holetron-lab/fleet-memory
1
0
Fork 0
Code Releases Packages Activity Actions

feat: switch default model to gpt-4o-mini (#410)

Browse source
This commit is contained in:
Nicolò Boschi 2026-02-19 18:43:52 +01:00 committed by GitHub
parent 0758827d39
commit 325b5cc141
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
28 changed files with 89 additions and 112 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.env.example
View file

@ -5,7 +5,7 @@
# Supported providers: openai, groq, ollama, gemini, anthropic, lmstudio, vertexai
HINDSIGHT_API_LLM_PROVIDER=openai
HINDSIGHT_API_LLM_API_KEY=your-api-key-here
HINDSIGHT_API_LLM_MODEL=o3-mini
HINDSIGHT_API_LLM_MODEL=gpt-4o-mini
HINDSIGHT_API_LLM_BASE_URL=https://api.openai.com/v1
# Example: Anthropic Claude configuration

103
.github/workflows/test.yml vendored
View file

@ -171,10 +171,9 @@ jobs:
test-rust-cli:
runs-on: ubuntu-latest
env:
HINDSIGHT_API_LLM_PROVIDER: groq
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
HINDSIGHT_API_LLM_PROVIDER: openai
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
HINDSIGHT_API_URL: http://localhost:8888
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
UV_INDEX: pytorch=https://download.pytorch.org/whl/cpu
@ -234,7 +233,6 @@ jobs:
HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
EOF
- name: Start API server
@ -345,7 +343,9 @@ jobs:
- name: Smoke test - verify container starts
if: matrix.variant == 'slim'
env:
GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
HINDSIGHT_API_LLM_PROVIDER: openai
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
HINDSIGHT_API_EMBEDDINGS_PROVIDER: openai
HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HINDSIGHT_API_RERANKER_PROVIDER: cohere
@ -355,15 +355,13 @@ jobs:
test-api:
runs-on: ubuntu-latest
env:
HINDSIGHT_API_LLM_PROVIDER: groq
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
HINDSIGHT_API_LLM_PROVIDER: openai
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Prefer CPU-only PyTorch in CI (but keep PyPI for everything else)
UV_INDEX: pytorch=https://download.pytorch.org/whl/cpu
@ -417,10 +415,9 @@ jobs:
test-python-client:
runs-on: ubuntu-latest
env:
HINDSIGHT_API_LLM_PROVIDER: groq
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
HINDSIGHT_API_LLM_PROVIDER: openai
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
HINDSIGHT_API_URL: http://localhost:8888
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Prefer CPU-only PyTorch in CI (but keep PyPI for everything else)
@ -462,7 +459,6 @@ jobs:
HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
EOF
- name: Start API server
@ -495,10 +491,9 @@ jobs:
test-typescript-client:
runs-on: ubuntu-latest
env:
HINDSIGHT_API_LLM_PROVIDER: groq
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
HINDSIGHT_API_LLM_PROVIDER: openai
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
HINDSIGHT_API_URL: http://localhost:8888
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Prefer CPU-only PyTorch in CI (but keep PyPI for everything else)
@ -545,7 +540,6 @@ jobs:
HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
EOF
- name: Start API server
@ -578,10 +572,9 @@ jobs:
test-rust-client:
runs-on: ubuntu-latest
env:
HINDSIGHT_API_LLM_PROVIDER: groq
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
HINDSIGHT_API_LLM_PROVIDER: openai
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
HINDSIGHT_API_URL: http://localhost:8888
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Prefer CPU-only PyTorch in CI (but keep PyPI for everything else)
@ -627,7 +620,6 @@ jobs:
HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
EOF
- name: Start API server
@ -660,10 +652,9 @@ jobs:
test-go-client:
runs-on: ubuntu-latest
env:
HINDSIGHT_API_LLM_PROVIDER: groq
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
HINDSIGHT_API_LLM_PROVIDER: openai
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
