Conversation
1) Ponder Schema - describing Ponder runtime state. 2) ENSIndexer Schema - describing ENSIndexer runtime state. 3) ENSNode Schema - describing runtime state across ENSNode services.
Replaces `makeDrizzle` DB connection helper with `makeReadOnlyDrizzle` one that is guaranteed to connect in read-only mode.
…itions. Handle multi-tenancy in ENSNode Metadata table.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
🦋 Changeset detectedLatest commit: 03fecc1 The changes in this PR will be included in the next version bump. This PR includes changesets to release 19 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
📝 WalkthroughWalkthroughThis PR adds a multi-tenant ENSNode metadata table and wiring, updates EnsDbClient to accept and scope by ensIndexerRef, converts ENSApi DB usage to a read-only Drizzle connection, and restructures the ensnode-schema package exports, build entries, and related tests/mocks. Changes
Sequence Diagram(s)sequenceDiagram
participant Indexer as EnsDbClient
participant Handler as ReadOnly Drizzle Factory
participant DB as PostgreSQL
Indexer->>Handler: init client (databaseUrl, ensIndexerRef, schema)
Note right of Handler: parse DB URL + add "-c default_transaction_read_only=on"
Indexer->>Handler: query/upsert (ensIndexerRef, key, value)
Handler->>DB: execute SQL (WHERE ensIndexerRef = ... / ON CONFLICT (ensIndexerRef, key))
DB-->>Handler: rows / ack
Handler-->>Indexer: result
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches
🧪 Generate unit tests (beta)
📝 Coding Plan for PR comments
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Pull request overview
Refactors @ensnode/ensnode-schema to expose three independently importable schema modules (Ponder, ENSIndexer, ENSNode), updates ENSIndexer’s ENSDb client to use the new ENSNode metadata schema (with multi-tenant ensIndexerRef), and makes ENSApi’s Drizzle connection read-only to avoid accidental writes.
Changes:
- Split
@ensnode/ensnode-schemainto./ponder,./ensindexer, and./ensnodeentrypoints (plus root re-export for compatibility). - Update ENSIndexer ENSDb client to read/write ENSNode metadata in the
ensnodeschema and scope records by(ensIndexerRef, key). - Update ENSApi DB initialization to use a read-only Postgres session configuration.
Reviewed changes
Copilot reviewed 15 out of 21 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| pnpm-lock.yaml | Adjusts ensnode-schema dependency classification (peer vs dev) and adds drizzle-orm dev dep. |
| packages/ensnode-schema/tsup.config.ts | Builds multiple entrypoints (root, ponder-schema, ensindexer-schema, ensnode-schema) and emits DTS. |
| packages/ensnode-schema/tsconfig.json | Switches to shared lib tsconfig and sets rootDir to resolve ambiguity. |
| packages/ensnode-schema/src/schemas/ensnode-metadata.schema.ts | Removes old ENSNode metadata definition from the previous combined ponder schema. |
| packages/ensnode-schema/src/ponder.schema.ts | Removes old “single combined schema” barrel export file. |
| packages/ensnode-schema/src/ponder-schema/schema.ts | Introduces Drizzle pgSchema wrapper/constants for the Ponder sync schema. |
| packages/ensnode-schema/src/ponder-schema/index.ts | Adds the Ponder sync-store (RPC cache) table definitions under the Ponder schema. |
| packages/ensnode-schema/src/index.ts | Re-exports ensindexer schema from the package root for backward compatibility. |
