oh-my-opencode 3.13.1 → 3.14.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.ja.md +2 -2
- package/README.ko.md +2 -2
- package/README.md +2 -2
- package/README.ru.md +2 -2
- package/README.zh-cn.md +2 -2
- package/dist/agents/types.d.ts +2 -1
- package/dist/cli/doctor/checks/model-resolution-types.d.ts +3 -0
- package/dist/cli/doctor/checks/model-resolution.d.ts +2 -1
- package/dist/cli/doctor/constants.d.ts +1 -1
- package/dist/cli/index.js +41911 -346
- package/dist/cli/refresh-model-capabilities.d.ts +15 -0
- package/dist/config/index.d.ts +1 -1
- package/dist/config/schema/agent-overrides.d.ts +360 -15
- package/dist/config/schema/categories.d.ts +48 -2
- package/dist/config/schema/dynamic-context-pruning.d.ts +1 -1
- package/dist/config/schema/experimental.d.ts +1 -1
- package/dist/config/schema/fallback-models.d.ts +45 -1
- package/dist/config/schema/model-capabilities.d.ts +8 -0
- package/dist/config/schema/oh-my-opencode-config.d.ts +367 -16
- package/dist/config/schema.d.ts +1 -0
- package/dist/features/background-agent/types.d.ts +3 -10
- package/dist/features/opencode-skill-loader/loader.d.ts +2 -0
- package/dist/hooks/auto-update-checker/hook/model-capabilities-status.d.ts +2 -0
- package/dist/hooks/auto-update-checker/types.d.ts +2 -0
- package/dist/hooks/keyword-detector/ultrawork/default.d.ts +1 -1
- package/dist/hooks/keyword-detector/ultrawork/gemini.d.ts +1 -1
- package/dist/hooks/keyword-detector/ultrawork/gpt.d.ts +1 -1
- package/dist/hooks/model-fallback/hook.d.ts +5 -0
- package/dist/hooks/runtime-fallback/fallback-models.d.ts +12 -0
- package/dist/hooks/start-work/start-work-hook.d.ts +1 -0
- package/dist/index.js +43251 -1161
- package/dist/oh-my-opencode.schema.json +996 -15
- package/dist/plugin/chat-params.d.ts +1 -0
- package/dist/shared/connected-providers-cache.d.ts +20 -5
- package/dist/shared/fallback-chain-from-models.d.ts +10 -1
- package/dist/shared/index.d.ts +7 -1
- package/dist/shared/known-variants.d.ts +6 -0
- package/dist/shared/legacy-plugin-warning.d.ts +6 -0
- package/dist/shared/log-legacy-plugin-startup-warning.d.ts +1 -0
- package/dist/shared/model-capabilities-cache.d.ts +20 -0
- package/dist/shared/model-capabilities.d.ts +91 -0
- package/dist/shared/model-capability-aliases.d.ts +21 -0
- package/dist/shared/model-capability-guardrails.d.ts +38 -0
- package/dist/shared/model-capability-heuristics.d.ts +10 -0
- package/dist/shared/model-requirements.d.ts +8 -0
- package/dist/shared/model-resolution-types.d.ts +13 -0
- package/dist/shared/model-resolver.d.ts +10 -3
- package/dist/shared/model-settings-compatibility.d.ts +40 -0
- package/dist/shared/plugin-identity.d.ts +4 -3
- package/dist/shared/project-discovery-dirs.d.ts +4 -0
- package/dist/shared/session-prompt-params-helpers.d.ts +12 -0
- package/dist/shared/session-prompt-params-state.d.ts +9 -0
- package/dist/tools/delegate-task/background-task.d.ts +2 -6
- package/dist/tools/delegate-task/category-resolver.d.ts +2 -5
- package/dist/tools/delegate-task/model-selection.d.ts +2 -0
- package/dist/tools/delegate-task/subagent-resolver.d.ts +3 -6
- package/dist/tools/delegate-task/sync-prompt-sender.d.ts +2 -6
- package/dist/tools/delegate-task/sync-session-poller.d.ts +1 -0
- package/dist/tools/delegate-task/sync-task.d.ts +2 -6
- package/dist/tools/delegate-task/types.d.ts +3 -5
- package/dist/tools/delegate-task/unstable-agent-task.d.ts +2 -6
- package/package.json +14 -12
package/README.ja.md
CHANGED
|
@@ -168,7 +168,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
|
|
|
168
168
|
|
|
169
169
|
**Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) はあなたのメインのオーケストレーターです。計画を立て、専門家に委任し、攻撃的な並列実行でタスクを完了まで推進します。途中で投げ出すことはありません。
