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
{{ message }}
Repository navigation
Commit 5d86c4a
Browse filesBrowse the repository at this point in the historyBrowse files
docs(claude): separate the fixed picker floor from launch-slot marking
Discovery and Desktop picker rows use the fixed 829,800-token floor.
Launch env slots follow the configured compact threshold. Forced
subagents mark a non-Anthropic selector at that floor and keep the
genuine-1M rule for Anthropic Claude and bare claude-* ids.
Co-authored-by: JUN <[email protected]>
Copy file name to clipboardExpand all lines: docs-site/src/content/docs/fr/guides/claude-code.md
+8-6Lines changed: 8 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -470,8 +470,9 @@ résolution de l'alias et le routage.
470
470
Claude Code attribue une limite de 200k jetons à tout modèle qu'il ne reconnaît pas. Le **contexte automatique**, activé
471
471
par défaut, corrige ce comportement :
472
472
473
-
1. Les modèles dont la fenêtre réelle dépasse 200k **et** atteint au moins le seuil de compactage automatique obtiennent le
474
-
marqueur `[1m]` dans les lignes du sélecteur et les variables d'environnement qui les désignent.
473
+
1. Les variables d'environnement de lancement reçoivent le marqueur `[1m]` lorsque la fenêtre réelle dépasse 200k **et**
474
+
atteint au moins le seuil de compactage automatique configuré. Les lignes de découverte et du sélecteur Desktop ne suivent pas
475
+
ce seuil : elles utilisent le plancher fixe de 829 800 jetons (1M réel pour un modèle Claude sur une route Anthropic).
475
476
2.`CLAUDE_CODE_AUTO_COMPACT_WINDOW` (`829800` par défaut, plage `100000`–`1000000`) est injecté afin
476
477
que la conversation soit automatiquement résumée à ce seuil.
477
478
@@ -484,8 +485,9 @@ Trois états de configuration :
484
485
La valeur de compactage est réglable dans **Connexion → Claude**. **Avertissement :** une valeur supérieure à la fenêtre réelle d'un modèle
485
486
rend ce modèle inutilisable : les tours échouent avant que le résumé puisse se déclencher.
486
487
487
-
Les modèles Anthropic natifs dont le contexte est inférieur à 1M ne sont jamais marqués automatiquement. Les valeurs que vous exportez vous-même
488
-
restent prioritaires ; le proxy s'appuie sur votre valeur pour déterminer les modèles qui peuvent recevoir le marqueur sans risque.
488
+
Les modèles Anthropic natifs dont le contexte est inférieur à 1M ne sont jamais marqués automatiquement. Une fenêtre de compactage que vous exportez vous-même
489
+
reste prioritaire pour le marquage des variables de lancement ; le proxy s'appuie sur votre valeur pour déterminer les modèles qui peuvent recevoir le marqueur sans risque.
490
+
Les lignes de découverte ignorent cet export et conservent le plancher fixe.
489
491
Les valeurs de configuration invalides définies manuellement reviennent à 829,800.
490
492
491
493
### Environnement effectif des modèles
@@ -746,7 +748,7 @@ une valeur `ANTHROPIC_BASE_URL` obsolète. Ouvrez un nouveau terminal ou réexé
746
748
747
749
**Plafond de contexte 200k malgré un grand modèle** — Sélectionnez la variante `[1m]` dans le sélecteur ou activez
748
750
le contexte automatique, activé par défaut. Si le sélecteur n'affiche aucune ligne `[1m]`, la fenêtre de contexte de référence du modèle
749
-
peut être inférieure au seuil de compactage automatique.
751
+
peut être inférieure au plancher fixe de 829 800 jetons.
750
752
751
753
**Nombre élevé de jetons provenant du chargement des compétences** — La compétence `claude-api` fournie (~136k jetons) se charge automatiquement
752
754
quand un modèle Claude est mentionné. Ce comportement est normal avec le transfert natif ; pour les modèles routés, opencodex la remplace
@@ -770,7 +772,7 @@ The Subagents page offers **Force all subagents onto one model**, off by default
770
772
771
773
`ocx agent subagents force combo/tev-auto` sets `claudeCode.subagentModelForce`; `ocx agent subagents force -` clears it. `ocx agent status` reports the setting. `GET /api/subagent-models` returns `force`, `forceAvailable`, and `forceStatus`; `PUT` accepts `{ "force": "combo/tev-auto" }` or `{ "force": null }` without changing the roster. Omitting `force` leaves it unchanged. Invalid or unexposed targets are rejected on write; stale targets are reported and skipped at launch.
772
774
773
-
This takes effect on the **next routed `ocx claude` launch**, injecting `CLAUDE_CODE_SUBAGENT_MODEL` as an explicit proxy alias (with `[1m]`only for an authoritative million-token window; native Claude targets use a reversible native alias) and `CLAUDE_CODE_SUBAGENT_MODEL_FORCE=1`. Each nonempty shell-exported variable independently wins. Native launches inject neither variable; plain `claude` is not affected. No plugin files or `settings.json` are modified by this setting.