HINDSIGHT_API_URL: http://localhost:8888
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Prefer CPU-only PyTorch in CI (but keep PyPI for everything else)
@ -703,7 +694,6 @@ jobs:
HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
EOF
- name: Start API server
@ -740,10 +730,9 @@ jobs:
test-openclaw-integration:
runs-on: ubuntu-latest
env:
HINDSIGHT_API_LLM_PROVIDER: groq
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
HINDSIGHT_API_LLM_PROVIDER: openai
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
HINDSIGHT_API_URL: http://localhost:8888
HINDSIGHT_EMBED_PACKAGE_PATH: ${{ github.workspace }}/hindsight-embed
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@ -810,7 +799,6 @@ jobs:
HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
EOF
- name: Start API server
@ -843,10 +831,9 @@ jobs:
test-integration:
runs-on: ubuntu-latest
env:
HINDSIGHT_API_LLM_PROVIDER: groq
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
HINDSIGHT_API_LLM_PROVIDER: openai
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
HINDSIGHT_API_URL: http://localhost:8888
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
UV_INDEX: pytorch=https://download.pytorch.org/whl/cpu
@ -903,7 +890,6 @@ jobs:
HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
EOF
- name: Start API server
@ -994,10 +980,9 @@ jobs:
test-embed:
runs-on: ubuntu-latest
env:
HINDSIGHT_API_LLM_PROVIDER: groq
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
HINDSIGHT_API_LLM_PROVIDER: openai
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
# Prefer CPU-only PyTorch in CI
UV_INDEX: pytorch=https://download.pytorch.org/whl/cpu
@ -1039,14 +1024,13 @@ jobs:
test-hindsight-all:
runs-on: ubuntu-latest
env:
HINDSIGHT_API_LLM_PROVIDER: groq
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
HINDSIGHT_API_LLM_PROVIDER: openai
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
# For test_server_integration.py compatibility
HINDSIGHT_LLM_PROVIDER: groq
HINDSIGHT_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
HINDSIGHT_LLM_MODEL: openai/gpt-oss-20b
HINDSIGHT_LLM_PROVIDER: openai
HINDSIGHT_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HINDSIGHT_LLM_MODEL: gpt-4o-mini
# Prefer CPU-only PyTorch in CI
UV_INDEX: pytorch=https://download.pytorch.org/whl/cpu
@ -1089,10 +1073,9 @@ jobs:
runs-on: ubuntu-latest
needs: test-rust-cli
env:
HINDSIGHT_API_LLM_PROVIDER: groq
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
HINDSIGHT_API_LLM_PROVIDER: openai
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
HINDSIGHT_API_URL: http://localhost:8888
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
UV_INDEX: pytorch=https://download.pytorch.org/whl/cpu
@ -1148,7 +1131,6 @@ jobs:
HINDSIGHT_API_LLM_PROVIDER=${{ env.HINDSIGHT_API_LLM_PROVIDER }}
HINDSIGHT_API_LLM_API_KEY=${{ env.HINDSIGHT_API_LLM_API_KEY }}
HINDSIGHT_API_LLM_MODEL=${{ env.HINDSIGHT_API_LLM_MODEL }}
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER=${{ env.HINDSIGHT_API_LLM_GROQ_SERVICE_TIER }}
EOF
- name: Start API server
@ -1183,10 +1165,9 @@ jobs:
test-upgrade:
runs-on: ubuntu-latest
env:
HINDSIGHT_API_LLM_PROVIDER: groq
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.GROQ_API_KEY }}
HINDSIGHT_API_LLM_MODEL: openai/gpt-oss-20b
HINDSIGHT_API_LLM_GROQ_SERVICE_TIER: flex
HINDSIGHT_API_LLM_PROVIDER: openai
HINDSIGHT_API_LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
UV_INDEX: pytorch=https://download.pytorch.org/whl/cpu

2
CLAUDE.md
View file

@ -317,7 +317,7 @@ npm install
Required env vars:
- `HINDSIGHT_API_LLM_PROVIDER`: openai, anthropic, gemini, groq, ollama, lmstudio
- `HINDSIGHT_API_LLM_API_KEY`: Your API key
- `HINDSIGHT_API_LLM_MODEL`: Model name (e.g., o3-mini, claude-sonnet-4-20250514)
- `HINDSIGHT_API_LLM_MODEL`: Model name (e.g., gpt-4o-mini, claude-sonnet-4-20250514)
Optional (uses local models by default):
- `HINDSIGHT_API_EMBEDDINGS_PROVIDER`: local (default) or tei

