@mafdet/cli 0.4.2 → 0.4.3

package/CHANGELOG.md

@@ -6,6 +6,35 @@ The version is the contract for the JSON output shapes and the exit codes.
 Being 0.x, semver still permits a break in a minor bump; the intent is not to
 use that latitude, and the promise becomes binding at 1.0.0.
 
+## 0.4.3 - 2026-08-11
+
+A long agent run no longer walks into the model's context window, a one-shot
+chat can be saved, and the Windows timeout kill now walks the process tree.
+
+**Automatic compaction.** When a run gets close to the model's context window,
+the oldest tool exchanges are dropped from what is sent and you are told it
+happened. The size is measured rather than estimated: every response reports
+how many input tokens it actually cost, which is the provider's own count of
+exactly the conversation we sent. What gets dropped is always a whole exchange
+
+- an assistant tool call and the results answering it are inseparable - and
+  the system prompt and your original goal are never touched. A model whose
+  context length the catalogue does not publish is left alone, because guessing
+  a window would either truncate a conversation that fit or fail to truncate one
+  that did not. Your saved transcript is unaffected; only what is sent gets
+  shorter.
+
+**`mafdet chat "..." --save`** records a one-shot chat, through exactly the
+same store as an interactive session - the same redaction, the same private
+files, the same `mafdet sessions delete`. Chats are still not saved by
+default, `--no-history` still wins over `--save`, and a chat you cancel is not
+saved at all.
+
+**Windows command timeouts** now use `taskkill /T`, then `taskkill /T /F`,
+where POSIX uses SIGTERM then SIGKILL on the process group. Note the standing
+caveat: this path has not been run on a real Windows machine, so a surviving
+grandchild process there remains a known limitation rather than a fixed bug.
+
 ## 0.4.2 - 2026-08-11
 
 Conversations are now saved on this computer, and a session's cost can be

package/README.md

@@ -77,20 +77,20 @@ prompt as an argument, or use `--input <file>`.
 
 ## Commands
 
-| Command                                                                                     | What it does                                                               |
-| ------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------- |
-| `mafdet doctor`                                                                             | One pass over key, endpoints, model, tool-calling, balance, workspace, git |
-| `mafdet models list [--surface chat\|embeddings\|speech] [--agent]`                         | Models this key can call, joined with catalogue metadata                   |
-| `mafdet models show <id>`                                                                   | One model in detail, including whether the agent may drive it              |
-| `mafdet chat [prompt] [--model] [--system <file>] [--input <file>] [--no-stream] [--quiet]` | Send a prompt; streams by default                                          |
-| `mafdet agent "<goal>" [--allow-write] [--allow-command "<prefix>"]`                        | Local agent; read-only unless told otherwise                               |
-| `mafdet agent` (no goal, needs a terminal)                                                  | Interactive session                                                        |
-| `mafdet embed [text\|<file>] --model <id> [--output <file>]`                                | Text to vector                                                             |
-| `mafdet speech [text\|<file>] --model <id> --output <file> --voice <name>`                  | Text to an audio file                                                      |
-| `mafdet account balance\|usage\|subscription`                                               | Wallet, spend and plan (needs the `account:read` scope)                    |
-| `mafdet sessions list\|show\|usage\|delete`                                                 | Conversations saved on this computer (never calls a model)                 |
-| `mafdet sessions usage <id> --refresh`                                                      | Replace the local estimate with the billing ledger's figure                |
-| `mafdet config list`                                                                        | The resolved settings and where each came from                             |
+| Command                                                                                              | What it does                                                               |
+| ---------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------- |
+| `mafdet doctor`                                                                                      | One pass over key, endpoints, model, tool-calling, balance, workspace, git |
+| `mafdet models list [--surface chat\|embeddings\|speech] [--agent]`                                  | Models this key can call, joined with catalogue metadata                   |
+| `mafdet models show <id>`                                                                            | One model in detail, including whether the agent may drive it              |
+| `mafdet chat [prompt] [--model] [--system <file>] [--input <file>] [--no-stream] [--quiet] [--save]` | Send a prompt; streams by default                                          |
+| `mafdet agent "<goal>" [--allow-write] [--allow-command "<prefix>"]`                                 | Local agent; read-only unless told otherwise                               |
+| `mafdet agent` (no goal, needs a terminal)                                                           | Interactive session                                                        |
+| `mafdet embed [text\|<file>] --model <id> [--output <file>]`                                         | Text to vector                                                             |
+| `mafdet speech [text\|<file>] --model <id> --output <file> --voice <name>`                           | Text to an audio file                                                      |
+| `mafdet account balance\|usage\|subscription`                                                        | Wallet, spend and plan (needs the `account:read` scope)                    |
+| `mafdet sessions list\|show\|usage\|delete`                                                          | Conversations saved on this computer (never calls a model)                 |
+| `mafdet sessions usage <id> --refresh`                                                               | Replace the local estimate with the billing ledger's figure                |
+| `mafdet config list`                                                                                 | The resolved settings and where each came from                             |
 
 `--json` on any query command emits one complete JSON document; `--plain`
 emits tab-separated rows with no header, for `cut` and `awk`.
@@ -216,10 +216,16 @@ Turning it off and cleaning up:
 
 ```bash
 mafdet --no-history            # this run is not recorded at all
+mafdet chat "..." --save       # a one-shot chat is saved only when asked
 mafdet sessions list           # what is saved, and the path when nothing is
 mafdet sessions delete <id> --yes
 ```
 
+A single `mafdet chat` is not a conversation anyone resumes, so it is not
+recorded unless `--save` is given. `--no-history` still wins over `--save`, and
+a chat cancelled with Ctrl+C is not saved at all — half a reply is a worse
+record than none.
+
 `--no-history` writes nothing — not an empty directory, not an index entry.
 