| packages/ensnode-schema/src/ensnode-schema/schema.ts | Introduces Drizzle pgSchema wrapper/constants for the ensnode schema. |
| packages/ensnode-schema/src/ensnode-schema/index.ts | Adds ENSNode metadata table with composite PK (ensIndexerRef, key). |
| packages/ensnode-schema/src/ensindexer-schema/tokenscope.subschema.ts | Adds TokenScope subschema tables. |
| packages/ensnode-schema/src/ensindexer-schema/subgraph.subschema.ts | Adds legacy-subgraph-compatible tables/relations used by the subgraph-compatible API. |
| packages/ensnode-schema/src/ensindexer-schema/registrars.subschema.ts | Adds registrar tracking subschema (registrar actions, lifecycle, etc). |
| packages/ensnode-schema/src/ensindexer-schema/protocol-acceleration.subschema.ts | Adds protocol-acceleration subschema (resolver records, reverse records, resolver relations). |
| packages/ensnode-schema/src/ensindexer-schema/index.ts | New barrel export for the ENSIndexer schema module. |
| packages/ensnode-schema/src/ensindexer-schema/ensv2.subschema.ts | Adds ENSv2 subschema tables/relations. |
| packages/ensnode-schema/package.json | Updates exports to new subpath modules and changes deps to peerDependencies. |
| apps/ensindexer/src/lib/ensdb-client/ensdb-client.ts | Updates ENSDb client to use @ensnode/ensnode-schema/ensnode, fixed schema name, and adds ensIndexerRef scoping. |
| apps/ensindexer/src/lib/ensdb-client/ensdb-client.test.ts | Updates mocks/assertions for new schema import and new composite conflict target/values. |
| apps/ensapi/src/lib/handlers/drizzle.ts | Renames to makeReadOnlyDrizzle and configures default read-only transactions for Postgres connections. |
| apps/ensapi/src/lib/db.ts | Switches ENSApi DB init to makeReadOnlyDrizzle for read-only ENSDb access. |
Files not reviewed (1)
- pnpm-lock.yaml: Language not supported
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
You can also share your feedback on Copilot code review. Take the survey.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@apps/ensapi/src/lib/handlers/drizzle.ts`:
- Around line 26-30: The connection options set when calling drizzle currently
overwrite any options returned by parseIntoClientConfig(databaseUrl); update the
call that builds the connection object (the drizzle invocation) to preserve
existing options: read the existing options from
parseIntoClientConfig(databaseUrl) (via the returned object's options property)
and combine them with "-c default_transaction_read_only=on" (e.g., append with a
space if options exists, otherwise set to the read-only option alone) so that
parseIntoClientConfig, drizzle, and the connection.options value all keep
URL-provided options.
In `@apps/ensindexer/src/lib/ensdb-client/ensdb-client.ts`:
- Around line 54-63: The constructor of EnsDbClient is repurposing the second
parameter as ensIndexerRef and hard-coding ensNodeSchema.ENSNODE_SCHEMA_NAME
into makeDrizzle, which ignores the configured database schema and breaks
multi-tenancy; update the constructor signature to accept the schema name and
the tenant ref separately (e.g., databaseUrl, databaseSchemaName, ensIndexerRef)
or ensure callers pass both values, then call makeDrizzle with databaseSchema:
databaseSchemaName (not ENSNODE_SCHEMA_NAME) and set this.ensIndexerRef from the
explicit ensIndexerRef argument; also update callers (e.g., where new
EnsDbClient(...) is invoked in singleton code) and the config model so
databaseSchemaName and ensIndexerRef are provided distinctly.
