upleb.uk

Public git repos — served from a NIP-34 GRASP relay at git.upleb.uk

summaryrefslogtreecommitdiff
path: root/src/purgatory/sync/context.rs
blob: e61de013aa003775d4513e8dcc7b20cf6ca23583 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
//! Sync context abstraction for testability.
//!
//! This module provides the `SyncContext` trait which abstracts external dependencies
//! for sync operations. This allows unit testing of sync logic by mocking:
//! - Repository data fetching
//! - OID existence checks
//! - Git fetch operations
//! - Event processing
//!
//! The real implementation (`RealSyncContext`) connects to actual database, git,
//! and relay systems. The mock implementation (`MockSyncContext`) is used in tests.

use anyhow::Result;
use async_trait::async_trait;
use std::collections::HashSet;
use std::path::{Path, PathBuf};

use crate::git::authorization::RepositoryData;

/// Result of processing newly available git data.
///
/// This struct captures what happened when we tried to release events from
/// purgatory after new git data became available.
#[derive(Debug, Default, Clone)]
pub struct ProcessResult {
    /// Number of state events released from purgatory
    pub states_released: usize,
    /// Number of PR events released from purgatory
    pub prs_released: usize,
    /// Number of repositories synced (OIDs copied + refs aligned)
    pub repos_synced: usize,
    /// Number of refs created across all repos
    pub refs_created: usize,
    /// Number of refs updated across all repos
    pub refs_updated: usize,
    /// Number of refs deleted across all repos
    pub refs_deleted: usize,
    /// Errors encountered (non-fatal)
    pub errors: Vec<String>,
}

impl ProcessResult {
    /// Check if any events were released
    pub fn released_any(&self) -> bool {
        self.states_released > 0 || self.prs_released > 0
    }
}

/// Abstraction over external dependencies for sync operations.
///
/// This trait allows unit testing of sync logic by mocking:
/// - Repository data fetching
/// - OID existence checks
/// - Git fetch operations
/// - Event processing
///
/// # Implementation Notes
///
/// The real implementation (`RealSyncContext`) holds references to purgatory,
/// database, etc., and the `process_newly_available_git_data` method delegates
/// to the unified function. This keeps the sync logic functions
/// (`sync_identifier_next_url`, `sync_identifier_from_url`) clean and testable
/// with mocks.
#[async_trait]
pub trait SyncContext: Send + Sync {
    /// Collect clone URLs from PR events in purgatory for a given identifier.
    ///
    /// PR events (kind 1618) and PR Update events (kind 1619) can include `clone` tags
    /// specifying where the PR commits can be fetched from. This method extracts those
    /// URLs to supplement the clone URLs from repository announcements.
    ///
    /// # Arguments
    /// * `identifier` - The repository identifier
    ///
    /// # Returns
    /// Set of clone URLs from PR events in purgatory for this identifier
    fn collect_pr_clone_urls(&self, identifier: &str) -> HashSet<String>;
    /// Get repository data (announcements, clone URLs, etc.) from the database.
    ///
    /// # Arguments
    /// * `identifier` - The repository identifier (d-tag value)
    ///
    /// # Returns
    /// Repository data including announcements and state events
    async fn fetch_repository_data(&self, identifier: &str) -> Result<RepositoryData>;

    /// Get all OIDs needed for purgatory events with this identifier.
    ///
    /// This collects commit hashes from:
    /// - State events in purgatory (branch/tag commits)
    /// - PR events in purgatory (commit hash from c-tag)
    ///
    /// # Arguments
    /// * `identifier` - The repository identifier
    ///
    /// # Returns
    /// Set of OID strings (commit hashes) that are still needed
    fn collect_needed_oids(&self, identifier: &str) -> HashSet<String>;