 Deleting removes the local messages and this session's usage mapping. It does

package/README.zh-CN.md

@@ -60,20 +60,20 @@ mafdet doctor
 
 ## 命令
 
-| 命令                                                                                        | 作用                                                                |
-| ------------------------------------------------------------------------------------------- | ------------------------------------------------------------------- |
-| `mafdet doctor`                                                                             | 一次检查 Node、两个端点、Key、工作区、git、模型与工具调用能力、余额 |
-| `mafdet models list [--surface chat\|embeddings\|speech] [--agent]`                         | 这把 Key 能调用的模型，并附上目录元数据                             |
-| `mafdet models show <id>`                                                                   | 单个模型详情，含 Agent 是否可以驱动它                               |
-| `mafdet chat [提示词] [--model] [--system <文件>] [--input <文件>] [--no-stream] [--quiet]` | 发一次对话，默认流式                                                |
-| `mafdet embed [文本\|<文件>] --model <id> [--output <文件>]`                                | 文本转向量                                                          |
-| `mafdet speech [文本\|<文件>] --model <id> --output <文件> --voice <音色>`                  | 文本转音频                                                          |
-| `mafdet agent "<目标>" [--allow-write] [--allow-command "<前缀>"]`                          | 本地 Agent，默认只读                                                |
-| `mafdet agent`（不带目标，需终端）                                                          | 交互会话                                                            |
-| `mafdet account balance\|usage\|subscription`                                               | 钱包、用量、套餐（需 `account:read` scope）                         |
-| `mafdet sessions list\|show\|usage\|delete`                                                 | 保存在这台电脑上的会话（不会调用模型）                              |
-| `mafdet sessions usage <id> --refresh`                                                      | 用账单账本的权威金额替换本地估算                                    |
-| `mafdet config list`                                                                        | 当前生效的配置及其来源                                              |
+| 命令                                                                                                 | 作用                                                                |
+| ---------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------- |
+| `mafdet doctor`                                                                                      | 一次检查 Node、两个端点、Key、工作区、git、模型与工具调用能力、余额 |
+| `mafdet models list [--surface chat\|embeddings\|speech] [--agent]`                                  | 这把 Key 能调用的模型，并附上目录元数据                             |
+| `mafdet models show <id>`                                                                            | 单个模型详情，含 Agent 是否可以驱动它                               |
+| `mafdet chat [提示词] [--model] [--system <文件>] [--input <文件>] [--no-stream] [--quiet] [--save]` | 发一次对话，默认流式                                                |
+| `mafdet embed [文本\|<文件>] --model <id> [--output <文件>]`                                         | 文本转向量                                                          |
+| `mafdet speech [文本\|<文件>] --model <id> --output <文件> --voice <音色>`                           | 文本转音频                                                          |
+| `mafdet agent "<目标>" [--allow-write] [--allow-command "<前缀>"]`                                   | 本地 Agent，默认只读                                                |
+| `mafdet agent`（不带目标，需终端）                                                                   | 交互会话                                                            |
+| `mafdet account balance\|usage\|subscription`                                                        | 钱包、用量、套餐（需 `account:read` scope）                         |
+| `mafdet sessions list\|show\|usage\|delete`                                                          | 保存在这台电脑上的会话（不会调用模型）                              |
+| `mafdet sessions usage <id> --refresh`                                                               | 用账单账本的权威金额替换本地估算                                    |
+| `mafdet config list`                                                                                 | 当前生效的配置及其来源                                              |
 
 查询类命令都支持 `--json`（输出一份完整 JSON 文档）与 `--plain`（无表头的 TSV，方便
 `cut`、`awk` 处理）。
@@ -186,10 +186,15 @@ Linux 与 macOS 上文件权限 `0600`、目录 `0700`；**Windows 没有等价
 
 ```bash
 mafdet --no-history            # 这一次运行完全不记录
+mafdet chat "..." --save       # 一次性对话只有明确要求时才保存
 mafdet sessions list           # 已保存的会话；没有时会告诉你路径
 mafdet sessions delete <id> --yes
 ```
 
+一次 `mafdet chat` 不是有人会去恢复的对话，所以**不带 `--save` 就不保存**。
+`--no-history` 仍然压过 `--save`；被 Ctrl+C 取消的对话**完全不保存**——
+半个回复是比没有更糟的记录。
+
 `--no-history` 什么都不留——不留空目录，也不留索引条目。
 
 删除会移除本地消息和这个会话的用量映射。它**不会**移除 API 用量、账单记录或扣费：

package/dist/agent/context-budget.d.ts

@@ -0,0 +1,37 @@
+import type { ChatMessage } from "./loop.js";
+/**
+ * Fraction of the usable window at which we start shortening.
+ *
+ * Not 1.0, and the gap is not caution for its own sake: the request that
+ * measured `prompt_tokens` is smaller than the next one will be, because the
+ * assistant reply, its tool results and the next user message all land in
+ * between and none of them are counted yet.
+ */
+export declare const COMPACT_AT = 0.75;
+/** Room left for the reply, which shares the window with the input. */
+export declare function replyReserve(contextLength: number): number;
+/** Tool exchanges kept whatever happens, so the recent work stays intact. */
+export declare const KEEP_RECENT_EXCHANGES = 2;
+/**
+ * Is the conversation close enough to the window to shorten it?
+ *
+ * `lastPromptTokens` is what the provider counted for the previous request in
+ * this run. Zero means nothing has been measured yet, and an unknown window
+ * means we have nothing to compare against.
+ */
+export declare function shouldCompact(contextLength: number | undefined, lastPromptTokens: number): boolean;
+export interface PruneResult {
+    /** Messages removed from the array. */
+    readonly removed: number;
+    /** Complete tool exchanges dropped. */
+    readonly exchanges: number;
+}
+/**
+ * Drop the oldest complete tool exchanges, in place.
+ *
+ * The system prompt and the opening goal are never touched - without the goal
+ * the model no longer knows what it is doing, which is a worse failure than
+ * running out of context.
+ */
+export declare function pruneToolExchanges(history: ChatMessage[], keepRecent?: number): PruneResult;
+//# sourceMappingURL=context-budget.d.ts.map

package/dist/agent/context-budget.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"context-budget.d.ts","sourceRoot":"","sources":["../../src/agent/context-budget.ts"],"names":[],"mappings":"AAsBA,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,WAAW,CAAC;AAE7C;;;;;;;GAOG;AACH,eAAO,MAAM,UAAU,OAAO,CAAC;AAE/B,uEAAuE;AACvE,wBAAgB,YAAY,CAAC,aAAa,EAAE,MAAM,GAAG,MAAM,CAE1D;AAED,6EAA6E;AAC7E,eAAO,MAAM,qBAAqB,IAAI,CAAC;AAEvC;;;;;;GAMG;AACH,wBAAgB,aAAa,CAC3B,aAAa,EAAE,MAAM,GAAG,SAAS,EACjC,gBAAgB,EAAE,MAAM,GACvB,OAAO,CAKT;AAED,MAAM,WAAW,WAAW;IAC1B,uCAAuC;IACvC,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;IACzB,uCAAuC;IACvC,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC;CAC5B;AAsCD;;;;;;GAMG;AACH,wBAAgB,kBAAkB,CAChC,OAAO,EAAE,WAAW,EAAE,EACtB,UAAU,GAAE,MAA8B,GACzC,WAAW,CAkBb"}

