docs(supermemory): purge stale session-ingest / /v4/conversations references
The per-turn capture rewrite removed the raw urllib /v4/conversations ingest, but stale references survived outside the diff hunks: - README "Behavior" still carried the "written once via the conversations endpoint" paragraph contradicted by the new bullets right above it. - website memory-providers (EN + zh-Hans) still listed full-session ingest, session-end /v4/conversations ingest, and ingest in the base-url and api_timeout rows — the PR had updated one line per file but missed the rest of the section. Now every surface describes per-turn documents.add capture with retry.
This commit is contained in:
@@ -93,12 +93,11 @@ Supermemory app, so you can filter, browse, and bulk-manage them per source agen
|
||||
When enabled, Hermes can:
|
||||
|
||||
- prefetch relevant memory context before each turn
|
||||
- write each completed user/assistant turn to **one document per session per 4-hour window** (`customId` = `<session>_<date>_b<0-5>`, so the API appends deltas), like the Codex and OpenClaw plugins
|
||||
- write each completed user/assistant turn to **one document per session per 4-hour window** (`customId` = `<session>_<date>_b<0-5>`, so the API appends deltas), matching the capture shape of the other Supermemory agent integrations
|
||||
- retry failed turn writes on the next turn, session end, `/reset`, or shutdown (at-least-once: if the API accepted a write but the response was lost, the same turn is appended again)
|
||||
- route every SDK and probe request through the configured hosted or self-hosted endpoint
|
||||
- expose explicit tools for search, store, forget, and profile access
|
||||
|
||||
The session is written once via the conversations endpoint, which drives Supermemory's entity extraction and profile building while keeping a clean, retrievable full transcript.
|
||||
|
||||
## Profile-Scoped Containers
|
||||
|
||||
|
||||
@@ -25,7 +25,7 @@ _API_KEY_URL = "http://app.supermemory.ai/integrations?connect=hermes"
|
||||
# Strips injected <supermemory-context> / <supermemory-containers> blocks before capture.
|
||||
_INJECTED_BLOCK_RE = re.compile(r"<supermemory-(context|containers)>[\s\S]*?</supermemory-\1>\s*", re.DOTALL)
|
||||
_DATA_URI_RE = re.compile(r"data:[^;,\s]+;base64,[A-Za-z0-9+/=]+") # pasted inline images are useless as memory text
|
||||
_CAPTURE_BUCKET_HOURS = 4 # one capture document per session per 4h window (matches codex/openclaw plugins)
|
||||
_CAPTURE_BUCKET_HOURS = 4 # one capture document per session per 4h window (matches the other Supermemory agent integrations)
|
||||
_DEFAULT_ENTITY_CONTEXT = (
|
||||
"User-assistant conversation. Format: [role: user]...[user:end] and [role: assistant]...[assistant:end].\n\n"
|
||||
"Only extract things useful in future conversations. Most messages are not worth remembering.\n\n"
|
||||
|
||||
@@ -617,17 +617,17 @@ stays local.
|
||||
| `profile_frequency` | `50` | Include profile facts on first turn and every N turns |
|
||||
| `capture_mode` | `all` | Skip tiny or trivial turns by default |
|
||||
| `search_mode` | `hybrid` | Search mode: `hybrid`, `memories`, or `documents` |
|
||||
| `api_timeout` | `5.0` | Timeout for SDK and ingest requests |
|
||||
| `api_timeout` | `5.0` | Timeout for SDK requests |
|
||||
|
||||
**Environment variables:** `SUPERMEMORY_API_KEY` (required), `SUPERMEMORY_BASE_URL` (compatibility fallback when `base_url` is not configured), `SUPERMEMORY_CONTAINER_TAG` (overrides config).
|
||||
|
||||
Base URL precedence is `supermemory.json` → `SUPERMEMORY_BASE_URL` → `https://api.supermemory.ai`. SDK operations, setup/status probes, and conversation ingest all use the resolved endpoint.