20
docker/test-image.sh
View file

@ -13,9 +13,9 @@
# target - Optional: 'cp-only' for control plane, otherwise assumes API image (default: api)
#
# Environment variables:
# GROQ_API_KEY - Required for API/standalone images (LLM verification)
# HINDSIGHT_API_LLM_PROVIDER - LLM provider (default: groq)
# HINDSIGHT_API_LLM_MODEL - LLM model (default: llama-3.3-70b-versatile)
# HINDSIGHT_API_LLM_API_KEY - Required for API/standalone images (LLM verification)
# HINDSIGHT_API_LLM_PROVIDER - LLM provider (default: openai)
# HINDSIGHT_API_LLM_MODEL - LLM model (default: gpt-4o-mini)
# HINDSIGHT_API_EMBEDDINGS_PROVIDER - Embeddings provider (optional, for slim images: openai, cohere, tei)
# HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY - OpenAI API key for embeddings (optional)
# HINDSIGHT_API_RERANKER_PROVIDER - Reranker provider (optional, for slim images: cohere, tei)
@ -34,7 +34,7 @@
# ./docker/test-image.sh hindsight-control-plane:test cp-only
#
# # Test slim image with external providers
# export GROQ_API_KEY=gsk_xxx
# export HINDSIGHT_API_LLM_API_KEY=sk_xxx
# export HINDSIGHT_API_EMBEDDINGS_PROVIDER=openai
# export HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY=sk-xxx
# export HINDSIGHT_API_RERANKER_PROVIDER=cohere
@ -60,8 +60,8 @@ IMAGE="${1:-}"
TARGET="${2:-api}"
TIMEOUT="${SMOKE_TEST_TIMEOUT:-120}"
CONTAINER_NAME="${SMOKE_TEST_CONTAINER_NAME:-hindsight-smoke-test}"
LLM_PROVIDER="${HINDSIGHT_API_LLM_PROVIDER:-groq}"
LLM_MODEL="${HINDSIGHT_API_LLM_MODEL:-llama-3.3-70b-versatile}"
LLM_PROVIDER="${HINDSIGHT_API_LLM_PROVIDER:-openai}"
LLM_MODEL="${HINDSIGHT_API_LLM_MODEL:-gpt-4o-mini}"
# Validate arguments
if [ -z "$IMAGE" ]; then
@ -88,9 +88,9 @@ else
fi
# Check for required environment variables
if [ "$NEEDS_LLM" = true ] && [ -z "${GROQ_API_KEY:-}" ]; then
echo -e "${RED}Error: GROQ_API_KEY environment variable is required for API/standalone images${NC}"
echo "Set it with: export GROQ_API_KEY=your-api-key"
if [ "$NEEDS_LLM" = true ] && [ -z "${HINDSIGHT_API_LLM_API_KEY:-}" ]; then
echo -e "${RED}Error: HINDSIGHT_API_LLM_API_KEY environment variable is required for API/standalone images${NC}"
echo "Set it with: export HINDSIGHT_API_LLM_API_KEY=your-api-key"
exit 2
fi
@ -123,7 +123,7 @@ else
# Build docker run command with required and optional env vars
DOCKER_CMD="docker run -d --name $CONTAINER_NAME"
DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_PROVIDER=$LLM_PROVIDER"
DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_API_KEY=${GROQ_API_KEY}"
DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_API_KEY=${HINDSIGHT_API_LLM_API_KEY}"
DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_MODEL=$LLM_MODEL"
# Add optional embeddings provider config