package/dist/agent/context-budget.js

@@ -0,0 +1,105 @@
+// §7.4 · Keeping a long run inside the model's context window.
+//
+// The plan asks for "总上下文按模型窗口设置预算，接近上限时压缩历史". Two decisions
+// shape what that can honestly be:
+//
+// The size of the history is *measured*, not estimated. Every response carries
+// `prompt_tokens` for the request that produced it, which is the provider's own
+// count of exactly the conversation we sent. Estimating instead would mean
+// shipping a tokenizer per provider - CLI-000B already found the gateway's own
+// reservation under-counts badly because it cannot see the tool schema, and a
+// second wrong estimate here would be no better.
+//
+// And what gets dropped is whole tool exchanges, never individual messages.
+// CLI-014 established the rule the hard way: an assistant message carrying
+// `tool_calls` and the `tool` results answering them are inseparable, because
+// the API rejects a tool result with no matching call and a call with no
+// result. So the unit of removal is the pair, or nothing.
+//
+// When the model's context length is unknown, nothing happens at all. A guess
+// at the window would either truncate a conversation that fit, or fail to
+// truncate one that did not.
+/**
+ * Fraction of the usable window at which we start shortening.
+ *
+ * Not 1.0, and the gap is not caution for its own sake: the request that
+ * measured `prompt_tokens` is smaller than the next one will be, because the
+ * assistant reply, its tool results and the next user message all land in
+ * between and none of them are counted yet.
+ */
+export const COMPACT_AT = 0.75;
+/** Room left for the reply, which shares the window with the input. */
+export function replyReserve(contextLength) {
+    return Math.min(4096, Math.floor(contextLength / 8));
+}
+/** Tool exchanges kept whatever happens, so the recent work stays intact. */
+export const KEEP_RECENT_EXCHANGES = 2;
+/**
+ * Is the conversation close enough to the window to shorten it?
+ *
+ * `lastPromptTokens` is what the provider counted for the previous request in
+ * this run. Zero means nothing has been measured yet, and an unknown window
+ * means we have nothing to compare against.
+ */
+export function shouldCompact(contextLength, lastPromptTokens) {
+    if (contextLength === undefined || contextLength <= 0)
+        return false;
+    if (lastPromptTokens <= 0)
+        return false;
+    const usable = contextLength - replyReserve(contextLength);
+    return usable > 0 && lastPromptTokens >= usable * COMPACT_AT;
+}
+/**
+ * The assistant-with-tool_calls messages and the tool results that answer them.
+ *
+ * An exchange is only counted when every one of its calls has a result: a
+ * partial one is the tail of a run still in progress, and removing half of it
+ * is precisely the shape the API refuses.
+ */
+function exchangesIn(history) {
+    const found = [];
+    for (let i = 0; i < history.length; i += 1) {
+        const message = history[i];
+        if (message === undefined)
+            continue;
+        const calls = message.role === "assistant" ? message.tool_calls : undefined;
+        if (calls === undefined || calls.length === 0)
+            continue;
+        const answered = new Set();
+        let end = i + 1;
+        while (end < history.length && history[end]?.role === "tool") {
+            const id = history[end]?.tool_call_id;
+            if (typeof id === "string")
+                answered.add(id);
+            end += 1;
+        }
+        if (calls.every((call) => answered.has(call.id))) {
+            found.push({ start: i, end });
+        }
+        i = end - 1;
+    }
+    return found;
+}
+/**
+ * Drop the oldest complete tool exchanges, in place.
+ *
+ * The system prompt and the opening goal are never touched - without the goal
+ * the model no longer knows what it is doing, which is a worse failure than
+ * running out of context.
+ */
+export function pruneToolExchanges(history, keepRecent = KEEP_RECENT_EXCHANGES) {
+    const exchanges = exchangesIn(history);
+    const droppable = exchanges.slice(0, Math.max(0, exchanges.length - keepRecent));
+    if (droppable.length === 0)
+        return { removed: 0, exchanges: 0 };
+    const drop = new Set();
+    for (const exchange of droppable) {
+        for (let i = exchange.start; i < exchange.end; i += 1)
+            drop.add(i);
+    }
+    const kept = history.filter((_, index) => !drop.has(index));
+    const removed = history.length - kept.length;
+    history.length = 0;
+    history.push(...kept);
+    return { removed, exchanges: droppable.length };
+}

package/dist/agent/loop.d.ts

@@ -106,6 +106,17 @@ export type AgentEvent = {
     type: "rate_limited";
     waitMs: number;
     attempt: number;
+}
+/**
+ * §7.4 · The history was shortened to stay inside the model's window.
+ * Surfaced rather than done quietly: the user is entitled to know that
+ * earlier tool output is no longer being sent.
+ */
+ | {
+    type: "compacted";
+    exchanges: number;
+    messages: number;
+    promptTokens: number;
 };
 export interface ChatMessage {
     role: "system" | "user" | "assistant" | "tool";

