[Dashboard] Update insight query group_by from time to block_timestamp #8000
Conversation
|
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Note Other AI code review bot(s) detectedCodeRabbit has detected other AI code review bot(s) in this pull request and will avoid duplicating their findings in the review comments. This may lead to a less comprehensive review. WalkthroughUpdated analytics utilities to rename the query parameter Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant UI as Dashboard UI
participant Util as Analytics Utils
participant API as Analytics Backend
UI->>Util: getContractEventBreakdown / getContractEventAnalytics(params)
Note over Util: Build query with<br/>chain_id=${params.chainId}<br/>aggregate=toStartOfDay(toDate(block_timestamp)) as time<br/>group_by=block_timestamp
Util->>API: HTTP GET /events?chain_id=...&group_by=block_timestamp&aggregate=...
API-->>Util: Rows grouped by block_timestamp with aggregated fields
Note over Util: Post-process rows into daily series using "time" alias
Util-->>UI: Return per-day metrics
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes ✨ Finishing Touches
🧪 Generate unit tests
Comment |
How to use the Graphite Merge QueueAdd either label to this PR to merge it via the merge queue:
You must have a Graphite account in order to use the merge queue. Sign up using this link. An organization admin has enabled the Graphite Merge Queue in this repository. Please do not merge from GitHub as this will restart CI on PRs being processed by the merge queue. |
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #8000 +/- ##
=======================================
Coverage 56.64% 56.64%
=======================================
Files 904 904
Lines 58677 58677
Branches 4164 4164
=======================================
Hits 33236 33236
Misses 25335 25335
Partials 106 106
🚀 New features to boost your workflow:
|
size-limit report 📦
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (2)
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.ts (1)
31-34: Prefer grouping by the day bucket to avoid cardinality blow-upYou aggregate to daily time but group by block_timestamp + event_signature, then re-aggregate on the client. Let the backend do the daily grouping to cut response size and CPU.
Apply:
- "group_by=block_timestamp", + "group_by=toStartOfDay(toDate(block_timestamp)) as time", "group_by=topic_0 as event_signature", "aggregate=toStartOfDay(toDate(block_timestamp)) as time",If expressions aren’t allowed in group_by, we can keep current params but remove the client-side summing by switching the first group_by back to the day bucket once supported.
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-function-breakdown.ts (1)
31-34: Do daily grouping server-side for efficiencySame pattern: grouping by block_timestamp + function_selector leads to unnecessary cardinality; group by the daily bucket instead.
Apply:
- "group_by=block_timestamp", + "group_by=toStartOfDay(toDate(block_timestamp)) as time", "group_by=function_selector", "aggregate=toStartOfDay(toDate(block_timestamp)) as time",
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (5)
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.ts(1 hunks)apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts(1 hunks)apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-function-breakdown.ts(1 hunks)apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-transactions.ts(1 hunks)apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-wallet-analytics.ts(1 hunks)
🧰 Additional context used
📓 Path-based instructions (4)
**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.{ts,tsx}: Write idiomatic TypeScript with explicit function declarations and return types
Limit each file to one stateless, single-responsibility function for clarity
Re-use shared types from@/typesor localtypes.tsbarrels
Prefer type aliases over interface except for nominal shapes
Avoidanyandunknownunless unavoidable; narrow generics when possible
Choose composition over inheritance; leverage utility types (Partial,Pick, etc.)
Comment only ambiguous logic; avoid restating TypeScript in prose
**/*.{ts,tsx}: Use explicit function declarations and explicit return types in TypeScript
Limit each file to one stateless, single‑responsibility function
Re‑use shared types from@/typeswhere applicable
Prefertypealiases overinterfaceexcept for nominal shapes
Avoidanyandunknownunless unavoidable; narrow generics when possible
Prefer composition over inheritance; use utility types (Partial, Pick, etc.)