14
docker/test-slim-local.sh
View file

@ -6,24 +6,17 @@
# It expects API keys to be set in environment variables.
#
# Usage:
# export GROQ_API_KEY=gsk_xxx
# export OPENAI_API_KEY=sk-xxx
# export COHERE_API_KEY=xxx
# ./docker/test-slim-local.sh
#
# Or inline:
# GROQ_API_KEY=gsk_xxx OPENAI_API_KEY=sk_xxx COHERE_API_KEY=xxx ./docker/test-slim-local.sh
# OPENAI_API_KEY=sk_xxx COHERE_API_KEY=xxx ./docker/test-slim-local.sh
#
set -euo pipefail
# Check for required API keys
if [ -z "${GROQ_API_KEY:-}" ]; then
echo "❌ Error: GROQ_API_KEY environment variable is required"
echo "Set it with: export GROQ_API_KEY=gsk_xxx"
exit 1
fi
if [ -z "${OPENAI_API_KEY:-}" ]; then
echo "❌ Error: OPENAI_API_KEY environment variable is required"
echo "Set it with: export OPENAI_API_KEY=sk-xxx"
@ -41,7 +34,10 @@ IMAGE="${1:-hindsight-slim:test}"
echo "Testing image: $IMAGE"
echo ""
# Set up external providers
# Set up LLM and external providers
export HINDSIGHT_API_LLM_PROVIDER=openai
export HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY
export HINDSIGHT_API_LLM_MODEL=gpt-4o-mini
export HINDSIGHT_API_EMBEDDINGS_PROVIDER=openai
export HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY=$OPENAI_API_KEY
export HINDSIGHT_API_RERANKER_PROVIDER=cohere

4
hindsight-api/hindsight_api/config.py
View file

@ -314,7 +314,7 @@ DEFAULT_LLM_PROVIDER = "openai"
# Provider-specific default models
PROVIDER_DEFAULT_MODELS = {
"openai": "o3-mini",
"openai": "gpt-4o-mini",
"anthropic": "claude-haiku-4-5-20251001",
"gemini": "gemini-2.5-flash",
"groq": "openai/gpt-oss-120b",
@ -325,7 +325,7 @@ PROVIDER_DEFAULT_MODELS = {
"claude-code": "claude-sonnet-4-5-20250929",
"mock": "mock-model",
}
DEFAULT_LLM_MODEL = "o3-mini" # Fallback if provider not in table
DEFAULT_LLM_MODEL = "gpt-4o-mini" # Fallback if provider not in table
DEFAULT_LLM_MAX_CONCURRENT = 32
DEFAULT_LLM_MAX_RETRIES = 10 # Max retry attempts for LLM API calls
DEFAULT_LLM_INITIAL_BACKOFF = 1.0 # Initial backoff in seconds for retry exponential backoff

2
hindsight-api/tests/test_provider_default_models.py
View file

@ -93,7 +93,7 @@ def test_per_operation_provider_default_model():
config = HindsightConfig.from_env()
# Global LLM should use OpenAI default
assert config.llm_model == "o3-mini", f"Expected o3-mini, got {config.llm_model}"
assert config.llm_model == "gpt-4o-mini", f"Expected gpt-4o-mini, got {config.llm_model}"
# Retain should use Anthropic default
assert (

2
hindsight-docs/docs/cookbook/applications/go-memory-service.md
View file

@ -29,7 +29,7 @@ export OPENAI_API_KEY=your-key
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-e HINDSIGHT_API_LLM_MODEL=o3-mini \
-e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```

2
hindsight-docs/docs/cookbook/recipes/litellm-memory-demo.md
View file

@ -31,7 +31,7 @@ export OPENAI_API_KEY=your-key
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-e HINDSIGHT_API_LLM_MODEL=o3-mini \
-e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```

2
hindsight-docs/docs/cookbook/recipes/quickstart.md
View file

@ -25,7 +25,7 @@ export OPENAI_API_KEY=your-key
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-e HINDSIGHT_API_LLM_MODEL=o3-mini \
-e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```

2
hindsight-docs/docs/cookbook/recipes/tool-learning-demo.md
View file

@ -35,7 +35,7 @@ export OPENAI_API_KEY=your-key
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-e HINDSIGHT_API_LLM_MODEL=o3-mini \
-e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```

