vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-04 03:20:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: refresh history sanitization tag mirrors

Browse Source
This commit is contained in:
Peter Steinberger
2026-04-04 22:21:26 +01:00
parent eee868452f
commit bc910942e2
11 changed files with 48 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
docs/concepts/delegate-architecture.md
View File

@@ -285,11 +285,13 @@ The delegate's `AGENTS.md` defines its autonomous authority — what it may do w
If you grant `sessions_history`, remember it is a bounded, safety-filtered
recall view. OpenClaw redacts credential/token-like text, truncates long
content, strips thinking tags / `<relevant-memories>` scaffolding / plain-text
tool-call XML payloads (including `<tool_calls>` and truncated tool-call
blocks) / downgraded tool-call scaffolding / leaked ASCII/full-width model
control tokens / malformed MiniMax tool-call XML from assistant recall, and
can replace oversized rows with `[sessions_history omitted: message too
large]` instead of returning a raw transcript dump.
tool-call XML payloads (including `<tool_call>...</tool_call>`,
`<function_call>...</function_call>`, `<tool_calls>...</tool_calls>`,
`<function_calls>...</function_calls>`, and truncated tool-call blocks) /
downgraded tool-call scaffolding / leaked ASCII/full-width model control
tokens / malformed MiniMax tool-call XML from assistant recall, and can
replace oversized rows with `[sessions_history omitted: message too large]`
instead of returning a raw transcript dump.
## Scaling pattern

8
docs/concepts/multi-agent.md
View File

@@ -26,9 +26,11 @@ Auth profiles are **per-agent**. Each agent reads from its own:
`sessions_history` is the safer cross-session recall path here too: it returns
a bounded, sanitized view, not a raw transcript dump. Assistant recall strips
thinking tags, `<relevant-memories>` scaffolding, plain-text tool-call XML
payloads (including `<tool_calls>` and truncated tool-call blocks), downgraded
tool-call scaffolding, leaked ASCII/full-width model control tokens, and
malformed MiniMax tool-call XML before redaction/truncation.
payloads (including `<tool_call>...</tool_call>`,
`<function_call>...</function_call>`, `<tool_calls>...</tool_calls>`,
`<function_calls>...</function_calls>`, and truncated tool-call blocks),
downgraded tool-call scaffolding, leaked ASCII/full-width model control
tokens, and malformed MiniMax tool-call XML before redaction/truncation.
Main agent credentials are **not** shared automatically. Never reuse `agentDir`
across agents (it causes auth/session collisions). If you want to share creds,

5
docs/concepts/session-tool.md
View File

@@ -38,8 +38,9 @@ The returned view is intentionally bounded and safety-filtered:
- thinking tags are stripped
- `<relevant-memories>` / `<relevant_memories>` scaffolding blocks are stripped
- plain-text tool-call XML payload blocks such as `<tool_call>...</tool_call>`,
`<tool_calls>...</tool_calls>`, and `<function_calls>...</function_calls>`
are stripped, including truncated payloads that never close cleanly
`<function_call>...</function_call>`, `<tool_calls>...</tool_calls>`, and
`<function_calls>...</function_calls>` are stripped, including truncated
payloads that never close cleanly
- downgraded tool-call/result scaffolding such as `[Tool Call: ...]`,
`[Tool Result ...]`, and `[Historical context ...]` is stripped
- leaked model control tokens such as `<|assistant|>`, other ASCII