In `@packages/ensnode-schema/package.json`:
- Around line 19-23: The package.json top-level "exports" currently points to
source files ("./src/index.ts", "./src/ponder-schema/index.ts",
"./src/ensindexer-schema/index.ts", "./src/ensnode-schema/index.ts") while
"files" only includes "dist", so consumers will get broken entry points after
publish; update the top-level "exports" entries (e.g., "./": "./dist/index.js",
"./ponder": "./dist/ponder-schema/index.js", "./ensindexer":
"./dist/ensindexer-schema/index.js", "./ensnode":
"./dist/ensnode-schema/index.js") to reference built outputs, or alternatively
add "src" to the "files" array so the current "./src/*" export paths are
included in the package artifacts before publishing.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: 87674b99-ce73-416c-bc7b-f0b7cd95ff6d
⛔ Files ignored due to path filters (1)
pnpm-lock.yamlis excluded by!**/pnpm-lock.yaml
📒 Files selected for processing (20)
apps/ensapi/src/lib/db.tsapps/ensapi/src/lib/handlers/drizzle.tsapps/ensindexer/src/lib/ensdb-client/ensdb-client.test.tsapps/ensindexer/src/lib/ensdb-client/ensdb-client.tspackages/ensnode-schema/package.jsonpackages/ensnode-schema/src/ensindexer-schema/ensv2.subschema.tspackages/ensnode-schema/src/ensindexer-schema/index.tspackages/ensnode-schema/src/ensindexer-schema/protocol-acceleration.subschema.tspackages/ensnode-schema/src/ensindexer-schema/registrars.subschema.tspackages/ensnode-schema/src/ensindexer-schema/subgraph.subschema.tspackages/ensnode-schema/src/ensindexer-schema/tokenscope.subschema.tspackages/ensnode-schema/src/ensnode-schema/index.tspackages/ensnode-schema/src/ensnode-schema/schema.tspackages/ensnode-schema/src/index.tspackages/ensnode-schema/src/ponder-schema/index.tspackages/ensnode-schema/src/ponder-schema/schema.tspackages/ensnode-schema/src/ponder.schema.tspackages/ensnode-schema/src/schemas/ensnode-metadata.schema.tspackages/ensnode-schema/tsconfig.jsonpackages/ensnode-schema/tsup.config.ts
💤 Files with no reviewable changes (2)
- packages/ensnode-schema/src/ponder.schema.ts
- packages/ensnode-schema/src/schemas/ensnode-metadata.schema.ts
There was a problem hiding this comment.
Actionable comments posted: 6
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@packages/ensnode-schema/src/README.md`:
- Line 20: Replace the wording "May be large in size, depending on selected ENS
Namespace and active plugins." in the README with the more concise "May be
large, depending on selected ENS Namespace and active plugins." to match the
simpler phrasing used elsewhere and improve consistency.
- Line 13: The sentence "For example, pulling production backup into local
environment in order to test production workflows in isolation." uses the
verbose phrase "in order to test"; update that sentence to use the concise
wording "to test" (i.e., change "in order to test" -> "to test") so it reads
"For example, pulling production backup into local environment to test
production workflows in isolation." Ensure only that phrase is changed and
preserve the rest of the sentence.
- Line 27: Replace the phrase "Tiny in size." in the README with the more
concise "Tiny" to match wording consistency across sections; locate the text
"Tiny in size." and update it to "Tiny" so phrasing aligns with other short
descriptors.
- Line 17: Replace the vague phrase "influenced by Ponder implementation
details" with a concise list of the specific aspects Ponder affects (for
example: "schema structure, table naming conventions, indexing metadata,
relation mappings, and migration behavior") and update the sentence mentioning
ENSIndexer so it reads something like: "Owned by an ENSIndexer instance and
influenced by Ponder implementation details (schema structure, table naming
conventions, indexing metadata, relation mappings, migration behavior)." Refer
to the term ENSIndexer and Ponder in the README to ensure clarity.
- Around line 20-22: The README's "ENSIndexer Schema" section currently
describes size and rebuild cost but omits backup guidance; update the ENSIndexer
Schema section to mirror the Ponder Schema backup recommendation by adding a
short backup/restore recommendation (e.g., take periodic snapshots or export
indexes before changing indexing logic or plugins) and explicitly advise
creating backups prior to rebuild-triggering changes such as event handler or
plugin modifications so users can restore instead of rebuilding from scratch.
- Line 10: Replace the phrase "Usually large in size, depending on selected ENS
Namespace." with a more concise wording such as "Usually large, depending on
selected ENS Namespace." — update the README sentence to remove the redundant
"in size" for improved readability.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: a68ac681-c3ea-47d2-8dfc-ac1fcf74695a
📒 Files selected for processing (2)
packages/ensnode-schema/src/README.mdpackages/ensnode-schema/src/ponder-schema/index.ts
| - Owned by Ponder app. | ||
| - Shared across ENSIndexer instances. | ||
| - Includes responses to RPC requests made by cached public clients. | ||
| - Usually large in size, depending on selected ENS Namespace. |
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Consider more concise wording.
The phrase "large in size" could be simplified to "large" for better readability.
✍️ Proposed style improvement
-- Usually large in size, depending on selected ENS Namespace.
