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

Merge remote-tracking branch 'origin/master' into cross-family-fs-sandbox

Browse Source 
# Conflicts:
#	docs/config-catalog.md
#	docs/module-graph.md
#	docs/rfc/INDEX.md
#	examples/acp-agent/composition.md
#	examples/acp-agent/cordis.yml
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl
#	examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/permission-switching/session.jsonl
#	examples/acp-agent/tests/snapshots/skill-load/session.jsonl
#	examples/acp-agent/tests/snapshots/text-turn/session.jsonl
#	packages/bash/bash-sandbox/package.json
#	packages/bash/bash/package.json
#	packages/bash/tool-bash/src/index.ts
#	packages/fs/fs/package.json
#	packages/fs/tool-fs/package.json
#	packages/fs/tool-fs/src/index.ts
#	packages/fs/tool-fs/tests/tools.spec.ts
#	pnpm-lock.yaml
This commit is contained in:
kingwl
2026-07-15 21:39:02 +08:00
parent 91247babd9 b045b553a9
commit d46d37f372
450 changed files with 11555 additions and 2977 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/acp-agent/README.md
+4 -4
View File
@@ -7,11 +7,11 @@ pnpm run demo:acp # needs DEEPSEEK_API_KEY (repo-root .env or env)
pnpm run demo:code-mode acp # the same server in Code Mode: one wire tool, run_code
```
The leaf config loads the ACP app, DeepSeek adapter, sandboxed bash, approval and permission services, model-facing tools, and repeat guard. The app bundles the agent spine, JSONL persistence, and bridge, creates agents on `session/new`, and keeps stdout logger-free. [`code-mode.cordis.yml`](code-mode.cordis.yml) overlays the same tree with `run_code` and its generated TypeScript SDK; see [Code Mode](../../packages/core/tools/README.md#code-mode).
The leaf config loads the ACP app, DeepSeek adapter, sandboxed bash, the sandboxed filesystem stack, approval and permission services, model-facing tools, and repeat guard. The app bundles the agent spine, JSONL persistence, and bridge, creates agents on `session/new`, and keeps stdout logger-free. [`code-mode.cordis.yml`](code-mode.cordis.yml) adds `run_code` and its generated TypeScript SDK. See [Code Mode](../../packages/core/tools/README.md#code-mode).
## stdout is the protocol
This example loads **no stdout logger** — `stdout` carries the JSON-RPC frames, and any other write corrupts them. `@deepseek-ai/dsh-acp-agent` includes no logger entry, so this leaf has none to get wrong by default; do not add one (use a stderr exporter if you need logs).
This example loads **no stdout logger** — `stdout` carries the JSON-RPC frames, and any other write corrupts them. `@deepseek-ai/dsh-acp-demo` includes no logger entry, so this leaf has none to get wrong by default; do not add one (use a stderr exporter if you need logs).
## Zed configuration
@@ -39,11 +39,11 @@ This example hosts the ACP snapshot suite. `dsh-llm-replay` reconstructs model s
The default tree composes [`@deepseek-ai/dsh-sandbox-local`](../../packages/sandbox/sandbox-local/), [`@deepseek-ai/dsh-sandbox-policy`](../../packages/sandbox/sandbox-policy/), [`@deepseek-ai/dsh-bash-sandbox`](../../packages/bash/bash-sandbox/), [`@deepseek-ai/dsh-fs-sandbox`](../../packages/fs/fs-sandbox/), [`@deepseek-ai/dsh-user-approval`](../../packages/ui/user-approval/), and [`@deepseek-ai/dsh-permission`](../../packages/ui/permission/). Bash and the `read`/`write`/`edit` tools start in `workspace-write`; a denied operation returns a structured marker, and a retry with `sandbox_permissions` plus `justification` becomes a one-shot `session/request_permission` prompt in the editor. "Allow once" runs exactly that retry under the wider mode ([sandbox RFC § Escalation](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)).
- **One session config option is live**: a capable client shows one `Permissions` select. `workspace-write` means workspace-confined bash plus `ask`; `danger-full-access` means unconfined file access plus `never`. Switching writes one `permission/preset` event through to the sandbox-mode and approval-policy events, and `session/load` reports the resumed value.
- **One session config option is live**: a capable client shows one `Permissions` select. `workspace-write` means workspace-confined bash plus `ask`; `danger-full-access` means unconfined bash plus `never`. Switching writes one `permission/preset` event through to the sandbox-mode and approval-policy events, and `session/load` reports the resumed value.
- **Every approval is one-shot**: the choices are `Allow once` and `Reject`; a dismissal, rejection, missing editor, or unavailable runner fails closed.
- **The boundary spans bash and the filesystem tools, and is config-fixed today**: bash confines through the OS runner and the `read`/`write`/`edit` tools through an in-process path fence ([`dsh-fs-sandbox`](../../packages/fs/fs-sandbox/)), both keyed to the same `workspaceRoot` — which remains the server's launch directory (a per-session root is deferred).
`tests/escalation.e2e.ts` boots this default tree keyless, drives the permission select, and—with a key and usable runner—proves both approval outcomes against the filesystem. The snapshot suite uses the same tree: snapshot mode starts at `danger-full-access` so established fixtures remain runner-independent, while the permission-switching and escalation inputs explicitly select `workspace-write` before exercising that policy path. No fixture pins a real denial because kernel error text is backend-specific; real confinement remains covered by the sandbox packages' kernel e2e suites.
`tests/escalation.e2e.ts` boots this default tree keyless, drives the permission select, and—with a key and usable runner—proves both approval outcomes against the filesystem. Most snapshots use that tree and start at `danger-full-access` so bash fixtures remain runner-independent; scenarios that call `read`, `write`, or `edit` use the fixed full-access fs overlay and a separate request-header pin. The permission-switching and escalation inputs select `workspace-write` before exercising the bash policy path. No fixture pins a real denial because kernel error text is backend-specific; real confinement remains covered by the sandbox packages' kernel e2e suites.
## MVP limitations