@livx.cc/agentx 0.99.143 → 0.99.145

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 CHANGED
@@ -121,7 +121,7 @@ agentx --resume <id> "…" # resume a specific session
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
123
  - **Voice call (duplex v3)** — `agentx --call --voice` (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.
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}`. The v2 inputs (`user`/`text`/`agent_state`) still work.
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.
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.
127
127
  - **MCP servers** — declare `mcpServers: { name: { command, args } | { url } }` in config and they're auto-mounted at startup (in parallel, with an optional `mountTimeoutMs` deadline so one slow/dead server never blocks the rest): the client does the JSON-RPC handshake (stdio or HTTP) + `tools/list`, and the discovered tools appear as `mcp__<name>__<tool>` in `/tools` (inspect with `/mcp`). A bad server is logged and skipped, never blocking the agent. For large tool sets, **deferred mode** (`makeMcpToolSearch` / `mountMcpDeferred`) exposes just two bounded tools (`ToolSearch` + `McpCall`) instead of N defs — dodging the provider tool-cap and improving selection accuracy; the CLI applies this automatically past 12 mounted tools (a 42-tool server was costing ~80k tok/turn in schema alone), and permission rules written against the real `mcp__<name>__<tool>` names still match through `McpCall`. **`mountMcpCatalog`** goes further: a cached, hash-keyed catalog + lazy connect means a turn that uses no MCP tool opens **zero** connections, and one that uses a tool connects exactly that server — latency scales with tools-used, not servers-configured. A down server is **negative-cached** (`failureCooldownMs`) so it never re-floors a later turn at the deadline. For zero turn-path latency even on a cold process, call **`warmMcpCatalog`** at boot + on a timer (off-turn discovery) and mount with **`{ discover: 'cache-only' }`** — the turn then never synchronously connects: it serves the warmed catalog and discovers any miss in the background. **Slow tools are jobs, not timeouts**: `timeoutMs` (default 30s) bounds protocol requests (`initialize`, `tools/list`) only; a `tools/call` still running after the soft foreground timeout (`foregroundMs.mcp`, 30s) returns `[still running] … background job job-N` while the request keeps going, and its result is delivered when it lands. The client sends a `progressToken` and reads progress over stdio and incrementally over HTTP/SSE; a call is cancelled (`notifications/cancelled`) only by `JobKill`, the stuck-job reaper, or its hard cap `callTimeoutMs` (per server, default 30 min).
package/dist/cli.d.ts CHANGED
@@ -1,5 +1,5 @@
1
1
  #!/usr/bin/env bun
2
- import { w as RouterState, H as Hooks, c as AgentOptions, x as RunResult, f as ChatUsage, R as ReasoningEffort, d as ChannelMode, b as Agent } from './secondChannel--Iv3ZQ69.js';
2
+ import { w as RouterState, H as Hooks, c as AgentOptions, x as RunResult, f as ChatUsage, R as ReasoningEffort, d as ChannelMode, b as Agent } from './secondChannel-BFPgXN2z.js';
3
3
  import { IFilesystem } from '@livx.cc/wcli/core';
4
4
  import { M as Message, U as UserQuestion, H as HostBridge, c as ContentPart, o as MessageContent } from './tools-DwfeF8VQ.js';
5
5
 
package/dist/cli.js CHANGED
@@ -10459,7 +10459,16 @@ function fitsLanguage(line, lang) {
10459
10459
  }
10460
10460
  var norm3 = (s) => s.toLowerCase().replace(/[^\p{L}\p{N}' ]/gu, "").replace(/\s+/g, " ").trim();
10461
10461
  function cleanLine(s, lang, maxWords = 6) {
10462
- const raw = s.trim().split("\n")[0];
10462
+ const first = s.trim().split("\n")[0];
10463
+ const tags = [...first.matchAll(LINE_TAG)].map((m) => `[${m[1].toLowerCase()}]`).filter((t, i, a) => a.indexOf(t) === i).join(" ");
10464
+ const raw = first.replace(LINE_TAG, " ").trim();
10465
+ if (tags && !/[\p{L}\p{N}]/u.test(raw)) return /laughter|gasp/.test(tags) ? tags : "";
10466
+ const words4 = cleanWords(raw, lang, maxWords);
10467
+ return words4 && tags ? `${tags} ${words4}` : words4;
10468
+ }
10469
+ var LINE_TAG = /\[(laughter|gasp|quiet)\]/gi;
10470
+ var lineWords = (line) => line.replace(LINE_TAG, " ").trim();
10471
+ function cleanWords(raw, lang, maxWords) {
10463
10472
  const l = raw.replace(/^[-*•\d.)\s]+/, "").replace(/^["'“”«»]+|["'“”«»]+$/g, "").replace(new RegExp("^\\p{L}+:\\s*", "u"), "").trim();
10464
10473
  if (!l || isLeakSuspect(raw) || isLeakSuspect(l)) {
10465
10474
  if (l) log23.debug(`line "${raw}" reads as meta \u2014 rejected`);
@@ -13992,7 +14001,7 @@ var SecondChannel = class {
13992
14001
  }
13993
14002
  if (this.o.generate && this.o.generateFor.includes(kind) && (kind !== "backchannel" || react)) {
13994
14003
  const ac = new AbortController();
13995
- const ctx = { kind, heard: this.tail(), state: this.main, avoid: [...this.recent], lang: this.lang, ...kind === "backchannel" && this.o.reactionGapMs ? { react: true } : {} };
