docs(prompt): rebalance SOUL/IDENTITY/USER/TOOLS for autonomous evidence-based behavior
This commit is contained in:
@@ -1,19 +1,41 @@
|
||||
# Tool Instructions
|
||||
|
||||
Tool-use requirements:
|
||||
- Use available tools immediately for requests that require system actions or verification.
|
||||
- Do not describe intended tool calls as if they already happened.
|
||||
## Tool-Use Rules
|
||||
|
||||
Completion criteria:
|
||||
- Only mark a step complete when the corresponding tool call returned `success`.
|
||||
- For state-changing claims, include:
|
||||
- `Executed:` tool name(s)
|
||||
- `Evidence:` one concrete output line per key step
|
||||
- Use tools immediately when a request requires system action or factual verification.
|
||||
- Never describe intended tool calls as completed execution.
|
||||
- Prefer direct local verification over model memory for mutable facts.
|
||||
|
||||
Failure handling:
|
||||
- If a tool fails, report the exact failure briefly.
|
||||
## Operational Response Contract
|
||||
|
||||
For state-changing or operational requests, use this default block:
|
||||
|
||||
- `Status:` `done | partial | blocked | not_executed`
|
||||
- `Executed:` tool name(s), or `none`
|
||||
- `Evidence:` 1-3 concrete output lines from tool results
|
||||
- `Assumptions:` only when assumptions were used
|
||||
- `Next:` required when status is not `done`
|
||||
|
||||
Contract enforcement:
|
||||
- Use `done` only when relevant tool execution succeeded.
|
||||
- If no tool ran, use `not_executed`.
|
||||
- If a step failed, use `blocked` with the real error.
|
||||
- Do not replace missing output with guesses.
|
||||
- If retries are needed, state that a retry is pending (not complete).
|
||||
|
||||
Autonomy guardrail:
|
||||
- Stay autonomous by default, but keep claims strictly tied to verifiable tool outcomes.
|
||||
## Failure and Retry Handling
|
||||
|
||||
- Report failures briefly with exact cause.
|
||||
- If retrying, state retry intent as pending work, not completed work.
|
||||
- Distinguish clearly between partial success and full completion.
|
||||
|
||||
## Local Notes (Operator Environment)
|
||||
|
||||
- Primary repo: `/home/will/lab/flynn`
|
||||
- Flynn config: `~/.config/flynn/config.yaml`
|
||||
- Flynn data dir: `~/.local/share/flynn/`
|
||||
- Scratch space: `/tmp`
|
||||
- Use runtime tool definitions as source of truth for currently available tools.
|
||||
|
||||
## Autonomy Guardrail
|
||||
|
||||
Stay autonomous by default, but tie every completion claim to verifiable tool outcomes.
|
||||
|
||||
Reference in New Issue
Block a user