+- Usually large, depending on selected ENS Namespace.📝 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.
| - Usually large in size, depending on selected ENS Namespace. | |
| - Usually large, depending on selected ENS Namespace. |
🧰 Tools
🪛 LanguageTool
[style] ~10-~10: This wording could be more concise.
Context: ...ade by cached public clients. - Usually large in size, depending on selected ENS Namespace. -...
(ADJECTIVE_IN_ATTRIBUTE)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@packages/ensnode-schema/src/README.md` at line 10, Replace the phrase
"Usually large in size, depending on selected ENS Namespace." with a more
concise wording such as "Usually large, depending on selected ENS Namespace." —
update the README sentence to remove the redundant "in size" for improved
readability.
| - Usually large in size, depending on selected ENS Namespace. | ||
| - Takes a long time to build. | ||
| - Backups highly recommended for sharing RPC cache across different ENSNode environments. | ||
| - For example, pulling production backup into local environment in order to test production workflows in isolation. |
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Consider more concise wording.
The phrase "in order to test" could be simplified to "to test" for better readability.
✍️ Proposed style improvement
- - For example, pulling production backup into local environment in order to test production workflows in isolation.
+ - For example, pulling production backup into local environment to test production workflows in isolation.📝 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.
| - For example, pulling production backup into local environment in order to test production workflows in isolation. | |
| - For example, pulling production backup into local environment to test production workflows in isolation. |
🧰 Tools
🪛 LanguageTool
[style] ~13-~13: Consider a more concise word here.
Context: ...roduction backup into local environment in order to test production workflows in isolation....
(IN_ORDER_TO_PREMIUM)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@packages/ensnode-schema/src/README.md` at line 13, The sentence "For example,
pulling production backup into local environment in order to test production
workflows in isolation." uses the verbose phrase "in order to test"; update that
sentence to use the concise wording "to test" (i.e., change "in order to test"
-> "to test") so it reads "For example, pulling production backup into local
environment to test production workflows in isolation." Ensure only that phrase
is changed and preserve the rest of the sentence.
|
|
||
| ## ENSIndexer Schema | ||
|
|
||
| - Owned by an ENSIndexer instance and also influenced by Ponder implementation details, as ENSIndexer is a Ponder app. |
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Clarify what "influenced by Ponder implementation details" means.
The phrase "influenced by Ponder implementation details" is vague. Consider being more specific about what aspects are influenced (e.g., schema structure, table naming conventions, indexing metadata).
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@packages/ensnode-schema/src/README.md` at line 17, Replace the vague phrase
"influenced by Ponder implementation details" with a concise list of the
specific aspects Ponder affects (for example: "schema structure, table naming
conventions, indexing metadata, relation mappings, and migration behavior") and
update the sentence mentioning ENSIndexer so it reads something like: "Owned by
an ENSIndexer instance and influenced by Ponder implementation details (schema
structure, table naming conventions, indexing metadata, relation mappings,
migration behavior)." Refer to the term ENSIndexer and Ponder in the README to
ensure clarity.
| - Owned by an ENSIndexer instance and also influenced by Ponder implementation details, as ENSIndexer is a Ponder app. | ||
| - Isolated for specific ENSIndexer instance. | ||
| - Includes indexed data based on event handlers logic from active ENSIndexer plugins. | ||
| - May be large in size, depending on selected ENS Namespace and active plugins. |
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Consider more concise wording.
The phrase "large in size" could be simplified to "large" for consistency with the suggested improvements in other sections.
✍️ Proposed style improvement
-- May be large in size, depending on selected ENS Namespace and active plugins.
+- May be large, depending on selected ENS Namespace and active plugins.📝 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.
| - May be large in size, depending on selected ENS Namespace and active plugins. | |
| - May be large, depending on selected ENS Namespace and active plugins. |
🧰 Tools
🪛 LanguageTool
[style] ~20-~20: To form a complete sentence, be sure to include a subject.
Context: ...logic from active ENSIndexer plugins. - May be large in size, depending on selected...
(MISSING_IT_THERE)
[style] ~20-~20: This wording could be more concise.
Context: ...rom active ENSIndexer plugins. - May be large in size, depending on selected ENS Namespace an...