Lazy‑import optional features and avoid top‑level side‑effects to reduce bundle size
Files:
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-transactions.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-wallet-analytics.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-function-breakdown.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts
**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (CLAUDE.md)
Load heavy dependencies inside async paths to keep initial bundle lean (lazy loading)
Files:
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-transactions.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-wallet-analytics.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-function-breakdown.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts
apps/{dashboard,playground-web}/**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
apps/{dashboard,playground-web}/**/*.{ts,tsx}: Import UI primitives from@/components/ui/*(Button, Input, Select, Tabs, Card, Sidebar, Badge, Separator) in dashboard and playground apps
UseNavLinkfor internal navigation with automatic active states in dashboard and playground apps
Use Tailwind CSS only – no inline styles or CSS modules
Usecn()from@/lib/utilsfor conditional class logic
Use design system tokens (e.g.,bg-card,border-border,text-muted-foreground)
Server Components (Node edge): Start files withimport "server-only";
Client Components (browser): Begin files with'use client';
Always callgetAuthToken()to retrieve JWT from cookies on server side
UseAuthorization: Bearerheader – never embed tokens in URLs
Return typed results (e.g.,Project[],User[]) – avoidany
Wrap client-side data fetching calls in React Query (@tanstack/react-query)
Use descriptive, stablequeryKeysfor React Query cache hits
ConfigurestaleTime/cacheTimein React Query based on freshness (default ≥ 60s)
Keep tokens secret via internal API routes or server actions
Never importposthog-jsin server components
Files:
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-transactions.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-wallet-analytics.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-function-breakdown.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts
apps/{dashboard,playground}/**/*.{ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
apps/{dashboard,playground}/**/*.{ts,tsx}: Import UI primitives from@/components/ui/_(e.g., Button, Input, Tabs, Card)
UseNavLinkfor internal navigation to get active state handling
Use Tailwind CSS for styling; no inline styles
Merge class names withcn()from@/lib/utilsfor conditional classes
Stick to design tokens (e.g., bg-card, border-border, text-muted-foreground)
Server Components must start withimport "server-only"; usenext/headers, server‑only env, heavy data fetching, andredirect()where appropriate
Client Components must start with'use client'; handle interactivity with hooks and browser APIs
Server-side data fetching: callgetAuthToken()from cookies, sendAuthorization: Bearer <token>header, and return typed results (avoidany)
Client-side data fetching: wrap calls in React Query with descriptive, stablequeryKeysand set sensiblestaleTime/cacheTime(≥ 60s default); keep tokens secret via internal routes or server actions
Do not importposthog-jsin server components (client-side only)
Files:
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-transactions.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-wallet-analytics.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-function-breakdown.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts
🧠 Learnings (1)
📚 Learning: 2025-07-18T19:19:55.613Z
Learnt from: CR
PR: thirdweb-dev/js#0
File: CLAUDE.md:0-0
Timestamp: 2025-07-18T19:19:55.613Z
Learning: Applies to src/@/analytics/report.ts : Review `src/@/analytics/report.ts` before adding analytics events to check for duplicates
Applied to files:
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (6)
- GitHub Check: E2E Tests (pnpm, webpack)
- GitHub Check: Size
- GitHub Check: E2E Tests (pnpm, vite)
- GitHub Check: Unit Tests
- GitHub Check: Lint Packages
- GitHub Check: Analyze (javascript)
🔇 Additional comments (1)
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts (1)
35-35: I’ve initiated verification to confirm the existing grouping and inspect surrounding context. Once results are in, I’ll update the comment accordingly.
| const queryParams = [ | ||
| `chain=${params.chainId}`, | ||
| "group_by=time", | ||
| "group_by=block_timestamp", |
There was a problem hiding this comment.
💡 Verification agent
🧩 Analysis chain
Bug: per-block buckets returned instead of per-day totals
Same issue here—grouping on block_timestamp explodes cardinality and breaks the intended day series.
Apply:
- "group_by=block_timestamp",
+ "group_by=toStartOfDay(toDate(block_timestamp)) as time",🏁 Script executed:
#!/usr/bin/env bash
set -e
# Locate the contract-transactions utility file
file=$(fd --hidden --relative-path --glob 'contract-transactions.ts')
[ -n "$file" ] || { echo "File not found"; exit 1; }
# Print the first 200 lines to inspect the group_by usage
sed -n '1,200p' "$file"Length of output: 2558
Group by day instead of block timestamp
Change in apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-transactions.ts line 35:
- "group_by=block_timestamp",
+ "group_by=toStartOfDay(toDate(block_timestamp))",📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| "group_by=block_timestamp", | |
| // … | |
| "group_by=toStartOfDay(toDate(block_timestamp))", | |
| // … |
🤖 Prompt for AI Agents
In
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-transactions.ts
around line 35, the query currently uses "group_by=block_timestamp" but should
group by day; replace the parameter with "group_by=day" (and adjust any related
date-bucket parsing/formatting code if it assumes a block timestamp bucket) so
the analytics aggregate is performed per day instead of per block timestamp.
| const queryParams = [ | ||
| `chain=${params.chainId}`, | ||
| "group_by=time", | ||
| "group_by=block_timestamp", |
There was a problem hiding this comment.