4
hindsight-docs/docs/developer/models.md
View file

@ -53,7 +53,7 @@ Each provider has a recommended default model that's used when `HINDSIGHT_API_LL
| Provider | Default Model |
|----------|--------------|
| `openai` | `o3-mini` |
| `openai` | `gpt-4o-mini` |
| `anthropic` | `claude-haiku-4-5-20251001` |
| `gemini` | `gemini-2.5-flash` |
| `groq` | `openai/gpt-oss-120b` |
@ -80,7 +80,7 @@ export HINDSIGHT_API_LLM_MODEL=claude-sonnet-4-5-20250929
This also applies to per-operation overrides:
```bash
# Global: OpenAI o3-mini (default)
# Global: OpenAI gpt-4o-mini (default)
export HINDSIGHT_API_LLM_PROVIDER=openai
# Retain: Anthropic claude-haiku-4-5-20251001 (default)

4
hindsight-docs/docs/sdks/integrations/openclaw.md
View file

@ -30,7 +30,7 @@ export GROQ_API_KEY="your-key"
# Option E: Claude Code (uses claude-sonnet-4-20250514, no API key needed)
export HINDSIGHT_API_LLM_PROVIDER=claude-code
# Option F: OpenAI Codex (uses o3-mini, no API key needed)
# Option F: OpenAI Codex (uses gpt-4o-mini, no API key needed)
export HINDSIGHT_API_LLM_PROVIDER=openai-codex
```
@ -103,7 +103,7 @@ The plugin auto-detects your LLM provider from these environment variables:
| 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` | `o3-mini` | No API key needed |
| OpenAI Codex | `HINDSIGHT_API_LLM_PROVIDER=openai-codex` | `gpt-4o-mini` | No API key needed |
**Override with explicit config:**

2
hindsight-docs/versioned_docs/version-0.3/cookbook/recipes/litellm-memory-demo.md
View file

@ -31,7 +31,7 @@ export OPENAI_API_KEY=your-key
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-e HINDSIGHT_API_LLM_MODEL=o3-mini \
-e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```

2
hindsight-docs/versioned_docs/version-0.3/cookbook/recipes/quickstart.md
View file

@ -25,7 +25,7 @@ export OPENAI_API_KEY=your-key
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-e HINDSIGHT_API_LLM_MODEL=o3-mini \
-e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```

2
hindsight-docs/versioned_docs/version-0.3/cookbook/recipes/tool-learning-demo.md
View file

@ -35,7 +35,7 @@ export OPENAI_API_KEY=your-key
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-e HINDSIGHT_API_LLM_MODEL=o3-mini \
-e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```

2
hindsight-docs/versioned_docs/version-0.4/cookbook/applications/go-memory-service.md
View file

@ -29,7 +29,7 @@ export OPENAI_API_KEY=your-key
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-e HINDSIGHT_API_LLM_MODEL=o3-mini \
-e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```

2
hindsight-docs/versioned_docs/version-0.4/cookbook/recipes/litellm-memory-demo.md
View file

@ -31,7 +31,7 @@ export OPENAI_API_KEY=your-key
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-e HINDSIGHT_API_LLM_MODEL=o3-mini \
-e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```

2
hindsight-docs/versioned_docs/version-0.4/cookbook/recipes/quickstart.md
View file

@ -25,7 +25,7 @@ export OPENAI_API_KEY=your-key
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-e HINDSIGHT_API_LLM_MODEL=o3-mini \
-e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```

2
hindsight-docs/versioned_docs/version-0.4/cookbook/recipes/tool-learning-demo.md
View file

@ -35,7 +35,7 @@ export OPENAI_API_KEY=your-key
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-e HINDSIGHT_API_LLM_MODEL=o3-mini \
-e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```

