Alvin Unreal 3 mesi fa
parent
commit
7492a9ee4e

+ 11 - 4
README.md

@@ -23,12 +23,20 @@ To explore the agents themselves, see **[Meet the Pantheon](#meet-the-pantheon)*
 
 ### Quick Start
 
+Copy and paste this prompt to your LLM agent (Claude Code, AmpCode, Cursor, etc.):
+
+
+```
+Install and configure oh-my-opencode-slim: https://raw.githubusercontent.com/alvinunreal/oh-my-opencode-slim/refs/heads/master/README.md
+```
+
+
+### Manual Installation
+
 ```bash
 bunx oh-my-opencode-slim@latest install
 ```
 
-For bug reports and feature requests, use GitHub Issues. For setup questions, troubleshooting, or general support, use the Telegram channel linked above.
-
 ### Getting Started
 
 The installer generates an OpenAI preset by default, using `openai/gpt-5.4` for the higher-judgment agents and `openai/gpt-5.4-mini` for the faster scoped agents.
@@ -73,7 +81,7 @@ The default generated configuration looks like this:
 
 ### For Alternative Providers
 
-To use Kimi, GitHub Copilot, ZAI Coding Plan, or a mixed-provider setup, see **[Provider Configurations](docs/provider-configurations.md)** for step-by-step config examples. If you want a ready-made starting point, check the **[Author's Preset](docs/authors-preset.md)** and **[$30 Preset](docs/thirty-dollars-preset.md)** - the `$30` preset is the best cheap setup.
+To use Kimi, GitHub Copilot, ZAI Coding Plan, or a mixed-provider setup, use **[Configuration](docs/configuration.md)** for the full reference. If you want a ready-made starting point, check the **[Author's Preset](docs/authors-preset.md)** and **[$30 Preset](docs/thirty-dollars-preset.md)** - the `$30` preset is the best cheap setup.
 
 You can also mix and match any models per agent. For model suggestions, see the **Recommended Models** listed under each agent below.
 
@@ -446,7 +454,6 @@ Use this section as a map: start with installation, then jump to features, confi
 | Doc | What it covers |
 |-----|----------------|
 | **[Installation Guide](docs/installation.md)** | Install the plugin, use CLI flags, reset config, and troubleshoot setup |
-| **[Provider Configurations](docs/provider-configurations.md)** | Configure OpenAI, Kimi, GitHub Copilot, ZAI, Fireworks AI, or mixed-provider presets |
 
 <a id="features-and-workflows"></a>
 

+ 2 - 2
docs/installation.md

@@ -56,7 +56,7 @@ bunx oh-my-opencode-slim@latest install --reset
 
 ### After Installation
 
-The installer generates an OpenAI configuration by default (using `gpt-5.4` and `gpt-5.4-mini` models). To use alternative providers like Kimi, GitHub Copilot, or ZAI Coding Plan, see **[Provider Configurations](provider-configurations.md)** for step-by-step instructions.
+The installer generates an OpenAI configuration by default (using `gpt-5.4` and `gpt-5.4-mini` models). To switch providers or build a mixed setup, use **[Configuration Reference](configuration.md)** for the full option reference and the preset docs for copyable examples.
 
 Then:
 
@@ -153,7 +153,7 @@ Verify all agents respond successfully.
 
 **Crucial Advice for the User:**
 - They can easily assign **different models to different agents** by editing `~/.config/opencode/oh-my-opencode-slim.json` (or `.jsonc`).
-- If they want to add a different provider later (Kimi, GitHub Copilot, ZAI), they can update this file manually. See **[Provider Configurations](provider-configurations.md)** for examples.
+- If they want to add a different provider later (Kimi, GitHub Copilot, ZAI), they can update this file manually. See **[Configuration Reference](configuration.md)** and the preset docs for examples.
 - Read the generated `~/.config/opencode/oh-my-opencode-slim.json` (or `.jsonc`) file to understand the current configuration.
 