    /// Check if an OID exists locally in a repository.
    ///
    /// # Arguments
    /// * `repo_path` - Path to the git repository
    /// * `oid` - The object ID (commit hash) to check
    ///
    /// # Returns
    /// true if the OID exists in the repository
    fn oid_exists(&self, repo_path: &Path, oid: &str) -> bool;

    /// Fetch OIDs from a remote server.
    ///
    /// Attempts to fetch the specified OIDs from the given URL into the
    /// local repository.
    ///
    /// # Arguments
    /// * `repo_path` - Path to the local git repository
    /// * `url` - Remote URL to fetch from
    /// * `oids` - List of OIDs to fetch
    ///
    /// # Returns
    /// List of OIDs that were successfully fetched
    async fn fetch_oids(&self, repo_path: &Path, url: &str, oids: &[String])
        -> Result<Vec<String>>;

    /// Process newly available git data.
    ///
    /// This is called after each successful OID fetch to check if any purgatory
    /// events can now be satisfied with the available git data.
    ///
    /// The function:
    /// 1. Discovers satisfiable events from purgatory
    /// 2. Syncs OIDs to authorized owner repos
    /// 3. Aligns refs (+ sets HEAD)
    /// 4. Saves events to database
    /// 5. Notifies WebSocket subscribers
    /// 6. Removes from purgatory
    ///
    /// # Arguments
    /// * `source_repo_path` - Path to the repository that has the new git data
    /// * `new_oids` - Set of OIDs that were just fetched
    ///
    /// # Returns
    /// Result describing what was processed
    async fn process_newly_available_git_data(
        &self,
        source_repo_path: &Path,
        new_oids: &HashSet<String>,
    ) -> Result<ProcessResult>;

    /// Check if there are still pending events for this identifier.
    ///
    /// Returns true if purgatory has state events or PR events for this identifier.
    ///
    /// # Arguments
    /// * `identifier` - The repository identifier
    fn has_pending_events(&self, identifier: &str) -> bool;

    /// Find the best local repository to fetch into.
    ///
    /// Given repository data from the database, finds an existing local repository
    /// that can be used as the fetch target. Typically returns the first owner's
    /// repository that exists on disk.
    ///
    /// # Arguments
    /// * `db_repo_data` - Repository data from the database
    ///
    /// # Returns
    /// Path to the target repository, or None if no suitable repo exists
    fn find_target_repo(&self, db_repo_data: &RepositoryData) -> Option<PathBuf>;

    /// Get our domain (to exclude from clone URLs).
    ///
    /// When syncing, we don't want to fetch from ourselves. This returns our
    /// domain so it can be filtered out of clone URL lists.
    fn our_domain(&self) -> Option<&str>;
}

// =============================================================================
// Real Implementation
// =============================================================================

use nostr_relay_builder::LocalRelay;
use std::process::Command;
use std::sync::Arc;
use tracing::debug;

use crate::nostr::builder::SharedDatabase;
use crate::nostr::events::RepositoryState;
use crate::purgatory::Purgatory;

/// Real implementation of `SyncContext` that connects to actual systems.
///
/// This is the production implementation used by the sync loop. It:
/// - Queries the database for repository data
/// - Collects needed OIDs from purgatory state and PR events
/// - Uses git commands to check OID existence and fetch from remote servers
/// - Delegates to the unified `process_newly_available_git_data` function
pub struct RealSyncContext {
    /// Purgatory instance for checking pending events and collecting needed OIDs
    purgatory: Arc<Purgatory>,

    /// Database for querying repository data and saving events
    database: SharedDatabase,

    /// Base path for git repositories
    git_data_path: PathBuf,

    /// Our domain (to exclude from clone URLs when syncing)
    our_domain_value: Option<String>,