14004
+ const ctx = { kind, heard: this.tail(), state: this.main, avoid: [...this.recent], lang: this.lang, ...kind === "backchannel" && this.o.reactionGapMs ? { react: true } : {}, ...kind === "backchannel" && this.o.mode === "live" ? { tags: true } : {} };
13996
14005
  const raw = await withBudget(this.o.generate(ctx, ac.signal), this.o.generateBudgetMs, `${kind} generate`);
13997
14006
  if (raw === null) ac.abort();
13998
14007
  const text = cleanLine(raw ?? "", this.lang);
@@ -14028,8 +14037,9 @@ var SecondChannel = class {
14028
14037
  if (kind === "backchannel") this.bcTimes.push(this.lastAt);
14029
14038
  if (kind === "bridge") this.bridged = true;
14030
14039
  this.recent = [...this.recent, text].slice(-this.o.avoidLines);
14031
- this.live = text.trim();
14032
- this.o.show(text, kind);
14040
+ this.live = lineWords(text);
14041
+ const words4 = this.live;
14042
+ if (words4) this.o.show(words4, kind);
14033
14043
  const p = Promise.resolve(r).then(() => {
14034
14044
  }, (e) => {
14035
14045
  log28.warn(`channel line playback failed: ${e?.message ?? e}`);
@@ -14069,10 +14079,16 @@ var KIND_HINT2 = {
14069
14079
  bridge: 'a neutral one-moment cue while the answer is prepared ("let me see\u2026", "one sec\u2026") \u2014 never the start of a statement or opinion ("the thing is", "well actually")'
14070
14080
  };
14071
14081
  var REACT_HINT = 'a short reaction to their LAST words instead: feeling ("oh no", "ha, nice", "ugh"), surprise ("wait, really?", "huh"), a light laugh if they joke or laugh ("ha!"), or an echo of their key word ("the deploy?") \u2014 still never asks for an answer or takes the turn; if nothing there deserves a reaction, a plain "mm-hm"';
14082
+ var TAG_HINT = 'Real listeners often react without words: the line may be, or begin with, [laughter] or [gasp], and [quiet] before words breathes them under the voice ("[gasp]", "[laughter]", "[gasp] [quiet] no way"). Use a sound when it fits what they said.';
14083
+ function channelLine(line, kind) {
14084
+ const text = lineWords(line);
14085
+ return { type: "channel", kind, text, ...text === line ? {} : { speech: line } };
14086
+ }
14072
14087
  function fastLineGenerator(ai, model, gender) {
14073
14088
  return async (c, signal) => {
14074
14089
  const prompt = `You voice the tiny side-sounds of a live spoken conversation. Write ONE line of 1-5 words: ${KIND_HINT2[c.kind]}.
14075
14090
  ` + (c.react ? `Here the line may be ${REACT_HINT}.
14091
+ ` : "") + (c.tags ? `${TAG_HINT}
14076
14092
  ` : "") + `The user just said: "${c.heard}"
14077
14093
  The assistant is: ${c.state}.
14078
14094
  ` + (c.avoid.length ? `Do not reuse any of: ${c.avoid.map((a) => `"${a}"`).join(", ")}.
@@ -14216,6 +14232,11 @@ var VoiceCall = class {
14216
14232
  if (this.ended || !text.trim()) return;
14217
14233
  if (typeof aec === "boolean") this.fill.options.aec = aec;
14218
14234
  this.gate.speaking();
14235
+ const c = this.cur;
14236
+ if (this.o.mode === "live" && c?.running && !c.worded && text.trim().split(/\s+/).length >= 2) {
14237
+ log29.debug("user resumed before the reply \u2014 yielded");
14238
+ this.barge();
14239
+ }
14219
14240
  this.follow(text);
14220
14241
  this.fill.onInterim(text);
14221
14242
  }
@@ -23462,7 +23483,10 @@ async function duplexServe(args, ai, cfg, cwd) {
23462
23483
  });
23463
23484
  if (args.voiceSystemPrompt) dx.voice.options.systemPrompt += "\n\n" + args.voiceSystemPrompt;
23464
23485
  let scTurn = 0;
23465
- const sc = args.duplexV2 ? makeSecondChannel(ai, dx.options.reflexModel, args.channelMode, { show: (text, kind) => out({ type: "channel", kind, text }) }) : void 0;
23486
+ const sc = args.duplexV2 ? makeSecondChannel(ai, dx.options.reflexModel, args.channelMode, { speak: (line, kind) => {
23487
+ out(channelLine(line, kind));
23488
+ return true;
23489
+ } }) : void 0;
23466
23490
  const store = new SessionStore(cwd);
23467
23491
  const session = startSession(args, store, dx.voice, cwd);
23468
23492
  persist = () => {
@@ -23534,11 +23558,13 @@ async function channelServe(args, ai, cfg) {
23534
23558
  mode: args.channelMode,
23535
23559
  gender: args.voiceGender ?? "",
23536
23560
  channel: channelOptions(ai, process.env.AGENTX_CHANNEL_MODEL || model, args.voiceGender),
23537
- speak: () => true,
23538
- // the host plays {type:'channel'} lines (shown via show)
23561
+ speak: (line, kind) => {
23562
+ out(channelLine(line, kind));
23563
+ return true;
23564
+ },
23565
+ // the host plays {type:'channel'} lines: `speech` keeps the tags, `text` shows
23539
23566
  hostAudio: true,
23540
23567
  // …and says when one really plays ({type:'heard'}) — a line its player drops never counts as sound
23541
- show: (text, kind) => out({ type: "channel", kind, text }),
23542
23568
  sendTurn: (text, o) => out({ type: "turn", id: o.id, text, ...o.replaces ? { replaces: o.replaces } : {} }),
23543
23569
  abortTurn: (id) => out({ type: "abort", id }),
23544
23570
  onMetric: (m) => {