reasonix 0.5.20 → 0.5.21

package/README.md

@@ -3,7 +3,7 @@
 </p>
 
 <p align="center">
-  <em>Cache-first agent loop for DeepSeek V3 &amp; R1 — Ink TUI, MCP first-class, no LangChain.</em>
+  <em>Cache-first agent loop for DeepSeek V4 (flash + pro) — Ink TUI, MCP first-class, no LangChain.</em>
 </p>
 
 # Reasonix
@@ -133,6 +133,34 @@ shell call will execute. Use for high-stakes changes you want to
 audit before the model touches disk. `/plan off` or picker
 Approve/Cancel exits.
 
+### Prompt prefixes — `!cmd` and `@path`
+
+Two inline shortcuts that don't need a slash:
+
+**`!<cmd>` — run a shell command in the sandbox and feed it to the
+model.** Typed at the prompt, like bash. Output lands in the visible
+log AND in the session so the model's next turn reasons about it:
+
+```
+reasonix code › !git status --short
+▸ M src/users.ts
+▸ M src/users.test.ts
+
+reasonix code › 把这两个文件的改动说明一下
+assistant
+  ▸ tool<read_file> → src/users.ts, src/users.test.ts
+  ▸ …
+```
+
+No allowlist gate — user-typed shell = explicit consent. 60s timeout,
+32k char cap, survives session resume since 0.5.14.
+
+**`@path/to/file` — inline a file under "Referenced files."** Start
+typing `@` and a picker appears (↑/↓ navigate, Tab/Enter to insert).
+Good for "what does @src/users.ts do?" without making the model
+`read_file` it first. Sandboxed: relative paths only, no `..` escape,
+64KB per-file cap. Recent files rank higher.
+
 ### `/commit` — stage + commit in one step
 
 ```
@@ -145,12 +173,14 @@ reasonix code › /commit "fix: findByEmail case-insensitive"
 
 - `/tool 1` — dump the last tool call's full output (when the 400-char
   inline clip isn't enough).
-- `/think` — see the model's full R1 reasoning for the last turn
-  (reasoner preset only).
+- `/think` — see the model's full reasoning for the last turn
+  (thinking-mode models: v4-flash / v4-pro / reasoner alias).
 - `/undo` — roll back the last applied edit batch.
 - `/new` — start fresh in the same directory without losing the
   session file.
-- `npx reasonix code --preset max` — R1 + 3-way self-consistency
+- `/effort high` — step down from the default `max` agent-class
+  reasoning_effort for cheaper/faster turns on simple tasks.
+- `npx reasonix code --preset max` — v4-pro + 3-way self-consistency
   branching for gnarly refactors.
 - `npx reasonix code src/` — narrower sandbox (only `src/` is
   writable).
@@ -182,7 +212,9 @@ in the file. No prompts, no completions, no tool arguments.
 ### Staying current
 
 The panel header shows the running version next to `Reasonix` (e.g.
-`Reasonix v0.4.22 · model …`). A quiet 24-hour background check against
+`Reasonix v0.5.21 · deepseek-v4-pro · harvest · max …`, the trailing
+`max` is the reasoning-effort badge — `/effort high` to step down).
+A quiet 24-hour background check against
 the npm registry surfaces a yellow `update: X.Y.Z` on the right side
 of the same row when a newer version has been published. No blocking,
 no nagging — the check runs once per day max and is silent on failure
@@ -403,18 +435,25 @@ rendering, retries.
