dsh-tdai-memory 0.2.14 → 0.3.0

package/README.md

@@ -76,6 +76,8 @@ tdai-memory:
     llm:                      # L1/L2/L3 extraction model (OpenAI-compatible)
       baseUrl: 'https://opencode.ai/zen/go/v1'
       model: 'mimo-v2.5'      # deepseek-v4-flash produces invalid extraction JSON
+      sendSessionHeader: true # send x-opencode-session on LLM requests (required by OpenCode Go & similar gateways)
+      sessionId: ''           # fixed session id; empty = persistent auto id under the data dir
     embedding:                # vectors (OpenAI-compatible /v1/embeddings)
       baseUrl: 'http://127.0.0.1:8088/v1'
       model: 'Qwen3-Embedding-0.6B'
@@ -106,19 +108,19 @@ settings page (记忆 / Memory) or directly in `settings.yaml` under
 > - This plugin is a standard **profile bundle** (`dsh.bundle.patch`):
 >   `dsh plugin --profile web add dsh-tdai-memory` installs and mounts it in
 >   one step — no manual `cordis.patch.yml` edits needed.
-> - DSH exposes the registered `tdai-memory` settings namespace directly; the
->   plugin does not modify files in the host installation.
-> - Settings changes apply **after a restart** (TdaiCore is built at startup).
-> - Version 0.2.13 and newer require DSH `0.1.0-rc.7` or newer and are tested
->   against `0.1.0-rc.7`, `0.1.0-rc.8`, and `0.1.1-rc.1`.
-> - DSH `0.1.0-rc.6` users must pin `dsh-tdai-memory@0.2.11`, the last release
->   carrying the legacy settings-allowlist compatibility patch.
-
-`node-llama-cpp` is an optional peer used only by the fully local embedding
-backend. It is intentionally not installed by default because its native build
-requires explicit pnpm build approval. Remote OpenAI-compatible embeddings do
-not need it. Users who select the local backend should install and approve
-`node-llama-cpp` in the target DSH profile separately.
+> - DSH exposes the registered `tdai-memory` settings namespace directly; the
+>   plugin does not modify files in the host installation.
+> - Settings changes apply **after a restart** (TdaiCore is built at startup).
+> - Version 0.2.13 and newer require DSH `0.1.0-rc.7` or newer and are tested
+>   against `0.1.0-rc.7`, `0.1.0-rc.8`, and `0.1.1-rc.1`.
+> - DSH `0.1.0-rc.6` users must pin `dsh-tdai-memory@0.2.11`, the last release
+>   carrying the legacy settings-allowlist compatibility patch.
+
+`node-llama-cpp` is an optional peer used only by the fully local embedding
+backend. It is intentionally not installed by default because its native build
+requires explicit pnpm build approval. Remote OpenAI-compatible embeddings do
+not need it. Users who select the local backend should install and approve
+`node-llama-cpp` in the target DSH profile separately.
 
 ## Known trade-offs
 

package/README.zh.md

@@ -16,13 +16,13 @@
 - **自动召回注入**：每次组装提示词时，按当前用户消息检索相关记忆 + 画像，作为动态上下文注入（模型"凭空想起"）
 - **工具**：`tdai_memory_search`（L1 结构化检索）、`tdai_conversation_search`（L0 原文检索）
 
-数据目录复用现有 `~/.memory-tencentdb/memory-tdai`，**旧记忆无缝继承**。
-
-`node-llama-cpp` 仅供完全本地的 embedding 后端使用，现在声明为可选 peer，默认安装不会再触发原生构建脚本。使用 OpenAI 兼容远程 embedding 时不需要它；选择本地后端的用户需在目标 DSH profile 中单独安装并批准 `node-llama-cpp` 的构建。
-
-从 `0.2.13` 起最低支持 DSH `0.1.0-rc.7`，已针对 `0.1.0-rc.7`、
-`0.1.0-rc.8` 和 `0.1.1-rc.1` 测试。仍使用 DSH `0.1.0-rc.6` 的用户请锁定
-`dsh-tdai-memory@0.2.11`；这是最后一个包含旧 settings 白名单兼容补丁的版本。
+数据目录复用现有 `~/.memory-tencentdb/memory-tdai`，**旧记忆无缝继承**。
+
+`node-llama-cpp` 仅供完全本地的 embedding 后端使用，现在声明为可选 peer，默认安装不会再触发原生构建脚本。使用 OpenAI 兼容远程 embedding 时不需要它；选择本地后端的用户需在目标 DSH profile 中单独安装并批准 `node-llama-cpp` 的构建。
+
+从 `0.2.13` 起最低支持 DSH `0.1.0-rc.7`，已针对 `0.1.0-rc.7`、
+`0.1.0-rc.8` 和 `0.1.1-rc.1` 测试。仍使用 DSH `0.1.0-rc.6` 的用户请锁定
+`dsh-tdai-memory@0.2.11`；这是最后一个包含旧 settings 白名单兼容补丁的版本。
 
 ## 架构（移植方式）
 
@@ -63,6 +63,8 @@ tdai-memory:
     llm:                      # L1/L2/L3 提取模型（OpenAI 兼容）
       baseUrl: 'https://opencode.ai/zen/go/v1'
       model: 'mimo-v2.5'      # deepseek-v4-flash 对提取 JSON 输出不合格
+      sendSessionHeader: true # 给 LLM 请求带 x-opencode-session（OpenCode Go 等网关要求）
+      sessionId: ''           # 固定会话 ID；留空 = 数据目录下自动持久化 ID（重启不变）
     embedding:                # 向量（OpenAI 兼容 /v1/embeddings）
       baseUrl: 'http://127.0.0.1:8088/v1'
       model: 'Qwen3-Embedding-0.6B'

package/client.js

@@ -64,6 +64,11 @@ window.__ModuleLoader__.load({
       fieldLlmModel: "模型",
       fieldLlmMaxTokens: "最大输出 Tokens",
       fieldLlmTimeoutMs: "超时（毫秒）",
+      fieldLlmSendSessionHeader: "发送会话标识头（x-opencode-session）",
+      fieldLlmSessionHeaderName: "会话标识头名称",
+      fieldLlmSessionId: "固定会话 ID（留空 = 自动持久化）",
+      hintLlmSendSessionHeader: "OpenCode Go 等网关要求每个 LLM 请求带稳定的会话标识；请求不带可能报错（2026-09-06 起）。值：优先用固定 ID，否则在数据目录生成持久 ID（重启不变）。",
+      hintLlmSessionId: "后台抽取请求的固定会话标识；留空则自动生成并持久化到数据目录的 session-id 文件。",
       fieldEmbeddingBaseUrl: "Base URL",
       fieldEmbeddingApiKey: "API Key",
       fieldEmbeddingModel: "模型",
@@ -103,6 +108,11 @@ window.__ModuleLoader__.load({
       fieldLlmModel: "Model",
       fieldLlmMaxTokens: "Max output tokens",
       fieldLlmTimeoutMs: "Timeout (ms)",
+      fieldLlmSendSessionHeader: "Send session-id header (x-opencode-session)",
+      fieldLlmSessionHeaderName: "Session-id header name",
+      fieldLlmSessionId: "Fixed session id (empty = persistent auto)",
+      hintLlmSendSessionHeader: "OpenCode Go and similar gateways require a stable session id on every LLM request; requests without it may error (from 2026-09-06). Value: the fixed id below, else a persistent per-instance id stored under the data dir.",
+      hintLlmSessionId: "Fixed session id for background extraction requests; leave empty for a persistent auto id under the data dir (survives restarts).",
       fieldEmbeddingBaseUrl: "Base URL",
       fieldEmbeddingApiKey: "API Key",
       fieldEmbeddingModel: "Model",
@@ -135,6 +145,9 @@ window.__ModuleLoader__.load({
       { path: ["llm", "model"], label: "fieldLlmModel", type: "text", group: "groupLlm" },
       { path: ["llm", "maxTokens"], label: "fieldLlmMaxTokens", type: "number", group: "groupLlm" },
       { path: ["llm", "timeoutMs"], label: "fieldLlmTimeoutMs", type: "number", group: "groupLlm" },
+      { path: ["llm", "sendSessionHeader"], label: "fieldLlmSendSessionHeader", type: "checkbox", group: "groupLlm" },
+      { path: ["llm", "sessionHeaderName"], label: "fieldLlmSessionHeaderName", type: "text", group: "groupLlm" },
+      { path: ["llm", "sessionId"], label: "fieldLlmSessionId", type: "text", group: "groupLlm" },
       { path: ["embedding", "baseUrl"], label: "fieldEmbeddingBaseUrl", type: "text", group: "groupEmbedding" },
       { path: ["embedding", "apiKey"], label: "fieldEmbeddingApiKey", type: "password", secret: true, group: "groupEmbedding" },
       { path: ["embedding", "model"], label: "fieldEmbeddingModel", type: "text", group: "groupEmbedding" },