💡 Verification agent
🧩 Analysis chain
Bug: unique wallets no longer aggregated by day
Grouping by block_timestamp returns distinct-counts per block, not per day, changing chart semantics and increasing payload size.
Apply:
- "group_by=block_timestamp",
+ "group_by=toStartOfDay(toDate(block_timestamp)) as time",🏁 Script executed:
#!/bin/bash
# Locate the analytics utility file
fd contract-wallet-analytics.tsLength of output: 156
🏁 Script executed:
#!/bin/bash
sed -n '1,100p' 'apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-wallet-analytics.ts'Length of output: 2235
Aggregate by day instead of per-block timestamps
Replace in apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-wallet-analytics.ts (line 35):
- "group_by=block_timestamp",
+ "group_by=toStartOfDay(toDate(block_timestamp)) as time",This ensures unique wallet counts are batched per day rather than per block (clickhouse.com).
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| "group_by=block_timestamp", | |
| "group_by=toStartOfDay(toDate(block_timestamp)) as time", |
🤖 Prompt for AI Agents
In
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-wallet-analytics.ts
around line 35, change the grouping from per-block timestamps to daily buckets
by replacing "group_by=block_timestamp" with an expression that rounds
timestamps to the day (e.g. "group_by=toStartOfDay(block_timestamp)" or
"group_by=toDate(block_timestamp)" depending on downstream usage); ensure any
SELECT and GROUP BY use the same day-rounded expression so unique wallet counts
are aggregated per day rather than per block.
gregfromstl
force-pushed
the
fix/insight-group-by
branch
from
56258ca to
2512e5f
Compare
![graphite-app[bot]](https://avatars.githubusercontent.com/in/158384?s=60&v=4){kind=small}
| "group_by=block_timestamp", | ||
| "aggregate=toStartOfDay(toDate(block_timestamp)) as time", |
There was a problem hiding this comment.
The change from group_by=time to group_by=block_timestamp introduces a potential field naming inconsistency. While the grouping parameter now uses block_timestamp, the aggregation still creates a time alias with toStartOfDay(toDate(block_timestamp)) as time.
This mismatch between the grouping field and aggregation alias might cause issues if the backend expects consistent naming between these clauses. Consider either:
-
Updating the aggregation to use a matching alias:
"aggregate=toStartOfDay(toDate(block_timestamp)) as block_timestamp" -
Or documenting why this apparent inconsistency is intentional and safe in this context
This would ensure the query parameters maintain logical consistency and reduce the risk of unexpected behavior.
| "group_by=block_timestamp", | |
| "aggregate=toStartOfDay(toDate(block_timestamp)) as time", | |
| "group_by=block_timestamp", | |
| "aggregate=toStartOfDay(toDate(block_timestamp)) as block_timestamp", |
Spotted by Diamond
Is this helpful? React 👍 or 👎 to let us know.
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (5)
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.ts (5)
29-35: Confirm cardinality impact of grouping by raw block_timestamp; prefer server-side day bucketing if supportedGrouping by block_timestamp can explode rows and shift daily bucketing to the client. If Insight supports grouping by the day boundary directly, switch to server-side daily grouping to reduce payload and CPU in the browser.
Apply if supported:
const queryParams = [ `chain=${params.chainId}`, - "group_by=block_timestamp", + "group_by=toStartOfDay(toDate(block_timestamp)) as time", "group_by=topic_0 as event_signature", - "aggregate=toStartOfDay(toDate(block_timestamp)) as time", "aggregate=count(*) as count",If the API does not support grouping by computed expressions, keep your current approach and see the next comment to remove timezone ambiguity.
33-33: If grouping must remain on block_timestamp, return epoch for time to avoid timezone parsing issuesThe current time comes back as a string; new Date(string) can be locale-dependent. Returning epoch seconds is safer.
- "aggregate=toStartOfDay(toDate(block_timestamp)) as time", + "aggregate=toUnixTimestamp(toStartOfDay(toDate(block_timestamp))) as time",
100-103: Parse epoch seconds when present; falls back to ISO parsingPairs with the previous suggestion; keeps behavior correct either way.