package/dist/agent/loop.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"loop.d.ts","sourceRoot":"","sources":["../../src/agent/loop.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,gBAAgB,CAAC;AACjD,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,kBAAkB,CAAC;AACrD,OAAO,KAAK,EAAE,QAAQ,EAAE,MAAM,gBAAgB,CAAC;AAC/C,OAAO,EAEL,KAAK,WAAW,EAChB,KAAK,cAAc,EACpB,MAAM,kBAAkB,CAAC;AAE1B,iBAAiB;AACjB,eAAO,MAAM,cAAc;;;IAGzB,iFAAiF;;;qBAGnD,MAAM,GAAG,SAAS;CACjD,CAAC;AAEF,MAAM,MAAM,WAAW,GAAG,OAAO,cAAc,CAAC;AAEhD,MAAM,MAAM,UAAU,GAClB,WAAW,GACX,WAAW,GACX,SAAS,GACT,UAAU,GACV,WAAW,GACX,cAAc,GACd,OAAO,CAAC;AAEZ,MAAM,WAAW,WAAW;IAC1B,UAAU,EAAE,UAAU,CAAC;IACvB,wDAAwD;IACxD,SAAS,EAAE,MAAM,CAAC;IAClB,KAAK,EAAE,MAAM,CAAC;IACd,aAAa,EAAE,MAAM,CAAC;IACtB,aAAa,EAAE,MAAM,CAAC;IACtB,WAAW,EAAE,MAAM,CAAC;IACpB,QAAQ,EAAE;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,EAAE,EAAE,OAAO,CAAA;KAAE,EAAE,CAAC;IAC1C,YAAY,EAAE,MAAM,CAAC;IACrB,gBAAgB,EAAE,MAAM,CAAC;IACzB,YAAY,EAAE,MAAM,CAAC;IACrB,uDAAuD;IACvD,KAAK,CAAC,EAAE,MAAM,CAAC;CAChB;AAED,MAAM,WAAW,YAAY;IAC3B,MAAM,EAAE,UAAU,CAAC;IACnB,KAAK,EAAE,MAAM,CAAC;IACd,mEAAmE;IACnE,OAAO,CAAC,EAAE,YAAY,CAAC;IACvB,IAAI,EAAE,MAAM,CAAC;IACb,YAAY,EAAE,MAAM,CAAC;IACrB,KAAK,EAAE,cAAc,EAAE,CAAC;IACxB,WAAW,EAAE,WAAW,CAAC;IACzB;;;OAGG;IACH,OAAO,CAAC,EAAE,WAAW,EAAE,CAAC;IACxB,6EAA6E;IAC7E,QAAQ,CAAC,EAAE,QAAQ,CAAC;IACpB,MAAM,CAAC,EAAE,OAAO,CAAC,WAAW,CAAC,CAAC;IAC9B,MAAM,CAAC,EAAE,WAAW,CAAC;IACrB,kEAAkE;IAClE,OAAO,CAAC,EAAE,CAAC,KAAK,EAAE,UAAU,KAAK,IAAI,CAAC;IACtC,uDAAuD;IACvD,KAAK,CAAC,EAAE,CAAC,EAAE,EAAE,MAAM,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;IACtC,GAAG,CAAC,EAAE,MAAM,MAAM,CAAC;IACnB,MAAM,CAAC,EAAE,MAAM,MAAM,CAAC;CACvB;AAED;;;;;;;;GAQG;AACH,MAAM,MAAM,UAAU,GAClB;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,IAAI,EAAE,MAAM,CAAA;CAAE,GAC9B;IAAE,IAAI,EAAE,cAAc,CAAC;IAAC,IAAI,EAAE,MAAM,CAAC;IAAC,SAAS,EAAE,MAAM,CAAA;CAAE,GACzD;IAAE,IAAI,EAAE,wBAAwB,CAAC;IAAC,IAAI,EAAE,MAAM,CAAC;IAAC,OAAO,EAAE,MAAM,CAAA;CAAE,GACjE;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,IAAI,EAAE,MAAM,CAAC;IAAC,EAAE,EAAE,OAAO,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE,GAC3D;IAAE,IAAI,EAAE,UAAU,CAAC;IAAC,IAAI,EAAE,MAAM,CAAC;IAAC,OAAO,EAAE,MAAM,CAAA;CAAE,GACnD;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,IAAI,EAAE,MAAM,CAAA;CAAE;AAChC;;;;;GAKG;GACD;IACE,IAAI,EAAE,OAAO,CAAC;IACd,KAAK,EAAE,MAAM,CAAC;IACd,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,YAAY,EAAE,MAAM,CAAC;IACrB,gBAAgB,EAAE,MAAM,CAAC;IACzB,YAAY,EAAE,MAAM,CAAC;CACtB,GACD;IAAE,IAAI,EAAE,cAAc,CAAC;IAAC,MAAM,EAAE,MAAM,CAAC;IAAC,OAAO,EAAE,MAAM,CAAA;CAAE,CAAC;AAE9D,MAAM,WAAW,WAAW;IAC1B,IAAI,EAAE,QAAQ,GAAG,MAAM,GAAG,WAAW,GAAG,MAAM,CAAC;IAC/C,OAAO,EAAE,MAAM,GAAG,IAAI,CAAC;IACvB,UAAU,CAAC,EAAE,QAAQ,EAAE,CAAC;IACxB,YAAY,CAAC,EAAE,MAAM,CAAC;CACvB;AAED,UAAU,QAAQ;IAChB,EAAE,EAAE,MAAM,CAAC;IACX,IAAI,EAAE,UAAU,CAAC;IACjB,QAAQ,EAAE;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,SAAS,EAAE,MAAM,CAAA;KAAE,CAAC;CAC/C;AAYD;;;;;;;;;GASG;AACH,wBAAsB,QAAQ,CAAC,OAAO,EAAE,YAAY,GAAG,OAAO,CAAC,WAAW,CAAC,CAoI1E;AAqID,+EAA+E;AAC/E,wBAAgB,SAAS,CACvB,iBAAiB,EAAE,MAAM,GAAG,SAAS,EACrC,OAAO,EAAE,MAAM,EACf,MAAM,GAAE,MAAM,MAAoB,GACjC,MAAM,CAOR"}
+{"version":3,"file":"loop.d.ts","sourceRoot":"","sources":["../../src/agent/loop.ts"],"names":[],"mappings":"AAEA,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,gBAAgB,CAAC;AACjD,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,kBAAkB,CAAC;AACrD,OAAO,KAAK,EAAE,QAAQ,EAAE,MAAM,gBAAgB,CAAC;AAC/C,OAAO,EAEL,KAAK,WAAW,EAChB,KAAK,cAAc,EACpB,MAAM,kBAAkB,CAAC;AAE1B,iBAAiB;AACjB,eAAO,MAAM,cAAc;;;IAGzB,iFAAiF;;;qBAGnD,MAAM,GAAG,SAAS;CACjD,CAAC;AAEF,MAAM,MAAM,WAAW,GAAG,OAAO,cAAc,CAAC;AAEhD,MAAM,MAAM,UAAU,GAClB,WAAW,GACX,WAAW,GACX,SAAS,GACT,UAAU,GACV,WAAW,GACX,cAAc,GACd,OAAO,CAAC;AAEZ,MAAM,WAAW,WAAW;IAC1B,UAAU,EAAE,UAAU,CAAC;IACvB,wDAAwD;IACxD,SAAS,EAAE,MAAM,CAAC;IAClB,KAAK,EAAE,MAAM,CAAC;IACd,aAAa,EAAE,MAAM,CAAC;IACtB,aAAa,EAAE,MAAM,CAAC;IACtB,WAAW,EAAE,MAAM,CAAC;IACpB,QAAQ,EAAE;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,EAAE,EAAE,OAAO,CAAA;KAAE,EAAE,CAAC;IAC1C,YAAY,EAAE,MAAM,CAAC;IACrB,gBAAgB,EAAE,MAAM,CAAC;IACzB,YAAY,EAAE,MAAM,CAAC;IACrB,uDAAuD;IACvD,KAAK,CAAC,EAAE,MAAM,CAAC;CAChB;AAED,MAAM,WAAW,YAAY;IAC3B,MAAM,EAAE,UAAU,CAAC;IACnB,KAAK,EAAE,MAAM,CAAC;IACd,mEAAmE;IACnE,OAAO,CAAC,EAAE,YAAY,CAAC;IACvB,IAAI,EAAE,MAAM,CAAC;IACb,YAAY,EAAE,MAAM,CAAC;IACrB,KAAK,EAAE,cAAc,EAAE,CAAC;IACxB,WAAW,EAAE,WAAW,CAAC;IACzB;;;OAGG;IACH,OAAO,CAAC,EAAE,WAAW,EAAE,CAAC;IACxB,6EAA6E;IAC7E,QAAQ,CAAC,EAAE,QAAQ,CAAC;IACpB,MAAM,CAAC,EAAE,OAAO,CAAC,WAAW,CAAC,CAAC;IAC9B,MAAM,CAAC,EAAE,WAAW,CAAC;IACrB,kEAAkE;IAClE,OAAO,CAAC,EAAE,CAAC,KAAK,EAAE,UAAU,KAAK,IAAI,CAAC;IACtC,uDAAuD;IACvD,KAAK,CAAC,EAAE,CAAC,EAAE,EAAE,MAAM,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;IACtC,GAAG,CAAC,EAAE,MAAM,MAAM,CAAC;IACnB,MAAM,CAAC,EAAE,MAAM,MAAM,CAAC;CACvB;AAED;;;;;;;;GAQG;AACH,MAAM,MAAM,UAAU,GAClB;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,IAAI,EAAE,MAAM,CAAA;CAAE,GAC9B;IAAE,IAAI,EAAE,cAAc,CAAC;IAAC,IAAI,EAAE,MAAM,CAAC;IAAC,SAAS,EAAE,MAAM,CAAA;CAAE,GACzD;IAAE,IAAI,EAAE,wBAAwB,CAAC;IAAC,IAAI,EAAE,MAAM,CAAC;IAAC,OAAO,EAAE,MAAM,CAAA;CAAE,GACjE;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,IAAI,EAAE,MAAM,CAAC;IAAC,EAAE,EAAE,OAAO,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE,GAC3D;IAAE,IAAI,EAAE,UAAU,CAAC;IAAC,IAAI,EAAE,MAAM,CAAC;IAAC,OAAO,EAAE,MAAM,CAAA;CAAE,GACnD;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,IAAI,EAAE,MAAM,CAAA;CAAE;AAChC;;;;;GAKG;GACD;IACE,IAAI,EAAE,OAAO,CAAC;IACd,KAAK,EAAE,MAAM,CAAC;IACd,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,YAAY,EAAE,MAAM,CAAC;IACrB,gBAAgB,EAAE,MAAM,CAAC;IACzB,YAAY,EAAE,MAAM,CAAC;CACtB,GACD;IAAE,IAAI,EAAE,cAAc,CAAC;IAAC,MAAM,EAAE,MAAM,CAAC;IAAC,OAAO,EAAE,MAAM,CAAA;CAAE;AAC3D;;;;GAIG;GACD;IACE,IAAI,EAAE,WAAW,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;IAClB,QAAQ,EAAE,MAAM,CAAC;IACjB,YAAY,EAAE,MAAM,CAAC;CACtB,CAAC;AAEN,MAAM,WAAW,WAAW;IAC1B,IAAI,EAAE,QAAQ,GAAG,MAAM,GAAG,WAAW,GAAG,MAAM,CAAC;IAC/C,OAAO,EAAE,MAAM,GAAG,IAAI,CAAC;IACvB,UAAU,CAAC,EAAE,QAAQ,EAAE,CAAC;IACxB,YAAY,CAAC,EAAE,MAAM,CAAC;CACvB;AAED,UAAU,QAAQ;IAChB,EAAE,EAAE,MAAM,CAAC;IACX,IAAI,EAAE,UAAU,CAAC;IACjB,QAAQ,EAAE;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,SAAS,EAAE,MAAM,CAAA;KAAE,CAAC;CAC/C;AAYD;;;;;;;;;GASG;AACH,wBAAsB,QAAQ,CAAC,OAAO,EAAE,YAAY,GAAG,OAAO,CAAC,WAAW,CAAC,CAyJ1E;AAqID,+EAA+E;AAC/E,wBAAgB,SAAS,CACvB,iBAAiB,EAAE,MAAM,GAAG,SAAS,EACrC,OAAO,EAAE,MAAM,EACf,MAAM,GAAE,MAAM,MAAoB,GACjC,MAAM,CAOR"}

package/dist/agent/loop.js

@@ -1,4 +1,5 @@
 import { ApiError } from "../api/errors.js";
+import { pruneToolExchanges, shouldCompact } from "./context-budget.js";
 import { toolToJsonSchema, } from "./tools/types.js";
 /** Plan §7.4. */
 export const DEFAULT_LIMITS = {
@@ -44,6 +45,8 @@ export async function runAgent(options) {
         completionTokens: 0,
         costMicroUsd: 0n,
     };
+    /** What the provider counted for the previous request; 0 until one lands. */
+    let lastPromptTokens = 0;
     for (let turn = 1; turn <= limits.maxTurns; turn += 1) {
         if (options.signal?.aborted)
             return stop(report, "cancelled");
@@ -55,6 +58,22 @@ export async function runAgent(options) {
         }
         report.turns = turn;
         options.onEvent?.({ type: "turn", turn });
+        // §7.4 · Shorten before asking, using what the provider counted last time.
+        // Only whole tool exchanges go, and only when the window is known.
+        if (shouldCompact(options.pricing?.contextLength, lastPromptTokens)) {
+            const pruned = pruneToolExchanges(messages);
+            if (pruned.exchanges > 0) {
+                options.onEvent?.({
+                    type: "compacted",
+                    exchanges: pruned.exchanges,
+                    messages: pruned.removed,
+                    promptTokens: lastPromptTokens,
+                });
+                // Reset the measurement: the next response measures the shorter
+                // history, and reusing the old figure would compact again every turn.
+                lastPromptTokens = 0;
+            }
+        }
         let response;
         try {
             response = await requestWithRateLimitHandling(options, limits, {
@@ -74,6 +93,7 @@ export async function runAgent(options) {
             return stop(report, "error", error instanceof Error ? error.message : String(error));
         }
         const usage = response.usage;
+        lastPromptTokens = usage?.prompt_tokens ?? lastPromptTokens;
         report.promptTokens += usage?.prompt_tokens ?? 0;
         report.completionTokens += usage?.completion_tokens ?? 0;
         // Cost comes from returned usage, never from the reservation: CLI-000B

package/dist/agent/tools/run-command.d.ts

@@ -15,6 +15,34 @@ export interface CommandResult {
  * failure mode where a "timed out" test run keeps holding a port.
  */
 export declare function executeCommand(argv: readonly string[], cwd: string, timeoutMs?: number): Promise<CommandResult>;
+/**
+ * What "kill the whole tree" means on this platform.
+ *
+ * Pure, and separated from doing it, because the Windows branch cannot be
+ * executed here: there is no Windows machine in this project, and a kill path
+ * that has never run is exactly the kind of code that is wrong in a way only
+ * production finds. Keeping the decision pure means the *shape* of the command
+ * is under test on both platforms even though only one of them can be run.
+ *
+ * POSIX: a negative pid signals the process group, which is why the child is
+ * spawned detached. Killing the parent alone leaves grandchildren running -
+ * the familiar case where a "timed out" test runner keeps holding a port.
+ *
+ * Windows has no process groups in that sense. `taskkill /T` walks the child
+ * tree instead, and `/F` is the forceful pass: without it taskkill asks
+ * politely, which a console process is free to ignore - the same distinction
+ * as SIGTERM and SIGKILL.
+ */
+export type KillPlan = {
+    readonly kind: "signal";
+    readonly target: number;
+    readonly signal: NodeJS.Signals;
+} | {
+    readonly kind: "spawn";
+    readonly command: string;
+    readonly args: readonly string[];
+};
+export declare function killPlan(pid: number, force: boolean, platform?: string): KillPlan;
 export declare const runCommandTool: ToolDefinition;
 export declare const COMMAND_TOOLS: ToolDefinition[];
 //# sourceMappingURL=run-command.d.ts.map

package/dist/agent/tools/run-command.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"run-command.d.ts","sourceRoot":"","sources":["../../../src/agent/tools/run-command.ts"],"names":[],"mappings":"AAKA,OAAO,KAAK,EAA+B,cAAc,EAAE,MAAM,YAAY,CAAC;AAE9E,0DAA0D;AAC1D,eAAO,MAAM,kBAAkB,SAAU,CAAC;AAG1C,MAAM,WAAW,aAAa;IAC5B,IAAI,EAAE,MAAM,GAAG,IAAI,CAAC;IACpB,MAAM,EAAE,MAAM,GAAG,IAAI,CAAC;IACtB,MAAM,EAAE,MAAM,CAAC;IACf,QAAQ,EAAE,OAAO,CAAC;CACnB;AAED;;;;;;GAMG;AACH,wBAAsB,cAAc,CAClC,IAAI,EAAE,SAAS,MAAM,EAAE,EACvB,GAAG,EAAE,MAAM,EACX,SAAS,GAAE,MAA2B,GACrC,OAAO,CAAC,aAAa,CAAC,CAkDxB;AAwBD,eAAO,MAAM,cAAc,EAAE,cAmC5B,CAAC;AAEF,eAAO,MAAM,aAAa,EAAE,cAAc,EAAqB,CAAC"}
+{"version":3,"file":"run-command.d.ts","sourceRoot":"","sources":["../../../src/agent/tools/run-command.ts"],"names":[],"mappings":"AAKA,OAAO,KAAK,EAA+B,cAAc,EAAE,MAAM,YAAY,CAAC;AAE9E,0DAA0D;AAC1D,eAAO,MAAM,kBAAkB,SAAU,CAAC;AAG1C,MAAM,WAAW,aAAa;IAC5B,IAAI,EAAE,MAAM,GAAG,IAAI,CAAC;IACpB,MAAM,EAAE,MAAM,GAAG,IAAI,CAAC;IACtB,MAAM,EAAE,MAAM,CAAC;IACf,QAAQ,EAAE,OAAO,CAAC;CACnB;AAED;;;;;;GAMG;AACH,wBAAsB,cAAc,CAClC,IAAI,EAAE,SAAS,MAAM,EAAE,EACvB,GAAG,EAAE,MAAM,EACX,SAAS,GAAE,MAA2B,GACrC,OAAO,CAAC,aAAa,CAAC,CAkDxB;AAED;;;;;;;;;;;;;;;;;GAiBG;AACH,MAAM,MAAM,QAAQ,GAChB;IACE,QAAQ,CAAC,IAAI,EAAE,QAAQ,CAAC;IACxB,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;IACxB,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC,OAAO,CAAC;CACjC,GACD;IACE,QAAQ,CAAC,IAAI,EAAE,OAAO,CAAC;IACvB,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;IACzB,QAAQ,CAAC,IAAI,EAAE,SAAS,MAAM,EAAE,CAAC;CAClC,CAAC;AAEN,wBAAgB,QAAQ,CACtB,GAAG,EAAE,MAAM,EACX,KAAK,EAAE,OAAO,EACd,QAAQ,GAAE,MAAyB,GAClC,QAAQ,CAaV;AA8BD,eAAO,MAAM,cAAc,EAAE,cAmC5B,CAAC;AAEF,eAAO,MAAM,aAAa,EAAE,cAAc,EAAqB,CAAC"}

package/dist/agent/tools/run-command.js

@@ -48,8 +48,8 @@ export async function executeCommand(argv, cwd, timeoutMs = COMMAND_TIMEOUT_MS)
         const timer = setTimeout(() => {
             timedOut = true;
             killTree(child.pid);
-            // A process ignoring SIGTERM still has to go.
-            setTimeout(() => killTree(child.pid, "SIGKILL"), 2000).unref();
+            // A process ignoring the polite request still has to go.
+            setTimeout(() => killTree(child.pid, true), 2000).unref();
         }, timeoutMs);
         const finish = (code, signal) => {
             clearTimeout(timer);
@@ -59,23 +59,44 @@ export async function executeCommand(argv, cwd, timeoutMs = COMMAND_TIMEOUT_MS)
         child.on("close", (code, signal) => finish(code, signal));
     });
 }
+export function killPlan(pid, force, platform = process.platform) {
+    if (platform === "win32") {
+        return {
+            kind: "spawn",
+            command: "taskkill",
+            args: ["/PID", String(pid), "/T", ...(force ? ["/F"] : [])],
+        };
+    }
+    return {
+        kind: "signal",
+        target: -pid,
+        signal: force ? "SIGKILL" : "SIGTERM",
+    };
+}
 /**
- * Kill the whole process group, not just the child.
+ * Kill the whole tree.
  *
- * Killing the parent alone leaves grandchildren running - the familiar case
- * where a "timed out" test runner keeps holding a port. The negative pid is
- * POSIX; Windows has no process groups in this sense, so there the direct
- * child is killed and the limitation is stated rather than papered over
- * (no Windows machine here to verify a taskkill /T path).
+ * ⚠️ The Windows branch is UNVERIFIED on a real machine. Its shape is tested;
+ * whether `taskkill /T` actually reaches every grandchild of a Node-spawned
+ * process is not something this project has been able to check.
  */
-function killTree(pid, signal = "SIGTERM") {
+function killTree(pid, force = false) {
     if (pid === undefined)
         return;
+    const plan = killPlan(pid, force);
     try {
-        if (process.platform === "win32")
-            process.kill(pid, signal);
-        else
-            process.kill(-pid, signal);
+        if (plan.kind === "signal") {
+            process.kill(plan.target, plan.signal);
+            return;
+        }
+        // Detached and ignored: this is fire-and-forget cleanup, and a taskkill
+        // that fails must not become an unhandled error on the way out.
+        const killer = spawn(plan.command, [...plan.args], {
+            stdio: "ignore",
+            windowsHide: true,
+        });
+        killer.on("error", () => { });
+        killer.unref();
     }
     catch {
         // Already exited, or never became a group leader.

package/dist/commands/chat.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"chat.d.ts","sourceRoot":"","sources":["../../src/commands/chat.ts"],"names":[],"mappings":"AAEA,OAAO,EAAgB,KAAK,YAAY,EAAE,MAAM,kBAAkB,CAAC;AACnE,OAAO,EAAkB,KAAK,WAAW,EAAE,MAAM,sBAAsB,CAAC;AAExE,OAAO,EAAE,QAAQ,EAAE,MAAM,yBAAyB,CAAC;AAEnD,OAAO,EAIL,KAAK,SAAS,EACf,MAAM,cAAc,CAAC;AAUtB,MAAM,WAAW,MAAO,SAAQ,SAAS;IACvC,qDAAqD;IACrD,SAAS,CAAC,EAAE,MAAM,OAAO,CAAC,MAAM,CAAC,CAAC;IAClC,gDAAgD;IAChD,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB;AAWD,wBAAsB,WAAW,CAC/B,IAAI,EAAE,SAAS,MAAM,EAAE,EACvB,EAAE,EAAE,MAAM,GACT,OAAO,CAAC,QAAQ,CAAC,CA8BnB;AAwLD,wBAAgB,sBAAsB,CACpC,KAAK,EAAE,YAAY,GAAG,SAAS,EAC/B,KAAK,EAAE,WAAW,GACjB,MAAM,GAAG,SAAS,CASpB"}
+{"version":3,"file":"chat.d.ts","sourceRoot":"","sources":["../../src/commands/chat.ts"],"names":[],"mappings":"AAEA,OAAO,EAAgB,KAAK,YAAY,EAAE,MAAM,kBAAkB,CAAC;AACnE,OAAO,EAAkB,KAAK,WAAW,EAAE,MAAM,sBAAsB,CAAC;AAOxE,OAAO,EAAE,QAAQ,EAAE,MAAM,yBAAyB,CAAC;AAEnD,OAAO,EAIL,KAAK,SAAS,EACf,MAAM,cAAc,CAAC;AAatB,MAAM,WAAW,MAAO,SAAQ,SAAS;IACvC,qDAAqD;IACrD,SAAS,CAAC,EAAE,MAAM,OAAO,CAAC,MAAM,CAAC,CAAC;IAClC,gDAAgD;IAChD,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB;AAcD,wBAAsB,WAAW,CAC/B,IAAI,EAAE,SAAS,MAAM,EAAE,EACvB,EAAE,EAAE,MAAM,GACT,OAAO,CAAC,QAAQ,CAAC,CA8BnB;AAoSD,wBAAgB,sBAAsB,CACpC,KAAK,EAAE,YAAY,GAAG,SAAS,EAC/B,KAAK,EAAE,WAAW,GACjB,MAAM,GAAG,SAAS,CASpB"}

package/dist/commands/chat.js

@@ -2,15 +2,23 @@ import { readFileSync } from "node:fs";
 import { fetchCatalog } from "../api/models.js";
 import { readChatStream } from "../api/sse-parser.js";
 import { ApiError } from "../api/errors.js";
+import { sessionsDir } from "../config/paths.js";
+import { keyDigest } from "../security/redact.js";
+import { upsertIndexEntry } from "../sessions/index-file.js";
+import { decideRecording } from "../sessions/policy.js";
+import { SessionWriter } from "../sessions/store.js";
 import { ExitCode } from "../output/exit-codes.js";
 import { formatUsd } from "../output/money.js";
 import { buildRuntime, reportError, requireApiKey, } from "./runtime.js";
 const USAGE = `Usage:
   mafdet chat [prompt] [--model <id>] [--system <file>] [--input <file>]
-              [--no-stream] [--max-tokens <n>] [--quiet]
+              [--no-stream] [--max-tokens <n>] [--quiet] [--save]
 
 The prompt comes from an argument, from --input <file>, or from stdin when
 neither is given. Use "--input -" to force reading stdin.
+
+A single chat is not saved unless --save is given. Saved conversations stay
+on this computer; see 'mafdet sessions'.
 `;
 export async function chatCommand(argv, io) {
     try {
@@ -51,6 +59,8 @@ async function parseArgs(argv, configuredModel, io) {
     let inputFile;
     let stream = true;
     let quiet = false;
+    let save = false;
+    let noHistory = false;
     let maxTokens;
     for (let i = 0; i < argv.length; i += 1) {
         const arg = argv[i];
@@ -65,6 +75,10 @@ async function parseArgs(argv, configuredModel, io) {
             stream = false;
         else if (arg === "--quiet")
             quiet = true;
+        else if (arg === "--save")
+            save = true;
+        else if (arg === "--no-history")
+            noHistory = true;
         else if (arg === "--max-tokens") {
             const raw = next();
             maxTokens = Number(raw);
@@ -123,6 +137,8 @@ async function parseArgs(argv, configuredModel, io) {
         stream,
         maxTokens,
         quiet,
+        save,
+        noHistory,
     };
 }
 function readTextFile(path, flag) {
@@ -137,26 +153,117 @@ function readTextFile(path, flag) {
         });
     }
 }
+/**
+ * CLI-024/§20.4 · Save a one-shot chat, when asked.
+ *
+ * A single `mafdet chat` is not a conversation anyone resumes, so it is not
+ * recorded by default; `--save` opts in and `--no-history` still wins over it.
+ * Everything written goes through the same store as an interactive session, so
+ * the same redaction, the same 0600 files and the same `mafdet sessions
+ * delete` apply - there is no second, weaker path to disk.
+ *
+ * Failures here are swallowed: losing the record of a chat is bad, losing the
+ * answer the user is waiting for is worse.
+ */
+function saveChat(args, io, answer, usage, requestId, model) {
+    const decision = decideRecording({
+        surface: "one-shot",
+        noHistory: args.noHistory,
+        save: args.save,
+    });
+    if (!decision.record)
+        return;
+    const env = io.env ?? process.env;
+    try {
+        const root = sessionsDir(env);
+        const writer = SessionWriter.create({
+            root,
+            title: chatTitle(args.prompt),
+            modelId: args.model,
+            workspace: io.cwd ?? process.cwd(),
+            mode: "chat",
+        });
+        if (args.system !== undefined) {
+            writer.append({ type: "user_message", content: args.system });
+        }
+        writer.append({ type: "user_message", content: args.prompt });
+        writer.append({ type: "assistant_message", content: answer });
+        if (usage) {
+            const micros = estimateChargeMicroUsd(model, usage);
+            writer.append({
+                type: "usage",
+                ...(requestId === undefined ? {} : { request_id: requestId }),
+                model_id: args.model,
+                prompt_tokens: usage.prompt_tokens,
+                completion_tokens: usage.completion_tokens,
+                estimated_charge_micro_usd: (micros ?? 0n).toString(),
+                settlement_status: "pending",
+                api_key_ref: keyDigest(readKey(io)),
+            });
+        }
+        writer.close();
+        upsertIndexEntry(root, writer.metadata);
+        if (!args.quiet) {
+            io.stderr(`saved as ${writer.sessionId} (local only)\n`);
+        }
+    }
+    catch (error) {
+        io.stderr(`mafdet chat: not saved: ${error instanceof Error ? error.message : String(error)}\n`);
+    }
+}
+/** The first line, trimmed to something that fits a listing. */
+function chatTitle(prompt) {
+    const line = prompt.split("\n").find((l) => l.trim().length > 0) ?? "Chat";
+    const trimmed = line.trim();
+    return trimmed.length > 60 ? `${trimmed.slice(0, 57)}...` : trimmed;
+}
+function readKey(io) {
+    return (io.env ?? process.env).MAFDET_API_KEY ?? "";
+}
+/**
+ * The catalogue entry for pricing, fetched once and shared.
+ *
+ * A pricing lookup must never fail the call that already succeeded, so a
+ * failure here is an absent price rather than an error - the tokens are still
+ * reported, and `sessions usage --refresh` can still get the settled figure.
+ */
+async function priceModel(runtime, modelId, needed) {
+    if (!needed)
+        return undefined;
+    try {
+        return (await fetchCatalog(runtime.accountPlane)).find((m) => m.modelId === modelId);
+    }
+    catch {
+        return undefined;
+    }
+}
 async function streamChat(runtime, body, args, io) {
-    const { response } = await runtime.dataPlane.postStream("/chat/completions", body, {
+    const { response, requestId } = await runtime.dataPlane.postStream("/chat/completions", body, {
         signal: io.signal,
     });
     // Text goes to stdout as it arrives; everything else is stderr, so
     // `mafdet chat ... > answer.txt` captures only the answer.
     const result = await readChatStream(response, { onText: io.stdout }, io.signal);
     io.stdout("\n");
+    const model = await priceModel(runtime, args.model, !args.quiet || args.save);
     if (io.signal?.aborted) {
         io.stderr("mafdet: cancelled - the connection was closed mid-generation\n");
-        await summarise(runtime, args, result.usage, io, { partial: true });
+        summarise(args, result.usage, io, model, { partial: true });
+        // A cancelled chat is not saved: the answer is incomplete, and an archive
+        // of half a reply is a worse record than none.
         return ExitCode.Cancelled;
     }
-    await summarise(runtime, args, result.usage, io);
+    summarise(args, result.usage, io, model);
+    saveChat(args, io, result.text, result.usage, requestId, model);
     return ExitCode.Ok;
 }
 async function completeChat(runtime, body, args, io) {
-    const { data } = await runtime.dataPlane.postJson("/chat/completions", body, { signal: io.signal });
-    io.stdout(`${data.choices?.[0]?.message?.content ?? ""}\n`);
-    await summarise(runtime, args, data.usage, io);
+    const { data, requestId } = await runtime.dataPlane.postJson("/chat/completions", body, { signal: io.signal });
+    const answer = data.choices?.[0]?.message?.content ?? "";
+    io.stdout(`${answer}\n`);
+    const model = await priceModel(runtime, args.model, !args.quiet || args.save);
+    summarise(args, data.usage, io, model);
+    saveChat(args, io, answer, data.usage, requestId, model);
     return ExitCode.Ok;
 }
 /**
@@ -165,20 +272,13 @@ async function completeChat(runtime, body, args, io) {
  * verified against the ledger to the micro-dollar. It is still labelled as an
  * estimate: the wallet, not the client, is the authority.
  */
-async function summarise(runtime, args, usage, io, options = {}) {
+function summarise(args, usage, io, model, options = {}) {
     if (args.quiet || !usage)
         return;
     let cost = "";
-    try {
-        const catalog = await fetchCatalog(runtime.accountPlane);
-        const model = catalog.find((m) => m.modelId === args.model);
-        const micros = estimateChargeMicroUsd(model, usage);
-        if (micros !== undefined)
-            cost = `, ~${formatUsd(micros)}`;
-    }
-    catch {
-        // A pricing lookup must never fail the call that already succeeded.
-    }
+    const micros = estimateChargeMicroUsd(model, usage);
+    if (micros !== undefined)
+        cost = `, ~${formatUsd(micros)}`;
     const prefix = options.partial ? "partial: " : "";
     io.stderr(`${prefix}${usage.prompt_tokens} in / ${usage.completion_tokens} out tokens${cost}\n`);
 }

