Provider-agnostic LLM registry, config check, migration runbook
[llm] assigns the bulk and editor roles by name over a [providers.*] registry (kind = openai | anthropic, per-provider model, effort, daily ceiling and price table); DeepseekBackend becomes OpenAiCompatibleBackend (reasoning_effort passthrough), AnthropicBackend builds from the same ProviderConfig, meters and provider_costs are keyed by provider name. Gemini 3.8 Flash is declared via Google's OpenAI-compatible endpoint so switching the editor is one line (or DAILY_EPUB_LLM__EDITOR=gemini for an A/B dry run). Stale [deepseek]/[anthropic] tables, the top-level max_daily_usd and the old key env vars fail loudly. daily-epub config check validates and prints the resolved roles, models, key presence and paths without opening the database. docs/runbooks/curation-v2-migration.md walks the server upgrade from v1. Registry implemented by a Claude agent from an orchestrator brief; verified fmt/clippy(-W dead_code)/test green. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01A1rCLQeKBgnBo3oTgHuTMe
This commit is contained in:
Claude Fable 5.1
+52
-22
@@ -3,18 +3,19 @@
|
||||
# Load order (later wins): built-in defaults ← this file ← `DAILY_EPUB_*` env vars.
|
||||
# Nested keys use a double underscore in env vars, e.g.
|
||||
# DAILY_EPUB_MINIFLUX__API_KEY=...
|
||||
# DAILY_EPUB_DEEPSEEK__API_KEY=...
|
||||
# DAILY_EPUB_ANTHROPIC__API_KEY=...
|
||||
# DAILY_EPUB_PROVIDERS__DEEPSEEK__API_KEY=...
|
||||
# DAILY_EPUB_PROVIDERS__ANTHROPIC__API_KEY=...
|
||||
# DAILY_EPUB_PROVIDERS__GEMINI__API_KEY=...
|
||||
# DAILY_EPUB_VOYAGE__API_KEY=...
|
||||
# DAILY_EPUB_SERVER__HMAC_SECRET=...
|
||||
# DAILY_EPUB_LOOKBACK_HOURS=30
|
||||
# DAILY_EPUB_LLM__EDITOR=gemini # one-off role override, no file edit
|
||||
|
||||
timezone = "America/New_York"
|
||||
lookback_hours = 26
|
||||
target_article_count = 20
|
||||
retention_days = 21 # EPUBs, by age
|
||||
xtc_retention_count = 5 # XTC issues, by count (~80-100 MB each)
|
||||
max_daily_usd = 2.0 # DeepSeek ceiling per UTC day; [anthropic] and [voyage] have their own
|
||||
world_briefing = true
|
||||
|
||||
# SQLite database file. Parent directories are created on demand.
|
||||
@@ -32,37 +33,66 @@ base_url = "http://127.0.0.1:8082"
|
||||
# api_key via DAILY_EPUB_MINIFLUX__API_KEY env
|
||||
page_limit = 250
|
||||
|
||||
[deepseek]
|
||||
# The two LLM roles, each assigned to a provider declared in [providers.*]
|
||||
# below. Switching the editor to Gemini is `editor = "gemini"` plus its key in
|
||||
# the env file; nothing else changes. An empty editor ("") runs everything on
|
||||
# the bulk provider. Every editor call degrades to bulk when the editor's key
|
||||
# is missing, its daily ceiling is hit, or the API refuses/fails.
|
||||
[llm]
|
||||
bulk = "deepseek" # triage, deep assessment, and every fallback
|
||||
editor = "anthropic" # lineup, summaries, The Brief, the weekly profile rebuild
|
||||
triage_batch_size = 25 # articles per first-pass triage request
|
||||
deep_batch_size = 8 # articles per close-reading assessment request
|
||||
score_temperature = 0.3 # sent only by providers that take a temperature (kind = "openai")
|
||||
editorial_temperature = 0.8 # summaries and The Brief on an openai-kind provider
|
||||
|
||||
# The provider registry. Any number of entries; a role above names one by its
|
||||
# table name. Keys never live here: DAILY_EPUB_PROVIDERS__<NAME>__API_KEY.
|
||||
# `max_daily_usd` is a per-provider runaway guard per UTC day (0 = none), not
|
||||
# accounting — set hard spend limits in each provider's dashboard as well.
|
||||
# Prices are USD per 1M tokens and only feed the guard's arithmetic.
|
||||
[providers.deepseek]
|
||||
kind = "openai" # openai | anthropic
|
||||
base_url = "https://api.deepseek.com/v1"
|
||||
model = "deepseek-v4-flash" # DeepSeek-V4-Flash-0731 (confirmed 2026-08-15)
|
||||
# api_key via DAILY_EPUB_DEEPSEEK__API_KEY env
|
||||
deep_batch_size = 8 # articles per close-reading assessment request
|
||||
triage_batch_size = 25 # articles per first-pass triage request
|
||||
# api_key via DAILY_EPUB_PROVIDERS__DEEPSEEK__API_KEY env
|
||||
max_daily_usd = 2.0
|
||||
max_concurrent_requests = 4 # triage and deep-assessment batches in flight
|
||||
score_temperature = 0.3
|
||||
editorial_temperature = 0.8 # used only when DeepSeek is the fallback editor
|
||||
# USD per 1M tokens, used for the cost guardrail.
|
||||
price_input_per_mtok = 0.14
|
||||
price_cached_input_per_mtok = 0.0028
|
||||
price_cache_read_per_mtok = 0.0028 # prefix-cache hits
|
||||
price_cache_write_per_mtok = 0.0 # DeepSeek caches implicitly, no write charge
|
||||
price_output_per_mtok = 0.28
|
||||
|
||||
# Claude is the editor: selection, summaries, The Brief and the weekly profile
|
||||
# rebuild. Every call degrades to DeepSeek when the key is missing, the daily
|
||||
# ceiling is hit, or the API refuses/fails. Server-side refusal fallback
|
||||
# (`fallbacks = "default"`) is always on. Set a spend limit in the Anthropic
|
||||
# dashboard too: `max_daily_usd` is a runaway guard, not accounting.
|
||||
[anthropic]
|
||||
enabled = true
|
||||
# Claude Opus 5 over the Messages API. Requests carry `output_config.effort`,
|
||||
# a cached system block, and `fallbacks = "default"` so a classifier refusal is
|
||||
# re-routed server-side; a refusal that still comes back degrades to bulk.
|
||||
[providers.anthropic]
|
||||
kind = "anthropic"
|
||||
base_url = "https://api.anthropic.com"
|
||||
model = "claude-opus-5"
|
||||
# api_key via DAILY_EPUB_ANTHROPIC__API_KEY env
|
||||
effort = "high" # low | medium | high | xhigh | max
|
||||
# api_key via DAILY_EPUB_PROVIDERS__ANTHROPIC__API_KEY env
|
||||
effort = "high" # low | medium | high | xhigh | max → output_config.effort
|
||||
max_daily_usd = 3.0
|
||||
max_concurrent_requests = 4 # summaries in flight when this is the summary provider
|
||||
price_input_per_mtok = 5.0
|
||||
price_cache_write_per_mtok = 6.25
|
||||
price_cache_read_per_mtok = 0.5
|
||||
price_cache_write_per_mtok = 6.25
|
||||
price_output_per_mtok = 25.0
|
||||
|
||||
# Gemini 3.8 Flash through Google's OpenAI-compatible endpoint (beta, verified
|
||||
# 2026-09-02). Declared but unreferenced until a role names it.
|
||||
[providers.gemini]
|
||||
kind = "openai"
|
||||
base_url = "https://generativelanguage.googleapis.com/v1beta/openai"
|
||||
model = "gemini-3.8-flash"
|
||||
# api_key via DAILY_EPUB_PROVIDERS__GEMINI__API_KEY env
|
||||
effort = "high" # minimal | low | medium | high → reasoning_effort
|
||||
max_daily_usd = 3.0
|
||||
max_concurrent_requests = 4
|
||||
price_input_per_mtok = 0.75 # promotional through 2026-12-31; $1.50 from 2027-01-01
|
||||
price_cache_read_per_mtok = 0.075 # implicit cache hits; $0.15 from 2027-01-01
|
||||
price_cache_write_per_mtok = 0.0
|
||||
price_output_per_mtok = 3.75 # includes thinking tokens; $7.50 from 2027-01-01
|
||||
|
||||
# Voyage AI embeddings behind the interest and rated-neighbour signals. Set
|
||||
# `enabled = false` (or leave the key unset) and the paper still builds: the
|
||||
@@ -154,7 +184,7 @@ per_cluster_cap = 2
|
||||
utility_protected = 10
|
||||
|
||||
[editorial]
|
||||
summary_model = "editor" # editor (Claude) | bulk (DeepSeek)
|
||||
summary_model = "editor" # editor | bulk — which [llm] role writes the summaries
|
||||
summary_input_tokens = 3000 # article text offered per summary
|
||||
|
||||
[publish]
|
||||
|
||||
Reference in New Issue
Block a user