|
|
170
170
|
|
|
171
|
-
**Hephaestus** (`gpt-5.
|
|
171
|
+
**Hephaestus** (`gpt-5.4`) はあなたの自律的なディープワーカーです。レシピではなく、目標を与えてください。手取り足取り教えなくても、コードベースを探索し、パターンを研究し、端から端まで実行します。*正当なる職人 (The Legitimate Craftsman).*
|
|
172
172
|
|
|
173
173
|
**Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) はあなたの戦略プランナーです。インタビューモードで動作し、コードに触れる前に質問をしてスコープを特定し、詳細な計画を構築します。
|
|
174
174
|
|
|
@@ -176,7 +176,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
|
|
|
176
176
|
|
|
177
177
|
> Anthropicが[私たちのせいでOpenCodeをブロックしました。](https://x.com/thdxr/status/2010149530486911014) だからこそHephaestusは「正当なる職人 (The Legitimate Craftsman)」と呼ばれているのです。皮肉を込めています。
|
|
178
178
|
>
|
|
179
|
-
> Opusで最もよく動きますが、Kimi K2.5 + GPT-5.
|
|
179
|
+
> Opusで最もよく動きますが、Kimi K2.5 + GPT-5.4の組み合わせだけでも、バニラのClaude Codeを軽く凌駕します。設定は一切不要です。
|
|
180
180
|
|
|
181
181
|
### エージェントの��ーケストレーション
|
|
182
182
|
|
package/README.ko.md
CHANGED
|
@@ -162,7 +162,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
|
|
|
162
162
|
|
|
163
163
|
**Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**)는 당신의 메인 오케스트레이터입니다. 공격적인 병렬 실행으로 계획을 세우고, 전문가들에게 위임하며, 완료될 때까지 밀어붙입니다. 중간에 포기하는 법이 없습니다.
|
|
164
164
|
|
|
165
|
-
**Hephaestus** (`gpt-5.
|
|
165
|
+
**Hephaestus** (`gpt-5.4`)는 당신의 자율 딥 워커입니다. 레시피가 아니라 목표를 주세요. 베이비시터 없이 알아서 코드베이스를 탐색하고, 패턴을 연구하며, 끝에서 끝까지 전부 해냅니다. *진정한 장인(The Legitimate Craftsman).*
|
|
166
166
|
|
|
167
167
|
**Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**)는 당신의 전략 플래너입니다. 인터뷰 모드로 작동합니다. 코드 한 줄 만지기 전에 질문을 던져 스코프를 파악하고 상세한 계획부터 세웁니다.
|
|
168
168
|
|
|
@@ -170,7 +170,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
|
|
|
170
170
|
|
|
171
171
|
> Anthropic이 [우리 때문에 OpenCode를 막아버렸습니다.](https://x.com/thdxr/status/2010149530486911014) 그래서 Hephaestus의 별명이 "진정한 장인(The Legitimate Craftsman)"인 겁니다. (어디서 많이 들어본 이름이죠?) 아이러니를 노렸습니다.
|
|
172
172
|
>
|
|
173
|
-
> Opus에서 제일 잘 돌아가긴 하지만, Kimi K2.5 + GPT-5.
|
|
173
|
+
> Opus에서 제일 잘 돌아가긴 하지만, Kimi K2.5 + GPT-5.4 조합만으로도 바닐라 Claude Code는 가볍게 바릅니다. 설정도 필요 없습니다.
|
|
174
174
|
|
|
175
175
|
### 에이전트 오케스트레이션
|
|
176
176
|
|
package/README.md
CHANGED
|
@@ -164,7 +164,7 @@ Even only with following subscriptions, ultrawork will work well (this project i
|
|
|
164
164
|
|
|
165
165
|
**Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`** ) is your main orchestrator. He plans, delegates to specialists, and drives tasks to completion with aggressive parallel execution. He does not stop halfway.
