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

docs: classify consumer-owned model effects as indirect

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-13 22:40:19 +08:00
parent d77f797d89
commit a4417f4924
14 changed files with 24 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
packages/sandbox/sandbox/README.md
View File

@@ -12,11 +12,7 @@ Implementations: [`@deepseek-ai/dsh-sandbox-local`](../sandbox-local/) (Linux: `
## Model Experience
### Sandbox result, indirectly
**What the model sees**: Through `dsh-bash-sandbox` and `dsh-tool-bash`, enforcement facts may become that consumer's exact denial marker. `SandboxUnavailableError` becomes exactly `Error: sandbox mode "<mode>" is requested but no sandbox backend is usable on this host; refusing to run the command unconfined. Install bubblewrap or run a Landlock-enforcing kernel (Linux), ensure sandbox-exec is usable (macOS) — Windows has no confinement backend yet — or switch the consumer to danger-full-access.`, optionally followed by ` Runner failure: <detail>`.
**Token effect**: This package adds no prompt or schema. Only a denial or failed confinement adds retained result tokens.
Indirectly, through [`dsh-bash-sandbox`](../../bash/bash-sandbox/README.md) and `dsh-tool-bash`, which render this seam's enforcement facts as the exact denial or `SandboxUnavailableError` text documented by the consumer, with retained tokens added only for a denial or failed confinement.
## Known Limitations and Deferred Work