0c959e3ff3
## 缺陷（-race 实测）
rtChild 里 pump 是**唯一**"构造后被改写、又有并发读者"的字段，
但它的读写绕过了 rc.mu：
Dispose（StopRTChild 的 goroutine） rc.pump = nil ← 写
rtEmit （rtLoop 的 goroutine） rc.pump ← 读
-race 栈：
Read at … core.(*Agent).rtEmit rtchild.go:1275
Previous write … core.(*rtChild).Dispose rtchild.go:377
## 为什么之前没被发现
TestRTChild_E2E_Sustained 覆盖同一个窗口，但它是**偶发命中**：
全量负载下 5 次中 1 次，单跑 20 次 0 次，基线 af17af5 全量 0 次。
这种形状在 CI 里等于没有 —— 红了是运气，绿了不代表安全。
## 修法：锁贯彻到底（不是只补这一处）
rtChild 全部字段逐个判定过：
字段 构造后写? 遵守锁规?
pump 是(Dispose) ★ 本提交修：读写都持 rc.mu
light/mainRO 是(Dispose) ✓ 无并发读者，只在 Dispose 内用
slot/input/output/agent 否 ✓ 只读，不需要锁
history 是(append) ✓ 三处访问全部持锁（原有）
round/lastSeq/curCancel/critical/suppressedCancels ✓ 原本就持锁
即：pump 是唯一的漏网者，其余要么本已正确、要么根本没有并发写。
## 两个顺序要求（不只是"加个锁"）
① **取走并置 nil 在锁内，Close 在锁外**
pump.Close() 内部 wg.Wait() 等消费 goroutine 收尾；持锁等待可能与
另一个持锁路径交叉。而"置 nil"必须与读者的"读"互斥，否则读者会
拿到一个已被清掉的指针。
② **rtEmit 锁内取、锁外 Push**
Push 在队列满时会阻塞，持锁会卡死 Dispose 的置 nil。
## 判据（2 条，2 次变异全部实测变红）
TestRTPumpAccessIsLocked
一边不停 emit、一边 Dispose，用 -race 判定。
变异 A（rtEmit 裸读） ⇒ 连跑 3 次全部命中 DATA RACE
变异 B（Dispose 裸写） ⇒ 第 1 次命中 DATA RACE
TestRTPumpAfterDisposeIsNil
钉住顺序语义：Dispose 之后 rc.pump 必须为 nil（否则 emit 会推
送到已关闭的 pump），且兜底路径不 panic。
## 判据第一版是假的（记下来）
第一版读者写的是 `for i := 0; i < 500; i++` —— 500 次 emit 微秒级跑完，
而写者 sleep 1ms 才动手，两者**根本不重叠**。变异 B（裸写）连跑 6 次
都不红。改成"持续跑到写者宣布结束"之后才真正抓到。
这正是「判据必须能变红」的意义：不跑变异就永远不知道它是真判据还是摆设。
## 判据的边界（诚实说明）
这条判据的"红"依赖 -race 检测器。不带 -race 时它只能发现 panic/死锁。
所以必须与 `go test -race` 一起跑 —— 提交纪律第 4 条已要求全量 -race，
这里只是把「哪个窗口最危险」钉成可复跑的形态。
## 验证（提交纪律四项全绿）
go build ./... 0
go vet ./... 0
gofmt -l internal/ cmd/ pkg/ 干净
go test ./... -count=1 -race 0 竞态，62 包全过
干净检出（worktree） build + TestRTPump 全绿
⚠️ 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.