    /// Local relay for notifying WebSocket subscribers
    local_relay: Option<LocalRelay>,
}

impl RealSyncContext {
    /// Create a new real sync context.
    ///
    /// # Arguments
    /// * `purgatory` - Purgatory instance for pending events
    /// * `database` - Database for queries and saves
    /// * `git_data_path` - Base path for git repositories
    /// * `our_domain` - Our domain to exclude from clone URLs
    /// * `local_relay` - Local relay for WebSocket notifications
    pub fn new(
        purgatory: Arc<Purgatory>,
        database: SharedDatabase,
        git_data_path: PathBuf,
        our_domain: Option<String>,
        local_relay: Option<LocalRelay>,
    ) -> Self {
        Self {
            purgatory,
            database,
            git_data_path,
            our_domain_value: our_domain,
            local_relay,
        }
    }
}

#[async_trait]
impl SyncContext for RealSyncContext {
    fn collect_pr_clone_urls(&self, identifier: &str) -> HashSet<String> {
        let mut urls = HashSet::new();

        for entry in self.purgatory.find_prs_for_identifier(identifier) {
            if let Some(ref event) = entry.event {
                for tag in event.tags.iter() {
                    let tag_vec = tag.clone().to_vec();
                    if tag_vec.len() >= 2 && tag_vec[0] == "clone" {
                        // Clone tags can have multiple URLs: ["clone", "url1", "url2", ...]
                        urls.extend(tag_vec[1..].iter().cloned());
                    }
                }
            }
        }

        debug!(
            identifier = %identifier,
            pr_clone_urls_count = urls.len(),
            "Collected clone URLs from PR events in purgatory"
        );

        urls
    }

    async fn fetch_repository_data(&self, identifier: &str) -> Result<RepositoryData> {
        crate::git::authorization::fetch_repository_data(&self.database, identifier).await
    }

    fn collect_needed_oids(&self, identifier: &str) -> HashSet<String> {
        let mut needed_oids = HashSet::new();

        // Collect OIDs from state events in purgatory
        for entry in self.purgatory.find_state(identifier) {
            // Parse state event to extract branch/tag commits
            if let Ok(state) = RepositoryState::from_event(entry.event.clone()) {
                for branch in &state.branches {
                    // Skip symbolic refs (e.g., "ref: refs/heads/main")
                    if !branch.commit.starts_with("ref: ") {
                        needed_oids.insert(branch.commit.clone());
                    }
                }
                for tag in &state.tags {
                    if !tag.commit.starts_with("ref: ") {
                        needed_oids.insert(tag.commit.clone());
                    }
                }
            }
        }

        // Collect OIDs from PR events in purgatory
        for entry in self.purgatory.find_prs_for_identifier(identifier) {
            // PR events have a commit field (from c-tag)
            if !entry.commit.is_empty() {
                needed_oids.insert(entry.commit.clone());
            }
        }

        debug!(
            identifier = %identifier,
            needed_oids_count = needed_oids.len(),
            "Collected needed OIDs from purgatory"
        );

        needed_oids
    }

    fn oid_exists(&self, repo_path: &Path, oid: &str) -> bool {
        crate::git::oid_exists(repo_path, oid)
    }

    async fn fetch_oids(
        &self,
        repo_path: &Path,
        url: &str,
        oids: &[String],
    ) -> Result<Vec<String>> {
        if oids.is_empty() {
            return Ok(vec![]);
        }

        // Filter to only OIDs that don't already exist locally
        let missing: Vec<&String> = oids
            .iter()
            .filter(|oid| !self.oid_exists(repo_path, oid))
            .collect();

        if missing.is_empty() {
            debug!(
                url = %url,
                "All requested OIDs already exist locally"
            );
            return Ok(oids.to_vec());
        }

        debug!(
            url = %url,
            missing_count = missing.len(),
            "Fetching OIDs from remote server"
        );