 | command | what it does |
 |---|---|
 | `/preset <fast\|smart\|max>` | one-tap bundle (model + harvest + branch) |
-| `/model <id>` | switch DeepSeek model (`deepseek-chat`, `deepseek-reasoner`) |
+| `/model <id>` | switch DeepSeek model (`deepseek-v4-flash`, `deepseek-v4-pro`, plus `deepseek-chat` / `deepseek-reasoner` compat aliases) |
+| `/models` | list live models from DeepSeek `/models` endpoint |
 | `/harvest [on\|off]` | toggle R1 plan-state extraction |
 | `/branch <N\|off>` | run N parallel samples per turn, pick best (N ≥ 2) |
-| `/think` | dump the last turn's full R1 reasoning |
+| `/effort <high\|max>` | reasoning_effort cap — `max` is the agent default, `high` is cheaper/faster |
+| `/think` | dump the last turn's full thinking-mode reasoning |
 
 **Context & tools**
 
 | command | what it does |
 |---|---|
-| `/mcp` | list attached MCP servers and their tools |
+| `/mcp` | list attached MCP servers and their tools / resources / prompts |
+| `/resource [uri]` | browse + read MCP resources (no arg → list URIs; `<uri>` → fetch) |
+| `/prompt [name]` | browse + fetch MCP prompts |
 | `/tool [N]` | dump the Nth tool call's full output (1 = latest) |
-| `/compact [cap]` | shrink oversized tool results in the log |
+| `/compact [tokens]` | shrink oversized tool results in the log (default 4000 tokens/result) |
+| `/context` | break down where context tokens are going (system / tools / log) |
+| `/stats` | cross-session cost dashboard (today / week / month / all-time) |
+| `/keys` | keyboard shortcuts + prompt prefixes (`!` / `@` / `/`) cheatsheet |
 
 **Memory & skills**
 
@@ -468,8 +507,8 @@ rendering, retries.
 - Malformed `assistant.tool_calls` / `tool` pairing is validated on
   every outgoing API call so a corrupted session can't keep 400ing.
 - Context gauge turns yellow at 50%, red at 80% with a `/compact`
-  nudge. Approaching the 131k window triggers an automatic
-  compaction attempt before falling back to a forced summary.
+  nudge. Approaching the 1M-token window (V4 flash + pro) triggers an
+  automatic compaction attempt before falling back to a forced summary.
 - The `reasonix code` sandbox refuses any path that resolves outside
   the launch directory, including symlink escape and `..` traversal.
 
@@ -728,7 +767,7 @@ cd reasonix
 npm install
 npm run dev code        # run CLI from source via tsx
 npm run build           # tsup to dist/
-npm test                # vitest (648 tests)
+npm test                # vitest (1007 tests)
 npm run lint            # biome
 npm run typecheck       # tsc --noEmit
 ```

package/dist/cli/index.js

@@ -210,6 +210,12 @@ var DeepSeekClient = class {
     if (opts.temperature !== void 0) payload.temperature = opts.temperature;
     if (opts.maxTokens !== void 0) payload.max_tokens = opts.maxTokens;
     if (opts.responseFormat) payload.response_format = opts.responseFormat;
+    if (opts.thinking) {
+      payload.extra_body = { thinking: { type: opts.thinking } };
+    }
+    if (opts.reasoningEffort) {
+      payload.reasoning_effort = opts.reasoningEffort;
+    }
     return payload;
   }
   /**
@@ -424,6 +430,13 @@ async function harvest(reasoningContent, client, options = {}, signal) {
       responseFormat: { type: "json_object" },
       temperature: 0,
       maxTokens: 600,
+      // Pin mode + effort so a future default-model swap (e.g. someone
+      // sets `options.model = "deepseek-v4-pro"`) can't accidentally
+      // turn this micro-extraction into a multi-thousand-reasoning-
+      // token call. DeepSeek ignores these on non-thinking models, so
+      // the request stays valid regardless of the chosen model.