- values.push({ - time: new Date(day), - ...value, - } as EventBreakdownEntry); + const ts = Number(day); + values.push({ + time: Number.isFinite(ts) ? new Date(ts * 1000) : new Date(day), + ...value, + });
58-60: Guard against empty/missing aggregations to avoid runtime errorsInsight occasionally returns empty aggregations; this will throw on
[0].- const json = (await res.json()) as InsightResponse; - const aggregations = Object.values(json.aggregations[0]); + const json = (await res.json()) as InsightResponse; + const aggObj = json?.aggregations?.[0] ?? {}; + const aggregations = Object.values(aggObj); + if (Object.keys(aggObj).length === 0) { + return []; + }
107-109: Minor: avoid redundant Date construction
timeis already a Date.- return values.sort((a, b) => { - return new Date(a.time).getTime() - new Date(b.time).getTime(); - }); + return values.sort((a, b) => a.time.getTime() - b.time.getTime());
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (2)
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.ts(1 hunks)apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts(1 hunks)
🚧 Files skipped from review as they are similar to previous changes (1)
- apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts
🧰 Additional context used
📓 Path-based instructions (4)
**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.{ts,tsx}: Write idiomatic TypeScript with explicit function declarations and return types
Limit each file to one stateless, single-responsibility function for clarity
Re-use shared types from@/typesor localtypes.tsbarrels
Prefer type aliases over interface except for nominal shapes
Avoidanyandunknownunless unavoidable; narrow generics when possible
Choose composition over inheritance; leverage utility types (Partial,Pick, etc.)
Comment only ambiguous logic; avoid restating TypeScript in prose
**/*.{ts,tsx}: Use explicit function declarations and explicit return types in TypeScript
Limit each file to one stateless, single‑responsibility function
Re‑use shared types from@/typeswhere applicable
Prefertypealiases overinterfaceexcept for nominal shapes
Avoidanyandunknownunless unavoidable; narrow generics when possible
Prefer composition over inheritance; use utility types (Partial, Pick, etc.)
Lazy‑import optional features and avoid top‑level side‑effects to reduce bundle size
Files:
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.ts
**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (CLAUDE.md)
Load heavy dependencies inside async paths to keep initial bundle lean (lazy loading)
Files:
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.ts
apps/{dashboard,playground-web}/**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
apps/{dashboard,playground-web}/**/*.{ts,tsx}: Import UI primitives from@/components/ui/*(Button, Input, Select, Tabs, Card, Sidebar, Badge, Separator) in dashboard and playground apps
UseNavLinkfor internal navigation with automatic active states in dashboard and playground apps
Use Tailwind CSS only – no inline styles or CSS modules
Usecn()from@/lib/utilsfor conditional class logic
Use design system tokens (e.g.,bg-card,border-border,text-muted-foreground)
Server Components (Node edge): Start files withimport "server-only";
Client Components (browser): Begin files with'use client';
Always callgetAuthToken()to retrieve JWT from cookies on server side
UseAuthorization: Bearerheader – never embed tokens in URLs
Return typed results (e.g.,Project[],User[]) – avoidany
Wrap client-side data fetching calls in React Query (@tanstack/react-query)
Use descriptive, stablequeryKeysfor React Query cache hits
ConfigurestaleTime/cacheTimein React Query based on freshness (default ≥ 60s)
Keep tokens secret via internal API routes or server actions
Never importposthog-jsin server components
Files:
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.ts
apps/{dashboard,playground}/**/*.{ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
apps/{dashboard,playground}/**/*.{ts,tsx}: Import UI primitives from@/components/ui/_(e.g., Button, Input, Tabs, Card)
UseNavLinkfor internal navigation to get active state handling
Use Tailwind CSS for styling; no inline styles
Merge class names withcn()from@/lib/utilsfor conditional classes
Stick to design tokens (e.g., bg-card, border-border, text-muted-foreground)
Server Components must start withimport "server-only"; usenext/headers, server‑only env, heavy data fetching, andredirect()where appropriate
Client Components must start with'use client'; handle interactivity with hooks and browser APIs
Server-side data fetching: callgetAuthToken()from cookies, sendAuthorization: Bearer <token>header, and return typed results (avoidany)
Client-side data fetching: wrap calls in React Query with descriptive, stablequeryKeysand set sensiblestaleTime/cacheTime(≥ 60s default); keep tokens secret via internal routes or server actions
Do not importposthog-jsin server components (client-side only)
Files:
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.ts
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (6)
- GitHub Check: E2E Tests (pnpm, esbuild)
- GitHub Check: E2E Tests (pnpm, vite)
- GitHub Check: Size
- GitHub Check: Unit Tests
- GitHub Check: Lint Packages
- GitHub Check: Analyze (javascript)
…ecated chain param Updated all insight /v1/events endpoint calls to use chain_id parameter as chain is deprecated. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
There was a problem hiding this comment.
