@livx.cc/agentx 0.99.159 → 0.99.161
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +1 -1
- package/dist/cli.d.ts +1 -0
- package/dist/cli.js +369 -80
- package/dist/cli.js.map +1 -1
- package/dist/index.d.ts +25 -1
- package/dist/index.js +56 -9
- package/dist/index.js.map +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -120,7 +120,7 @@ agentx --resume <id> "…" # resume a specific session
|
|
|
120
120
|
- **@-file mentions & headless JSON** — reference files inline in a prompt with `@path` (e.g. `explain @src/Agent.ts`; `~/` expands to the home directory; quote paths with spaces as `@"…"` — drag-dropped files, e.g. macOS screenshots, quote themselves automatically); script with `-p --output-format json` to get one machine-readable result object on stdout (activity stays on stderr).
|
|
121
121
|
- **Raise, don't guess** (`AskUserQuestion` + `finishReason: 'needs_input'`) — when a decision is genuinely the user's, the agent asks. Interactively that's an arrow-select prompt. **Headless** (`-p`, piped, no TTY) there's nobody to prompt, so instead of blocking on a prompt no one can see — or, worse, "proceeding with best judgment" — the run **stops and hands the question to its caller**: exit code `2`, a yellow `? needs input` footer, and `{finishReason:'needs_input', question:{…}, sessionId}` in `--output-format json`. The transcript is preserved, so the caller answers and continues (`--resume <id> -p "<answer>"`) instead of re-running. A delegated agent silently deciding something that was never its to decide is the failure this closes.
|
|
122
122
|
- **Tab-completion** — `Tab` completes `/<command>` names and `@<path>` file/dir references (descends subdirs, dotfiles hidden unless typed) straight from the working tree.
|
|
123
|
-
- **Voice call (duplex v3)** — `agentx --call --voice
|
|
123
|
+
- **Voice call (duplex v3)** — `agentx --live` (= `--call --voice --channel-mode live`: mic on at start, Jev turn judge, quick lane; also what interactive `--duplex`/`--duplex-v2`/`--voice` run now; `AGENTX_DUPLEX_V1=1` keeps the reflex engine below for one release): the main agent (`-m`, full tools, real history) hears the user's exact words and answers every turn; a fast model (`--voice-model`, default Claude Haiku) only covers the wait — backchannels, fillers, bridges and tool-progress lines — and has no path into the history. `VoiceCall` (`src/voice/call.ts`, exported) is the host-agnostic core: `TurnGate` holds mid-phrase finals, merges re-finals, drops duplicates and a second goodbye; `Progress` speaks "checking the board…" during long tool runs. `--voice-persona <file>` sets who the call is: it replaces the default call style in MAIN's prompt and feeds the live prediction tree. In `--channel-mode live`, bridges and progress carry the request's own words ("Hacker News, one sec.": a tree leaf, else the fast model, else silence), never a stock line. A call's greeting uses no tools and its prompt is warmed first. While MAIN works (`noteTurn` + `workReply`), a remark gets an immediate fast-model answer and reaches MAIN as a note on its next turn; a change runs as MAIN's next turn; a stop aborts it. Progress lines start about 3 s into a silence and repeat about every 5 s, never the same line. `--call` sets `ENABLE_TOOL_SEARCH=false` (claude-code/*: tools loaded up front, a larger prompt for no ToolSearch round trip). A persona should say to react first, then give the fact: `When they react or push back ("what?", "are you serious?"), react first, like a person, then give the fact.`
|
|
124
124
|
- **Fill channel for host apps** — `agentx --channel-only --input-format stream-json --output-format stream-json` hosts a `VoiceCall` behind NDJSON for an app whose MAIN is its own agent: stdin `{type:'final', text, sttId?}`, `{type:'main', ev}` (MAIN's start/text/tool/tool_done/audio/done/error), `{type:'interim'|'pause'|'barge'|'overlap'}`; stdout `{type:'turn', id, text, replaces?}` (run MAIN on it), `{type:'abort', id}`, `{type:'channel', kind, text, speech?}` (`speech`: what to play when it differs: tagged; `text` is '' for a sound alone). The v2 inputs (`user`/`text`/`agent_state`) still work. With `--quick-lane --channel-mode live` it runs two lanes like `--call`: the quick lane answers chit-chat, reactions and exact restates itself and acks real work before the `turn`; stdin adds `{type:'cut', full, heard}` (a barge cut MAIN's reply), stdout adds `{type:'note', text}` (put it, model-only, in MAIN's next turn), `{type:'user_line', text, how: quick|aside|kept}` (user words that start no turn), `{type:'resumed'}` (a "go on" said the cut rest: drop your cut note) and `channel` kinds `ack`/`reply`. Hosts without the flag are unchanged.
|
|
125
125
|
- **Duplex mode** — `agentx --duplex` runs the full standard REPL (slash commands, sessions, postures, rewind, MCP) with the three-tier engine driving turns: a fast voice model (`--voice-model`, default `groq/openai/gpt-oss-120b`) answers every line instantly and delegates real work to background workers built with the same wiring as a normal run (fs mode, permissions, MCP); worker activity shows as dim chrome and results are re-voiced when ready. Switch any tier live with `/model` (opens a reflex/act/think picker), or the `/voice-model` · `/think-model` shortcuts. `/tasks` lists background tasks, inspects a task's live output tail, and cancels a running one from a picker (Esc mid-turn cancels the foreground turn; Esc again at the idle prompt cancels running workers).
|
|
126
126
|
- **Headless duplex for host apps** — `agentx --voice --input-format stream-json --output-format stream-json` runs the same duplex engine behind an NDJSON pipe, for an app that owns its own mic/TTS (the Bare browser uses it). stdin: `{type:'user', text, id?, replaces?, cut?}` (`cut` = the host voice engine's `takeInterruptedReply()`, so "heard up to" / parked deliveries work exactly as in the CLI), `{type:'barge'}`, `{type:'cancel', task}`, `{type:'exit'}`. stdout: reflex `text`/`thinking` deltas, worker `speak` utterances, `filler`, `task` lifecycle events, `turn_done`, `revoice_done`, `exit`. `--append-system-prompt` goes to the workers, `--voice-system-prompt` to the voice model.
|