775
+
This takes effect on the **next routed `ocx claude` launch**, injecting `CLAUDE_CODE_SUBAGENT_MODEL` as an explicit proxy alias (with `[1m]`when the authoritative window reaches the fixed 829,800-token floor, and only for a genuine 1M window on Anthropic Claude models and bare `claude-*` selectors; native Claude targets use a reversible native alias) and `CLAUDE_CODE_SUBAGENT_MODEL_FORCE=1`. Each nonempty shell-exported variable independently wins. Native launches inject neither variable; plain `claude` is not affected. No plugin files or `settings.json` are modified by this setting.
774
776
775
777
Claude Code **2.1.257 or newer** is required for FORCE. Plugin and built-in agents (including Explore/Plan) and per-call model arguments are overridden. Forks and subagent skills with `model: inherit` keep the main conversation model. The main loop and Haiku/small-fast sidecars are unaffected. Existing roster files remain available.
Copy file name to clipboardExpand all lines: docs-site/src/content/docs/guides/claude-code.md
+9-6Lines changed: 9 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -645,8 +645,10 @@ resolution and routing.
645
645
Claude Code accounts 200k tokens for any model it does not recognize. **Auto context** (on by
646
646
default) fixes that:
647
647
648
-
1. Models whose real window is above 200k **and** at least the auto-compact threshold get the
649
-
`[1m]` marker on their picker rows and env slots.
648
+
1. Launch env slots get the `[1m]` marker when the model's real window is above 200k **and** at
649
+
least the configured auto-compact threshold. Discovery and Desktop picker rows do not follow
650
+
that threshold: they use the fixed 829,800-token floor (a genuine 1M for Claude models on an
651
+
Anthropic route).
650
652
2.`CLAUDE_CODE_AUTO_COMPACT_WINDOW` (default `829800`, range `100000`–`1000000`) is injected so
651
653
the conversation auto-summarizes at that point.
652
654
@@ -671,8 +673,9 @@ history and try compacting a fork with fewer enabled tool or MCP schemas, if you
671
673
that workflow. A `[1m]` marker or larger client accounting setting does not raise the upstream
672
674
limit, and OpenCodex does not silently remove history or tools to make it fit.
673
675
674
-
Sub-1M native Anthropic models are never auto-marked. Values you export yourself always win (the
675
-
proxy uses YOUR value to decide which models are safe to mark). Invalid hand-edited config values
676
+
Sub-1M native Anthropic models are never auto-marked. A compact window you export yourself wins
677
+
for launch-slot marking (the proxy uses YOUR value to decide which models are safe to mark).
678
+
Discovery rows ignore that export and keep the fixed floor. Invalid hand-edited config values
676
679
fall back to 829,800.
677
680
678
681
### Effective model environment
@@ -1004,7 +1007,7 @@ set (automatic with `ocx claude`). Run `ocx claude` to refresh the gateway model
1004
1007
1005
1008
**200k context ceiling despite big model** — Select the `[1m]` variant in the picker, or enable
1006
1009
auto-context (on by default). If the picker shows no `[1m]` row, the model's authoritative context
1007
-
window may be below the auto-compact threshold.
1010
+
window may be below the fixed 829,800-token floor.
1008
1011
1009
1012
**High token count from skill loads** — The bundled `claude-api` skill (~136k tokens) auto-loads
1010
1013
on Claude model mentions. This is normal for native passthrough; on routed models, opencodex stubs
@@ -1070,7 +1073,7 @@ The Subagents page offers **Force all subagents onto one model**, off by default
1070
1073
1071
1074
`ocx agent subagents force combo/tev-auto` sets `claudeCode.subagentModelForce`; `ocx agent subagents force -` clears it. `ocx agent status` reports the setting. `GET /api/subagent-models` returns `force`, `forceAvailable`, and `forceStatus`; `PUT` accepts `{ "force": "combo/tev-auto" }` or `{ "force": null }` without changing the roster. Omitting `force` leaves it unchanged. Invalid or unexposed targets are rejected on write; stale targets are reported and skipped at launch.
1072
1075
1073
-
This takes effect on the **next routed `ocx claude` launch**, injecting `CLAUDE_CODE_SUBAGENT_MODEL` as an explicit proxy alias (with `[1m]`only for an authoritative million-token window; native Claude targets use a reversible native alias) and `CLAUDE_CODE_SUBAGENT_MODEL_FORCE=1`. Each nonempty shell-exported variable independently wins. Native launches inject neither variable; plain `claude` is not affected. No plugin files or `settings.json` are modified by this setting.
1076
+
This takes effect on the **next routed `ocx claude` launch**, injecting `CLAUDE_CODE_SUBAGENT_MODEL` as an explicit proxy alias (with `[1m]`when the authoritative window reaches the fixed 829,800-token floor, and only for a genuine 1M window on Anthropic Claude models and bare `claude-*` selectors; native Claude targets use a reversible native alias) and `CLAUDE_CODE_SUBAGENT_MODEL_FORCE=1`. Each nonempty shell-exported variable independently wins. Native launches inject neither variable; plain `claude` is not affected. No plugin files or `settings.json` are modified by this setting.
