thallada/the-daily-epub
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Provider-agnostic LLM registry, config check, migration runbook

Browse Source 
[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:
thallada
2026-09-02 18:44:57 +00:00
co-authored by Claude Fable 5.1
parent 5edbeb509f
commit 99d1338890
19 changed files with 2136 additions and 620 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/curate/assess.rs
+3 -3
View File
@@ -481,8 +481,8 @@ pub async fn run(
#[cfg(test)]
mod tests {
use super::*;
use crate::config::{CurationConfig, DeepseekConfig};
use crate::curate::llm::{MockBackend, UsageMeter};
use crate::config::{CurationConfig, ProviderConfig};
use crate::curate::llm::{MockBackend, PriceTable, UsageMeter};
use crate::curate::prefilter::tests::{article, with_social};
use crate::curate::signals::{Neighbour, TopInterest};
use crate::types::{TokenUsage, Triage};
@@ -520,7 +520,7 @@ mod tests {
LlmClient::with_backend(
"deepseek-v4-flash",
"SYSTEM".into(),
UsageMeter::new(&DeepseekConfig::default(), limit_usd),
UsageMeter::with_prices(PriceTable::from(&ProviderConfig::deepseek()), limit_usd),
backend,
)
}
src/curate/editor.rs
+4 -6
View File
@@ -637,7 +637,7 @@ pub fn select_without_llm(
#[cfg(test)]
mod tests {
use super::*;
use crate::config::{AnthropicConfig, CurationConfig, DeepseekConfig};
use crate::config::{CurationConfig, ProviderConfig};
use crate::curate::llm::{ChatBackend, LlmClient, MockBackend, PriceTable, UsageMeter};
use crate::curate::prefilter::tests::article;
use crate::curate::signals::{Neighbour, TopInterest};
@@ -696,9 +696,9 @@ mod tests {
fn mock(provider: &'static str, backend: Arc<MockBackend>, limit: f64) -> LlmClient {
let prices = if provider == "anthropic" {
PriceTable::anthropic(&AnthropicConfig::default())
PriceTable::from(&ProviderConfig::anthropic())
} else {
PriceTable::deepseek(&DeepseekConfig::default())
PriceTable::from(&ProviderConfig::deepseek())
};
LlmClient::with_backend_options(
provider,
@@ -1079,9 +1079,7 @@ mod tests {
#[tokio::test]
async fn refusal_on_the_editor_falls_back_to_bulk_with_the_same_prompt() {
let editor = Arc::new(MockBackend::new());
editor.push_llm_error(LlmError::Refusal {
provider: "anthropic",
});
editor.push_llm_error(LlmError::refusal("anthropic"));
let bulk = Arc::new(MockBackend::new());
bulk.push(picks_json(5), TokenUsage::default());
let llms = editor_and_bulk(Arc::clone(&editor), Arc::clone(&bulk));
src/curate/editorial.rs
+14 -19
View File
@@ -1,4 +1,4 @@
//! Claude-first summaries and The Brief, with per-call DeepSeek fallback (§14).
//! Editor-first summaries and The Brief, with per-call bulk fallback (§14).
use std::collections::BTreeMap;
use std::fmt::Write as _;
@@ -12,7 +12,6 @@ use crate::config::{EditorialConfig, SummaryModel};
use crate::types::{ArticleId, Editorial, Lineup, Pick};
pub const FALLBACK_SUMMARY_WORDS: usize = 45;
pub const SUMMARY_CONCURRENCY: usize = 4;
pub const SUMMARY_INSTRUCTIONS: &str = "\
TASK: write the newspaper abstract for one article in today's issue.
@@ -102,9 +101,7 @@ pub async fn summarize_article(
let response: SummaryResponse = llm.complete_json(&prompt, temperature).await?;
let summary = response.summary.trim().to_string();
if summary.is_empty() {
return Err(LlmError::EmptyResponse {
provider: llm.provider,
});
return Err(LlmError::empty_response(llm.provider()));
}
Ok(summary)
}
@@ -172,12 +169,17 @@ pub async fn summarize_all(
temperature: f32,
) -> BTreeMap<ArticleId, String> {
let (primary, fallback) = summary_clients(llms, config.summary_model);
// The summary provider's own `max_concurrent_requests` bounds the fan-out.