 ---

+ 0 - 247
docs/provider-configurations.md

@@ -1,247 +0,0 @@
-# Provider Configurations
-
-oh-my-opencode-slim uses **OpenAI** as the default provider. This document shows how to configure alternative providers by editing your plugin config file.
-
-## Config File Location
-
-Edit `~/.config/opencode/oh-my-opencode-slim.json` (or `.jsonc` for comments support).
-
-## Default: OpenAI
-
-The installer generates this configuration automatically:
-
-```json
-{
-  "preset": "openai",
-  "presets": {
-    "openai": {
-      "orchestrator": { "model": "openai/gpt-5.4", "variant": "high", "skills": ["*"], "mcps": ["*", "!context7"] },
-      "oracle": { "model": "openai/gpt-5.4", "variant": "high", "skills": ["simplify"], "mcps": [] },
-      "librarian": { "model": "openai/gpt-5.4-mini", "variant": "low", "skills": [], "mcps": ["websearch", "context7", "grep_app"] },
-      "explorer": { "model": "openai/gpt-5.4-mini", "variant": "low", "skills": ["cartography"], "mcps": [] },
-      "designer": { "model": "openai/gpt-5.4-mini", "variant": "medium", "skills": ["agent-browser"], "mcps": [] },
-      "fixer": { "model": "openai/gpt-5.4-mini", "variant": "low", "skills": [], "mcps": [] }
-    }
-  }
-}
-```
-
-## Kimi For Coding
-
-To use Kimi, add a `kimi` preset and set it as active:
-
-```json
-{
-  "preset": "kimi",
-  "presets": {
-    "kimi": {
-      "orchestrator": { "model": "kimi-for-coding/k2p5", "variant": "high", "skills": ["*"], "mcps": ["*", "!context7"] },
-      "oracle": { "model": "kimi-for-coding/k2p5", "variant": "high", "skills": ["simplify"], "mcps": [] },
-      "librarian": { "model": "kimi-for-coding/k2p5", "variant": "low", "skills": [], "mcps": ["websearch", "context7", "grep_app"] },
-      "explorer": { "model": "kimi-for-coding/k2p5", "variant": "low", "skills": ["cartography"], "mcps": [] },
-      "designer": { "model": "kimi-for-coding/k2p5", "variant": "medium", "skills": ["agent-browser"], "mcps": [] },
-      "fixer": { "model": "kimi-for-coding/k2p5", "variant": "low", "skills": [], "mcps": [] }
-    }
-  }
-}
-```
-
-Then authenticate:
-```bash
-opencode auth login
-# Select "Kimi For Coding" provider
-```
-
-## GitHub Copilot
-
-To use GitHub Copilot with Grok Code Fast:
-
-```json
-{
-  "preset": "copilot",
-  "presets": {
-    "copilot": {
-      "orchestrator": { "model": "github-copilot/claude-opus-4.6", "variant": "high", "skills": ["*"], "mcps": ["*", "!context7"] },
-      "oracle": { "model": "github-copilot/claude-opus-4.6", "variant": "high", "skills": ["simplify"], "mcps": [] },
-      "librarian": { "model": "github-copilot/grok-code-fast-1", "variant": "low", "skills": [], "mcps": ["websearch", "context7", "grep_app"] },
-      "explorer": { "model": "github-copilot/grok-code-fast-1", "variant": "low", "skills": ["cartography"], "mcps": [] },
-      "designer": { "model": "github-copilot/gemini-3.1-pro-preview", "variant": "medium", "skills": ["agent-browser"], "mcps": [] },
-      "fixer": { "model": "github-copilot/claude-sonnet-4.6", "variant": "low", "skills": [], "mcps": [] }
-    }
-  }
-}
-```
-
-Then authenticate:
-```bash
-opencode auth login
-# Select "github-copilot" provider
-```
-
-## ZAI Coding Plan
-
-To use ZAI Coding Plan with GLM 5:
-
-```json
-{
-  "preset": "zai-plan",
-  "presets": {
-    "zai-plan": {
-      "orchestrator": { "model": "zai-coding-plan/glm-5", "variant": "high", "skills": ["*"], "mcps": ["*", "!context7"] },
-      "oracle": { "model": "zai-coding-plan/glm-5", "variant": "high", "skills": ["simplify"], "mcps": [] },
-      "librarian": { "model": "zai-coding-plan/glm-5", "variant": "low", "skills": [], "mcps": ["websearch", "context7", "grep_app"] },
-      "explorer": { "model": "zai-coding-plan/glm-5", "variant": "low", "skills": ["cartography"], "mcps": [] },
-      "designer": { "model": "zai-coding-plan/glm-5", "variant": "medium", "skills": ["agent-browser"], "mcps": [] },
-      "fixer": { "model": "zai-coding-plan/glm-5", "variant": "low", "skills": [], "mcps": [] }
-    }
-  }
-}
-```
-
-Then authenticate:
-```bash
-opencode auth login
-# Select "zai-coding-plan" provider