1074
1077
1075
1078
Claude Code **2.1.257 or newer** is required for FORCE. Plugin and built-in agents (including Explore/Plan) and per-call model arguments are overridden. Forks and subagent skills with `model: inherit` keep the main conversation model. The main loop and Haiku/small-fast sidecars are unaffected. Existing roster files remain available.
@@ -624,7 +625,7 @@ The Subagents page offers **Force all subagents onto one model**, off by default
624
625
625
626
`ocx agent subagents force combo/tev-auto` sets `claudeCode.subagentModelForce`; `ocx agent subagents force -` clears it. `ocx agent status` reports the setting. `GET /api/subagent-models` returns `force`, `forceAvailable`, and `forceStatus`; `PUT` accepts `{ "force": "combo/tev-auto" }` or `{ "force": null }` without changing the roster. Omitting `force` leaves it unchanged. Invalid or unexposed targets are rejected on write; stale targets are reported and skipped at launch.
626
627
627
-
This takes effect on the **next routed `ocx claude` launch**, injecting `CLAUDE_CODE_SUBAGENT_MODEL` as an explicit proxy alias (with `[1m]`only for an authoritative million-token window; native Claude targets use a reversible native alias) and `CLAUDE_CODE_SUBAGENT_MODEL_FORCE=1`. Each nonempty shell-exported variable independently wins. Native launches inject neither variable; plain `claude` is not affected. No plugin files or `settings.json` are modified by this setting.
628
+
This takes effect on the **next routed `ocx claude` launch**, injecting `CLAUDE_CODE_SUBAGENT_MODEL` as an explicit proxy alias (with `[1m]`when the authoritative window reaches the fixed 829,800-token floor, and only for a genuine 1M window on Anthropic Claude models and bare `claude-*` selectors; native Claude targets use a reversible native alias) and `CLAUDE_CODE_SUBAGENT_MODEL_FORCE=1`. Each nonempty shell-exported variable independently wins. Native launches inject neither variable; plain `claude` is not affected. No plugin files or `settings.json` are modified by this setting.
628
629
629
630
Claude Code **2.1.257 or newer** is required for FORCE. Plugin and built-in agents (including Explore/Plan) and per-call model arguments are overridden. Forks and subagent skills with `model: inherit` keep the main conversation model. The main loop and Haiku/small-fast sidecars are unaffected. Existing roster files remain available.
켜져 있는 자동 컨텍스트를 사용하세요. 선택기에 `[1m]` 행이 없다면 모델의 공식 컨텍스트 창이
670
-
자동 압축 임곗값보다 작을 수 있어요.
672
+
고정된 829,800 토큰 하한보다 작을 수 있어요.
671
673
672
674
**스킬을 불러올 때 토큰 수가 많음** — 번들 `claude-api` 스킬(약 136k 토큰)은 Claude 모델을
673
675
언급하면 자동으로 불러와요. 네이티브 패스스루에서는 정상이며, 라우팅 모델에서는 opencodex가
@@ -687,7 +689,7 @@ The Subagents page offers **Force all subagents onto one model**, off by default
687
689
688
690
`ocx agent subagents force combo/tev-auto` sets `claudeCode.subagentModelForce`; `ocx agent subagents force -` clears it. `ocx agent status` reports the setting. `GET /api/subagent-models` returns `force`, `forceAvailable`, and `forceStatus`; `PUT` accepts `{ "force": "combo/tev-auto" }` or `{ "force": null }` without changing the roster. Omitting `force` leaves it unchanged. Invalid or unexposed targets are rejected on write; stale targets are reported and skipped at launch.
689
691
690
-
This takes effect on the **next routed `ocx claude` launch**, injecting `CLAUDE_CODE_SUBAGENT_MODEL` as an explicit proxy alias (with `[1m]`only for an authoritative million-token window; native Claude targets use a reversible native alias) and `CLAUDE_CODE_SUBAGENT_MODEL_FORCE=1`. Each nonempty shell-exported variable independently wins. Native launches inject neither variable; plain `claude` is not affected. No plugin files or `settings.json` are modified by this setting.
692
+
This takes effect on the **next routed `ocx claude` launch**, injecting `CLAUDE_CODE_SUBAGENT_MODEL` as an explicit proxy alias (with `[1m]`when the authoritative window reaches the fixed 829,800-token floor, and only for a genuine 1M window on Anthropic Claude models and bare `claude-*` selectors; native Claude targets use a reversible native alias) and `CLAUDE_CODE_SUBAGENT_MODEL_FORCE=1`. Each nonempty shell-exported variable independently wins. Native launches inject neither variable; plain `claude` is not affected. No plugin files or `settings.json` are modified by this setting.
691
693
692
694
Claude Code **2.1.257 or newer** is required for FORCE. Plugin and built-in agents (including Explore/Plan) and per-call model arguments are overridden. Forks and subagent skills with `model: inherit` keep the main conversation model. The main loop and Haiku/small-fast sidecars are unaffected. Existing roster files remain available.
0 commit comments