(ADJECTIVE_IN_ATTRIBUTE)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@packages/ensnode-schema/src/README.md` at line 20, Replace the wording "May
be large in size, depending on selected ENS Namespace and active plugins." in
the README with the more concise "May be large, depending on selected ENS
Namespace and active plugins." to match the simpler phrasing used elsewhere and
improve consistency.
| - May be large in size, depending on selected ENS Namespace and active plugins. | ||
| - May take a long time to build. Must be re-built from scratch in case of indexing logic changes (i.e. event handler code change, active plugins change). | ||
|
|
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Consider adding backup recommendation for consistency.
The Ponder Schema section recommends backups (line 12), but ENSIndexer Schema doesn't mention backups despite also being large and time-consuming to build. Consider adding backup guidance, especially since line 21 notes it "must be re-built from scratch" on logic changes—backups before such changes could be valuable.
🧰 Tools
🪛 LanguageTool
[style] ~20-~20: To form a complete sentence, be sure to include a subject.
Context: ...logic from active ENSIndexer plugins. - May be large in size, depending on selected...
(MISSING_IT_THERE)
[style] ~20-~20: This wording could be more concise.
Context: ...rom active ENSIndexer plugins. - May be large in size, depending on selected ENS Namespace an...
(ADJECTIVE_IN_ATTRIBUTE)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@packages/ensnode-schema/src/README.md` around lines 20 - 22, The README's
"ENSIndexer Schema" section currently describes size and rebuild cost but omits
backup guidance; update the ENSIndexer Schema section to mirror the Ponder
Schema backup recommendation by adding a short backup/restore recommendation
(e.g., take periodic snapshots or export indexes before changing indexing logic
or plugins) and explicitly advise creating backups prior to rebuild-triggering
changes such as event handler or plugin modifications so users can restore
instead of rebuilding from scratch.
|
|
||
| - Owned by ENSNode services. | ||
| - Includes metadata describing configuration and state of various ENSNode services. | ||
| - Tiny in size. |
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Consider more concise wording.
The phrase "Tiny in size" could be simplified to "Tiny" for consistency with the suggested improvements in other sections.
✍️ Proposed style improvement
-- Tiny in size.
+- Tiny.📝 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.
| - Tiny in size. | |
| - Tiny. |
🧰 Tools
🪛 LanguageTool
[style] ~27-~27: This wording could be more concise.
Context: ...nd state of various ENSNode services. - Tiny in size. - Takes virtually no time to be built....
(ADJECTIVE_IN_ATTRIBUTE)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@packages/ensnode-schema/src/README.md` at line 27, Replace the phrase "Tiny
in size." in the README with the more concise "Tiny" to match wording
consistency across sections; locate the text "Tiny in size." and update it to
"Tiny" so phrasing aligns with other short descriptors.
…n needed for ENSIndexer schemas
tk-o
force-pushed
the
refactor/ensdb-schema
branch
from
db6da86 to
9c05883
Compare
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 20 out of 26 changed files in this pull request and generated 1 comment.
Files not reviewed (1)
- pnpm-lock.yaml: Language not supported
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
You can also share your feedback on Copilot code review. Take the survey.
|
@greptile review |
We do not write into ENSIndexer Schema anymore, so no need for extra queries to make writes to work.
|
@greptile review |
![github-code-quality[bot]](https://avatars.githubusercontent.com/u/9919?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
apps/ensindexer/src/lib/ensdb-client/ensdb-client.ts (1)
142-149: 🛠️ Refactor suggestion | 🟠 MajorDrop the redundant
@returnstag.
