ed/manual_slop
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

wip docs

Browse Source
This commit is contained in:
Edward R. Gonzalez
2026-02-22 11:22:08 -05:00
parent da8df7a393
commit 1b71b748db
6 changed files with 31 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docs/guide_tools.md
View File

@@ -46,5 +46,8 @@ The core system prompt explicitly guides the AI on how to use this tool safely:
### Synthetic Context Refresh
Immediately after **any** tool call turn finishes, ai_client runs _reread_file_items. It fetches the latest disk state of all files in the current project context and appends them as a synthetic [FILES UPDATED] message to the tool result.
This means if the AI writes to a file, it instantly "sees" the modification in its next turn without having to waste a cycle calling read_file.
After the **last** tool call in each round finishes (when multiple tools are called in a single round, the refresh happens once after all of them), ai_client runs `_reread_file_items`. It fetches the latest disk state of all files in the current project context. The `file_items` variable is reassigned so subsequent tool rounds within the same request use the fresh content.
For Anthropic, the refreshed contents are injected as a text block in the `tool_results` user message. For Gemini, they are appended to the last function response's output string. In both cases, the block is prefixed with `[FILES UPDATED]` / `[SYSTEM: FILES UPDATED]`.
On the next tool round, stale file-refresh blocks from previous rounds are stripped from history to prevent token accumulation. This means if the AI writes to a file, it instantly "sees" the modification in its next turn without having to waste a cycle calling `read_file`, and the cost of carrying the full file snapshot is limited to one round.