4
hindsight-docs/versioned_docs/version-0.4/developer/models.md
View file

@ -53,7 +53,7 @@ Each provider has a recommended default model that's used when `HINDSIGHT_API_LL
| Provider | Default Model |
|----------|--------------|
| `openai` | `o3-mini` |
| `openai` | `gpt-4o-mini` |
| `anthropic` | `claude-haiku-4-5-20251001` |
| `gemini` | `gemini-2.5-flash` |
| `groq` | `openai/gpt-oss-120b` |
@ -80,7 +80,7 @@ export HINDSIGHT_API_LLM_MODEL=claude-sonnet-4-5-20250929
This also applies to per-operation overrides:
```bash
# Global: OpenAI o3-mini (default)
# Global: OpenAI gpt-4o-mini (default)
export HINDSIGHT_API_LLM_PROVIDER=openai
# Retain: Anthropic claude-haiku-4-5-20251001 (default)

4
hindsight-docs/versioned_docs/version-0.4/sdks/integrations/openclaw.md
View file

@ -30,7 +30,7 @@ export GROQ_API_KEY="your-key"
# Option E: Claude Code (uses claude-sonnet-4-20250514, no API key needed)
export HINDSIGHT_API_LLM_PROVIDER=claude-code
# Option F: OpenAI Codex (uses o3-mini, no API key needed)
# Option F: OpenAI Codex (uses gpt-4o-mini, no API key needed)
export HINDSIGHT_API_LLM_PROVIDER=openai-codex
```
@ -103,7 +103,7 @@ The plugin auto-detects your LLM provider from these environment variables:
| 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` | `o3-mini` | No API key needed |
| OpenAI Codex | `HINDSIGHT_API_LLM_PROVIDER=openai-codex` | `gpt-4o-mini` | No API key needed |
**Override with explicit config:**

2
skills/hindsight-docs/references/cookbook/applications/go-memory-service.md
View file

@ -29,7 +29,7 @@ export OPENAI_API_KEY=your-key
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-e HINDSIGHT_API_LLM_MODEL=o3-mini \
-e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```

2
skills/hindsight-docs/references/cookbook/recipes/litellm-memory-demo.md
View file

@ -31,7 +31,7 @@ export OPENAI_API_KEY=your-key
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-e HINDSIGHT_API_LLM_MODEL=o3-mini \
-e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```

2
skills/hindsight-docs/references/cookbook/recipes/quickstart.md
View file

@ -25,7 +25,7 @@ export OPENAI_API_KEY=your-key
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-e HINDSIGHT_API_LLM_MODEL=o3-mini \
-e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```

2
skills/hindsight-docs/references/cookbook/recipes/tool-learning-demo.md
View file

@ -35,7 +35,7 @@ export OPENAI_API_KEY=your-key
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-e HINDSIGHT_API_LLM_MODEL=o3-mini \
-e HINDSIGHT_API_LLM_MODEL=gpt-4o-mini \
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
ghcr.io/vectorize-io/hindsight:latest
```

4
skills/hindsight-docs/references/developer/models.md
View file

@ -53,7 +53,7 @@ Each provider has a recommended default model that's used when `HINDSIGHT_API_LL
| Provider | Default Model |
|----------|--------------|
| `openai` | `o3-mini` |
| `openai` | `gpt-4o-mini` |
| `anthropic` | `claude-haiku-4-5-20251001` |
| `gemini` | `gemini-2.5-flash` |
| `groq` | `openai/gpt-oss-120b` |
@ -80,7 +80,7 @@ export HINDSIGHT_API_LLM_MODEL=claude-sonnet-4-5-20250929
This also applies to per-operation overrides:
```bash
# Global: OpenAI o3-mini (default)
# Global: OpenAI gpt-4o-mini (default)
export HINDSIGHT_API_LLM_PROVIDER=openai
# Retain: Anthropic claude-haiku-4-5-20251001 (default)

4
skills/hindsight-docs/references/sdks/integrations/openclaw.md
View file

@ -30,7 +30,7 @@ export GROQ_API_KEY="your-key"
# Option E: Claude Code (uses claude-sonnet-4-20250514, no API key needed)
export HINDSIGHT_API_LLM_PROVIDER=claude-code
# Option F: OpenAI Codex (uses o3-mini, no API key needed)
# Option F: OpenAI Codex (uses gpt-4o-mini, no API key needed)
export HINDSIGHT_API_LLM_PROVIDER=openai-codex
```
@ -103,7 +103,7 @@ The plugin auto-detects your LLM provider from these environment variables:
| 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` | `o3-mini` | No API key needed |
| OpenAI Codex | `HINDSIGHT_API_LLM_PROVIDER=openai-codex` | `gpt-4o-mini` | No API key needed |
**Override with explicit config:**