You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Add the /effort and query-marker xhigh behavior to the current fork delta, including per-turn status-line visibility. Keep the English and Chinese sections aligned after the new feature entry.
Copy file name to clipboardExpand all lines: README.md
+32-8Lines changed: 32 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -105,7 +105,19 @@ From recent fork-specific changes:
105
105
106
106
This brings a Claude Code-style export flow into the TUI without requiring external scripts or manual transcript scraping.
107
107
108
-
### 6. Parallel-first subagent planning policy
108
+
### 6. Reasoning effort controls and per-turn status visibility
109
+
110
+
From recent fork-specific changes:
111
+
112
+
- adds `/effort` for changing the active reasoning effort directly from the TUI
113
+
- supports one-turn high-effort markers in the user query: standalone `ulw`, `ultra`, or `xhigh` submit that turn with `xhigh` reasoning
114
+
- keeps marker-based `xhigh` current-turn-only, so it does not mutate the session's default effort
115
+
- shows the submitted per-turn effort in the `model-with-reasoning` status-line item while that foreground turn is pending or running
116
+
- restores the status line to the session/default effort when the turn completes, fails, or is interrupted
117
+
118
+
This closes the UX gap between "the request was submitted with xhigh" and "the footer still looks like high": the status line now describes the active foreground turn without making a temporary marker look like a persistent configuration change.
119
+
120
+
### 7. Parallel-first subagent planning policy
109
121
110
122
Implemented through the user-scope `~/.codex/AGENTS.md` instruction layer, with an extracted repo example in [`docs/parallel-first-agent-execution.md`](docs/parallel-first-agent-execution.md):
111
123
@@ -116,7 +128,7 @@ Implemented through the user-scope `~/.codex/AGENTS.md` instruction layer, with
116
128
117
129
This is an instruction-policy feature rather than a hardcoded scheduler: it enables a more aggressive subagent mechanism while keeping shared-file edits coordinated.
118
130
119
-
### 7. Nonblocking background execution
131
+
### 8. Nonblocking background execution
120
132
121
133
From recent fork-specific TUI changes:
122
134
@@ -139,7 +151,7 @@ The shared interaction model is:
139
151
140
152
This is the essential interaction change behind the Claude Code-style behavior: background work stays visible and controllable, but it no longer blocks normal chat flow.
141
153
142
-
### 8. Status line token throughput visibility (Beta)
154
+
### 9. Status line token throughput visibility (Beta)
143
155
144
156
From commit `85e937b855`:
145
157
@@ -150,7 +162,7 @@ From commit `85e937b855`:
150
162
151
163
This is intentionally marked **Beta**: the current value is useful as a rough responsiveness signal, but it is not yet an exact real-time throughput metric.
152
164
153
-
### 9. Workspace git status in the status line
165
+
### 10. Workspace git status in the status line
154
166
155
167
The status line can now surface the current workspace diff through the configurable `workspace-changes` item:
0 commit comments