Get ENSNode metadata recordalready says what this method returns, so the@returnsline is just repetition. Since this JSDoc block is already being edited, please remove it to match the repo's TS doc rules. As per coding guidelines, "Do not add JSDoc@returnstags that merely restate the method summary; remove such redundancy during PR review".🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@apps/ensindexer/src/lib/ensdb-client/ensdb-client.ts` around lines 142 - 149, Remove the redundant JSDoc `@returns` tag from the ENSNode metadata method's docblock (the block starting "Get ENSNode metadata record"); leave the summary and the `@throws` text referencing the composite PK on 'ensIndexerRef' and 'key' but delete the line that restates the return value so the docs follow the repo's rule against redundant `@returns` tags.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@apps/ensindexer/src/lib/ensdb-client/ensdb-client.ts`:
- Around line 56-60: The code in the constructor uses makeDrizzle with
ensNodeSchema and the runtime depends on the composite primary key (ON CONFLICT
(ensIndexerRef, key)), so ensure the database migration that creates the ensnode
table and adds the composite PK is shipped together with this client; add or
reference the migration that creates the ensnode schema and the composite
primary key (ensIndexerRef,key) before enabling/rolling out this code, or add an
explicit startup check in the constructor (or in the init path used by
constructor) that verifies the ensnode table and composite index exist and fails
fast with a clear error if not, preventing deployment against unmigrated ENSDb
(also apply the same fix to the other usages referenced around the code block at
symbols handling reads/writes in lines ~182-190).
---
Outside diff comments:
In `@apps/ensindexer/src/lib/ensdb-client/ensdb-client.ts`:
- Around line 142-149: Remove the redundant JSDoc `@returns` tag from the ENSNode
metadata method's docblock (the block starting "Get ENSNode metadata record");
leave the summary and the `@throws` text referencing the composite PK on
'ensIndexerRef' and 'key' but delete the line that restates the return value so
the docs follow the repo's rule against redundant `@returns` tags.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: 38bb9ba0-977e-4318-8294-032793dc2246
📒 Files selected for processing (4)
apps/ensapi/src/lib/db.tsapps/ensapi/src/lib/handlers/drizzle.tsapps/ensindexer/src/lib/ensdb-client/drizzle.tsapps/ensindexer/src/lib/ensdb-client/ensdb-client.ts
💤 Files with no reviewable changes (1)
- apps/ensindexer/src/lib/ensdb-client/drizzle.ts
| constructor(databaseUrl: string, ensIndexerRef: string) { | ||
| this.db = makeDrizzle({ | ||
| databaseSchema: databaseSchemaName, | ||
| databaseUrl, | ||
| schema, | ||
| schema: ensNodeSchema, | ||
| }); |
There was a problem hiding this comment.
Ship the ensnode schema/PK migration before rolling this out.
This client now hard-depends on the ensnode schema and on ON CONFLICT (ensIndexerRef, key), but the PR notes say migration management for that schema is deferred to a follow-up PR and local testing required manual schema creation. On any existing ENSDb that has not been migrated yet, the first read/write here will fail at runtime. Please land the schema + composite-PK migration in the same release, or explicitly block deployment of this client until the database is migrated.
Also applies to: 182-190
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@apps/ensindexer/src/lib/ensdb-client/ensdb-client.ts` around lines 56 - 60,
The code in the constructor uses makeDrizzle with ensNodeSchema and the runtime
depends on the composite primary key (ON CONFLICT (ensIndexerRef, key)), so
ensure the database migration that creates the ensnode table and adds the
composite PK is shipped together with this client; add or reference the
migration that creates the ensnode schema and the composite primary key
(ensIndexerRef,key) before enabling/rolling out this code, or add an explicit
startup check in the constructor (or in the init path used by constructor) that
verifies the ensnode table and composite index exist and fails fast with a clear
error if not, preventing deployment against unmigrated ENSDb (also apply the
same fix to the other usages referenced around the code block at symbols
handling reads/writes in lines ~182-190).
There was a problem hiding this comment.
@tk-o, understood — thanks for the context! Tracking the follow-up in #1753 and #1754 sounds like a solid plan. I'll keep an eye on those PRs to confirm the ensnode schema creation and the composite PK migration land before this client is deployed against production ENSDb instances.