-```
-
-## Mixing Providers
-
-You can mix models from different providers across agents. Create a custom preset:
-
-```json
-{
-  "preset": "my-mix",
-  "presets": {
-    "my-mix": {
-      "orchestrator": { "model": "openai/gpt-5.4", "skills": ["*"], "mcps": ["*", "!context7"] },
-      "oracle": { "model": "openai/gpt-5.4", "variant": "high", "skills": ["simplify"], "mcps": [] },
-      "librarian": { "model": "kimi-for-coding/k2p5", "variant": "low", "skills": [], "mcps": ["websearch", "context7", "grep_app"] },
-      "explorer": { "model": "github-copilot/grok-code-fast-1", "variant": "low", "skills": ["cartography"], "mcps": [] },
-      "designer": { "model": "kimi-for-coding/k2p5", "variant": "medium", "skills": ["agent-browser"], "mcps": [] },
-      "fixer": { "model": "openai/gpt-5.4-mini", "variant": "low", "skills": [], "mcps": [] }
-    }
-  }
-}
-```
-
-## Switching Presets
-
-**Method 1: Edit the config file** — Change the `preset` field to match a key in your `presets` object.
-
-**Method 2: Environment variable** (takes precedence over config file):
-```bash
-export OH_MY_OPENCODE_SLIM_PRESET=my-mix
-opencode
-```
-
----
-
-## Fallback / Failover
-
-The plugin can automatically fail over from one model to the next when a prompt times out or errors. This is separate from your preset selection — it's a runtime safety net.
-
-**How it works:**
-
-- Each agent can have a fallback chain under `fallback.chains.<agent>`
-- The agent uses its configured model first
-- If that model fails or times out, the manager aborts the session, waits briefly, and tries the next model in the chain
-- Duplicate model IDs are ignored — the same model is never retried twice
-- If fallback is disabled, tasks run with no failover
-
-**Example:**
-
-```jsonc
-{
-  "fallback": {
-    "enabled": true,
-    "timeoutMs": 15000,
-    "retryDelayMs": 500,
-    "chains": {
-      "orchestrator": [
-        "openai/gpt-5.4",
-        "anthropic/claude-sonnet-4-6",
-        "google/gemini-3.1-pro"
-      ],
-      "fixer": [
-        "fireworks-ai/accounts/fireworks/routers/kimi-k2p5-turbo",
-        "openai/gpt-5.4-mini"
-      ]
-    }
-  }
-}
-```
-
-**Notes:**
-- Model IDs must use `provider/model` format
-- Chains are per agent: `orchestrator`, `oracle`, `designer`, `explorer`, `librarian`, `fixer`, `councillor`, `council-master`
-- If an agent has no chain configured, only its primary model is used
-
----
-
-## Provider-Specific Options
-
-You can pass provider-specific model parameters via the `options` field on any agent config. These are forwarded directly to the AI SDK's `providerOptions` and affect model behavior at the API level.
-
-### OpenAI — Concise Responses
-
-```jsonc
-{
-  "presets": {
-    "openai": {
-      "oracle": {
-        "model": "openai/gpt-5.4",
-        "options": {
-          "textVerbosity": "low"  // "low" | "medium" | "high"
-        }
-      }
-    }
-  }
-}
-```
-
-### Anthropic — Extended Thinking
-
-```jsonc
-{
-  "presets": {
-    "anthropic": {
-      "oracle": {
-        "model": "anthropic/claude-sonnet-4-6",
-        "options": {
-          "thinking": {
-            "type": "enabled",
-            "budgetTokens": 16000
-          }
-        }
-      }
-    }
-  }
-}
-```
-
-### Google — Thinking Budget
-
-```jsonc
-{
-  "presets": {
-    "google": {
-      "oracle": {
-        "model": "google/gemini-3.1-pro",
-        "options": {
-          "thinkingConfig": {
-            "includeThoughts": true,
-            "thinkingBudget": 16000
-          }
-        }
-      }
-    }
-  }
-}
-```
-
-**Notes:**
-- `options` works per-agent and per-preset, just like `model` and `variant`
-- Options are **static** — they don't swap when fallback chains switch providers
-- Provider-specific keys are namespaced by the SDK, so OpenAI options are safely ignored by Anthropic and vice versa
-- Options from presets and root config are deep-merged (root keys override preset keys)
-- Nested objects in options are recursively merged by key — to fully replace a nested object (e.g., disable a preset's `thinking` config), set all subkeys explicitly

