b3ae99e32f
## 迁移
secret_meta_test.go → webui/test/
## 这一条迁移暴露的问题比前几次多
原测试用两种白盒写法：
h := &Handler{settings: ...} // 直接构造，设私有字段
h.handleSettings(w, req) // 直接调未导出 handler
h.handleSettingsReveal(...) // 同上
改成黑箱后依次撞到四件事，逐个解决：
### ① 路由是 `/api/v1/settings`，不是 `/api/settings`
原测试写的路径 `/api/settings` 从来没被路由表匹配过 —— 它直接调 handler，
所以路径是摆设。真实注册在 handler.go:551：
mux.HandleFunc("/api/v1/settings", h.requireAPI(h.handleSettings))
⇒ 走真实路由后必须用对路径，否则 404。
### ② `Handler()` 会套三层中间件，依赖完整装配
`Handler()` = proxyDispatch + gzipMW + logged + mux。其中 `logged` 读
`h.settings` 的 webui 配置、`requestLog` 读 history store 等 ——
这些在最小装配下是 nil，直接 panic。
这不是"中间件写坏了"，是本判据不该测它们。**用导出的 `RegisterRoutes`**：
mux := http.NewServeMux()
h.RegisterRoutes(mux) // 只注册业务路由，不套中间件
`RegisterRoutes` 是导出接口，拿到的是真实路由表 —— 仍是黑箱，
只是不带外层。判据测的是 settings 的 meta 与 reveal，不该被请求日志和
反代的依赖拖下水。
### ③ `requireAPI` 需要 api_key，没配就 503
{"error":"webui api_key not configured"}
补 `seedWebUIConfig`（与包内同名辅助一致），并在请求上带
`X-API-Key`。这是生产上非浏览器客户端的正常路径
（`validAPIKey` 优先于 cookie session）。
### ④ `SecretPlaceholder` 需导出访问
改成 `webui.SecretPlaceholder`。
## 判据有效性（变异验证）
secret 标记的传递链是
`ConfigDef.Secret → mapDefs → sdk.ConfigDef.Secret → HTTP meta`。
在 `internal/sdk/settings_impl.go` 的 mapDefs 里删掉 `Secret: d.Secret`：
--- FAIL: TestSecretFlagReachesSettingsMeta
Secret:true 未传递到 meta（前端会明文回显）:
map[default: display_name:标志式 key:by_flag type:string]
恢复后全绿。这条判据守的是真实缺陷形态：SDK 的 ConfigDef 一直有 Secret
字段，但内核侧三处转换都漏过它，导致敏感项被渲染成普通文本框明文回显。
## 进度
webui/ 178 条（迁走 2 条）
webui/test/ 24 条
`webui/` 剩 19 个测试文件。剩下的大头是 `proxy_test.go`（45 处未导出引用）
与 `handler_test.go`（90 处），它们直接调 `handleXxx` 并依赖
`newTestHandler`/`testSDK` 这套装配辅助 —— 迁移需要先把那套辅助搬到
test/ 共享，再逐个改调用点。
## 验证
go build ./... PASS
go vet ./... PASS
gofmt -l 干净
go test ./... -count=1 67 包全过，0 FAIL
⚠️ AI-Assisted Programming Notice: Parts of this project's code, documentation, and commit history were generated or modified with AI assistance. Key changes have been human-reviewed, but please evaluate and verify before use.
HologramAgent
中文: README.md
Self-hosted agent kernel. Runs on your own hardware; plugins attach as separate processes.
make build build-cli
./build/homed -data /tmp/ha
API keys go in the web UI at http://localhost:8080. Requires Linux.
The main difference from typical agent frameworks is context handling: instead of truncating on overflow or asking the model to summarize, it scores history by relevance and sinks the low-scoring events into cold context, then distills those into a graph. Two other things differ: startup order is resolved at build time, and plugins launch as soon as their facilities are ready.
Architecture
homed (kernel)
LLM orchestration · memory · retrieval
│
┌──────────────┼──────────────┐
│ │ │
stdio RPC shared mem event ring
control bulk data notify
│ │ │
└──────────────┼──────────────┘
│
plugins (separate processes)
web UI · QQ · CLI · files · browser
The kernel process handles orchestration, memory and retrieval; HTTP, files and devices belong to
plugins (internal/plugin). A crashed plugin is restarted with backoff 1s / 2s / 3s; the 4th
crash within 5 minutes stops automatic restarting pending human intervention
(cmd/homed/kmod_runtime.go).
Context window
internal/agent/core/context.go
Each event gets two vectors on entry: a dense vector sharing one space with media and cold context, and a TF-IDF word vector as fallback. Pruning scores history against the current input and keeps topK, with the most recent N events exempt from scoring.
N defaults to 10, bounded by budget: min(configured, ContextTokens / avg tokens per event).
That bound came from a measurement. At a 50k window with 5800 tokens per event and a 40000 budget, pinning 10 events needed 58k, more than the budget itself. Every prune met its target without freeing space; the budget was gone after two rounds and the task terminated, with recall falling from 44% to 22%. Small windows now tighten automatically; a 1M window uses the configured value.