+      thinking: "disabled",
+      reasoningEffort: "high",
       signal
     });
     return parsePlanState(resp.content, maxItems, maxItemLen);
@@ -1783,6 +1796,8 @@ var CacheFirstLoop = class {
   harvestOptions;
   branchEnabled;
   branchOptions;
+  /** See ReconfigurableOptions — mutable so `/effort` can flip mid-session. */
+  reasoningEffort;
   sessionName;
   /**
    * Hook list, mutable so `/hooks reload` can swap it without
@@ -1808,7 +1823,8 @@ var CacheFirstLoop = class {
     this.client = opts.client;
     this.prefix = opts.prefix;
     this.tools = opts.tools ?? new ToolRegistry();
-    this.model = opts.model ?? "deepseek-chat";
+    this.model = opts.model ?? "deepseek-v4-pro";
+    this.reasoningEffort = opts.reasoningEffort ?? "max";
     this.maxToolIters = opts.maxToolIters ?? 64;
     this.hooks = opts.hooks ?? [];
     this.hookCwd = opts.hookCwd ?? process.cwd();
@@ -1924,6 +1940,7 @@ var CacheFirstLoop = class {
   configure(opts) {
     if (opts.model !== void 0) this.model = opts.model;
     if (opts.stream !== void 0) this._streamPreference = opts.stream;
+    if (opts.reasoningEffort !== void 0) this.reasoningEffort = opts.reasoningEffort;
     if (opts.branch !== void 0) {
       if (typeof opts.branch === "number") {
         this.branchOptions = { budget: opts.branch };
@@ -2102,7 +2119,9 @@ var CacheFirstLoop = class {
               model: this.model,
               messages,
               tools: toolSpecs.length ? toolSpecs : void 0,
-              signal
+              signal,
+              thinking: thinkingModeForModel(this.model),
+              reasoningEffort: this.reasoningEffort
             },
             {
               ...this.branchOptions,
@@ -2154,7 +2173,9 @@ var CacheFirstLoop = class {
             model: this.model,
             messages,
             tools: toolSpecs.length ? toolSpecs : void 0,
-            signal
+            signal,
+            thinking: thinkingModeForModel(this.model),
+            reasoningEffort: this.reasoningEffort
           })) {
             if (chunk.contentDelta) {
               assistantContent += chunk.contentDelta;
@@ -2208,7 +2229,9 @@ var CacheFirstLoop = class {
             model: this.model,
             messages,
             tools: toolSpecs.length ? toolSpecs : void 0,
-            signal
+            signal,
+            thinking: thinkingModeForModel(this.model),
+            reasoningEffort: this.reasoningEffort
           });
           assistantContent = resp.content;
           reasoningContent = resp.reasoningContent ?? "";
@@ -2401,7 +2424,9 @@ ${reason}`;
         model: this.model,
         messages,
         // no tools → model is forced to answer in text
-        signal: this._turnAbort.signal
+        signal: this._turnAbort.signal,
+        thinking: thinkingModeForModel(this.model),
+        reasoningEffort: this.reasoningEffort
       });
       const rawContent = resp.content?.trim() ?? "";
       const cleaned = stripHallucinatedToolMarkup(rawContent);
@@ -2469,6 +2494,12 @@ function isThinkingModeModel(model) {
   if (model === "deepseek-v4-flash" || model === "deepseek-v4-pro") return true;
   return false;
 }
+function thinkingModeForModel(model) {
+  if (model === "deepseek-chat") return "disabled";
+  if (model.includes("reasoner")) return "enabled";
+  if (model === "deepseek-v4-flash" || model === "deepseek-v4-pro") return "enabled";
+  return void 0;
+}