🧠 Learnings used
Learnt from: CR
Repo: namehash/ensnode PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-03-02T05:28:59.644Z
Learning: Applies to apps/ensindexer/**/*.ts : Use Ponder as the indexer framework for blockchain indexing
Learnt from: tk-o
Repo: namehash/ensnode PR: 1715
File: apps/ensindexer/ponder/src/api/handlers/ensnode-api.ts:21-25
Timestamp: 2026-03-04T11:40:35.846Z
Learning: In `apps/ensindexer/ponder/src/api/handlers/ensnode-api.ts`, the guard `if (typeof publicConfig === "undefined") { throw new Error("Unreachable: ...") }` in the `/config` handler is intentionally unreachable. The `EnsDbWriterWorker` populates the ENSIndexer public config into ENSDb at startup (fail-fast), so the HTTP layer is guaranteed to only serve requests after the config is available. The `throw` is a defensive invariant, not a real error path.
Learnt from: tk-o
Repo: namehash/ensnode PR: 1639
File: packages/ensnode-sdk/src/ensapi/api/indexing-status/zod-schemas.ts:21-76
Timestamp: 2026-02-16T17:53:46.139Z
Learning: In the ENSNode SDK (`packages/ensnode-sdk`), schema builder functions exported from `zod-schemas.ts` files (e.g., `makeEnsApiIndexingStatusResponseSchema`) are considered internal API, not public API. These can have breaking changes without requiring deprecated aliases, even when exported via the `internal` entry point.
Learnt from: Goader
Repo: namehash/ensnode PR: 1663
File: packages/ens-referrals/src/v1/award-models/rev-share-limit/metrics.ts:74-96
Timestamp: 2026-02-24T15:53:06.633Z
Learning: In TypeScript code reviews, prefer placing invariants on type aliases only when the invariant is context-independent or reused across multiple fields. If an invariant depends on surrounding rules or object semantics (e.g., field-specific metrics), keep the invariant as a field JSDoc instead. This guideline applies to TS files broadly (e.g., the repo's v1/award-models and similar modules).
Learnt from: CR
Repo: namehash/ensnode PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-03-02T05:28:59.644Z
Learning: Applies to **/*.ts : Use Drizzle as the ORM for database interactions
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 20 out of 26 changed files in this pull request and generated 1 comment.
Files not reviewed (1)
- pnpm-lock.yaml: Language not supported
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
You can also share your feedback on Copilot code review. Take the survey.
There was a problem hiding this comment.
This file is modified in a later commit to only include reference to Ponder code repository. Feel free to skip reviewing it.
There was a problem hiding this comment.
This file is removed in a later commit. Feel free to skip reviewing it.
| index("rpc_request_results_chain_id_block_number_index").on(table.chainId, table.blockNumber), | ||
| ], | ||
| ); | ||
| export const PONDER_SCHEMA_NAME = "ponder_sync"; |
There was a problem hiding this comment.
Keeping this one to signal the name of Ponder Schema in database.
![vercel[bot]](https://avatars.githubusercontent.com/in/8329?s=60&v=4){kind=small}
| * @returns selected record in ENSDb. | ||
| * @throws when more than one matching metadata record is found | ||
| * (should be impossible given the PK constraint on 'key') | ||
| * (should be impossible given the composite PK constraint on |
There was a problem hiding this comment.
JSDoc @returns tag on getEnsNodeMetadata method merely restates information already conveyed by the method summary
| @@ -1,7 +1,7 @@ | |||
| import type { NodePgDatabase } from "drizzle-orm/node-postgres"; | |||
| import { eq, sql } from "drizzle-orm/sql"; | |||
| import { and, eq, sql } from "drizzle-orm/sql"; | |||
There was a problem hiding this comment.
| import { and, eq, sql } from "drizzle-orm/sql"; | |
| import { and, eq } from "drizzle-orm/sql"; |
The sql import from drizzle-orm/sql is unused in ensdb-client.ts and should be removed
Lite PR
Tip: Review docs on the ENSNode PR process
Summary
Database schemas
@ensnode/ensnode-schemapackage was refactored to support three distinct database schemas:@ensnode/ensnode-schema/ponder@ensnode/ensnode-schema/ensindexer@ensnode/ensnode-schema/ensnodeENSApi
ENSIndexer
ensIndexerRef.ensIndexerRefandkeycolumns are now part of composite primary key for ENSNode Metadata table .Why
Testing
ensnodeschema in local ENSDb.Notes for Reviewer (Optional)
main, will receive updates from PRs:Pre-Review Checklist (Blocking)