feat: remove hardcoded default models from integrations (#670)
* feat(openclaw): remove hardcoded default models, rely on Hindsight API defaults * feat(claude-code): remove hardcoded default models, rely on Hindsight API defaults * feat(claude-code,docs): remove hardcoded default models from claude-code integration and docs * feat: use claude-haiku-4-5 as default Anthropic model
This commit is contained in:
Nicolò Boschi
GitHub
parent
4f533dde94
commit
58e68f3e4a
5 changed files with 52 additions and 50 deletions
|
|
@ -354,7 +354,7 @@ DEFAULT_LLM_PROVIDER = "openai"
|
|||
# Provider-specific default models
|
||||
PROVIDER_DEFAULT_MODELS = {
|
||||
"openai": "gpt-4o-mini",
|
||||
"anthropic": "claude-haiku-4-5-20251001",
|
||||
"anthropic": "claude-haiku-4-5",
|
||||
"gemini": "gemini-2.5-flash",
|
||||
"groq": "openai/gpt-oss-120b",
|
||||
"minimax": "MiniMax-M2.7",
|
||||
|
|
|
|||
|
|
@ -74,13 +74,15 @@ The plugin automatically starts and stops `hindsight-embed` via `uvx`. Requires
|
|||
|
||||
Set an LLM provider:
|
||||
```bash
|
||||
export OPENAI_API_KEY="sk-your-key" # Auto-detected, uses gpt-4o-mini
|
||||
export OPENAI_API_KEY="sk-your-key"
|
||||
# or
|
||||
export ANTHROPIC_API_KEY="your-key" # Auto-detected, uses claude-3-5-haiku
|
||||
export ANTHROPIC_API_KEY="your-key"
|
||||
# or
|
||||
export HINDSIGHT_LLM_PROVIDER=claude-code # No API key needed
|
||||
```
|
||||
|
||||
The model is selected automatically by the Hindsight API. To override, set `HINDSIGHT_API_LLM_MODEL`.
|
||||
|
||||
### 3. Existing Local Server
|
||||
|
||||
If you already have `hindsight-embed` running, leave `hindsightApiUrl` empty and set `apiPort` to match your server's port. The plugin will detect it automatically.
|
||||
|
|
|
|||
|
|
@ -17,22 +17,22 @@ This plugin integrates [hindsight-embed](https://vectorize.io/hindsight/cli), a
|
|||
Choose one provider and set its API key:
|
||||
|
||||
```bash
|
||||
# Option A: OpenAI (uses gpt-4o-mini for memory extraction)
|
||||
# Option A: OpenAI
|
||||
export OPENAI_API_KEY="sk-your-key"
|
||||
|
||||
# Option B: Anthropic (uses claude-3-5-haiku for memory extraction)
|
||||
# Option B: Anthropic
|
||||
export ANTHROPIC_API_KEY="your-key"
|
||||
|
||||
# Option C: Gemini (uses gemini-2.5-flash for memory extraction)
|
||||
# Option C: Gemini
|
||||
export GEMINI_API_KEY="your-key"
|
||||
|
||||
# Option D: Groq (uses openai/gpt-oss-20b for memory extraction)
|
||||
# Option D: Groq
|
||||
export GROQ_API_KEY="your-key"
|
||||
|
||||
# Option E: Claude Code (uses claude-sonnet-4-20250514, no API key needed)
|
||||
# Option E: Claude Code (no API key needed)
|
||||
export HINDSIGHT_API_LLM_PROVIDER=claude-code
|
||||
|
||||
# Option F: OpenAI Codex (uses gpt-4o-mini, no API key needed)
|
||||
# Option F: OpenAI Codex (no API key needed)
|
||||
export HINDSIGHT_API_LLM_PROVIDER=openai-codex
|
||||
```
|
||||
|
||||
|
|
@ -161,20 +161,21 @@ By default, the plugin retains `user` and `assistant` messages after each turn.
