memorix 1.7.3 → 1.8.1

package/CHANGELOG.md

@@ -4,6 +4,47 @@ All notable changes to this project will be documented in this file.
 
 ## [Unreleased]
 
+## [1.8.1] - 2026-08-24
+
+### Changed
+- **Truthful coordination status** -- the persistent SQLite `TeamStore` is the
+  sole coordination truth for agents, tasks, messages, locks, handoffs, and poll
+  state. The Dashboard exposes read-only `Coordination Status` and `Task Status`
+  views, and `/api/team` reports explicit `error` or `degraded` status instead of
+  presenting a failed coordination read as a healthy empty result.
+
+## [1.8.0] - 2026-08-23
+
+### Added
+- **Persisted Evidence Cards** -- observation provenance is stored in SQLite
+  with project ownership, source reference, locator, captured hash, files,
+  verification state, freshness, and audit events. Cards are available through
+  `memorix_evidence`, `memorix evidence`, and the Dashboard Evidence Console.
+- **Auditable memory feedback** -- verification, use, correction, source-change,
+  conflict, strengthen, weaken, and revoke events materialize a bounded
+  retrieval/retention weight without deleting the original source record.
+- **Stateless MCP project handles** -- 2026-07-28-style requests can use an
+  explicit `Mcp-Project-Handle` that survives service restart, while legacy
+  stateful Streamable HTTP remains supported.
+- **One-shot CLI fallback budget** -- repeated MCP-unavailable probing for the
+  same project/task is deduplicated and fail-closed after one bounded context
+  request.
+- **Evidence Console** -- Dashboard includes a responsive, project-scoped
+  evidence view with source, locator, freshness, verification, and audit count.
+
+### Changed
+- HTTP TeamStore resolution is project-data-directory scoped, preventing A/B
+  coordination state from crossing when sessions bind different projects.
+- The 1.8.0 documentation records the shipped compatibility adapter, explicit
+  non-goals, fallback semantics, and the Antigravity/Gemini setup matrix.
+
+### Fixed
+- Preserve the 1.7 micro MCP profile's nine-tool budget by keeping Evidence and
+  Feedback in lite/team/full profiles.
+- Keep legacy relevance unchanged until a memory receives explicit feedback.
+- Keep SQLite-backed HTTP helpers lazy so mocked and lightweight MCP startup
+  paths do not open the database during module evaluation.
+
 ## [1.7.3] - 2026-08-22
 
 ### Added

package/README.md

@@ -437,7 +437,7 @@ Search is project-scoped by default. `scope="global"` searches across projects.
 
 Long-term memory is deliberately not an automatic dump of every note. A source observation, Claim, workflow, session, and code snapshot keep their existing roles. An agent may ask `memorix_store` to create an additional long-term record; an explicit request auto-qualifies and enters task briefs as a durable anchor, while hook-captured or Git-derived candidates stay pending until qualified. Approval stays an explicit operator review. Use `memorix memory long-term approve|archive|supersede` to record the evidence-backed lifecycle. Only a manually created or user-confirmed `user + portable` item may be considered in another local project; project code, Git facts, tests, workflows, sessions, and observations cannot be promoted into portable user memory.
 
-`memorix context "..."` is the default Memory Autopilot entry. It builds a compact task-lensed brief for agents: bugfix tasks lean toward tests and repros, release tasks lean toward package/changelog/build checks, onboarding tasks lean toward docs and entry points, and stale or unrelated memories stay in warning lanes instead of flooding the prompt. Use `--brief-json` when a CLI fallback needs the same bounded brief plus a receipt of what was selected or omitted; `--json` remains the detailed diagnostic form. A normal new task does not receive an old-session dump. For an explicit continuation, `memorix resume "..."` adds only the latest useful session summary, up to three readable durable anchors, and at most one recent source-labelled host compact checkpoint. A durable anchor carries a `durable:<id>` reference, so an agent can expand the full reviewed record through `memorix_detail` only when needed. Keyword matches stay primary; when no reviewed durable item matches and an embedding provider is configured, Memorix makes one 1.8-second, no-retry semantic fallback for paraphrases or cross-language tasks. A slow or unavailable provider simply leaves the normal keyword-only Workset intact. A checkpoint is lifecycle evidence, not durable memory or a transcript backup. Agents should read the suggested files before trusting stored memory.
+`memorix context "..."` is the default Memory Autopilot entry. It builds a compact task-lensed brief for agents: bugfix tasks lean toward tests and repros, release tasks lean toward package/changelog/build checks, onboarding tasks lean toward docs and entry points, and stale or unrelated memories stay in warning lanes instead of flooding the prompt. Use `--fallback --brief-json` when MCP is unavailable and a CLI fallback needs the same bounded brief plus a receipt of what was selected or omitted; `--json` remains the detailed diagnostic form. A normal new task does not receive an old-session dump. For an explicit continuation, `memorix resume "..."` adds only the latest useful session summary, up to three readable durable anchors, and at most one recent source-labelled host compact checkpoint. A durable anchor carries a `durable:<id>` reference, so an agent can expand the full reviewed record through `memorix_detail` only when needed. Keyword matches stay primary; when no reviewed durable item matches and an embedding provider is configured, Memorix makes one 1.8-second, no-retry semantic fallback for paraphrases or cross-language tasks. A slow or unavailable provider simply leaves the normal keyword-only Workset intact. A checkpoint is lifecycle evidence, not durable memory or a transcript backup. Agents should read the suggested files before trusting stored memory.
 
 <h2 id="runtime-modes"><picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/section-runtime.svg"><img src="assets/tags/section-runtime.svg" alt="Runtime Modes" height="32" /></picture></h2>
 

package/README.zh-CN.md

@@ -420,7 +420,7 @@ memcode
 
 长期记忆不是把所有笔记自动堆进去。Observation、Claim、工作流、session 和代码快照仍各自承担原来的职责。Agent 可以在 `memorix_store` 时要求额外生成长期记忆**候选**，但候选绝不会自动进入任务上下文；用 `memorix memory long-term qualify|approve|archive|supersede` 留下带证据的生命周期记录。只有人工创建或用户确认的 `user + portable` 记忆，才可能在同一台机器的其它项目中按任务相关性被使用；项目代码、Git 事实、测试、工作流、session 和 Observation 都不能被提升成可携带的用户记忆。
 
-`memorix context "..."` 是默认的 Memory Autopilot 入口。它会按任务生成紧凑 brief：修 bug 时偏向测试和复现，发版时偏向 package/changelog/build 检查，接手项目时偏向文档和入口文件；过期或不相关的记忆只作为 warning，不会一股脑塞进 prompt。CLI 回退需要结构化结果时用 `--brief-json`，它只返回同一份有预算的 brief 和“选了什么、略了什么”的回执；`--json` 保留给详细诊断。普通新任务不会自动得到旧会话的文本倾倒；明确要继续之前工作时，用 `memorix resume "..."`，只会补入最近一份有用的会话总结、最多三条当前可读的长期记忆锚点，以及最多一条带来源标识的近期宿主压缩检查点。每个长期锚点都有 `durable:<id>` 引用，Agent 只在确实需要完整已审核记录时才通过 `memorix_detail` 展开。关键词仍优先；没有命中而且用户已配置 embedding 时，Memorix 才会做一次 1.8 秒、不重试的语义回退，用于模型改写或跨语言任务。服务变慢或不可用时，正常的关键词 Workset 会原样返回。检查点只是生命周期证据，不是长期记忆，也不是聊天记录备份。Agent 应该先读 suggested files，再相信历史记忆。
+`memorix context "..."` 是默认的 Memory Autopilot 入口。它会按任务生成紧凑 brief：修 bug 时偏向测试和复现，发版时偏向 package/changelog/build 检查，接手项目时偏向文档和入口文件；过期或不相关的记忆只作为 warning，不会一股脑塞进 prompt。只有 MCP 不可用时才使用 CLI 回退，并带上 `--fallback --brief-json`，它只返回同一份有预算的 brief 和“选了什么、略了什么”的回执；`--json` 保留给详细诊断。普通新任务不会自动得到旧会话的文本倾倒；明确要继续之前工作时，用 `memorix resume "..."`，只会补入最近一份有用的会话总结、最多三条当前可读的长期记忆锚点，以及最多一条带来源标识的近期宿主压缩检查点。每个长期锚点都有 `durable:<id>` 引用，Agent 只在确实需要完整已审核记录时才通过 `memorix_detail` 展开。关键词仍优先；没有命中而且用户已配置 embedding 时，Memorix 才会做一次 1.8 秒、不重试的语义回退，用于模型改写或跨语言任务。服务变慢或不可用时，正常的关键词 Workset 会原样返回。检查点只是生命周期证据，不是长期记忆，也不是聊天记录备份。Agent 应该先读 suggested files，再相信历史记忆。
 
 <h2 id="运行模式"><picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/section-runtime.svg"><img src="assets/tags/section-runtime.svg" alt="运行模式" height="32" /></picture></h2>