vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 11:10:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(active-memory): add allowedChatIds/deniedChatIds per-conversation filters (openclaw#67977)

Browse Source 
Verified:
- pnpm install --frozen-lockfile
- git diff --check
- pnpm exec oxfmt --check --threads=1 extensions/active-memory/index.ts extensions/active-memory/index.test.ts docs/concepts/active-memory.md CHANGELOG.md
- OPENCLAW_TEST_HEAVY_CHECK_LOCK_HELD=1 OPENCLAW_VITEST_FS_MODULE_CACHE_PATH=.vitest-cache-pr67977 pnpm test extensions/active-memory/index.test.ts extensions/active-memory/config.test.ts
- gh pr checks 67977 --repo openclaw/openclaw --required

Co-authored-by: quengh <3940773+quengh@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
This commit is contained in:
quengh
2026-04-28 21:37:55 +08:00
committed by GitHub
parent 12aaef9035
commit 373e7fc242
5 changed files with 466 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
docs/concepts/active-memory.md
View File

@@ -256,6 +256,34 @@ allowedChatTypes: ["direct", "group"]
allowedChatTypes: ["direct", "group", "channel"]
```
For narrower rollout, use `config.allowedChatIds` and
`config.deniedChatIds` after choosing the allowed session types.
`allowedChatIds` is an explicit allowlist of resolved conversation ids. When it
is non-empty, Active Memory only runs when the session's conversation id is in
that list. This narrows every allowed chat type at once, including direct
messages. If you want all direct messages plus only specific groups, include
the direct peer ids in `allowedChatIds` or keep `allowedChatTypes` focused on
the group/channel rollout you are testing.
`deniedChatIds` is an explicit denylist. It always wins over
`allowedChatTypes` and `allowedChatIds`, so a matching conversation is skipped
even when its session type is otherwise allowed.
The ids come from the persistent channel session key: for example Feishu
`chat_id` / `open_id`, Telegram chat id, or Slack channel id. Matching is
case-insensitive. If `allowedChatIds` is non-empty and OpenClaw cannot resolve a
conversation id for the session, Active Memory skips the turn instead of
guessing.
Example:
```json5
allowedChatTypes: ["direct", "group"],
allowedChatIds: ["ou_operator_open_id", "oc_small_ops_group"],
deniedChatIds: ["oc_large_public_group"]
```
## Where it runs
Active memory is a conversational enrichment feature, not a platform-wide
@@ -534,6 +562,9 @@ The most important fields are:
| `enabled` | `boolean` | Enables the plugin itself |
| `config.agents` | `string[]` | Agent ids that may use active memory |
| `config.model` | `string` | Optional blocking memory sub-agent model ref; when unset, active memory uses the current session model |
| `config.allowedChatTypes` | `("direct" \| "group" \| "channel")[]` | Session types that may run Active Memory; defaults to direct-message style sessions |
| `config.allowedChatIds` | `string[]` | Optional per-conversation allowlist applied after `allowedChatTypes`; non-empty lists fail closed |
| `config.deniedChatIds` | `string[]` | Optional per-conversation denylist that overrides allowed session types and allowed ids |
| `config.queryMode` | `"message" \| "recent" \| "full"` | Controls how much conversation the blocking memory sub-agent sees |
| `config.promptStyle` | `"balanced" \| "strict" \| "contextual" \| "recall-heavy" \| "precision-heavy" \| "preference-only"` | Controls how eager or strict the blocking memory sub-agent is when deciding whether to return memory |
| `config.thinking` | `"off" \| "minimal" \| "low" \| "medium" \| "high" \| "xhigh" \| "adaptive" \| "max"` | Advanced thinking override for the blocking memory sub-agent; default `off` for speed |