alvis
bedb527145
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
2.5 KiB
Codex Happy Path Prompt Snapshots
These fixtures capture the default OpenAI/Codex happy path for prompt review:
- OpenAI model through the Codex harness and Codex app-server runtime.
- Codex harness default coverage for tool-only visible source replies.
- Telegram direct chat, Discord group chat, and a heartbeat turn with
heartbeat_respondavailable through searchable dynamic tools.
The Markdown files show selected app-server thread/turn params plus a reconstructed model-bound prompt layer stack: Codex gpt-5.5 model instructions from a pinned Codex model catalog fixture, Codex permission developer instructions for the happy-path yolo profile, OpenClaw developer instructions, turn input with simulated OpenClaw workspace bootstrap runtime context, heartbeat collaboration-mode guidance when applicable, and references to the complete dynamic tool catalog.
The workspace bootstrap simulation includes dummy workspace contents so prompt reviewers can see how OpenClaw routes stable profile files into Codex developer instructions, keeps MEMORY.md in turn input, and points heartbeat turns at HEARTBEAT.md without inlining it. AGENTS.md is intentionally not repeated here because Codex loads it natively.
The tool catalog is pinned to the canonical happy-path OpenClaw tools so optional locally installed plugin tools do not create fixture churn.
The Codex model prompt fixture is generated from the same Codex model catalog/cache shape that the Codex runtime uses for remote model metadata. Regenerate it from Codex's runtime cache or, when present, a local Codex checkout with:
pnpm prompt:snapshots:sync-codex-model
These snapshots are still not a byte-for-byte raw OpenAI request capture. Codex-owned native AGENTS.md, environment context, memories, app/plugin instructions, and built-in collaboration-mode instructions can be added inside the Codex runtime after OpenClaw sends thread and turn params.
Regenerate with:
pnpm prompt:snapshots:gen
Check for drift with:
pnpm prompt:snapshots:check
Snapshots:
- telegram-direct-codex-message-tool.md
- discord-group-codex-message-tool.md
- telegram-heartbeat-codex-tool.md
- codex-dynamic-tools.telegram-direct.json
- codex-dynamic-tools.discord-group.json
- codex-dynamic-tools.heartbeat-turn.json
Codex model prompt fixtures:
- ../codex-model-catalog/gpt-5.5.pragmatic.instructions.md
- ../codex-model-catalog/gpt-5.5.pragmatic.source.json