        // Use tokio::task::spawn_blocking for the git fetch since it's blocking
        let repo_path = repo_path.to_path_buf();
        let url = url.to_string();
        let missing_oids: Vec<String> = missing.into_iter().cloned().collect();

        tokio::task::spawn_blocking(move || -> Result<Vec<String>> {
            // git fetch <remote> <sha1> <sha2> ... - fetch all OIDs in one command
            let mut args = vec!["fetch", "--depth=1", &url];
            args.extend(missing_oids.iter().map(|s| s.as_str()));

            let output = Command::new("git")
                .args(&args)
                .current_dir(&repo_path)
                .output();

            match output {
                Ok(result) if result.status.success() => {
                    // Count how many OIDs we now have
                    let fetched: Vec<String> = missing_oids
                        .iter()
                        .filter(|oid| crate::git::oid_exists(&repo_path, oid))
                        .cloned()
                        .collect();

                    debug!(fetched_count = fetched.len(), "Successfully fetched OIDs");

                    Ok(fetched)
                }
                Ok(result) => {
                    let stderr = String::from_utf8_lossy(&result.stderr);
                    Err(anyhow::anyhow!("git fetch failed: {}", stderr))
                }
                Err(e) => Err(anyhow::anyhow!("git fetch command error: {}", e)),
            }
        })
        .await
        .map_err(|e| anyhow::anyhow!("Failed to spawn blocking task: {}", e))?
    }

    async fn process_newly_available_git_data(
        &self,
        source_repo_path: &Path,
        new_oids: &HashSet<String>,
    ) -> Result<ProcessResult> {
        // Delegate to the unified function from git::sync
        let result = crate::git::sync::process_newly_available_git_data(
            source_repo_path,
            new_oids,
            &self.database,
            self.local_relay.as_ref(),
            &self.purgatory,
            &self.git_data_path,
        )
        .await?;

        // Convert from git::sync::ProcessResult to our ProcessResult
        Ok(ProcessResult {
            states_released: result.states_released,
            prs_released: result.prs_released,
            repos_synced: result.repos_synced,
            refs_created: result.refs_created,
            refs_updated: result.refs_updated,
            refs_deleted: result.refs_deleted,
            errors: result.errors,
        })
    }

    fn has_pending_events(&self, identifier: &str) -> bool {
        self.purgatory.has_pending_events(identifier)
    }

    fn find_target_repo(&self, db_repo_data: &RepositoryData) -> Option<PathBuf> {
        // Find the first owner repository that exists on disk
        for announcement in &db_repo_data.announcements {
            let repo_path = self.git_data_path.join(announcement.repo_path());
            if repo_path.exists() {
                debug!(
                    repo_path = %repo_path.display(),
                    "Found existing repository for sync target"
                );
                return Some(repo_path);
            }
        }

        debug!("No existing repository found for sync target");
        None
    }

    fn our_domain(&self) -> Option<&str> {
        self.our_domain_value.as_deref()
    }
}

// =============================================================================
// Mock Implementation for Testing
// =============================================================================

#[cfg(test)]
pub mod mock {
    use super::*;
    use std::collections::HashMap;
    use std::sync::RwLock;

    /// Mock context for testing sync logic without I/O.
    ///
    /// This mock allows tests to:
    /// - Configure repository data (URLs, announcements)
    /// - Specify which OIDs are needed
    /// - Configure which URLs provide which OIDs
    /// - Track fetch attempts for assertions
    /// - Control whether events are "pending"
    ///
    /// # Example
    ///
    /// ```ignore
    /// let mock = MockSyncContext::new()
    ///     .with_urls(&["https://github.com/foo/bar.git", "https://gitlab.com/foo/bar.git"])
    ///     .with_needed_oids(&["abc123", "def456"])
    ///     .url_provides("https://github.com/foo/bar.git", &["abc123"]);
    ///
    /// // Use mock in tests...
    /// assert_eq!(mock.fetch_log(), vec!["https://github.com/foo/bar.git"]);
    /// ```
    pub struct MockSyncContext {
        /// Repository data to return from fetch_repository_data
        repo_data: RwLock<Option<RepositoryData>>,

        /// Clone URLs available for the repository (from announcements)
        clone_urls: Vec<String>,

