|
| 1 | +// SPDX-License-Identifier: EUPL-1.2 |
| 2 | +// SPDX-FileCopyrightText: 2026 Jonathan D.A. Jewell (hyperpolymath) <j.d.a.jewell@open.ac.uk> |
| 3 | + |
| 4 | +//! VeriSimDB proof-attempt writer for echidnabot. |
| 5 | +//! |
| 6 | +//! Records every proof attempt (success or failure) to VeriSimDB's |
| 7 | +//! `proof_attempts` table via `POST /api/v1/proof_attempts`. |
| 8 | +//! |
| 9 | +//! This closes the learning loop: |
| 10 | +//! |
| 11 | +//! ```text |
| 12 | +//! echidnabot verify_proof |
| 13 | +//! → VeriSimWriter::record |
| 14 | +//! → POST /api/v1/proof_attempts |
| 15 | +//! → ClickHouse proof_attempts table |
| 16 | +//! → mv_prover_success_by_class (auto-maintained) |
| 17 | +//! → Hypatia ProofStrategySelection.recommend/2 |
| 18 | +//! → echidnabot prover_hint in next dispatch |
| 19 | +//! ``` |
| 20 | +//! |
| 21 | +//! The writer is fully non-fatal: if VeriSimDB is unreachable, it logs a |
| 22 | +//! warning at `WARN` level and returns so the calling job continues. The |
| 23 | +//! learning loop degrades gracefully to the last known recommendations. |
| 24 | +//! |
| 25 | +//! # Configuration |
| 26 | +//! |
| 27 | +//! Set `HYPATIA_VERISIM_URL` to the verisim-api base URL |
| 28 | +//! (e.g. `http://localhost:8080`). If the variable is absent or empty, |
| 29 | +//! the writer is disabled and every call to `record` is a no-op. |
| 30 | +//! |
| 31 | +//! # Prover-agnosticism |
| 32 | +//! |
| 33 | +//! `prover_to_str` maps every `ProverKind` variant to the lowercase |
| 34 | +//! string the ClickHouse `Enum8` expects. Adding a new prover to |
| 35 | +//! `ProverKind` requires adding one arm here — no other change needed. |
| 36 | +
|
| 37 | +use chrono::{DateTime, Utc}; |
| 38 | +use reqwest::Client; |
| 39 | +use serde::{Deserialize, Serialize}; |
| 40 | +use tracing::{debug, warn}; |
| 41 | +use uuid::Uuid; |
| 42 | + |
| 43 | +use crate::dispatcher::{ProofResult, ProofStatus, ProverKind}; |
| 44 | + |
| 45 | +// ─── Row type ───────────────────────────────────────────────────────────────── |
| 46 | + |
| 47 | +/// A single row written to VeriSimDB's `proof_attempts` table. |
| 48 | +/// |
| 49 | +/// Field names are snake_case to match the JSON body expected by |
| 50 | +/// `POST /api/v1/proof_attempts` on verisim-api. The `prover_used` and |
| 51 | +/// `outcome` strings are lowercase Enum8 values in ClickHouse. |
| 52 | +/// |
| 53 | +/// Schema note: `obligation_id` is a stable hash of `(repo, file)` that |
| 54 | +/// groups retries of the same obligation. `attempt_id` is unique per call. |
| 55 | +#[derive(Debug, Serialize, Deserialize)] |
| 56 | +struct ProofAttemptRow { |
| 57 | + /// UUID v4 — unique to this invocation. |
| 58 | + attempt_id: String, |
| 59 | + /// Stable 16-hex-char hash of `(repo, file)` — groups retries. |
| 60 | + obligation_id: String, |
| 61 | + /// Repository slug, e.g. `"hyperpolymath/echidna"`. |
| 62 | + repo: String, |
| 63 | + /// Relative file path within the repo. |
| 64 | + file: String, |
| 65 | + /// Human-readable description of what is being proved. |
| 66 | + claim: String, |
| 67 | + /// Mathematical obligation class for strategy lookup. |
| 68 | + /// Examples: `"linearity"`, `"termination"`, `"equiv"`, `"safety"`. |
| 69 | + obligation_class: String, |
| 70 | + /// Lowercase prover name matching ClickHouse Enum8: |
| 71 | + /// `"coq"` | `"lean"` | `"agda"` | `"isabelle"` | `"z3"` | `"cvc5"` |
| 72 | + /// | `"metamath"` | `"hol_light"` | `"mizar"` | `"pvs"` | `"acl2"` |
| 73 | + /// | `"hol4"` | `"other"`. |
| 74 | + prover_used: String, |
| 75 | + /// Outcome: `"success"` | `"failure"` | `"timeout"` | `"unknown"`. |
| 76 | + outcome: String, |
| 77 | + /// Wall-clock duration in milliseconds. |
| 78 | + duration_ms: u64, |
| 79 | + /// Confidence in \[0.0, 1.0\]. Derived from outcome for echidnabot jobs. |
| 80 | + confidence: f32, |
| 81 | + /// Set for retries; `None` for first attempts. |
| 82 | + #[serde(skip_serializing_if = "Option::is_none")] |
| 83 | + parent_attempt_id: Option<String>, |
| 84 | + /// Strategy that dispatched this attempt. Fixed to `"echidnabot"` here. |
| 85 | + strategy_tag: String, |
| 86 | + /// ISO-8601 UTC — when the prover was invoked. |
| 87 | + started_at: String, |
| 88 | + /// ISO-8601 UTC — when the result was received. |
| 89 | + completed_at: String, |
| 90 | + /// Truncated prover stdout/stderr (≤ 8 KiB recommended). |
| 91 | + prover_output: String, |
| 92 | + /// Non-`None` when `outcome != "success"`. |
| 93 | + #[serde(skip_serializing_if = "Option::is_none")] |
| 94 | + error_message: Option<String>, |
| 95 | +} |
| 96 | + |
| 97 | +// ─── Writer ─────────────────────────────────────────────────────────────────── |
| 98 | + |
| 99 | +/// Asynchronously records proof attempts to VeriSimDB. |
| 100 | +/// |
| 101 | +/// Construct once per process with [`VeriSimWriter::from_env`], then call |
| 102 | +/// [`VeriSimWriter::record`] after every [`EchidnaClient::verify_proof`]. |
| 103 | +pub struct VeriSimWriter { |
| 104 | + base_url: String, |
| 105 | + http: Client, |
| 106 | + enabled: bool, |
| 107 | +} |
| 108 | + |
| 109 | +impl VeriSimWriter { |
| 110 | + /// Build from the `HYPATIA_VERISIM_URL` environment variable. |
| 111 | + /// |
| 112 | + /// If the variable is absent or empty the writer is disabled: |
| 113 | + /// every [`record`] call returns immediately without network I/O. |
| 114 | + pub fn from_env() -> Self { |
| 115 | + match std::env::var("HYPATIA_VERISIM_URL") { |
| 116 | + Ok(url) if !url.trim().is_empty() => { |
| 117 | + let http = Client::builder() |
| 118 | + .timeout(std::time::Duration::from_secs(10)) |
| 119 | + .build() |
| 120 | + .unwrap_or_else(|_| Client::new()); |
| 121 | + Self { |
| 122 | + base_url: url.trim_end_matches('/').to_string(), |
| 123 | + http, |
| 124 | + enabled: true, |
| 125 | + } |
| 126 | + } |
| 127 | + _ => { |
| 128 | + tracing::info!( |
| 129 | + "HYPATIA_VERISIM_URL not set — VeriSimDB proof-attempt recording disabled" |
| 130 | + ); |
| 131 | + Self { |
| 132 | + base_url: String::new(), |
| 133 | + http: Client::new(), |
| 134 | + enabled: false, |
| 135 | + } |
| 136 | + } |
| 137 | + } |
| 138 | + } |
| 139 | + |
| 140 | + /// Record one proof attempt to VeriSimDB. |
| 141 | + /// |
| 142 | + /// Non-fatal: any network or HTTP error is logged at `WARN` and |
| 143 | + /// the function returns so the caller's job loop continues. |
| 144 | + /// |
| 145 | + /// # Arguments |
| 146 | + /// |
| 147 | + /// * `result` — the outcome from [`EchidnaClient::verify_proof`] |
| 148 | + /// * `prover` — which prover backend was used |
| 149 | + /// * `repo` — repository slug, e.g. `"hyperpolymath/echidna"` |
| 150 | + /// * `file_path` — proof file path (relative or absolute) |
| 151 | + /// * `started_at` — timestamp recorded just before `verify_proof` was called |
| 152 | + pub async fn record( |
| 153 | + &self, |
| 154 | + result: &ProofResult, |
