diff --git a/examples/acp-agent/cordis.snapshot.yml b/examples/acp-agent/cordis.snapshot.yml index f69770b4dd..90a2fa6a2a 100644 --- a/examples/acp-agent/cordis.snapshot.yml +++ b/examples/acp-agent/cordis.snapshot.yml @@ -15,6 +15,16 @@ - id: llm-deepseek name: '@deepseek-ai/dsh-llm-deepseek' disabled: true + - id: sandbox + name: '@deepseek-ai/dsh-sandbox-local' + config: + runnerCommand: + - bash + - -c + - while [ "$1" != "--" ]; do shift; done; shift; exec "$@" + - passthrough-runner + runnerFailureSignatures: + - 'passthrough-runner: profile rejected' - insert: - id: llm-replay name: '@deepseek-ai/dsh-llm-replay' diff --git a/packages/ui/stdio/README.md b/packages/ui/stdio/README.md index 2bd4995d86..b7d320880d 100644 --- a/packages/ui/stdio/README.md +++ b/packages/ui/stdio/README.md @@ -20,3 +20,23 @@ The plugin seeds display labels from the live agent registry, then tracks `agent welcome: 'agent REPL ready. Give it a coding task.' agent: main ``` + +## Model Experience + +### Readline prompt input + +**What the model sees**: Each non-empty terminal line outside an active question becomes one text block, sent with `agent.send()` while the target agent is idle and `agent.steer()` while it is running. + +**Token effect**: Submitted text is retained under the agent loop's normal session-history and compaction rules. The welcome banner, `> ` prompt, rendered transcript, and `[tool call]` / `[tool result]` terminal lines add no tokens. + +### Terminal user-interaction answers + +**What the model sees**: When a consumer calls `ctx.userInteraction.ask()`, this provider renders the question in the terminal and returns selected option labels or `custom` text. Through `dsh-tool-ask-user`, closed stdin becomes `Error: ask_user_question cannot be answered because stdin is closed`; disposal or abort becomes `Error: ask_user_question was interrupted before the user answered`. + +**Token effect**: Waiting and terminal prompts add no tokens; the resolved answer or error is model-visible only through the calling tool or plugin's result. + +## Known Limitations and Deferred Work + +- **One configured agent receives stdin** — the session/event renderer can print output from any session, but input lines always drive the configured `agent` id rather than routing by the visible label. +- **Terminal questions are text-only and sequential** — the provider queues asks, supports option labels plus custom text, and has no richer UI shapes such as file pickers or diff previews. +- **Closed stdin ends the terminal channel** — EOF rejects active or queued questions and exits after submitted work reaches idle; there is no reconnect path for a long-lived process. diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index eee88947bc..3cab8bad46 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -172,9 +172,6 @@ importers: '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session - '@deepseek-ai/dsh-stdio': - specifier: workspace:^ - version: link:../stdio '@deepseek-ai/dsh-system-prompt': specifier: workspace:^ version: link:../../core/system-prompt @@ -1449,6 +1446,9 @@ importers: '@deepseek-ai/dsh-session-persistence-jsonl': specifier: workspace:^ version: link:../../session-persistence/session-persistence-jsonl + '@deepseek-ai/dsh-stdio': + specifier: workspace:^ + version: link:../stdio '@deepseek-ai/dsh-system-prompt': specifier: workspace:^ version: link:../../core/system-prompt