Swagger Json Automation #134
Conversation
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. 📝 WalkthroughWalkthroughAdds a DeepWiki badge to README, adds a runtime-scoped H2 dependency to the Maven POM, introduces a new application-swagger.properties with many placeholder Swagger-related settings, and adds a GitHub Actions workflow that builds the API, runs it to fetch Swagger JSON, and opens a PR to update docs in a separate repository. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant GH as "GitHub Actions\nRunner"
participant Build as "Maven Build\n(Java 17)"
participant API as "Local API\n(server:9090)"
participant Poll as "Poller\n(/v3/api-docs)"
participant Docs as "amrit-docs\nRepository"
participant PR as "Create Pull Request\nAction"
GH->>Build: checkout repo & setup JDK\nmvn -DskipTests package
GH->>API: start app (profile=swagger)\njava -jar ... (port 9090)
GH->>Poll: poll http://localhost:9090/v3/api-docs\n(retry up to 30 times)
Poll-->>GH: 200 + valid JSON (fhir-api.json)
GH->>API: stop server (kill PID)
GH->>Docs: checkout amrit-docs repo
GH->>Docs: copy fhir-api.json -> docs/swagger/
GH->>PR: create pull request to main\n(branch auto/swagger-update-...)
PR-->>GH: PR created
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes 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)
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 |
![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
🤖 Fix all issues with AI agents
In `@src/main/resources/application-swagger.properties`:
- Around line 52-57: Change the actuator exposure in the swagger profile so you
no longer expose all endpoints via management.endpoints.web.exposure.include;
replace the wildcard with an explicit allow-list (for example only "health" and
"info") or alternatively bind the management port to localhost by setting
management.server.address to 127.0.0.1 and/or a dedicated management.server.port
so sensitive endpoints like env and configprops are not publicly reachable;
update the entry for management.endpoints.web.exposure.include and add the
management.server.address/management.server.port properties around where
server.port and logging.level.* are defined.
- Around line 85-145: Multiple properties are defined twice (e.g.,
cors.allowed-origins, jwt.secret, eaushadhiStoreStockDetailsUrl,
eaushadhiStoreStockAckUrl, eAushadhiDummy, benSearchByBenIDURL, userAuthURL,
fhirUserName, fhirPassword, abhaMode, clientID, clientSecret,
ndhmuserAuthenticate, generateABDM_NotifySMS, atomsFeedStartPage,
feedAuthUserName, feedAuthPassword, parentUrl, atomFeedURLPatientDemographic,
atomFeedURLPatientEncounter, atomFeedURLPatientClinical), causing silent "last
wins" overrides; consolidate by removing the duplicate/earlier definitions and
keeping a single authoritative block (or merge values into one set) so each
property appears only once in application-swagger.properties, and if you
intended environment-specific overrides use Spring profiles or placeholders
instead.
🧹 Nitpick comments (1)
pom.xml (1)
271-275: Scope H2 to a Swagger-only Maven profile to reduce production artifact size.H2 is configured only in
application-swagger.propertiesfor the Swagger profile. Moving this dependency to a dedicated Maven profile (activated only during development/documentation builds) will keep the production WAR lean and eliminate an unnecessary runtime dependency.♻️ Example Maven profile-based scoping
- <dependency> - <groupId>com.h2database</groupId> - <artifactId>h2</artifactId> - <scope>runtime</scope> - </dependency> + <!-- moved to swagger profile --> + </dependencies> + + <profiles> + <profile> + <id>swagger</id> + <dependencies> + <dependency> + <groupId>com.h2database</groupId> + <artifactId>h2</artifactId> + <scope>runtime</scope> + </dependency> + </dependencies> + </profile> + </profiles>
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In @.github/workflows/swagger-json.yml:
- Around line 13-20: The workflow currently uses version tags for third‑party
actions (uses: actions/checkout@v4 and uses: actions/setup-java@v4); update
those "uses:" entries to pin each action to its corresponding commit SHA instead
of a floating tag (replace `@v4` with the full SHA for actions/checkout and
actions/setup-java), and apply the same SHA‑pinning to the other action usages
referenced around the file (the block noted at lines 65-78) so all third‑party
actions are pinned to immutable SHAs; also ensure you document/update your
repo’s process for keeping those SHAs current since Dependabot won’t alert on
SHA‑pinned actions.
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In @.github/workflows/swagger-json.yml:
- Around line 1-11: The workflow "Sync Swagger to AMRIT-Docs" currently relies
on default token permissions; add an explicit permissions block at the top-level
of the workflow to grant least-privilege scopes required by the "swagger-sync"
job (for example: contents: read or write only if needed, pull-requests: write
if the job opens PRs, id-token: none, packages: none, checks: none); update the
workflow to include the minimal permissions mapping so the job uses those
explicit permissions instead of broad defaults.
🧹 Nitpick comments (1)
.github/workflows/swagger-json.yml (1)
1-6: Prevent overlapping runs from spamming docs PRs.Multiple pushes to
maincan trigger concurrent runs and open multiple docs PRs. Consider adding a concurrency group to cancel in‑progress runs when a new commit arrives.♻️ Suggested change
on: push: branches: [ main ] workflow_dispatch: +concurrency: + group: swagger-sync-${{ github.ref }} + cancel-in-progress: true
|
|
@coderabbitai full review |
✅ Actions performedFull review triggered. |
2 participants
Summary by CodeRabbit
Documentation
Chores