JSON.stringify(followthroughDebugRequests.map((request) => request.plannedToolName ?? null))}`"
|
||||
detailsExpr: outbound.text
|
||||
Reference in New Issue
Block a user