|
|||
|
||||
The plugin auto-detects your LLM provider from these environment variables:
|
||||
|
||||
| Provider | Env Var | Default Model | Notes |
|
||||
|----------|---------|---------------|-------|
|
||||
| OpenAI | `OPENAI_API_KEY` | `gpt-4o-mini` | |
|
||||
| Anthropic | `ANTHROPIC_API_KEY` | `claude-3-5-haiku-20241022` | |
|
||||
| Gemini | `GEMINI_API_KEY` | `gemini-2.5-flash` | |
|
||||
| Groq | `GROQ_API_KEY` | `openai/gpt-oss-20b` | |
|
||||
| Claude Code | `HINDSIGHT_API_LLM_PROVIDER=claude-code` | `claude-sonnet-4-20250514` | No API key needed |
|
||||
| OpenAI Codex | `HINDSIGHT_API_LLM_PROVIDER=openai-codex` | `gpt-4o-mini` | No API key needed |
|
||||
| Provider | Env Var | Notes |
|
||||
|----------|---------|-------|
|
||||
| OpenAI | `OPENAI_API_KEY` | |
|
||||
| Anthropic | `ANTHROPIC_API_KEY` | |
|
||||
| Gemini | `GEMINI_API_KEY` | |
|
||||
| Groq | `GROQ_API_KEY` | |
|
||||
| Claude Code | `HINDSIGHT_API_LLM_PROVIDER=claude-code` | No API key needed |
|
||||
| OpenAI Codex | `HINDSIGHT_API_LLM_PROVIDER=openai-codex` | No API key needed |
|
||||
|
||||
The model is selected automatically by the Hindsight API. To override, set `HINDSIGHT_API_LLM_MODEL`.
|
||||
|
||||
**Override with explicit config:**
|
||||
|
||||
```bash
|
||||
export HINDSIGHT_API_LLM_PROVIDER=openai
|
||||
export HINDSIGHT_API_LLM_MODEL=gpt-4o-mini
|
||||
export HINDSIGHT_API_LLM_API_KEY=sk-your-key
|
||||
|
||||
# Optional: custom base URL (OpenRouter, Azure, vLLM, etc.)
|
||||
|
|
|
|||
|
|
@ -16,13 +16,13 @@ import os
|
|||
|
||||
# Provider detection table — same order as Openclaw
|
||||
PROVIDER_DETECTION = [
|
||||
{"name": "openai", "key_env": "OPENAI_API_KEY", "default_model": "gpt-4o-mini"},
|
||||
{"name": "anthropic", "key_env": "ANTHROPIC_API_KEY", "default_model": "claude-3-5-haiku-20241022"},
|
||||
{"name": "gemini", "key_env": "GEMINI_API_KEY", "default_model": "gemini-2.5-flash"},
|
||||
{"name": "groq", "key_env": "GROQ_API_KEY", "default_model": "openai/gpt-oss-20b"},
|
||||
{"name": "ollama", "key_env": "", "default_model": "llama3.2"},
|
||||
{"name": "openai-codex", "key_env": "", "default_model": "gpt-5.2-codex"},
|
||||
{"name": "claude-code", "key_env": "", "default_model": "claude-sonnet-4-5-20250929"},
|
||||
{"name": "openai", "key_env": "OPENAI_API_KEY"},
|
||||
{"name": "anthropic", "key_env": "ANTHROPIC_API_KEY"},
|
||||
{"name": "gemini", "key_env": "GEMINI_API_KEY"},
|
||||
{"name": "groq", "key_env": "GROQ_API_KEY"},
|
||||
{"name": "ollama", "key_env": ""},
|
||||
{"name": "openai-codex", "key_env": ""},
|
||||
{"name": "claude-code", "key_env": ""},
|
||||
]
|
||||
|
||||
# Providers that don't require an API key
|
||||
|
|
@ -59,7 +59,7 @@ def detect_llm_config(config: dict) -> dict:
|
|||
return {
|
||||
"provider": override_provider,
|
||||
"api_key": override_key or "",
|
||||
"model": override_model or (pinfo["default_model"] if pinfo else None),
|
||||
"model": override_model,
|
||||
"base_url": override_base_url,
|
||||