Pruned events move to the cold-context layer together with the media blocks they hold. Block IDs
stay the same; only the holding layer changes. Retrieval uses coldcontext_query: Peek to
confirm, then Remove the source copy. There is no fetch-and-delete path, since deletion follows
confirmation.
Three layers
internal/agent/core/context.go · internal/memory/coldcontext/ · internal/memory/graph.go
| Layer | Holds | Reaches the model | Cooling |
|---|---|---|---|
| L1 Context | events + blocks | directly, in the system prompt | low relevance sinks |
| L2 Cold Context | events + blocks (same shape as L1) | inserted back into L1 order on recall | ≤2 accesses and 72h idle, then distilled |
| L3 Stable | triples, nodes are blocks | on recall | never leaves |
A block has exactly one holder at any layer, with no reference counting. Images and audio are blocks in L2/L3 with their own vectors, searched in the same space as text.
Scenes
internal/memory/scene_emerge.go
A scene is built from five weighted features: channel 1.0, conversation partner 1.0, tools 0.8,
topic 0.4, time of day 0.2. A scene is created on the second occurrence of the same fingerprint
(minSceneEvidence = 2); one-off interactions don't create one. Join threshold 0.5, recall 0.35.
Recurrence adds 1 to strength; scenes that stop recurring decay by half-life.
Two entry points run in parallel: a plugin declares the scene at an injection point (e.g.
chan:qq/peer:group_1), or fingerprints cluster on their own. A declared scene derives features
only from its own key and does not absorb the full fingerprint. Absorbing it would make the
declared scene match nearly every later turn of that kind at close to 1.0 similarity, and the
clustering path could never grow narrower scenes.
Seven stages
internal/agent/core/stages.go
| Stage | When | Plugins can |
|---|---|---|
on_input |
message arrives | blocklist, rate limit, short-circuit reply |
pre_action |
context ready, before LLM | inject external data |
post_action |
LLM returns text and tool calls | filter, force redirect |
before_toolcall |
before one tool runs | audit, deny, rewrite args |
after_toolcall |
after one tool runs | redact, sort results |
before_output |
final text ready | format adaptation |
after_output |
after sending | statistics |
The inner loop is post_action → [before_toolcall → run → after_toolcall] → post_action. It exits
when the model stops calling tools, all calls are denied, or the limit is reached.
Everything else
- Channels: web UI, CLI, QQ groups and DMs, A2A, ACP in your IDE
- Tools: files, shell, code, browser (real Chrome), calendar, notes, RSS, music
- Modalities: images, video, voice, screenshots, web pages
28 built-in plugins, 89 model-callable tools. External plugins live one per repo under github.com/HologramAgent.
Downloads
Releases ship three variants:
| Variant | Contents | For |
|---|---|---|
| full | homed + waiter + desktop GUI + systemd unit | Single-machine, everything |
| server | homed + waiter + systemd unit | Servers (no desktop environment) |
| client | waiter + desktop GUI | Connecting to a remote HologramAgent |
- Linux:
.deb(amd64/arm64),.rpm(x86_64),.tar.gz - Windows:
HologramAgent_v1.2.0_{Full,Server,Client}_win64.exe(NSIS installer, includes the AGPL license page). Since v1.2.0homedno longer supports native Windows (it relies on fd inheritance and in-segment offset dereferencing), so the installer bootstraps WSL2 and installs the Linux packages inside the distribution the same way a Linux host would. - Portable:
homeagent-bin-<os>_<arch>.tar.gz(homed/waiter/initconfig) - Verification:
SHA256SUMS
The macOS homed requires a native macOS build (CGO + sqlite3), so release packages ship only waiter/initconfig.
Build
make build build-cli # Build daemon + CLI
make test # go test ./...
make install # Install to system
Dependencies: Go 1.25+, CGo (go-sqlite3), Linux.
homedrequires Linux (it relies on fd inheritance and intra-segment offset dereferencing of the shared memory region; seecmd/homed/platform_windows.go). On Windows onlywaiter.exeis built andhomedruns under WSL2 (see Downloads). macOS can buildwaiter/initconfig;homedmust be built on native macOS.
License
AGPL-3.0-only. See LICENSE.
Bundled third-party components keep their own licenses; full texts ship in
/usr/share/doc/hologramagent/licenses/.
Third-party components shipped with the packages
| Component | License | Location |
|---|---|---|
| Chinese-CLIP ViT-B/16 (ONNX artifacts) | Apache-2.0 | /usr/lib/hologram/models/chinese-clip-vit-b16-onnx/ |
ONNX Runtime (libonnxruntime.so) |
MIT | /usr/lib/hologram/onnxruntime/ |
| jieba dictionary (embedded in the binary) | MIT | internal/memory/jiebadict/ |
| Go dependencies (go-sqlite3, gojieba, bubbletea, …) | MIT / BSD-3 / Apache-2.0 | permissive, AGPL-3.0-compatible |
The package metadata declares this package as AGPL-3.0-only.