Actionable comments posted: 2
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.ts (1)
36-40: Convert timestamp filters to milliseconds
getUnixTime()returns seconds, but the Insight events API expects milliseconds since the Unix epoch (UTC). Multiply by 1000 for bothfilter_block_timestamp_gteandfilter_block_timestamp_lte.? `filter_block_timestamp_gte=${getUnixTime(params.startDate) * 1000}` : "", params.endDate ? `filter_block_timestamp_lte=${getUnixTime(params.endDate) * 1000}` : "",
♻️ Duplicate comments (1)
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts (1)
35-37: Field/alias mismatch noted already; align group_by with returned alias.Prior feedback flagged the inconsistency between
group_by=block_timestampandas time. The fix above resolves both the naming mismatch and the grouping granularity.
🧹 Nitpick comments (3)
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/total-contract-events.ts (1)
23-25: LGTM on chain_id switch; consider normalizing count expression.The param rename looks correct. For consistency with other files (one uses
count(*), anothercount(block_timestamp)), considercount()to avoid null-sensitivity and keep queries uniform.- "aggregate=count(block_number) as total", + "aggregate=count() as total",apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts (1)
66-79: Tighten runtime type narrowing with a type guard to satisfy TS and avoid casts.Current
"in"checks still leavevaluetyped asobject, so property access may trip strict TS configs. Add a type predicate and use it.+function isTimeCountEntry(v: unknown): v is { time: string; count: number } { + return ( + typeof v === "object" && + v !== null && + typeof (v as any).time === "string" && + typeof (v as any).count === "number" + ); +} for (const value of aggregations) { - if ( - typeof value === "object" && - value !== null && - "time" in value && - "count" in value && - typeof value.time === "string" && - typeof value.count === "number" - ) { + if (isTimeCountEntry(value)) { values.push({ - count: value.count, - time: new Date(value.time), + count: value.count, + time: new Date(value.time), }); } }apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.ts (1)
61-79: Strengthen type narrowing with a predicate for aggregation rows.Avoid accessing properties on a generic
object. This keeps strict TS happy and documents the wire shape.+function isAggregationEntry(v: unknown): v is InsightAggregationEntry { + return ( + typeof v === "object" && + v !== null && + typeof (v as any).event_signature === "string" && + typeof (v as any).time === "string" && + typeof (v as any).count === "number" + ); +} const collectedAggregations: InsightAggregationEntry[] = []; for (const value of aggregations) { - if ( - typeof value === "object" && - value !== null && - "time" in value && - "count" in value && - "event_signature" in value && - typeof value.event_signature === "string" && - typeof value.time === "string" && - typeof value.count === "number" - ) { - collectedAggregations.push({ - count: value.count, - event_signature: value.event_signature, - time: value.time, - }); - } + if (isAggregationEntry(value)) { + collectedAggregations.push({ + count: value.count, + event_signature: value.event_signature, + time: value.time, + }); + } }
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (3)
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.ts(1 hunks)apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts(1 hunks)apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/total-contract-events.ts(1 hunks)
🧰 Additional context used
📓 Path-based instructions (4)
**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.{ts,tsx}: Write idiomatic TypeScript with explicit function declarations and return types
Limit each file to one stateless, single-responsibility function for clarity
Re-use shared types from@/typesor localtypes.tsbarrels
Prefer type aliases over interface except for nominal shapes
Avoidanyandunknownunless unavoidable; narrow generics when possible
Choose composition over inheritance; leverage utility types (Partial,Pick, etc.)