"source": "HINDSIGHT_API_LLM_PROVIDER override",
|
||||
}
|
||||
|
|
@ -83,7 +83,7 @@ def detect_llm_config(config: dict) -> dict:
|
|||
return {
|
||||
"provider": cfg_provider,
|
||||
"api_key": api_key,
|
||||
"model": config.get("llmModel") or override_model or (pinfo["default_model"] if pinfo else None),
|
||||
"model": config.get("llmModel") or override_model,
|
||||
"base_url": override_base_url,
|
||||
"source": "plugin config",
|
||||
}
|
||||
|
|
@ -99,7 +99,7 @@ def detect_llm_config(config: dict) -> dict:
|
|||
return {
|
||||
"provider": pinfo["name"],
|
||||
"api_key": api_key,
|
||||
"model": override_model or pinfo["default_model"],
|
||||
"model": override_model,
|
||||
"base_url": override_base_url,
|
||||
"source": f"auto-detected from {pinfo['key_env']}",
|
||||
}
|
||||
|
|
@ -117,13 +117,14 @@ def detect_llm_config(config: dict) -> dict:
|
|||
raise RuntimeError(
|
||||
"No LLM configuration found for Hindsight.\n\n"
|
||||
"Option 1: Set a standard provider API key (auto-detect):\n"
|
||||
" export OPENAI_API_KEY=sk-your-key # Uses gpt-4o-mini\n"
|
||||
" export ANTHROPIC_API_KEY=your-key # Uses claude-3-5-haiku\n\n"
|
||||
" export OPENAI_API_KEY=sk-your-key\n"
|
||||
" export ANTHROPIC_API_KEY=your-key\n\n"
|
||||
"Option 2: Override with Hindsight-specific env vars:\n"
|
||||
" export HINDSIGHT_API_LLM_PROVIDER=openai\n"
|
||||
" export HINDSIGHT_API_LLM_API_KEY=sk-your-key\n\n"
|
||||
"Option 3: Use an external Hindsight API (server-side LLM):\n"
|
||||
" Set hindsightApiUrl in settings.json or HINDSIGHT_API_URL env var"
|
||||
" Set hindsightApiUrl in settings.json or HINDSIGHT_API_URL env var\n\n"
|
||||
"The model will be selected automatically by Hindsight. To override: export HINDSIGHT_API_LLM_MODEL=your-model"
|
||||
)
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -496,13 +496,13 @@ export function formatMemories(results: MemoryResult[]): string {
|
|||
|
||||
// Provider detection from standard env vars
|
||||
const PROVIDER_DETECTION = [
|
||||
{ name: 'openai', keyEnv: 'OPENAI_API_KEY', defaultModel: 'gpt-4o-mini' },
|
||||
{ name: 'anthropic', keyEnv: 'ANTHROPIC_API_KEY', defaultModel: 'claude-3-5-haiku-20241022' },
|
||||
{ name: 'gemini', keyEnv: 'GEMINI_API_KEY', defaultModel: 'gemini-2.5-flash' },
|
||||
{ name: 'groq', keyEnv: 'GROQ_API_KEY', defaultModel: 'openai/gpt-oss-20b' },
|
||||
{ name: 'ollama', keyEnv: '', defaultModel: 'llama3.2' },
|
||||
{ name: 'openai-codex', keyEnv: '', defaultModel: 'gpt-5.2-codex' },
|
||||
{ name: 'claude-code', keyEnv: '', defaultModel: 'claude-sonnet-4-5-20250929' },
|
||||
{ name: 'openai', keyEnv: 'OPENAI_API_KEY' },
|
||||
{ name: 'anthropic', keyEnv: 'ANTHROPIC_API_KEY' },
|
||||
{ name: 'gemini', keyEnv: 'GEMINI_API_KEY' },
|
||||
{ name: 'groq', keyEnv: 'GROQ_API_KEY' },
|
||||
{ name: 'ollama', keyEnv: '' },
|
||||
{ name: 'openai-codex', keyEnv: '' },
|
||||
{ name: 'claude-code', keyEnv: '' },
|
||||
];
|
||||
|
||||
function detectLLMConfig(pluginConfig?: PluginConfig): {
|
||||
|
|