 function stripHallucinatedToolMarkup(s) {
   let out = s;
   out = out.replace(/<｜DSML｜function_calls>[\s\S]*?<\/?｜DSML｜function_calls>/g, "");
@@ -3499,7 +3530,7 @@ function registerPlanTool(registry, opts = {}) {
 // src/tools/subagent.ts
 var DEFAULT_MAX_RESULT_CHARS2 = 8e3;
 var DEFAULT_MAX_ITERS = 16;
-var DEFAULT_SUBAGENT_MODEL = "deepseek-chat";
+var DEFAULT_SUBAGENT_MODEL = "deepseek-v4-pro";
 var SUBAGENT_TOOL_NAME = "spawn_subagent";
 var NEVER_INHERITED_TOOLS = /* @__PURE__ */ new Set([SUBAGENT_TOOL_NAME, "submit_plan"]);
 async function spawnSubagent(opts) {
@@ -7181,6 +7212,7 @@ function StatsPanel({
   prefixHash,
   harvestOn,
   branchBudget,
+  reasoningEffort,
   planMode,
   balance,
   updateAvailable,
@@ -7201,6 +7233,7 @@ function StatsPanel({
       harvestOn,
       branchOn,
       branchBudget: branchBudget ?? 1,
+      reasoningEffort,
       planMode,
       turns: summary.turns,
       updateAvailable,
@@ -7233,13 +7266,14 @@ function Header({
   harvestOn,
   branchOn,
   branchBudget,
+  reasoningEffort,
   planMode,
   turns,
   updateAvailable,
   narrow,
   busy
 }) {
-  return /* @__PURE__ */ React13.createElement(Box12, { justifyContent: "space-between" }, /* @__PURE__ */ React13.createElement(Box12, null, /* @__PURE__ */ React13.createElement(Wordmark, { busy }), /* @__PURE__ */ React13.createElement(Text12, { dimColor: true }, ` v${VERSION}`), /* @__PURE__ */ React13.createElement(Text12, { dimColor: true }, " \xB7 "), /* @__PURE__ */ React13.createElement(Text12, { color: "yellow" }, model), narrow ? null : /* @__PURE__ */ React13.createElement(React13.Fragment, null, /* @__PURE__ */ React13.createElement(Text12, { dimColor: true }, " \xB7 "), /* @__PURE__ */ React13.createElement(Text12, { dimColor: true }, prefixHash)), harvestOn ? /* @__PURE__ */ React13.createElement(Text12, { color: "magenta" }, " \xB7 harvest") : null, branchOn ? /* @__PURE__ */ React13.createElement(Text12, { color: "blue" }, " \xB7 branch", branchBudget) : null, planMode ? /* @__PURE__ */ React13.createElement(Text12, { color: "red", bold: true }, " \xB7 PLAN") : null), /* @__PURE__ */ React13.createElement(Text12, null, updateAvailable ? /* @__PURE__ */ React13.createElement(Text12, { color: "yellow", bold: true }, `update: ${updateAvailable} \xB7 `) : null, /* @__PURE__ */ React13.createElement(Text12, { dimColor: true }, narrow ? `turn ${turns}` : `turn ${turns} \xB7 /help`)));
+  return /* @__PURE__ */ React13.createElement(Box12, { justifyContent: "space-between" }, /* @__PURE__ */ React13.createElement(Box12, null, /* @__PURE__ */ React13.createElement(Wordmark, { busy }), /* @__PURE__ */ React13.createElement(Text12, { dimColor: true }, ` v${VERSION}`), /* @__PURE__ */ React13.createElement(Text12, { dimColor: true }, " \xB7 "), /* @__PURE__ */ React13.createElement(Text12, { color: "yellow" }, model), narrow ? null : /* @__PURE__ */ React13.createElement(React13.Fragment, null, /* @__PURE__ */ React13.createElement(Text12, { dimColor: true }, " \xB7 "), /* @__PURE__ */ React13.createElement(Text12, { dimColor: true }, prefixHash)), harvestOn ? /* @__PURE__ */ React13.createElement(Text12, { color: "magenta" }, " \xB7 harvest") : null, branchOn ? /* @__PURE__ */ React13.createElement(Text12, { color: "blue" }, " \xB7 branch", branchBudget) : null, reasoningEffort === "max" ? /* @__PURE__ */ React13.createElement(Text12, { color: "green" }, " \xB7 max") : null, reasoningEffort === "high" ? /* @__PURE__ */ React13.createElement(Text12, { color: "yellow" }, " \xB7 high") : null, planMode ? /* @__PURE__ */ React13.createElement(Text12, { color: "red", bold: true }, " \xB7 PLAN") : null), /* @__PURE__ */ React13.createElement(Text12, null, updateAvailable ? /* @__PURE__ */ React13.createElement(Text12, { color: "yellow", bold: true }, `update: ${updateAvailable} \xB7 `) : null, /* @__PURE__ */ React13.createElement(Text12, { dimColor: true }, narrow ? `turn ${turns}` : `turn ${turns} \xB7 /help`)));