let concurrency = primary
.map(|client| client.max_concurrent_requests)
.unwrap_or(1)
.max(1);
stream::iter(lineup.picks.iter())
.map(|pick| async move {
let summary = summarize_pick(pick, primary, fallback, config, temperature).await;
(pick.article.id, summary)
})
.buffer_unordered(SUMMARY_CONCURRENCY)
.buffer_unordered(concurrency)
.filter_map(|(id, summary)| async move { summary.map(|summary| (id, summary)) })
.collect()
.await
@@ -232,10 +234,7 @@ pub async fn brief(
) -> Result<String, LlmError> {
let prompt = build_brief_prompt(lineup, summaries);
let Some(primary) = llms.editor_or_bulk() else {
return Err(LlmError::Api {
provider: "editorial",
message: "no provider configured".into(),
});
return Err(LlmError::api("editorial", "no provider configured"));
};
let response = match primary
.complete_json::<BriefResponse>(&prompt, temperature)
@@ -258,9 +257,7 @@ pub async fn brief(
};
let brief = response.brief.trim().to_string();
if brief.is_empty() {
return Err(LlmError::EmptyResponse {
provider: primary.provider,
});
return Err(LlmError::empty_response(primary.provider()));
}
Ok(brief)
}
@@ -381,7 +378,7 @@ pub fn summary_to_html(summary: &str) -> String {
#[cfg(test)]
mod tests {
use super::*;
use crate::config::{AnthropicConfig, DeepseekConfig};
use crate::config::ProviderConfig;
use crate::curate::llm::{ChatBackend, MockBackend, PriceTable, UsageMeter};
use crate::curate::prefilter::tests::article;
use crate::types::TokenUsage;
@@ -420,9 +417,9 @@ mod tests {
fn mock(provider: &'static str, backend: Arc<MockBackend>, limit: f64) -> LlmClient {
let prices = if provider == "anthropic" {
PriceTable::anthropic(&AnthropicConfig::default())
PriceTable::from(&ProviderConfig::anthropic())
} else {
PriceTable::deepseek(&DeepseekConfig::default())
PriceTable::from(&ProviderConfig::deepseek())
};
LlmClient::with_backend_options(
provider,
@@ -534,9 +531,7 @@ mod tests {
r#"{"summary": "Opus wrote this one."}"#,
TokenUsage::default(),
);
editor.push_llm_error(LlmError::Refusal {
provider: "anthropic",
});
editor.push_llm_error(LlmError::refusal("anthropic"));
editor.push(BRIEF_FIXTURE, TokenUsage::default());
let bulk = Arc::new(MockBackend::new());
bulk.push(
src/curate/llm.rs
+538 -258
View File
File diff suppressed because it is too large Load Diff
src/curate/mod.rs
+6 -6
View File
@@ -39,7 +39,7 @@ pub struct Curator {
impl Curator {
/// An empty [`llm::Llms`] corresponds to `--skip-llm`: cheap-signal order is
/// used for selection and feed excerpts stand in for summaries (notes §6).
/// With only `bulk`, every editor call runs on DeepSeek (§4.2).
/// With only `bulk`, every editor call runs on the bulk provider (§4.2).
pub fn new(config: Config, db: Db, llms: llm::Llms) -> Self {
Self { config, db, llms }
}
@@ -67,15 +67,15 @@ impl Curator {
assess::run(
&self.db,
Some(bulk),
&self.config.deepseek.model,
&bulk.model,
candidates,
self.config.deepseek.deep_batch_size,
self.config.deepseek.max_concurrent_requests,
self.config.llm.deep_batch_size,
bulk.max_concurrent_requests,
self.config.curation.ranking.assessment_reuse_days,
rescore,
profile_version,
assessed_at,
self.config.deepseek.score_temperature,
self.config.llm.score_temperature,
&self.config.curation.sections,
)
.await
@@ -137,7 +137,7 @@ impl Curator {
&self.llms,
lineup,
&self.config.editorial,
self.config.deepseek.editorial_temperature,
self.config.llm.editorial_temperature,
)
.await)
}
src/curate/profile/mod.rs
+2 -2
View File
@@ -624,7 +624,7 @@ mod tests {
use std::sync::Arc;
use super::super::llm::{MockBackend, UsageMeter};
use crate::config::DeepseekConfig;
use crate::config::ProviderConfig;
use crate::types::{RatingEvent, TokenUsage};
let dir = tempfile::tempdir().unwrap();
@@ -667,7 +667,7 @@ mod tests {
let llm = LlmClient::with_backend(
"deepseek-v4-flash",
initial.text,
UsageMeter::new(&DeepseekConfig::default(), 2.0),
UsageMeter::for_provider(&ProviderConfig::deepseek()),
backend.clone(),
);
let rebuilt = rebuild(&db, &llm, &opml, &profile_path, 60).await.unwrap();
src/curate/telemetry.rs
+3 -2
View File
@@ -1370,7 +1370,7 @@ mod tests {
"2026-09-01",
"2026-09-01T09:30:00Z",
"2026-09-01T09:45:00Z",
r#"{"deepseek":{"input_tokens":1,"cached_tokens":0,"cache_write_tokens":0,"output_tokens":1,"cost_usd":0.14}}"#,
r#"{"deepseek":{"input_tokens":1,"cached_tokens":0,"cache_write_tokens":0,"output_tokens":1,"cost_usd":0.14},"gemini":{"input_tokens":1,"cached_tokens":0,"cache_write_tokens":0,"output_tokens":1,"cost_usd":0.07}}"#,
),
] {
let run_id = db
@@ -1452,8 +1452,9 @@ mod tests {
"exploration rated positively: 1",
"cost per day (anthropic): $0.043",
"cost per day (deepseek): $0.020",
"cost per day (gemini): $0.005",
"cost per day (voyage): $0.001",
"cost per day (total): $0.064",
"cost per day (total): $0.069",
"mean generation time: 15m00s (3 runs)",
] {
assert!(text.contains(line), "missing {line:?} in:\n{text}");
src/curate/triage.rs
+4 -4
View File
@@ -500,8 +500,8 @@ pub async fn run(
#[cfg(test)]
mod tests {
use super::*;
use crate::config::DeepseekConfig;
use crate::curate::llm::{MockBackend, UsageMeter};
use crate::config::ProviderConfig;
use crate::curate::llm::{MockBackend, PriceTable, UsageMeter};
use crate::curate::prefilter::tests::article;
use crate::curate::signals::{Neighbour, TopInterest};
use crate::types::TokenUsage;
@@ -584,11 +584,11 @@ mod tests {
r#"{"articles":[{"id":42,"interest":8,"kind":"essay","why":"first answer"}]}"#,
TokenUsage::default(),
);
let config = DeepseekConfig::default();
let config = ProviderConfig::deepseek();
let llm = LlmClient::with_backend(
&config.model,
"profile".into(),
UsageMeter::new(&config, 10.0),
UsageMeter::with_prices(PriceTable::from(&config), 10.0),
backend.clone(),
);
let pool = HashSet::from([42]);