@ -529,11 +529,10 @@ function detectLLMConfig(pluginConfig?: PluginConfig): {
|
|||
);
|
||||
}
|
||||
|
||||
const providerInfo = PROVIDER_DETECTION.find(p => p.name === overrideProvider);
|
||||
return {
|
||||
provider: overrideProvider,
|
||||
apiKey: overrideKey || '',
|
||||
model: overrideModel || (providerInfo?.defaultModel),
|
||||
model: overrideModel,
|
||||
baseUrl: overrideBaseUrl,
|
||||
source: 'HINDSIGHT_API_LLM_PROVIDER override',
|
||||
};
|
||||
|
|
@ -565,7 +564,7 @@ function detectLLMConfig(pluginConfig?: PluginConfig): {
|
|||
return {
|
||||
provider: pluginConfig.llmProvider,
|
||||
apiKey,
|
||||
model: pluginConfig.llmModel || overrideModel || providerInfo?.defaultModel,
|
||||
model: pluginConfig.llmModel || overrideModel,
|
||||
baseUrl: overrideBaseUrl,
|
||||
source: 'plugin config',
|
||||
};
|
||||
|
|
@ -585,8 +584,8 @@ function detectLLMConfig(pluginConfig?: PluginConfig): {
|
|||
return {
|
||||
provider: providerInfo.name,
|
||||
apiKey,
|
||||
model: overrideModel || providerInfo.defaultModel,
|
||||
baseUrl: overrideBaseUrl, // Only use explicit HINDSIGHT_API_LLM_BASE_URL
|
||||
model: overrideModel,
|
||||
baseUrl: overrideBaseUrl,
|
||||
source: `auto-detected from ${providerInfo.keyEnv}`,
|
||||
};
|
||||
}
|
||||
|
|
@ -609,21 +608,20 @@ function detectLLMConfig(pluginConfig?: PluginConfig): {
|
|||
throw new Error(
|
||||
`No LLM configuration found for Hindsight memory plugin.\n\n` +
|
||||
`Option 1: Set a standard provider API key (auto-detect):\n` +
|
||||
` export OPENAI_API_KEY=sk-your-key # Uses gpt-4o-mini\n` +
|
||||
` export ANTHROPIC_API_KEY=your-key # Uses claude-3-5-haiku\n` +
|
||||
` export GEMINI_API_KEY=your-key # Uses gemini-2.5-flash\n` +
|
||||
` export GROQ_API_KEY=your-key # Uses openai/gpt-oss-20b\n\n` +
|
||||
` export OPENAI_API_KEY=sk-your-key\n` +
|
||||
` export ANTHROPIC_API_KEY=your-key\n` +
|
||||
` export GEMINI_API_KEY=your-key\n` +
|
||||
` export GROQ_API_KEY=your-key\n\n` +
|
||||
`Option 2: Use Codex or Claude Code (no API key needed):\n` +
|
||||
` export HINDSIGHT_API_LLM_PROVIDER=openai-codex # Requires 'codex auth login'\n` +
|
||||
` export HINDSIGHT_API_LLM_PROVIDER=claude-code # Requires Claude Code CLI\n\n` +
|
||||
`Option 3: Set llmProvider in openclaw.json plugin config:\n` +
|
||||
` "llmProvider": "openai", "llmModel": "gpt-4o-mini"\n\n` +
|
||||
` "llmProvider": "openai"\n\n` +
|
||||
`Option 4: Override with Hindsight-specific env vars:\n` +
|
||||
` export HINDSIGHT_API_LLM_PROVIDER=openai\n` +
|
||||
` export HINDSIGHT_API_LLM_MODEL=gpt-4o-mini\n` +
|
||||
` export HINDSIGHT_API_LLM_API_KEY=sk-your-key\n` +
|
||||
` export HINDSIGHT_API_LLM_BASE_URL=https://openrouter.ai/api/v1 # Optional\n\n` +
|
||||
`Tip: Use a cheap/fast model for memory extraction (e.g., gpt-4o-mini, claude-3-5-haiku, or free models on OpenRouter)`
|
||||
`The model will be selected automatically by Hindsight. To override: export HINDSIGHT_API_LLM_MODEL=your-model`
|
||||
);
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue