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
fix: thread toast duration through session hook config
- preserves toast_duration_ms when building the narrowed hook config
- keeps dream notifications on the configured duration instead of falling back to 5s
- includes regression coverage
- keep restart/setup toasts on 10s fallback
Copy file name to clipboardExpand all lines: CONFIGURATION.md
+2Lines changed: 2 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -113,6 +113,7 @@ Higher-tier models with longer cache windows benefit from a longer TTL. Setting
113
113
|`ctx_reduce_enabled`|`boolean`|`true`| When `false`, hides `ctx_reduce` tool, disables all nudges/reminders, and strips reduction guidance from prompts. Heuristic cleanup, compartments, memory, and search still work. Useful for testing whether automatic cleanup alone is sufficient. |
114
114
|`cache_ttl`|`string` or `object`|`"5m"`| Time after a response before applying pending ops. String or per-model map. |
115
115
|`protected_tags`|`number` (1–100) |`20`| Last N active tags immune from immediate dropping. |
116
+
|`toast_duration_ms`|`number` (1000–60000) |`5000`| TUI toast lifetime for Magic Context notifications in milliseconds. Increase this if toasts disappear too quickly. |
116
117
|`execute_threshold_percentage`|`number` (20–80) or `object`|`65`| Context usage that forces queued ops to execute. Capped at 80% max for cache safety. Supports per-model map. |
117
118
|`execute_threshold_tokens`|`object` (per-model map) | — |**Optional absolute-tokens variant of `execute_threshold_percentage`.** Per-model map (e.g. `{ "default": 150000, "github-copilot/gpt-5.2-codex": 40000 }`). When set for a model, overrides the percentage-based threshold for that model. Clamped to `80% × context_limit` with a warn log. Requires a resolvable context limit — falls through to percentage if unavailable. See below. |
118
119
|`clear_reasoning_age`|`number`|`50`| Clear thinking/reasoning blocks older than N tags. |
@@ -627,6 +628,7 @@ Tier boundaries are hardcoded to keep behavior predictable and prevent cache-bus
Copy file name to clipboardExpand all lines: assets/magic-context.schema.json
+7Lines changed: 7 additions & 0 deletions
Original file line number
Diff line number
Diff line change
@@ -461,6 +461,13 @@
461
461
}
462
462
]
463
463
},
464
+
"toast_duration_ms": {
465
+
"default": 5000,
466
+
"description": "TUI toast lifetime in milliseconds for Magic Context notifications (min: 1000, max: 60000, default: 5000)",
467
+
"type": "number",
468
+
"minimum": 1000,
469
+
"maximum": 60000
470
+
},
464
471
"execute_threshold_percentage": {
465
472
"default": 65,
466
473
"description": "Context percentage that forces queued operations to execute. Number or per-model object ({ default: 65, \"provider/model\": 45 }). Values above 80 are rejected because the runtime caps at 80% for cache safety (MAX_EXECUTE_THRESHOLD). Default: DEFAULT_EXECUTE_THRESHOLD_PERCENTAGE",
0 commit comments