892247946a
staticcheck 门接入时把存量设为基线 24 条，本次全部清掉，基线改为 0。
## 生产代码里的真实缺陷（4 个）
### ① memory/fusion.go —— BFS 的 depth 参数形同虚设
for d := 1; d <= depth; d++ {
neighbors, _ := g.NeighbourBlocks(seed.BlockID) // ← 永远是 seed
...
break // ← 只跑一轮
}
三处叠加：循环体末尾无条件 `break`；每层传的还是 `seed.BlockID`；
于是 depth=2 与 depth=3 召回结果**完全一样**。
staticcheck SA4008（"变量在循环条件里从不改变"）正是从这里报出来的 ——
它看出来 `d` 除了打分没有参与寻址。
改成真正的逐层 BFS（frontier 推进到上一层新发现的节点）。实测：
depth=1 → 2 个 [节点0 节点1]
depth=2 → 3 个 [节点0 节点1 节点2] ← 修复前停在这里
depth=3 → 4 个 [节点0 节点1 节点2 节点3]
补判据 `TestBFS召回_层深真实生效`：必须用**链**（n0-n1-n2-n3），
星型在 depth=1 就能召回全部叶子、断不出有没有走深。
变异（改回单层）⇒ 实测红：`★ depth=2 召回 2 个，期望 3`。
### ② nlp/extractor.go —— subjRels/objRels 只写不读
两个切片被 append 了 4 处，但**从未被读取**。三元组的关系类型来自
`relLabel := result.Tokens[vi]`，置信度来自 `result.DepRels[si]`，
与这两个切片无关。删除。
### ③ plugins/cmd/plugin.go —— 配置解析失败会把上限写成 0
if n, err := fmt.Sscanf(s, "%d", &p.maxOutput); err == nil && n > 0 {
} // ← 空分支
直接 Sscanf 到 &p.maxOutput：解析失败时它可能已被写成 0 或部分值，
而空分支无法回滚 ⇒ 配置写错一个字符就把输出上限变成 0
（下游 `maxLen := p.maxOutput` 直接拿它算截断长度）。
改为解析到临时变量、失败时保持默认并记日志。
### ④ cmd/homed/bootstrap.go —— 空的 else 分支
`if err != nil { log } else { }` —— 删掉 else。
## 测试判据里的真实缺陷（3 个）
### ⑤ stop_semantics_test —— 短路求值让第二次调用从不执行
if !a.sched.consumeCancel() || !a.sched.consumeCancel()
第一次返回 true 时第二次**根本不会执行**，于是"两条配额都可消费"
这条断言实际只测了一次。拆成两次独立调用（两处同型）。
### ⑥ seq/store_test —— 永假断言
if maxCallDepth != maxCallDepth { t.Fatal("maxCallDepth 不稳定") }
自己跟自己比，从诞生起就不可能失败。改成显式读两次比较。
### ⑦ pluginhost/catalog_test —— typed-nil 守卫永假
var nb *kstate.SyncBus
var iface kstate.SyncState = nb
if iface == nil { t.Skip(...) } // ← 恒 false
把 typed-nil 装进接口后，接口的 (type, value) 二元组都不为 nil。
这道前置守卫**从未生效** —— 而这正是该判据要演示的陷阱本身。
改用 `reflect.ValueOf(iface).IsNil()`。
## 其余（写法/冗余，无行为变化）
agent.go / context.go / toolresult_store_test / apply_regression_test
空 if 块（注释移到真实分支上方）
codec_chunkfast_golden_test 未使用的三个返回值 + 空 if
scheduler_critical/stack_test `if _, _ = f(); true { }` → 直接调用
overflow_test / upgrade_test 变量被整体覆盖，首次赋值未使用
dense_test m[string(x)] 替代临时变量
lex_rules_test range over string 而非 []rune(string)
## 验证
staticcheck -checks 'SA4*,SA5*,SA6*,SA9*' 0 条（基线 24 → 0）
go build ./... PASS
go vet ./... PASS
gofmt -l 干净
go test ./... -count=1 65 包全过，0 FAIL
干净检出（worktree） build + memory/nlp/core 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.