        /// Clone URLs from PR events in purgatory
        pr_clone_urls: HashSet<String>,

        /// OIDs still needed (decremented when "fetched")
        needed_oids: RwLock<HashSet<String>>,

        /// Which OIDs each URL can provide
        url_provides_oids: HashMap<String, HashSet<String>>,

        /// Track fetch attempts for assertions
        fetch_log: RwLock<Vec<String>>,

        /// Whether there are pending events
        has_pending: RwLock<bool>,

        /// Our domain (to exclude from clone URLs)
        our_domain: Option<String>,

        /// Path to return from find_target_repo
        target_repo_path: Option<PathBuf>,

        /// Whether fetch_oids should fail
        fetch_should_fail: RwLock<HashSet<String>>,

        /// Results from process_newly_available_git_data calls
        process_results: RwLock<Vec<ProcessResult>>,
    }

    impl Default for MockSyncContext {
        fn default() -> Self {
            Self::new()
        }
    }

    impl MockSyncContext {
        /// Create a new mock context with default settings.
        pub fn new() -> Self {
            Self {
                repo_data: RwLock::new(None),
                clone_urls: Vec::new(),
                pr_clone_urls: HashSet::new(),
                needed_oids: RwLock::new(HashSet::new()),
                url_provides_oids: HashMap::new(),
                fetch_log: RwLock::new(Vec::new()),
                has_pending: RwLock::new(true),
                our_domain: None,
                target_repo_path: Some(PathBuf::from("/tmp/test-repo")),
                fetch_should_fail: RwLock::new(HashSet::new()),
                process_results: RwLock::new(Vec::new()),
            }
        }

        /// Configure clone URLs for the repository (from announcements).
        pub fn with_urls(mut self, urls: &[&str]) -> Self {
            self.clone_urls = urls.iter().map(|s| s.to_string()).collect();
            self
        }

        /// Configure clone URLs from PR events in purgatory.
        pub fn with_pr_clone_urls(mut self, urls: &[&str]) -> Self {
            self.pr_clone_urls = urls.iter().map(|s| s.to_string()).collect();
            self
        }

        /// Configure OIDs that are still needed.
        pub fn with_needed_oids(self, oids: &[&str]) -> Self {
            *self.needed_oids.write().unwrap() = oids.iter().map(|s| s.to_string()).collect();
            self
        }

        /// Configure which OIDs a specific URL can provide.
        pub fn url_provides(mut self, url: &str, oids: &[&str]) -> Self {
            self.url_provides_oids.insert(
                url.to_string(),
                oids.iter().map(|s| s.to_string()).collect(),
            );
            self
        }

        /// Configure our domain (to be excluded from clone URLs).
        pub fn with_our_domain(mut self, domain: &str) -> Self {
            self.our_domain = Some(domain.to_string());
            self
        }

        /// Configure the target repo path.
        pub fn with_target_repo(mut self, path: &str) -> Self {
            self.target_repo_path = Some(PathBuf::from(path));
            self
        }

        /// Configure whether there are pending events.
        pub fn with_pending_events(self, has_pending: bool) -> Self {
            *self.has_pending.write().unwrap() = has_pending;
            self
        }

        /// Configure a URL to fail when fetched.
        pub fn url_should_fail(self, url: &str) -> Self {
            self.fetch_should_fail
                .write()
                .unwrap()
                .insert(url.to_string());
            self
        }

        /// Get the log of fetch attempts (URLs that were fetched from).
        pub fn fetch_log(&self) -> Vec<String> {
            self.fetch_log.read().unwrap().clone()
        }

        /// Clear the fetch log.
        pub fn clear_fetch_log(&self) {
            self.fetch_log.write().unwrap().clear();
        }

        /// Get the current set of needed OIDs.
        pub fn current_needed_oids(&self) -> HashSet<String> {
            self.needed_oids.read().unwrap().clone()
        }

