Document relation conflicts from validation system for manual issue creation#12
Closed
Copilot wants to merge 5 commits into
Closed
Document relation conflicts from validation system for manual issue creation#12Copilot wants to merge 5 commits into
Copilot wants to merge 5 commits into
Conversation
Co-authored-by: Johnaverse <110527930+Johnaverse@users.noreply.github.com>
Co-authored-by: Johnaverse <110527930+Johnaverse@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Create issues for each relation_conflicts from /validate
Add endpoint to auto-create GitHub issues for relation conflicts
Feb 9, 2026
Co-authored-by: Johnaverse <110527930+Johnaverse@users.noreply.github.com>
Co-authored-by: Johnaverse <110527930+Johnaverse@users.noreply.github.com>
Copilot
AI
changed the title
Add endpoint to auto-create GitHub issues for relation conflicts
Document relation conflicts from validation system for manual issue creation
Feb 9, 2026
Owner
|
@copilot you cannot create issues in this repo ? |
Contributor
Author
I don't have access to a GitHub token in this environment to create issues programmatically. The If you'd like me to create the issues automatically, you can:
Otherwise, the 3 issues are documented in |
Johnaverse
pushed a commit
that referenced
this pull request
May 12, 2026
Seven independent fixes for issues surfaced in PR review. Each is verified by an existing or new test. #2 indexer doesn't retain chain.slip44 (bug) indexChainsSource and mergeChainlistEntry now keep the slip44 field from raw sources, so attachSlip44Info can actually populate chain.slip44Info. New regression test verifies the round-trip. #3,#9 SLIP-44 fetch failure indistinguishable from empty success (bug) loader.js now only calls parseSLIP44 when slip44Text isn't null, preserving null end-to-end through applyDataToCache and the snapshot round-trip. /sources will now correctly report slip44: 'not loaded' when the fetch failed (was always 'loaded' because {} is truthy). #8,#11 Starknet fallback chainId exceeds Number.MAX_SAFE_INTEGER (bug) Removed the Starknet entry (chainId 23448594291968334) from data/l2beat-fallback.json. The codebase treats chainId as a JS Number for object keys, parseIntParam, and comparisons, so a chainId beyond 2^53-1 would round and cause silent mis-lookups. Documented in the file's note field; the live API can still surface Starknet once the indexer learns to handle BigInt IDs. #12 L2BEAT stale data persists across refreshes (bug) indexL2BeatSource now clears chain.l2Beat and removes 'l2beat' from chain.sources for any chain whose chainId isn't in the fresh project list. Defensive: only clears when the new list is non-empty, so a transient unavailable fetch doesn't wipe known data. New regression test exercises a refresh with a dropped project. #1 /export had no rate limit (CodeQL: missing-rate-limiting) Wrapped /export with the same RELOAD_RATE_LIMIT_MAX config as /reload (both are I/O-heavy and previously unguarded). #5,#10 fetchData returned undefined for unknown format (contract bug) Added an explicit `return null` in the format-fallthrough branch with a logged error, matching the documented "returns null on failure" contract. New tests cover both the success and unknown-format paths. #6 "All data sources failed" error message misleading Renamed to "All core data sources failed" since L2BEAT is intentionally excluded from loadedSourceCount (it has its own static fallback and isn't useful without the core sources). Both existing test assertions updated. #7 scaling.js comment mentioned non-existent 'unavailable' freshness Updated to reflect actual runtime: only 'live' and 'fallback' ever appear in chain.l2Beat.dataFreshness. Chains the merge couldn't reach simply have no l2Beat field. Skipped (per triage): #4 duplicate RPC sweep on warm start — minor wastefulness, not user-visible; deferred. Suite: 582 passing / 0 failing / 4 skipped (was 576/0/4). +6 new regression tests (indexer-slip44, indexer-l2beat clearing, transport fetch contract).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The
/validateendpoint identifies 3 relation conflicts where The Graph indicates testnet relations but chainlist marks chains as non-testnet. These need to be tracked as GitHub issues.Changes
ISSUES_TO_CREATE.md: Documents 3 relation conflicts with ready-to-use issue titles, bodies, and labelstestnetOfin theGraph,isTestnet=falsein chainlisttestnetOfin theGraph,isTestnet=falsein chainlisttestnetOfin theGraph,isTestnet=falsein chainlistEach entry includes formatted issue content with:
[Data Validation] Relation conflict for chain {id} ({name})data-validation,relation-conflict,automatedAction Required
Create the 3 issues documented in
ISSUES_TO_CREATE.mdvia GitHub UI, gh CLI, or API.💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.