|
|
166
166
|
|
|
167
|
-
**Hephaestus** (`gpt-5.
|
|
167
|
+
**Hephaestus** (`gpt-5.4`) is your autonomous deep worker. Give him a goal, not a recipe. He explores the codebase, researches patterns, and executes end-to-end without hand-holding. *The Legitimate Craftsman.*
|
|
168
168
|
|
|
169
169
|
**Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`** ) is your strategic planner. Interview mode: it questions, identifies scope, and builds a detailed plan before a single line of code is touched.
|
|
170
170
|
|
|
@@ -172,7 +172,7 @@ Every agent is tuned to its model's specific strengths. No manual model-juggling
|
|
|
172
172
|
|
|
173
173
|
> Anthropic [blocked OpenCode because of us.](https://x.com/thdxr/status/2010149530486911014) That's why Hephaestus is called "The Legitimate Craftsman." The irony is intentional.
|
|
174
174
|
>
|
|
175
|
-
> We run best on Opus, but Kimi K2.5 + GPT-5.
|
|
175
|
+
> We run best on Opus, but Kimi K2.5 + GPT-5.4 already beats vanilla Claude Code. Zero config needed.
|
|
176
176
|
|
|
177
177
|
### Agent Orchestration
|
|
178
178
|
|
package/README.ru.md
CHANGED
|
@@ -152,7 +152,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
|
|
|
152
152
|
|
|
153
153
|
**Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) — главный оркестратор. Он планирует, делегирует задачи специалистам и доводит их до завершения с агрессивным параллельным выполнением. Он не останавливается на полпути.
|
|
154
154
|
|
|
155
|
-
**Hephaestus** (`gpt-5.
|
|
155
|
+
**Hephaestus** (`gpt-5.4`) — автономный глубокий исполнитель. Дайте ему цель, а не рецепт. Он исследует кодовую базу, изучает паттерны и выполняет задачи сквозным образом без лишних подсказок. *Законный Мастер.*
|
|
156
156
|
|
|
157
157
|
**Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) — стратегический планировщик. Режим интервью: задаёт вопросы, определяет объём работ и формирует детальный план до того, как написана хотя бы одна строка кода.
|
|
158
158
|
|
|
@@ -160,7 +160,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
|
|
|
160
160
|
|
|
161
161
|
> Anthropic [заблокировал OpenCode из-за нас.](https://x.com/thdxr/status/2010149530486911014) Именно поэтому Hephaestus зовётся «Законным Мастером». Ирония намеренная.
|
|
162
162
|
>
|
|
163
|
-
> Мы работаем лучше всего на Opus, но Kimi K2.5 + GPT-5.
|
|
163
|
+
> Мы работаем лучше всего на Opus, но Kimi K2.5 + GPT-5.4 уже превосходят ванильный Claude Code. Никакой настройки не требуется.
|
|
164
164
|
|
|
165
165
|
### Оркестрация агентов
|
|
166
166
|
|
package/README.zh-cn.md
CHANGED
|
@@ -169,7 +169,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
|
|
|
169
169
|
|
|
170
170
|
**Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) 是你的主指挥官。他负责制定计划、分配任务给专家团队,并以极其激进的并行策略推动任务直至完成。他从不半途而废。
|
|
171
171
|
|
|
172
|
-
**Hephaestus** (`gpt-5.
|
|
172
|
+
**Hephaestus** (`gpt-5.4`) 是你的自主深度工作者。你只需要给他目标,不要给他具体做法。他会自动探索代码库模式,从头到尾独立执行任务,绝不会中途要你当保姆。*名副其实的正牌工匠。*
|
|
173
173
|
|
|
174
174
|
**Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) 是你的战略规划师。他通过访谈模式,在动一行代码之前,先通过提问确定范围并构建详尽的执行计划。
|
|
175
175
|
|
|
@@ -177,7 +177,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
|
|
|
177
177
|
|
|
178
178
|
> Anthropic [因为我们屏蔽了 OpenCode](https://x.com/thdxr/status/2010149530486911014)。这就是为什么我们将 Hephaestus 命名为“正牌工匠 (The Legitimate Craftsman)”。这是一个故意的讽刺。
|
|
179
179
|
>
|
|
180
|
-
> 我们在 Opus 上运行得最好,但仅仅使用 Kimi K2.5 + GPT-5.