        /// Set whether there are pending events (can be called during test).
        pub fn set_pending_events(&self, has_pending: bool) {
            *self.has_pending.write().unwrap() = has_pending;
        }

        /// Mark specific OIDs as no longer needed (simulates successful fetch).
        pub fn mark_oids_fetched(&self, oids: &[&str]) {
            let mut needed = self.needed_oids.write().unwrap();
            for oid in oids {
                needed.remove(*oid);
            }
        }
    }

    #[async_trait]
    impl SyncContext for MockSyncContext {
        fn collect_pr_clone_urls(&self, _identifier: &str) -> HashSet<String> {
            self.pr_clone_urls.clone()
        }

        async fn fetch_repository_data(&self, _identifier: &str) -> Result<RepositoryData> {
            // Return stored repo_data or create a minimal one with clone URLs
            if let Some(data) = self.repo_data.read().unwrap().as_ref() {
                // Clone the data - this is a test mock so efficiency isn't critical
                Ok(RepositoryData {
                    announcements: data.announcements.clone(),
                    states: data.states.clone(),
                })
            } else {
                // Create minimal repo data with just clone URLs
                // In real tests, you'd set up proper announcements
                use crate::nostr::events::RepositoryAnnouncement;
                use nostr_sdk::{EventBuilder, Keys, Kind};

                let keys = Keys::generate();
                let mut announcements = Vec::new();

                if !self.clone_urls.is_empty() {
                    // Create a minimal announcement with the clone URLs
                    let mut tags = vec![nostr_sdk::Tag::custom(
                        nostr_sdk::TagKind::Custom("d".into()),
                        vec!["test-repo".to_string()],
                    )];

                    // Create a single clone tag with multiple values (NIP-34 format)
                    tags.push(nostr_sdk::Tag::custom(
                        nostr_sdk::TagKind::Custom("clone".into()),
                        self.clone_urls.to_vec(),
                    ));

                    let event = EventBuilder::new(Kind::from(30617), "")
                        .tags(tags)
                        .sign_with_keys(&keys)
                        .unwrap();

                    if let Ok(ann) = RepositoryAnnouncement::from_event(event) {
                        announcements.push(ann);
                    }
                }

                Ok(RepositoryData {
                    announcements,
                    states: Vec::new(),
                })
            }
        }

        fn collect_needed_oids(&self, _identifier: &str) -> HashSet<String> {
            self.needed_oids.read().unwrap().clone()
        }

        fn oid_exists(&self, _repo_path: &Path, oid: &str) -> bool {
            // OID exists if it's NOT in the needed set
            !self.needed_oids.read().unwrap().contains(oid)
        }

        async fn fetch_oids(
            &self,
            _repo_path: &Path,
            url: &str,
            oids: &[String],
        ) -> Result<Vec<String>> {
            // Log the fetch attempt
            self.fetch_log.write().unwrap().push(url.to_string());

            // Check if this URL should fail
            if self.fetch_should_fail.read().unwrap().contains(url) {
                return Err(anyhow::anyhow!("Simulated fetch failure for {}", url));
            }

            // Get OIDs this URL can provide
            let provides = self.url_provides_oids.get(url).cloned().unwrap_or_default();

            // Find which requested OIDs this URL can provide
            let fetched: Vec<String> = oids
                .iter()
                .filter(|oid| provides.contains(*oid))
                .cloned()
                .collect();

            // Remove fetched OIDs from needed set
            {
                let mut needed = self.needed_oids.write().unwrap();
                for oid in &fetched {
                    needed.remove(oid);
                }
            }

