Chris Olson
9131e83c08
Exa harvester: - EXA_CATEGORY=news (default) restricts to news articles, excluding evergreen careers/marketing landing pages that were producing irrelevant signals. - Event-focused query (acquisition/earnings/launch/leadership), dropped hiring/career terms that pulled recruiting pages. - Domain scoping now OFF by default (broad-web news about the account beats first-party careers pages); add EXA_EXCLUDE_DOMAINS and loop --domain-filter. LLM layer: - Remove the mock reasoner entirely (no provider => loop refuses to run). - On HTTP 429, WAIT (LLM_RATELIMIT_WAIT_SECONDS, default 900s; honors Retry-After) and retry up to LLM_RATELIMIT_MAX_RETRIES (24) instead of degrading to mock output. - If the LLM is ultimately unavailable for an account, skip it and leave its signals unconsumed (retried next run) — never fabricate briefs. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
50 lines
2.0 KiB
Plaintext
50 lines
2.0 KiB
Plaintext
# Copy to .env and fill in. The loop runs WITHOUT a key using a mock reasoner.
|
|
|
|
# --- LLM provider ---
|
|
# LLM_PROVIDER: openai | gemini | anthropic (auto-detected from whichever key is
|
|
# set if blank; OpenAI-compatible preferred). Provider w/ a missing key => mock.
|
|
LLM_PROVIDER=openai
|
|
|
|
# OpenAI-compatible endpoint — works with OpenAI, OpenRouter, Together, Groq,
|
|
# vLLM, Ollama, LM Studio, etc. Just point these three at any /chat/completions API:
|
|
OPENAI_BASE_URL=https://api.openai.com/v1
|
|
OPENAI_API_KEY=
|
|
OPENAI_MODEL=gpt-4o-mini
|
|
OPENAI_JSON_MODE=1 # set 0 if the endpoint rejects response_format=json_object
|
|
|
|
# There is NO mock fallback. On HTTP 429 the loop WAITS this long and retries
|
|
# (honors Retry-After if present), so it grinds through tight rate limits.
|
|
LLM_RATELIMIT_WAIT_SECONDS=900
|
|
LLM_RATELIMIT_MAX_RETRIES=24
|
|
|
|
# Other providers:
|
|
GEMINI_API_KEY=
|
|
GEMINI_MODEL=gemini-2.5-flash
|
|
ANTHROPIC_API_KEY=
|
|
LLM_MODEL=claude-sonnet-4-6
|
|
|
|
# Scoring thresholds (design Phase 5)
|
|
PRIORITY_THRESHOLD=0.72
|
|
STANDARD_THRESHOLD=0.45
|
|
|
|
# --- Exa.ai news/web harvester ---
|
|
# Without a key, the news connector falls back to data/fixtures.json.
|
|
EXA_API_KEY=
|
|
EXA_ENABLED=1
|
|
# Hard ceilings to stay inside the free plan (~20,000 req/month). The connector
|
|
# refuses to call Exa once either cap is reached. Monthly count persists in
|
|
# output/state/exa_usage.json and resets at the start of each calendar month.
|
|
EXA_MONTHLY_REQUEST_CAP=1000
|
|
EXA_PER_RUN_REQUEST_CAP=25
|
|
EXA_RESULTS_PER_QUERY=5
|
|
EXA_LOOKBACK_DAYS=45
|
|
# Exa content category. "news" keeps out careers/marketing landing pages — the
|
|
# biggest signal-quality lever. "" disables category filtering.
|
|
EXA_CATEGORY=news
|
|
# Scope to the account's own domain (1) or broad-web news about it (0, default).
|
|
# With category=news, broad web finds actual coverage; domain scoping finds the
|
|
# company's own newsroom. Override per run: loop --no-domain-filter / --domain-filter
|
|
EXA_DOMAIN_FILTER=0
|
|
# Hosts to always exclude (comma-separated), e.g. talent.example.com,careers.example.com
|
|
EXA_EXCLUDE_DOMAINS=
|