Pine/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases 1 Wiki Activity

fix(tools): make code result cards authoritative

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-21 18:38:22 +08:00
parent f9b938a4a8
commit 449e3cf298
19 changed files with 1526 additions and 374 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.md
+1 -1
View File
@@ -34,7 +34,7 @@ type ToolExecutionResult =
`tools/post-execute` has two mutually exclusive successful projections. Replacing `content` changes only Native/model presentation and preserves the canonical value and metadata. Replacing `value` revalidates the replacement and recomputes both presentation projections. A block removes the value and becomes a failure. Content replacement is therefore not a confidentiality mechanism: policy that must prevent programmatic access blocks the call or replaces the value.
Canonical values are execution-local. The agent loop persists `tool/result` with only `content`, `error`, and `meta`; Code Mode's `tool/code-dispatch` persists only its bounded summary. Neither event stores the intermediate value, so replay reproduces presentation but cannot reconstruct the programmatic result. `presentationMeta` is computed only for a direct surface call, including the outer `run_code`; a nested Code dispatch gets no metadata or result card. Generic and tool-owned spill projections similarly skip nested dispatches, whose canonical value never enters model context.
Canonical values are execution-local. The agent loop persists `tool/result` with only `content`, `error`, and optional `meta`; Code Mode's `tool/code-dispatch` persists only its bounded summary. Neither event stores the intermediate value, so replay reproduces presentation but cannot reconstruct the programmatic result. When a tool declares `presentationMeta`, it is computed only for a direct surface call; a nested Code dispatch gets no metadata or result card. The outer `run_code` card instead reads final post-policy content and declares no presentation metadata. Generic and tool-owned spill projections similarly skip nested dispatches, whose canonical value never enters model context.
The first-party tools preserve their existing Native text while returning domain DTOs: