@deepseek-ai/dsh-tmux-context 0.1.2-rc.1 → 0.1.5-alpha.1

package/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/context/tmux-context/README.md
-README.md: df94e309839a8ecdae902def8531856071269d20
-README.zh.md: da69791cb96cd4ef13b5fa31ddaf4e6470e08d60
+README.md: 2f00aa4e8f42670bbadba4e2a1777d5b596090b9
+README.zh.md: 06743d57d6332401fcb65bf00e6c23bf0ec7eec2

package/README.md

@@ -9,7 +9,7 @@ English | [中文](README.zh.md)
 
 ## Summary
 
-`dsh-tmux-context` tells the model where its agent process runs: on each turn whose tmux state changed, it appends a durable, source-attributed reading naming the tmux session, window, and pane plus the window's pane-tree layout. It is sampled once per turn during request preparation and only when the process genuinely lives inside the named pane — a terminal that merely inherited `$TMUX`/`$TMUX_PANE` from a tmux ancestor reads as not in tmux and adds nothing. An unchanged location adds nothing, and a failed query is a no-op, never a turn failure. The plugin is opt-in and not part of the shipped Web/headless composition.
+`dsh-tmux-context` lets the model identify the tmux session, window, pane, and pane-tree layout containing its agent process. It adds a durable, source-attributed reading on the first step of a turn only when that location changed. Terminals that merely inherit tmux environment variables without running in the named pane add nothing; failed queries also add nothing and do not fail the turn. This package is opt-in and is not included in the shipped Web or headless profiles.
 
 ## Table of Contents
 
@@ -85,7 +85,7 @@ At the first step of a turn, the listener checks whether an injection is due, qu
 
 Read these pages when the package-level contract is not enough. They move from the design decision to the executor the query runs through and the exhaustive configuration.
 
-- [Tmux location context decision record](../../../.agents/notes/implemented/feature/2026-07-27-tmux-location-context.md) — design rationale for the tty-based detection and reading shape.
+- [Tmux location context decision record](../../../.agents/notes/archived/feature/2026-07-27-tmux-location-context.md) — design rationale for the tty-based detection and reading shape.
 - [Shell subsystem](../../../docs/subsystems/shell.md) — the executor service the read-only query runs through.
 - [Context group map](../README.md) — sibling request-context packages.
 - [Generated configuration catalog](../../../docs/config-catalog.md#deepseek-aidsh-tmux-context) — every accepted config field and its source declaration.

package/README.zh.md

@@ -9,7 +9,7 @@ kind: "package-reference"
 
 ## 概述
 
-`dsh-tmux-context` 告诉模型它的 agent（智能体）进程运行在哪里：在 tmux 状态发生变化的每一轮，它追加一条持久、带来源的读数，命名 tmux session、window 与 pane，以及该 window 的 pane 树布局。它在准备模型请求时每轮采样一次，且仅当进程确实位于所指名的 pane 内时——仅从 tmux 祖先进程继承了 `$TMUX`／`$TMUX_PANE` 的终端会被视为不在 tmux 中，不添加任何内容。位置未变化时不添加任何内容；查询失败是空操作，绝不导致轮次失败。本插件需主动启用，且不属于随附 Web／无头组合。
+`dsh-tmux-context` 让模型识别其 agent（智能体）进程所在的 tmux session、window、pane 和 pane 树布局。它仅在位置发生变化时，于每轮的第一个步骤追加一条持久、带来源的读数。若终端只继承了 tmux 环境变量，却并未在所指名的 pane 中运行，则不添加任何内容；查询失败同样不添加内容，也不会使该轮失败。本包需主动启用，且不包含在随附的 Web 或无头 profile 中。
 
 ## 目录
 
@@ -85,7 +85,7 @@ kind: "package-reference"
 
 包级约定不够用时阅读以下页面。它们从设计决策进入查询所经由的执行器与穷尽式配置。
 
-- [tmux 位置上下文决策记录](../../../.agents/notes/implemented/feature/2026-07-27-tmux-location-context.zh.md)——基于 tty 的检测与读数形状的设计理由。
+- [tmux 位置上下文决策记录](../../../.agents/notes/archived/feature/2026-07-27-tmux-location-context.md)——基于 tty 的检测与读数形状的设计理由。
 - [shell 子系统](../../../docs/subsystems/shell.zh.md)——只读查询所经由的执行器服务。
 - [context 组地图](../README.zh.md)——相邻的请求上下文包。
 - [生成的配置目录](../../../docs/config-catalog.zh.md#deepseek-aidsh-tmux-context)——每个受支持配置字段及其源声明。

package/lib/index.js

@@ -496,6 +496,9 @@ function harnessErrorCode(error) {
 }
 //#endregion
 //#region ../../llm/llm/src/content.ts
+function quoted(value) {
+	return JSON.stringify(value);
+}
 /**
 * Stable text shown to a model that cannot accept one durable image reference.
 * @param ref - durable normalized attachment omitted from the request.
@@ -515,6 +518,76 @@ function textOnlyImageText(ref) {
 function contentHasImage(content) {
 	return content.some((block) => block.type === "image" || block.type === "tool-result" && contentHasImage(block.content));
 }
+/**
+* True when typed model content contains a file block, walking nested
+* tool-result content on the same recursion every file policy shares.
+* Reads current content on every call without retaining scan results.
+* @param content - typed model content blocks.
+* @returns whether any nested block is a file.
+*/
+function contentHasFile(content) {
+	for (const block of content) if (block.type === "file" || block.type === "tool-result" && contentHasFile(block.content)) return true;
+	return false;
+}
+/**
+* Stable model-facing handle for one durable file reference: the address of
+* the verbatim stored copy and the instruction to read it on demand. This is
+* the only representation a provider ever receives for a file.
+* @param ref - durable verbatim file reference.
+* @param readonlyPath - execution-world path of the stored copy, when resolvable.
+* @returns deterministic handle text naming the file, its size, and its address.
+*/
+function fileHandleText(ref, readonlyPath) {
+	const digest = String(ref.attachmentId).slice(7, 15);
+	const identity = `File ${quoted(ref.name)} (${ref.bytes} bytes, sha256:${digest})`;
+	if (readonlyPath === void 0) return `[${identity} was uploaded, but the current execution environment cannot access a readable path. Report that limitation if its contents are needed; do not claim to have read it.]`;
+	return `[${identity}: verbatim read-only copy saved at ${quoted(readonlyPath)}. Read that path with your file tools when its contents are needed; copy it to a writable location before modifying it. When delegating file work, include this saved path in the delegation prompt; only subagents sharing this execution environment can read it.]`;
+}
+/** Replace every file occurrence, including nested tool results, with handle text. */
+function replaceFilesWithHandles(blocks, resolvePath) {
+	let next;
+	for (const [index, block] of blocks.entries()) {
+		if (block.type === "file") {
+			next ??= blocks.slice(0, index);
+			next.push({
+				type: "text",
+				text: fileHandleText(block.attachment, resolvePath(block.attachment))
+			});
+			continue;
+		}
+		if (block.type === "tool-result") {
+			const content = replaceFilesWithHandles(block.content, resolvePath);
+			if (content !== block.content) {
+				next ??= blocks.slice(0, index);
+				next.push({
+					...block,
+					content
+				});
+				continue;
+			}
+		}
+		next?.push(block);
+	}
+	return next ?? blocks;
+}
+/**
+* Project durable file history into deterministic handle text for every model
+* route. Unlike images, no provider receives file blocks natively, so this
+* projection is unconditional in request assembly.
+* @param messages - complete request history.
+* @param resolvePath - resolve one reference's current execution-world read path.
+* @returns the original list without files, otherwise shallow message copies with handle text.
+*/
+function projectFilesToText(messages, resolvePath) {
+	if (!messages.some((message) => contentHasFile(message.content))) return messages;
+	return messages.map((message) => {
+		const content = replaceFilesWithHandles(message.content, resolvePath);
+		return content === message.content ? message : {
+			...message,
+			content
+		};
+	});
+}
 /** Replace every image occurrence, including nested tool results, for a text-only model. */
 function replaceImagesForTextModel(blocks) {
 	let next;
@@ -951,6 +1024,15 @@ var LlmError = class extends HarnessError {
 		imageRequestPricing(provider, model) {
 			return this.adapters.get(provider)?.adapter.imageRequestPricing(provider, model);
 		}
+		/**
+		* Resolve the exact text one durable file occurrence contributes to every
+		* provider request in the current execution environment.
+		* @param ref - durable verbatim file reference from model history.
+		* @returns the same deterministic handle text used at adapter dispatch.
+		*/
+		fileRequestText(ref) {
+			return fileHandleText(ref, this.fileReadPath(ref));
+		}
 		/** Detach typed adapter-owned modality metadata. */
 		detachedModalities(modalities) {
 			return modalities === void 0 ? void 0 : [...modalities];
@@ -1000,6 +1082,8 @@ var LlmError = class extends HarnessError {
 			const context = resolved.context;
 			if (context !== void 0 && (!Number.isInteger(context.contextWindow) || context.contextWindow <= 0)) throw new LlmError(`adapter returned invalid context metadata for provider "${provider}" model "${model}"`, "INVALID_MODEL_CONTEXT");
 			const inputModalities = this.detachedModalities(resolved.inputModalities);
+			const systemPromptUpdate = resolved.systemPromptUpdate;
+			if (systemPromptUpdate !== void 0 && systemPromptUpdate !== "in-history") throw new LlmError(`adapter returned invalid system prompt update mode for provider "${provider}" model "${model}"`, "INVALID_MODEL_INFO");
 			const defaultMaxTokens = resolved.defaultMaxTokens;
 			if (defaultMaxTokens !== void 0 && (!Number.isSafeInteger(defaultMaxTokens) || defaultMaxTokens <= 0)) throw new LlmError(`adapter returned invalid default maxTokens for provider "${provider}" model "${model}"`, "INVALID_MODEL_MAX_TOKENS");
 			const info = {
@@ -1009,7 +1093,8 @@ var LlmError = class extends HarnessError {
 				...resolved.description === void 0 ? {} : { description: resolved.description },
 				...inputModalities === void 0 ? {} : { inputModalities },
 				...context === void 0 ? {} : { context: { contextWindow: context.contextWindow } },
-				...defaultMaxTokens === void 0 ? {} : { defaultMaxTokens }
+				...defaultMaxTokens === void 0 ? {} : { defaultMaxTokens },
+				...resolved.systemPromptUpdate === void 0 ? {} : { systemPromptUpdate: resolved.systemPromptUpdate }
 			};
 			const reasoning = resolved.reasoning;
 			if (reasoning === void 0) return info;
@@ -1103,6 +1188,7 @@ var LlmError = class extends HarnessError {
 				adapterDefaults,
 				...context === void 0 ? {} : { context },
 				...modelInfo.inputModalities === void 0 ? {} : { inputModalities: Object.freeze([...modelInfo.inputModalities]) },
+				...modelInfo.systemPromptUpdate === void 0 ? {} : { systemPromptUpdate: modelInfo.systemPromptUpdate },
 				stream: (options) => {
 					if (dispatched) throw new LlmError("a prepared LLM call can only be dispatched once", "INVALID_PREPARED_CALL");
 					if (!callConfigEquals(options, resolvedConfig)) throw new LlmError("prepared LLM call config changed before adapter dispatch", "INVALID_PREPARED_CALL");
@@ -1144,6 +1230,20 @@ var LlmError = class extends HarnessError {
 			return Object.isFrozen(options) ? deepFreeze(filtered) : filtered;
 		}
 		/**
+		* Resolve the current execution-world read path of one durable file
+		* reference through the mounted attachment and filesystem providers.
+		*/
+		fileReadPath(ref) {
+			let hostPath;
+			try {
+				hostPath = this.ctx.get("attachments")?.fileHostPath(ref);
+			} catch {
+				return;
+			}
+			if (hostPath === void 0) return void 0;
+			return this.ctx.get("fs")?.processPathFromHostPath(hostPath);
+		}
+		/**
 		* Final adapter boundary. Adapter selection, dispatch, iterator construction,
 		* and iteration failures become one terminal failure chunk. Middleware and
 		* downstream consumer failures remain thrown plugin or consumer errors.
@@ -1174,13 +1274,16 @@ var LlmError = class extends HarnessError {
 					...options,
 					...resolvedConfig
 				};
-				const projectedOptions = modelInfo.inputModalities !== void 0 && !modelInfo.inputModalities.includes("image") && resolvedOptions.messages.some((message) => contentHasImage(message.content)) ? Object.isFrozen(resolvedOptions) ? deepFreeze({
+				let projectedMessages = resolvedOptions.messages;
+				if (projectedMessages.some((message) => contentHasFile(message.content))) projectedMessages = projectFilesToText(projectedMessages, (ref) => this.fileReadPath(ref));
+				if (modelInfo.inputModalities !== void 0 && !modelInfo.inputModalities.includes("image") && projectedMessages.some((message) => contentHasImage(message.content))) projectedMessages = projectImagesForTextModel(projectedMessages);
+				const projectedOptions = projectedMessages === resolvedOptions.messages ? resolvedOptions : Object.isFrozen(resolvedOptions) ? deepFreeze({
 					...resolvedOptions,
-					messages: projectImagesForTextModel(resolvedOptions.messages)
+					messages: projectedMessages
 				}) : {
 					...resolvedOptions,
-					messages: projectImagesForTextModel(resolvedOptions.messages)
-				} : resolvedOptions;
+					messages: projectedMessages
+				};
 				iterator = dispatch(this.forAdapter(projectedOptions, adapter))[Symbol.asyncIterator]();
 			} catch (error) {
 				yield adapterFailureChunk(error, options.signal);

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@deepseek-ai/dsh-tmux-context",
   "description": "Opt-in durable per-step context with this agent's tmux pane and window location",
-  "version": "0.1.2-rc.1",
+  "version": "0.1.5-alpha.1",
   "publishConfig": {
     "access": "public"
   },
@@ -31,19 +31,20 @@
     "@deepseek-ai/schemastery": "^3.18.2"
   },
   "peerDependencies": {
-    "@deepseek-ai/dsh-agent": "^0.1.2-rc.1",
-    "@deepseek-ai/dsh-shell": "^0.1.2-rc.1",
-    "@deepseek-ai/dsh-session": "^0.1.2-rc.1",
+    "@deepseek-ai/dsh-agent": "^0.1.5-alpha.1",
+    "@deepseek-ai/dsh-shell": "^0.1.5-alpha.1",
+    "@deepseek-ai/dsh-session": "^0.1.5-alpha.1",
     "@deepseek-ai/cordis": "^4.0.2",
-    "@deepseek-ai/dsh-session-projection": "^0.1.2-rc.1"
+    "@deepseek-ai/dsh-session-projection": "^0.1.5-alpha.1"
   },
   "devDependencies": {
-    "@deepseek-ai/dsh-agent": "^0.1.2-rc.1",
-    "@deepseek-ai/dsh-shell": "^0.1.2-rc.1",
-    "@deepseek-ai/dsh-llm": "^0.1.2-rc.1",
-    "@deepseek-ai/dsh-session": "^0.1.2-rc.1",
-    "@deepseek-ai/dsh-system-prompt": "^0.1.2-rc.1",
-    "@deepseek-ai/dsh-session-projection": "^0.1.2-rc.1",
-    "@deepseek-ai/cordis": "^4.0.2"
+    "@deepseek-ai/dsh-agent": "^0.1.5-alpha.1",
+    "@deepseek-ai/dsh-agent-loop-testkit": "^0.1.5-alpha.1",
+    "@deepseek-ai/dsh-shell": "^0.1.5-alpha.1",
+    "@deepseek-ai/dsh-llm": "^0.1.5-alpha.1",
+    "@deepseek-ai/dsh-session": "^0.1.5-alpha.1",
+    "@deepseek-ai/dsh-system-prompt": "^0.1.5-alpha.1",
+    "@deepseek-ai/cordis": "^4.0.2",
+    "@deepseek-ai/dsh-session-projection": "^0.1.5-alpha.1"
   }
 }