+ 0 - 1
docs/quick-reference.md

@@ -7,7 +7,6 @@
 | Doc | Contents |
 |-----|----------|
 | [Installation Guide](installation.md) | CLI flags, `--reset`, auth, troubleshooting |
-| [Provider Configurations](provider-configurations.md) | OpenAI, Kimi, Copilot, ZAI, Fireworks AI, mixing providers, fallback chains |
 
 ## ✨ Features
 

+ 2 - 2
docs/thirty-dollars-preset.md

@@ -12,7 +12,7 @@ It uses Codex Plus for the OpenAI models and GitHub Copilot for the premium coun
 {
     "preset": "thirtydollars",
     "presets": {
-      "best": { "orchestrator": { "model": "openai/gpt-5.4", "skills": [ "*" ], "mcps": [ "*", "websearch"] },
+      "thirtydollars": { "orchestrator": { "model": "openai/gpt-5.4", "skills": [ "*" ], "mcps": [ "*", "websearch"] },
         "oracle": { "model": "openai/gpt-5.4", "variant": "high", "skills": [], "mcps": [] },
         "librarian": { "model": "openai/gpt-5.4-mini", "variant": "low", "skills": [], "mcps": [ "websearch", "context7", "grep_app" ] },
         "explorer": { "model": "openai/gpt-5.4-mini", "variant": "low", "skills": [], "mcps": [] },
@@ -24,7 +24,7 @@ It uses Codex Plus for the OpenAI models and GitHub Copilot for the premium coun
       "master": { "model": "openai/gpt-5.4" },
       "presets": {
         "default": {
-          "alpha":  { "model": "github-copilot/claude-opus-4.6" },
+          "alpha":  { "model": "github-copilot/claude-sonnet-4.6" },
           "beta": { "model": "github-copilot/gemini-3.1-pro-preview" },
           "gamma": { "model": "openai/gpt-5.4" }
         }

+ 0 - 11
oh-my-opencode-slim.schema.json

@@ -435,17 +435,6 @@
         }
       }
     },
-    "background": {
-      "type": "object",
-      "properties": {
-        "maxConcurrentStarts": {
-          "default": 10,
-          "type": "number",
-          "minimum": 1,
-          "maximum": 50
-        }
-      }
-    },
     "interview": {
       "type": "object",
       "properties": {

+ 1 - 1
src/cli/index.ts

@@ -40,7 +40,7 @@ Options:
   -h, --help             Show this help message
 
 The installer generates an OpenAI configuration by default.
-For alternative providers, see docs/provider-configurations.md.
+For the full config reference, see docs/configuration.md.
 
 Examples:
   bunx oh-my-opencode-slim install

+ 3 - 4
src/cli/install.ts

@@ -241,12 +241,11 @@ async function runInstall(config: InstallConfig): Promise<number> {
   const modelsInfo =
     'Default configuration uses OpenAI models (gpt-5.4 / gpt-5.4-mini).';
   console.log(`${modelsInfo}`);
-  const altProviders =
-    'For alternative providers (Kimi, GitHub Copilot, ZAI Coding Plan)';
-  console.log(`${altProviders}, see:`);
+  const altProviders = 'For the full configuration reference, see:';
+  console.log(altProviders);
   const docsUrl =
     'https://github.com/alvinunreal/oh-my-opencode-slim/' +
-    'blob/master/docs/provider-configurations.md';
+    'blob/master/docs/configuration.md';
   console.log(`  ${BLUE}${docsUrl}${RESET}`);
   console.log();