| 155 | + prover: ProverKind, |
| 156 | + repo: &str, |
| 157 | + file_path: &str, |
| 158 | + started_at: DateTime<Utc>, |
| 159 | + ) { |
| 160 | + if !self.enabled { |
| 161 | + return; |
| 162 | + } |
| 163 | + |
| 164 | + let completed_at = Utc::now(); |
| 165 | + let obligation_class = classify_obligation_from_path(file_path, prover); |
| 166 | + let outcome = outcome_str(&result.status); |
| 167 | + let confidence = confidence_from_status(&result.status); |
| 168 | + let prover_str = prover_to_str(prover); |
| 169 | + |
| 170 | + let row = ProofAttemptRow { |
| 171 | + attempt_id: Uuid::new_v4().to_string(), |
| 172 | + obligation_id: stable_obligation_id(repo, file_path), |
| 173 | + repo: repo.to_string(), |
| 174 | + file: file_path.to_string(), |
| 175 | + claim: format!("Verify proof in {file_path}"), |
| 176 | + obligation_class, |
| 177 | + prover_used: prover_str.to_string(), |
| 178 | + outcome, |
| 179 | + duration_ms: result.duration_ms, |
| 180 | + confidence, |
| 181 | + parent_attempt_id: None, |
| 182 | + strategy_tag: "echidnabot".to_string(), |
| 183 | + started_at: started_at.to_rfc3339(), |
| 184 | + completed_at: completed_at.to_rfc3339(), |
| 185 | + prover_output: truncate_utf8(&result.prover_output, 8 * 1024), |
| 186 | + error_message: if result.status == ProofStatus::Verified { |
| 187 | + None |
| 188 | + } else { |
| 189 | + Some(result.message.clone()) |
| 190 | + }, |
| 191 | + }; |
| 192 | + |
| 193 | + let url = format!("{}/api/v1/proof_attempts", self.base_url); |
| 194 | + |
| 195 | + match self.http.post(&url).json(&row).send().await { |
| 196 | + Ok(resp) if resp.status().is_success() => { |
| 197 | + debug!( |
| 198 | + attempt_id = %row.attempt_id, |
| 199 | + prover = prover_str, |
| 200 | + outcome = %row.outcome, |
| 201 | + file = file_path, |
| 202 | + "proof_attempt recorded in VeriSimDB" |
| 203 | + ); |
| 204 | + } |
| 205 | + Ok(resp) => { |
| 206 | + let status = resp.status(); |
| 207 | + let body = resp.text().await.unwrap_or_default(); |
| 208 | + warn!( |
| 209 | + %status, |
| 210 | + body = %body, |
| 211 | + prover = prover_str, |
| 212 | + file = file_path, |
| 213 | + "VeriSimDB proof_attempts endpoint returned error — attempt not recorded" |
| 214 | + ); |
| 215 | + } |
| 216 | + Err(e) => { |
| 217 | + warn!( |
| 218 | + error = %e, |
| 219 | + prover = prover_str, |
| 220 | + file = file_path, |
| 221 | + "VeriSimDB unreachable — proof_attempt not recorded (learning loop degraded)" |
| 222 | + ); |
| 223 | + } |
| 224 | + } |
| 225 | + } |
| 226 | +} |
| 227 | + |
| 228 | +// ─── Helpers ────────────────────────────────────────────────────────────────── |
| 229 | + |
| 230 | +/// Map `ProofStatus` to the lowercase ClickHouse Enum8 outcome string. |
| 231 | +fn outcome_str(status: &ProofStatus) -> String { |
| 232 | + match status { |
| 233 | + ProofStatus::Verified => "success", |
| 234 | + ProofStatus::Timeout => "timeout", |
| 235 | + ProofStatus::Failed | ProofStatus::Error => "failure", |
| 236 | + ProofStatus::Unknown => "unknown", |
| 237 | + } |
| 238 | + .to_string() |
| 239 | +} |
| 240 | + |
| 241 | +/// Derive an obligation class from the file path and prover. |
| 242 | +/// |
| 243 | +/// Keyword-matching against the path provides coarse-grained class labels |
| 244 | +/// that feed `mv_prover_success_by_class`. Unknown paths fall back to a |
| 245 | +/// prover-namespaced class (e.g. `"metamath_proof"`) so the MV always has |
| 246 | +/// a non-null class to aggregate on. |