|
|
180
|
+
> 我们在 Opus 上运行得最好,但仅仅使用 Kimi K2.5 + GPT-5.4 就足以碾压原版的 Claude Code。完全不需要配置。
|
|
181
181
|
|
|
182
182
|
### 智能体调度机制
|
|
183
183
|
|
package/dist/agents/types.d.ts
CHANGED
|
@@ -55,6 +55,7 @@ export interface AgentPromptMetadata {
|
|
|
55
55
|
export declare function isGptModel(model: string): boolean;
|
|
56
56
|
export declare function isGpt5_4Model(model: string): boolean;
|
|
57
57
|
export declare function isGpt5_3CodexModel(model: string): boolean;
|
|
58
|
+
export declare function isMiniMaxModel(model: string): boolean;
|
|
58
59
|
export declare function isGeminiModel(model: string): boolean;
|
|
59
60
|
export type BuiltinAgentName = "sisyphus" | "hephaestus" | "oracle" | "librarian" | "explore" | "multimodal-looker" | "metis" | "momus" | "atlas" | "sisyphus-junior";
|
|
60
61
|
export type OverridableAgentName = "build" | BuiltinAgentName;
|
|
@@ -62,6 +63,6 @@ export type AgentName = BuiltinAgentName;
|
|
|
62
63
|
export type AgentOverrideConfig = Partial<AgentConfig> & {
|
|
63
64
|
prompt_append?: string;
|
|
64
65
|
variant?: string;
|
|
65
|
-
fallback_models?: string | string[];
|
|
66
|
+
fallback_models?: string | (string | import("../config/schema/fallback-models").FallbackModelObject)[];
|
|
66
67
|
};
|
|
67
68
|
export type AgentOverrides = Partial<Record<OverridableAgentName, AgentOverrideConfig>>;
|
|
@@ -1,3 +1,4 @@
|
|
|
1
|
+
import type { ModelCapabilitiesDiagnostics } from "../../../shared/model-capabilities";
|
|
1
2
|
import type { ModelRequirement } from "../../../shared/model-requirements";
|
|
2
3
|
export interface AgentResolutionInfo {
|
|
3
4
|
name: string;
|
|
@@ -6,6 +7,7 @@ export interface AgentResolutionInfo {
|
|
|
6
7
|
userVariant?: string;
|
|
7
8
|
effectiveModel: string;
|
|
8
9
|
effectiveResolution: string;
|
|
10
|
+
capabilityDiagnostics?: ModelCapabilitiesDiagnostics;
|
|
9
11
|
}
|
|
10
12
|
export interface CategoryResolutionInfo {
|
|
11
13
|
name: string;
|
|
@@ -14,6 +16,7 @@ export interface CategoryResolutionInfo {
|
|
|
14
16
|
userVariant?: string;
|
|
15
17
|
effectiveModel: string;
|
|
16
18
|
effectiveResolution: string;
|
|
19
|
+
capabilityDiagnostics?: ModelCapabilitiesDiagnostics;
|
|
17
20
|
}
|
|
18
21
|
export interface ModelResolutionInfo {
|
|
19
22
|
agents: AgentResolutionInfo[];
|
|
@@ -1,6 +1,7 @@
|
|
|
1
|
-
import type { CheckResult } from "../types";
|
|
1
|
+
import type { CheckResult, DoctorIssue } from "../types";
|
|
2
2
|
import type { ModelResolutionInfo, OmoConfig } from "./model-resolution-types";
|
|
3
3
|
export declare function getModelResolutionInfo(): ModelResolutionInfo;
|
|
4
4
|
export declare function getModelResolutionInfoWithOverrides(config: OmoConfig): ModelResolutionInfo;
|
|
5
|
+
export declare function collectCapabilityResolutionIssues(info: ModelResolutionInfo): DoctorIssue[];
|
|
5
6
|
export declare function checkModels(): Promise<CheckResult>;
|
|
6
7
|
export declare const checkModelResolution: typeof checkModels;
|
|
@@ -25,5 +25,5 @@ export declare const EXIT_CODES: {
|
|
|
25
25
|
readonly FAILURE: 1;
|
|
26
26
|
};
|
|
27
27
|
export declare const MIN_OPENCODE_VERSION = "1.0.150";
|
|
28
|
-
export declare const PACKAGE_NAME = "oh-my-
|
|
28
|
+
export declare const PACKAGE_NAME = "oh-my-openagent";
|
|
29
29
|
export declare const OPENCODE_BINARIES: readonly ["opencode", "opencode-desktop"];
|