            Ok(fetched)
        }

        async fn process_newly_available_git_data(
            &self,
            _source_repo_path: &Path,
            _new_oids: &HashSet<String>,
        ) -> Result<ProcessResult> {
            // Return a default result - tests can check if this was called
            let result = ProcessResult::default();
            self.process_results.write().unwrap().push(result.clone());
            Ok(result)
        }

        fn has_pending_events(&self, _identifier: &str) -> bool {
            *self.has_pending.read().unwrap()
        }

        fn find_target_repo(&self, _db_repo_data: &RepositoryData) -> Option<PathBuf> {
            self.target_repo_path.clone()
        }

        fn our_domain(&self) -> Option<&str> {
            self.our_domain.as_deref()
        }
    }

    #[cfg(test)]
    mod tests {
        use super::*;

        #[tokio::test]
        async fn mock_tracks_fetch_attempts() {
            let mock = MockSyncContext::new()
                .with_urls(&["https://github.com/foo/bar.git"])
                .with_needed_oids(&["abc123"]);

            // Fetch should log the URL
            let _ = mock
                .fetch_oids(
                    Path::new("/tmp"),
                    "https://github.com/foo/bar.git",
                    &["abc123".to_string()],
                )
                .await;

            assert_eq!(
                mock.fetch_log(),
                vec!["https://github.com/foo/bar.git".to_string()]
            );
        }

        #[tokio::test]
        async fn mock_provides_configured_oids() {
            let mock = MockSyncContext::new()
                .with_needed_oids(&["abc123", "def456"])
                .url_provides("https://github.com/foo/bar.git", &["abc123"]);

            let fetched = mock
                .fetch_oids(
                    Path::new("/tmp"),
                    "https://github.com/foo/bar.git",
                    &["abc123".to_string(), "def456".to_string()],
                )
                .await
                .unwrap();

            // Only abc123 should be fetched (it's what the URL provides)
            assert_eq!(fetched, vec!["abc123".to_string()]);

            // abc123 should no longer be needed
            let needed = mock.current_needed_oids();
            assert!(!needed.contains("abc123"));
            assert!(needed.contains("def456"));
        }

        #[tokio::test]
        async fn mock_url_failure() {
            let mock = MockSyncContext::new()
                .with_needed_oids(&["abc123"])
                .url_should_fail("https://bad-server.com/repo.git");

            let result = mock
                .fetch_oids(
                    Path::new("/tmp"),
                    "https://bad-server.com/repo.git",
                    &["abc123".to_string()],
                )
                .await;

            assert!(result.is_err());
        }

        #[test]
        fn mock_oid_exists_reflects_needed_state() {
            let mock = MockSyncContext::new().with_needed_oids(&["abc123"]);

            // abc123 is needed, so it doesn't exist
            assert!(!mock.oid_exists(Path::new("/tmp"), "abc123"));

            // def456 is not needed, so it "exists"
            assert!(mock.oid_exists(Path::new("/tmp"), "def456"));

            // Mark abc123 as fetched
            mock.mark_oids_fetched(&["abc123"]);

            // Now it exists
            assert!(mock.oid_exists(Path::new("/tmp"), "abc123"));
        }

        #[test]
        fn mock_pending_events_controllable() {
            let mock = MockSyncContext::new().with_pending_events(true);
            assert!(mock.has_pending_events("test-repo"));

            mock.set_pending_events(false);
            assert!(!mock.has_pending_events("test-repo"));
        }

        #[test]
        fn mock_collect_pr_clone_urls_returns_configured_urls() {
            let mock = MockSyncContext::new().with_pr_clone_urls(&[
                "https://fork-server.com/repo.git",
                "https://another-fork.com/repo.git",
            ]);

            let urls = mock.collect_pr_clone_urls("any-identifier");

            assert_eq!(urls.len(), 2);
            assert!(urls.contains("https://fork-server.com/repo.git"));
            assert!(urls.contains("https://another-fork.com/repo.git"));
        }

        #[test]
        fn mock_collect_pr_clone_urls_empty_by_default() {
            let mock = MockSyncContext::new();

            let urls = mock.collect_pr_clone_urls("any-identifier");

            assert!(urls.is_empty());
        }
    }
}