Repository navigation
humanitarian_verification response shape parity between OpenAI / Groq / Test #269
Description
Problem Statement. humanitarian_verification.py::_get_deterministic_response builds
the response out-of-band; OpenAI / Groq responses are parsed from raw JSON. The test
provider path serialises its own dict via json.dumps(separators=(",",":")) whereas
OpenAI / Groq responses come from data["choices"][0]["message"]["content"] and can be
mid-edit-token truncated.
Why it matters. Stable output is required by callers of the verification endpoint.
Technical Context.
app/ai-service/services/humanitarian_verification.py.
Expected Outcome. A parse_verification_response(provider_name, raw_content) function
unifies parsing; deterministic stamp on every response (provider, model,
prompt_variant).
Acceptance Criteria.
- E2E tests against all three providers produce identical-shape responses.
- A snapshot test pins the JSON schema.
Files or modules likely to be affected.
app/ai-service/services/humanitarian_verification.py,
new app/ai-service/schemas/humanitarian_verification_v2.py.
Difficulty. Medium
Estimated effort. M
Backlog item #61 from `docs/maintainer-issue-backlog.md.
Activity
Opulencechuks commentedon Jul 15, 2026
I am confident that i can work on this issue having worked on similar issues in the past
grantfox-oss commentedon Jul 16, 2026
🦊 GrantFox — @Opulencechuks has been assigned to this issue as part of the Official Campaign | FWC26 campaign!
Next steps:
Closes #269)Good luck! Track your progress on GrantFox.
grantfox-oss commentedon Jul 17, 2026
🎉 This issue has been marked as completed on GrantFox as part of the Official Campaign | FWC26 campaign!
@Opulencechuks's PR #375 was approved and merged by @kilodesodiq-arch.
🏆 @Opulencechuks: You earned 40 FoxPoints for this contribution! Your current tier: Builder (2,254 total points). Track your full progress on GrantFox.
👏 Great work, @Opulencechuks! Keep contributing to ChainForgee.