Comment only ambiguous logic; avoid restating TypeScript in prose
**/*.{ts,tsx}: Use explicit function declarations and explicit return types in TypeScript
Limit each file to one stateless, single‑responsibility function
Re‑use shared types from@/typeswhere applicable
Prefertypealiases overinterfaceexcept for nominal shapes
Avoidanyandunknownunless unavoidable; narrow generics when possible
Prefer composition over inheritance; use utility types (Partial, Pick, etc.)
Lazy‑import optional features and avoid top‑level side‑effects to reduce bundle size
Files:
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/total-contract-events.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts
**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (CLAUDE.md)
Load heavy dependencies inside async paths to keep initial bundle lean (lazy loading)
Files:
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/total-contract-events.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts
apps/{dashboard,playground-web}/**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
apps/{dashboard,playground-web}/**/*.{ts,tsx}: Import UI primitives from@/components/ui/*(Button, Input, Select, Tabs, Card, Sidebar, Badge, Separator) in dashboard and playground apps
UseNavLinkfor internal navigation with automatic active states in dashboard and playground apps
Use Tailwind CSS only – no inline styles or CSS modules
Usecn()from@/lib/utilsfor conditional class logic
Use design system tokens (e.g.,bg-card,border-border,text-muted-foreground)
Server Components (Node edge): Start files withimport "server-only";
Client Components (browser): Begin files with'use client';
Always callgetAuthToken()to retrieve JWT from cookies on server side
UseAuthorization: Bearerheader – never embed tokens in URLs
Return typed results (e.g.,Project[],User[]) – avoidany
Wrap client-side data fetching calls in React Query (@tanstack/react-query)
Use descriptive, stablequeryKeysfor React Query cache hits
ConfigurestaleTime/cacheTimein React Query based on freshness (default ≥ 60s)
Keep tokens secret via internal API routes or server actions
Never importposthog-jsin server components
Files:
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/total-contract-events.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts
apps/{dashboard,playground}/**/*.{ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
apps/{dashboard,playground}/**/*.{ts,tsx}: Import UI primitives from@/components/ui/_(e.g., Button, Input, Tabs, Card)
UseNavLinkfor internal navigation to get active state handling
Use Tailwind CSS for styling; no inline styles
Merge class names withcn()from@/lib/utilsfor conditional classes
Stick to design tokens (e.g., bg-card, border-border, text-muted-foreground)
Server Components must start withimport "server-only"; usenext/headers, server‑only env, heavy data fetching, andredirect()where appropriate
Client Components must start with'use client'; handle interactivity with hooks and browser APIs
Server-side data fetching: callgetAuthToken()from cookies, sendAuthorization: Bearer <token>header, and return typed results (avoidany)
Client-side data fetching: wrap calls in React Query with descriptive, stablequeryKeysand set sensiblestaleTime/cacheTime(≥ 60s default); keep tokens secret via internal routes or server actions
Do not importposthog-jsin server components (client-side only)
Files:
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/total-contract-events.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.tsapps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts
🧠 Learnings (1)
📚 Learning: 2025-07-18T19:19:55.613Z
Learnt from: CR
PR: thirdweb-dev/js#0
File: CLAUDE.md:0-0
Timestamp: 2025-07-18T19:19:55.613Z
Learning: Applies to src/@/analytics/report.ts : Review `src/@/analytics/report.ts` before adding analytics events to check for duplicates
Applied to files:
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)
- GitHub Check: Size
- GitHub Check: Lint Packages
- GitHub Check: Analyze (javascript)
| `chain_id=${params.chainId}`, | ||
| "group_by=block_timestamp", | ||
| "group_by=topic_0 as event_signature", | ||
| "aggregate=toStartOfDay(toDate(block_timestamp)) as time", | ||
| "aggregate=count(*) as count", |
There was a problem hiding this comment.
Same grouping issue: per-day breakdown should group by the day expression, not raw block_timestamp.
Group by the day bucket (aliased time) alongside event_signature, and remove the separate aggregate for time.
