Add HTTP client documentation for Astrology API integration#7
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Co-authored-by: DHCross <45954119+DHCross@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Add example for using Astrology API with HTTP client
Add HTTP client documentation for Astrology API integration
Dec 24, 2025
DHCross
added a commit
that referenced
this pull request
Mar 2, 2026
…ge clarity HIGH priority: - #6 symbolicWeather: soft-fail instead of re-throwing AuthorityViolationError - #7 TTS: add 10s AbortController timeout to ElevenLabs fetch (504 on timeout) - #9 injectProtocols: wrap in try/catch, continue without corpus on failure MEDIUM priority: - #2 LLM auth: normalize 401/403 to user-friendly message - #3 LLM timeout: add one retry in generateReplyWithRetry - #4 Empty LLM response: distinguish content_filter from true empty - #5 AuthorityViolation outer catch: hide internal module names LOW priority: - #1 Missing LLM key 503: clearer operator message - #8 useOracleChat: map 413 to user-friendly 'message too long' text - #10 Remove void-cast needsConcreteRetry/needsProtocolRepair calls
DHCross
pushed a commit
that referenced
this pull request
Apr 25, 2026
Original task (Task #7): All unit tests under `vessel/src/app/api/raven-chat/__tests__/` pass typecheck but were never executed by `npm test` — only `recoveryMessages.test.ts` was wired into the `test:smoke` script. Change: - `vessel/package.json`: extended the `test:smoke` script to include all 13 previously-unwired `raven-chat/__tests__/*.test.ts` files alongside the existing `recoveryMessages.test.ts`. Files added (alphabetical): circumstanceDisclosure, counterpartProvenance, enrichmentPhase, forecastIntent, generationIntegrity, intentDetection, promptLines, protocolRules, relationalPrep, requestParsing, sessionStateGuards, slashCommandDispatcher, turnContextResolver, userBlockBuilder. Notes / deviations from the task brief: - The task description listed `entityGuard` as one of the test files, but no `entityGuard.test.ts` exists in the directory. There are 14 files total (1 already wired + 13 newly wired). Treated as a typo in the brief; nothing to wire that doesn't exist. - Acceptance criterion "npm test exits 0 with all those tests passing" is NOT met. The pre-existing `test:smoke` baseline already had 26 failing tests in unrelated suites (planner, blueprint-firewall, instrument-ledger, etc.) so `npm test` was already non-zero before this change. After wiring, totals are 367 tests / 339 pass / 28 fail (was 281/255/26). The 2 newly-surfaced failures are real implementation gaps in the production code that the test files were asserting against, not wiring problems: 1. enrichmentPhase.test.ts — "runEnrichmentPhase reuses cached field report artifacts when no explicit two-clock request is present": `isTwoClockFetchRequest('read the symbolic moment for today')` returns true, so a two-clock fetch fires when the test expects it to be skipped. 2. promptLines.test.ts — "field report contract includes FIELD→MAP→VOICE→VALIDATION canon order": the literal "CANON ORDER:" line is not present in `promptLines.ts` field-report rules. Both look like red TDD specs for product work that hasn't landed yet, consistent with the 26 other red specs already in the suite. Filed as a follow-up rather than fixed inline to keep this task scoped to wiring. Replit-Task-Id: df2cf8ba-5edd-4664-abd8-8b8d1996aeb0
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.
User asked which HTTP client to use for the Astrology API (HTTP/Unirest/Axios/Fetch). The codebase already uses native
fetchconsistently.Changes
vessel/docs/ASTROLOGY_API_CLIENT.mddocumenting:fetchAPI (already established pattern)/api/astrologyproxy routeRAPIDAPI_KEYwithAstrology_API_KEYfallback)Example
The verbose Node.js HTTP code converts to:
Original prompt
💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.