package/dist/tui/agent-surface.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"agent-surface.d.ts","sourceRoot":"","sources":["../../src/tui/agent-surface.ts"],"names":[],"mappings":"AAQA,OAAO,EACL,UAAU,EACV,KAAK,cAAc,EACnB,KAAK,cAAc,EACpB,MAAM,qBAAqB,CAAC;AAI7B,OAAO,EAAW,KAAK,oBAAoB,EAAE,MAAM,YAAY,CAAC;AAEhE,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,yBAAyB,CAAC;AAC/D,OAAO,KAAK,EAAE,QAAQ,EAAE,MAAM,cAAc,CAAC;AAE7C,MAAM,WAAW,mBAAmB;IAClC,QAAQ,CAAC,EAAE,EAAE,QAAQ,CAAC;IACtB,QAAQ,CAAC,YAAY,EAAE,oBAAoB,CAAC;IAC5C,QAAQ,CAAC,MAAM,EAAE;QAAE,KAAK,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAAA;KAAE,CAAC;IAClD,0EAA0E;IAC1E,QAAQ,CAAC,OAAO,EAAE,IAAI,CACpB,cAAc,EACd,QAAQ,GAAG,QAAQ,GAAG,UAAU,GAAG,UAAU,GAAG,SAAS,CAC1D,CAAC;IACF;;;;;OAKG;IACH,QAAQ,CAAC,SAAS,CAAC,EAAE,MAAM,WAAW,GAAG,SAAS,CAAC;IACnD,wEAAwE;IACxE,QAAQ,CAAC,QAAQ,CAAC,EAAE,eAAe,CAAC;IACpC,yDAAyD;IACzD,QAAQ,CAAC,GAAG,CAAC,EAAE,OAAO,UAAU,CAAC;CAClC;AAED;;;;;;GAMG;AACH,wBAAsB,UAAU,CAC9B,EAAE,EAAE,QAAQ,EACZ,MAAM,EAAE,MAAM,GACb,OAAO,CAAC,MAAM,GAAG,SAAS,CAAC,CA+B7B;AAED,wBAAsB,eAAe,CACnC,OAAO,EAAE,mBAAmB,GAC3B,OAAO,CAAC,cAAc,CAAC,CA8DzB;AAED,wBAAgB,aAAa,CAC3B,OAAO,EAAE,cAAc,EACvB,YAAY,EAAE,oBAAoB,GACjC,MAAM,CAgBR"}
+{"version":3,"file":"agent-surface.d.ts","sourceRoot":"","sources":["../../src/tui/agent-surface.ts"],"names":[],"mappings":"AAQA,OAAO,EACL,UAAU,EACV,KAAK,cAAc,EACnB,KAAK,cAAc,EACpB,MAAM,qBAAqB,CAAC;AAI7B,OAAO,EAAW,KAAK,oBAAoB,EAAE,MAAM,YAAY,CAAC;AAEhE,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,yBAAyB,CAAC;AAC/D,OAAO,KAAK,EAAE,QAAQ,EAAE,MAAM,cAAc,CAAC;AAE7C,MAAM,WAAW,mBAAmB;IAClC,QAAQ,CAAC,EAAE,EAAE,QAAQ,CAAC;IACtB,QAAQ,CAAC,YAAY,EAAE,oBAAoB,CAAC;IAC5C,QAAQ,CAAC,MAAM,EAAE;QAAE,KAAK,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAAA;KAAE,CAAC;IAClD,0EAA0E;IAC1E,QAAQ,CAAC,OAAO,EAAE,IAAI,CACpB,cAAc,EACd,QAAQ,GAAG,QAAQ,GAAG,UAAU,GAAG,UAAU,GAAG,SAAS,CAC1D,CAAC;IACF;;;;;OAKG;IACH,QAAQ,CAAC,SAAS,CAAC,EAAE,MAAM,WAAW,GAAG,SAAS,CAAC;IACnD,wEAAwE;IACxE,QAAQ,CAAC,QAAQ,CAAC,EAAE,eAAe,CAAC;IACpC,yDAAyD;IACzD,QAAQ,CAAC,GAAG,CAAC,EAAE,OAAO,UAAU,CAAC;CAClC;AAED;;;;;;GAMG;AACH,wBAAsB,UAAU,CAC9B,EAAE,EAAE,QAAQ,EACZ,MAAM,EAAE,MAAM,GACb,OAAO,CAAC,MAAM,GAAG,SAAS,CAAC,CA+B7B;AAED,wBAAsB,eAAe,CACnC,OAAO,EAAE,mBAAmB,GAC3B,OAAO,CAAC,cAAc,CAAC,CAyEzB;AAED,wBAAgB,aAAa,CAC3B,OAAO,EAAE,cAAc,EACvB,YAAY,EAAE,oBAAoB,GACjC,MAAM,CAgBR"}

package/dist/tui/agent-surface.js

@@ -67,6 +67,13 @@ export async function runAgentSurface(options) {
             // when someone is deciding whether to press Ctrl+C.
             options.stdout.write(dim(`  rate limited - waiting ${Math.round(event.waitMs / 1000)}s\n`));
         }
+        if (event.type === "compacted") {
+            // Said out loud: from here the model can no longer see those results,
+            // which is the sort of thing that otherwise looks like it forgot.
+            // The saved transcript still has them - only what we send got shorter.
+            options.stdout.write(dim(`  context near the limit (${event.promptTokens} tokens) - dropped ` +
+                `${event.exchanges} earlier tool exchange(s) from what is sent\n`));
+        }
     };
     const sessionOptions = {
         ...options.session,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mafdet/cli",
-  "version": "0.4.2",
+  "version": "0.4.3",
   "description": "Mafdet AI command line — model calls, account queries, and a permissioned local agent.",
   "type": "module",
   "license": "MIT",