- `chain_id=${params.chainId}`,
- "group_by=block_timestamp",
- "group_by=topic_0 as event_signature",
- "aggregate=toStartOfDay(toDate(block_timestamp)) as time",
+ `chain_id=${params.chainId}`,
+ "group_by=toStartOfDay(toDate(block_timestamp)) as time",
+ "group_by=topic_0 as event_signature",Optionally normalize count:
- "aggregate=count(*) as count",
+ "aggregate=count() as count",📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| `chain_id=${params.chainId}`, | |
| "group_by=block_timestamp", | |
| "group_by=topic_0 as event_signature", | |
| "aggregate=toStartOfDay(toDate(block_timestamp)) as time", | |
| "aggregate=count(*) as count", | |
| `chain_id=${params.chainId}`, | |
| "group_by=toStartOfDay(toDate(block_timestamp)) as time", | |
| "group_by=topic_0 as event_signature", | |
| "aggregate=count() as count", |
🤖 Prompt for AI Agents
In
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-event-breakdown.ts
around lines 30 to 34, the query groups by raw block_timestamp instead of the
day bucket; change grouping to use the day expression
(toStartOfDay(toDate(block_timestamp)) as time) and group_by that alias plus
topic_0 as event_signature, remove the separate aggregate entry that defines
time, and keep aggregate=count(*) as count (or optionally normalize count
afterwards).
| `chain_id=${params.chainId}`, | ||
| "group_by=block_timestamp", | ||
| "aggregate=toStartOfDay(toDate(block_timestamp)) as time", |
There was a problem hiding this comment.
💡 Verification agent
🧩 Analysis chain
Daily buckets will fragment: grouping by raw block_timestamp yields per-block groups.
If the intent is daily aggregation, group_by=block_timestamp creates one group per block, not per day. Group by the day expression (aliased as time) and drop the redundant aggregate for time.
- `chain_id=${params.chainId}`,
- "group_by=block_timestamp",
- "aggregate=toStartOfDay(toDate(block_timestamp)) as time",
+ `chain_id=${params.chainId}`,
+ "group_by=toStartOfDay(toDate(block_timestamp)) as time",Optionally normalize count:
- "aggregate=count(block_timestamp) as count",
+ "aggregate=count() as count",🌐 Web query:
Does the Insight API support grouping by an aliased expression in the `group_by` param (e.g., `group_by=toStartOfDay(toDate(block_timestamp)) as time`), and should time filters use epoch seconds?
💡 Result:
Short answer: No — the group_by parameter must reference an existing field/alias (or the API's documented filter_alias), not an arbitrary SQL expression with an inline alias. And time filters depend on the provider: some Insight APIs (e.g. Dune) expect date/time strings (use timestamp/date strings in filters), while others (e.g. AWS X‑Ray Insights) require Unix epoch seconds — check the specific API docs. [1][2]
Sources:
- Dune API — filtering / result parameters (dates used as strings; group/filter operate on columns). [1]
- AWS X‑Ray GetInsightImpactGraph — start/end times in Unix time seconds. [2]
Group by existing alias, not inline SQL
Insight API only accepts columns or documented aliases in group_by. To bucket by day, keep aggregate=toStartOfDay(toDate(block_timestamp)) as time and change "group_by=block_timestamp" to "group_by=time" (or use the provider’s filter_alias for daily grouping). Optionally normalize counts: use aggregate=count() as count.
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts:34-36
🤖 Prompt for AI Agents
In
apps/dashboard/src/app/(app)/(dashboard)/(chain)/[chain_id]/[contractAddress]/analytics/utils/contract-events.ts
around lines 34-36, the query uses an inline expression in group_by which the
Insight API rejects; keep the aggregate alias
aggregate=toStartOfDay(toDate(block_timestamp)) as time and replace
"group_by=block_timestamp" with "group_by=time" (or the provider’s daily
filter_alias), and optionally change/augment aggregates to include a normalized
count like aggregate=count() as count if you need per-day counts.
Summary
block_timestampinstead oftimefor thegroup_byparameterChanges
group_by=timetogroup_by=block_timestampin:contract-event-breakdown.tscontract-events.tscontract-function-breakdown.tscontract-transactions.tscontract-wallet-analytics.tsTest plan
🤖 Generated with Claude Code
PR-Codex overview
This PR focuses on updating the query parameters in three utility files related to contract events in the dashboard application. The changes primarily involve renaming the
chainparameter tochain_idand modifying the grouping criteria for data aggregation.Detailed summary
total-contract-events.ts, changedchain=${params.chainId}tochain_id=${params.chainId}.contract-events.ts, updatedchain=${params.chainId}tochain_id=${params.chainId}and changed grouping fromgroup_by=timetogroup_by=block_timestamp.contract-event-breakdown.ts, modifiedchain=${params.chainId}tochain_id=${params.chainId}and changed grouping fromgroup_by=timetogroup_by=block_timestamp.Summary by CodeRabbit