| 247 | +fn classify_obligation_from_path(file_path: &str, prover: ProverKind) -> String { |
| 248 | + let lower = file_path.to_lowercase(); |
| 249 | + for (keyword, class) in &[ |
| 250 | + ("terminat", "termination"), |
| 251 | + ("linear", "linearity"), |
| 252 | + ("equiv", "equiv"), |
| 253 | + ("correct", "equiv"), |
| 254 | + ("safety", "safety"), |
| 255 | + ("secure", "safety"), |
| 256 | + ("memory", "safety"), |
| 257 | + ("sort", "termination"), |
| 258 | + ("bound", "termination"), |
| 259 | + ] { |
| 260 | + if lower.contains(keyword) { |
| 261 | + return class.to_string(); |
| 262 | + } |
| 263 | + } |
| 264 | + // Fallback: prover-namespaced so the MV still groups by (class, prover) |
| 265 | + format!("{}_proof", prover_to_str(prover)) |
| 266 | +} |
| 267 | + |
| 268 | +/// Derive a rough confidence score from the proof outcome. |
| 269 | +/// |
| 270 | +/// These are priors; the `mv_prover_success_by_class` MV computes true |
| 271 | +/// empirical rates from the growing table — the stored `confidence` here |
| 272 | +/// is per-attempt metadata, not a prediction. |
| 273 | +fn confidence_from_status(status: &ProofStatus) -> f32 { |
| 274 | + match status { |
| 275 | + ProofStatus::Verified => 0.95, |
| 276 | + ProofStatus::Failed => 0.10, |
| 277 | + ProofStatus::Timeout => 0.05, |
| 278 | + ProofStatus::Error => 0.10, |
| 279 | + ProofStatus::Unknown => 0.50, |
| 280 | + } |
| 281 | +} |
| 282 | + |
| 283 | +/// Stable 16-char hex obligation ID derived from `(repo, file)`. |
| 284 | +/// |
| 285 | +/// Uses a non-cryptographic hash — good enough for grouping retries. |
| 286 | +/// The same `(repo, file)` always produces the same ID across runs. |
| 287 | +fn stable_obligation_id(repo: &str, file: &str) -> String { |
| 288 | + use std::collections::hash_map::DefaultHasher; |
| 289 | + use std::hash::{Hash, Hasher}; |
| 290 | + let mut h = DefaultHasher::new(); |
| 291 | + repo.hash(&mut h); |
| 292 | + b'\0'.hash(&mut h); |
| 293 | + file.hash(&mut h); |
| 294 | + format!("{:016x}", h.finish()) |
| 295 | +} |
| 296 | + |
| 297 | +/// Truncate `s` to at most `max_bytes` bytes, preserving UTF-8 boundaries. |
| 298 | +fn truncate_utf8(s: &str, max_bytes: usize) -> String { |
| 299 | + if s.len() <= max_bytes { |
| 300 | + return s.to_string(); |
| 301 | + } |
| 302 | + let boundary = s |
| 303 | + .char_indices() |
| 304 | + .map(|(i, _)| i) |
| 305 | + .take_while(|&i| i <= max_bytes) |
| 306 | + .last() |
| 307 | + .unwrap_or(0); |
| 308 | + format!("{}…", &s[..boundary]) |
| 309 | +} |
| 310 | + |
| 311 | +/// Map every `ProverKind` variant to the lowercase ClickHouse Enum8 string. |
| 312 | +/// |
| 313 | +/// Adding a new prover requires adding one arm here. The `_ => "other"` arm |
| 314 | +/// is intentionally absent so the compiler flags missing variants. |
| 315 | +pub fn prover_to_str(kind: ProverKind) -> &'static str { |
| 316 | + match kind { |
| 317 | + ProverKind::Agda => "agda", |
| 318 | + ProverKind::Coq => "coq", |
| 319 | + ProverKind::Lean => "lean", |
| 320 | + ProverKind::Isabelle => "isabelle", |
| 321 | + ProverKind::Z3 => "z3", |
| 322 | + ProverKind::Cvc5 => "cvc5", |
| 323 | + ProverKind::Metamath => "metamath", |
| 324 | + ProverKind::HolLight => "hol_light", |
| 325 | + ProverKind::Mizar => "mizar", |
| 326 | + ProverKind::Pvs => "pvs", |
| 327 | + ProverKind::Acl2 => "acl2", |
| 328 | + ProverKind::Hol4 => "hol4", |
| 329 | + } |
| 330 | +} |
0 commit comments