 }
 function InlineMetrics({
   summary,
@@ -7697,6 +7731,12 @@ var SLASH_COMMANDS = [
     summary: "run N parallel samples per turn (N>=2)",
     argCompleter: ["off", "2", "3", "4", "5"]
   },
+  {
+    cmd: "effort",
+    argsHint: "<high|max>",
+    summary: "reasoning_effort cap \u2014 max is default (agent-class), high is cheaper/faster",
+    argCompleter: ["max", "high"]
+  },
   { cmd: "mcp", summary: "list MCP servers + tools attached to this session" },
   {
     cmd: "resource",
@@ -7874,6 +7914,7 @@ function handleSlash(cmd, args, loop, ctx = {}) {
           "  /model <id>              deepseek-chat or deepseek-reasoner",
           "  /harvest [on|off]        Pillar 2: structured plan-state extraction",
           "  /branch <N|off>          run N parallel samples (N>=2), pick most confident",
+          "  /effort <high|max>       reasoning_effort cap (max=agent default, high=cheaper)",
           "  /mcp                     list MCP servers + tools attached to this session",
           "  /resource [uri]          browse + read MCP resources (no arg \u2192 list URIs; <uri> \u2192 fetch)",
           "  /prompt [name]           browse + fetch MCP prompts (no arg \u2192 list names; <name> \u2192 render)",
@@ -8243,7 +8284,7 @@ ${entry.text}`
       const planLine = ctx.planMode ? "  plan    ON \u2014 writes gated (submit_plan + approval)" : "";
       const lines = [
         `  model   ${loop.model}`,
-        `  flags   harvest=${loop.harvestEnabled ? "on" : "off"} \xB7 branch=${branchBudget > 1 ? branchBudget : "off"} \xB7 stream=${loop.stream ? "on" : "off"}`,
+        `  flags   harvest=${loop.harvestEnabled ? "on" : "off"} \xB7 branch=${branchBudget > 1 ? branchBudget : "off"} \xB7 stream=${loop.stream ? "on" : "off"} \xB7 effort=${loop.reasoningEffort}`,
         ctxLine,
         mcpLine,
         sessionLine
@@ -8332,6 +8373,19 @@ ${entry.text}`
       loop.configure({ branch: n });
       return { info: `branch \u2192 ${n}  (harvest auto-enabled; streaming disabled)` };
     }
+    case "effort": {
+      const raw = (args[0] ?? "").toLowerCase();
+      if (raw === "") {
+        return {
+          info: `reasoning_effort \u2192 ${loop.reasoningEffort}  (use /effort high for cheaper/faster, /effort max for the agent-class default)`
+        };
+      }
+      if (raw !== "high" && raw !== "max") {
+        return { info: "usage: /effort <high|max>" };
+      }
+      loop.configure({ reasoningEffort: raw });
+      return { info: `reasoning_effort \u2192 ${raw}` };
+    }
     default:
       return { unknown: true, info: `unknown command: /${cmd}  (try /help)` };
   }
@@ -9872,6 +9926,7 @@ Stay in plan mode \u2014 address the feedback (explore more if needed), then sub
       prefixHash,
       harvestOn: loop.harvestEnabled,
       branchBudget: loop.branchOptions.budget,
+      reasoningEffort: loop.reasoningEffort,
       planMode,
       balance,
       busy,