|
||||
Base URL precedence is `supermemory.json` → `SUPERMEMORY_BASE_URL` → `https://api.supermemory.ai`. SDK operations and setup/status probes all use the resolved endpoint.
|
||||
|
||||
**Key features:**
|
||||
- Automatic context fencing — strips recalled memories from captured turns to prevent recursive memory pollution
|
||||
- Full-session ingest — the entire conversation is sent once at session boundaries
|
||||
- Session-end conversation ingest (to `/v4/conversations`) for richer profile + graph building in Supermemory
|
||||
- End-to-end self-hosted routing — SDK, probe, and conversation-ingest requests use the same configured endpoint
|
||||
- Per-turn capture — each completed turn is written as it happens, one document per session per 4-hour window
|
||||
- Failed turn writes are retried (at-least-once) on the next turn, session end, or shutdown
|
||||
- End-to-end self-hosted routing — SDK and probe requests use the same configured endpoint
|
||||
- Profile facts injected on first turn and at configurable intervals
|
||||
- **Profile-scoped containers** — use `{identity}` in `container_tag` (e.g. `hermes-{identity}` → `hermes-coder`) to isolate memories per Hermes profile
|
||||
- **Multi-container mode** — enable `enable_custom_container_tags` with a `custom_containers` list to let the agent read/write across named containers. Automatic operations stay on the primary container.
|
||||
|
||||
+5
-5
@@ -510,17 +510,17 @@ npx supermemory local
|
||||
| `profile_frequency` | `50` | 在第一轮及每 N 轮包含 profile 事实 |
|
||||
| `capture_mode` | `all` | 默认跳过过短或无意义的轮次 |
|
||||
| `search_mode` | `hybrid` | 搜索模式:`hybrid`、`memories` 或 `documents` |
|
||||
| `api_timeout` | `5.0` | SDK 和导入请求的超时时间 |
|
||||
| `api_timeout` | `5.0` | SDK 请求的超时时间 |
|
||||
|
||||
**环境变量:** `SUPERMEMORY_API_KEY`(必填)、`SUPERMEMORY_BASE_URL`(未配置 `base_url` 时的兼容回退)、`SUPERMEMORY_CONTAINER_TAG`(覆盖配置)。
|
||||
|
||||
Base URL 优先级为 `supermemory.json` → `SUPERMEMORY_BASE_URL` → `https://api.supermemory.ai`。SDK 操作、安装/状态探测和会话导入都会使用解析后的同一端点。
|
||||
Base URL 优先级为 `supermemory.json` → `SUPERMEMORY_BASE_URL` → `https://api.supermemory.ai`。SDK 操作和安装/状态探测都会使用解析后的同一端点。
|
||||
|
||||
**主要特性:**
|
||||
- 自动上下文隔离——从捕获的轮次中剥离已召回的记忆,防止递归记忆污染
|
||||
- 在会话边界时将整个会话**一次性导入**
|
||||
- 会话结束时同时导入到对话端点(`/v4/conversations`),用于 Supermemory 的 profile 和图谱构建
|
||||
- 端到端自托管路由——SDK、探测和会话导入请求使用同一配置端点
|
||||
- 逐轮捕获——每轮完成后立即写入,每个会话每 4 小时一个文档
|
||||
- 失败的轮次写入会重试(至少一次语义):下一轮、会话结束或关闭时
|
||||
- 端到端自托管路由——SDK 和探测请求使用同一配置端点
|
||||
- 在第一轮及可配置间隔注入 profile 事实
|
||||
- **Profile 范围容器**——在 `container_tag` 中使用 `{identity}`(例如 `hermes-{identity}` → `hermes-coder`),按 Hermes profile 隔离记忆
|
||||
- **多容器模式**——启用 `enable_custom_container_tags` 并配置 `custom_containers` 列表,让 Agent 跨命名容器读写。自动操作(同步、预取)保持在主容器上。
|
||||
|
||||
Reference in New Issue
Block a user