vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 16:30:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: typography hygiene across 6 pages

Browse Source
This commit is contained in:
Vincent Koc
2026-05-05 21:03:26 -07:00
parent 2df7ec5671
commit c5ea7c4d0f
6 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/concepts/messages.md
View File

@@ -181,7 +181,7 @@ Details: [Configuration](/gateway/config-agents#messages) and channel docs.
## Silent replies
The exact silent token `NO_REPLY` / `no_reply` means “do not deliver a user-visible reply”.
The exact silent token `NO_REPLY` / `no_reply` means "do not deliver a user-visible reply".
When a turn also has pending tool media, such as generated TTS audio, OpenClaw
strips the silent text but still delivers the media attachment.
OpenClaw resolves that behavior by conversation type:

4
docs/concepts/model-failover.md
View File

@@ -106,7 +106,7 @@ When a provider has multiple profiles, OpenClaw chooses an order like this:
</Step>
</Steps>
If no explicit order is configured, OpenClaw uses a round‑robin order:
If no explicit order is configured, OpenClaw uses a round-robin order:
- **Primary key:** profile type (**OAuth before API keys**).
- **Secondary key:** `usageStats.lastUsed` (oldest first, within each type).
@@ -128,7 +128,7 @@ Auto-pinned profiles (selected by the session router) are treated as a **prefere
### Why OAuth can "look lost"
If you have both an OAuth profile and an API key profile for the same provider, round‑robin can switch between them across messages unless pinned. To force a single profile:
If you have both an OAuth profile and an API key profile for the same provider, round-robin can switch between them across messages unless pinned. To force a single profile:
- Pin with `auth.order[provider] = ["provider:profileId"]`, or
- Use a per-session override via `/model …` with a profile override (when supported by your UI/chat surface).

2
docs/concepts/queue.md
View File

@@ -113,7 +113,7 @@ keys.
## Troubleshooting
- If commands seem stuck, enable verbose logs and look for “queued for …ms” lines to confirm the queue is draining.
- If commands seem stuck, enable verbose logs and look for "queued for ...ms" lines to confirm the queue is draining.
- If you need queue depth, enable verbose logs and watch for queue timing lines.
- Codex app-server runs that accept a turn and then stop emitting progress are interrupted by the Codex adapter so the active session lane can release instead of waiting for the outer run timeout.
- When diagnostics are enabled, sessions that remain in `processing` past `diagnostics.stuckSessionWarnMs` with no observed reply, tool, status, block, or ACP progress are classified by current activity. Active work logs as `session.long_running`; active work with no recent progress logs as `session.stalled`; `session.stuck` is reserved for stale session bookkeeping with no active work, and only that path can release the affected session lane so queued work drains. Repeated `session.stuck` diagnostics back off while the session remains unchanged.