feat(email-writing): build authorized thread context - #1329
Conversation
|
Warning Review limit reachedNext included review available in 56 minutes. View limit detailsLimit details: You’ve used the included review currently available. You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository. Review configuration: ⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Team Run ID: 📒 Files selected for processing (4)
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 review |
|
|
PR governance metadata gate is not ready for
|
…idence-task3' into feat/llm-email-writing-context-task4
…idence-task3' into feat/llm-email-writing-context-task4 Co-authored-by: Seongho Bae <seonghobae@users.noreply.github.com>
|
@coderabbitai review Please review the unchanged exact current head |
|
|
…ask4' into feat/llm-email-writing-orchestrator-task5 Retarget Task 5 onto live #1329 head 4570747 (merged onto live #1328 51fb5e8 / #1327 fb7c406 / #1322 bfc2df1 / develop@dd8d1519). Preserve the hardened contextual-orchestrator boundary. Do not restore write-capable Task 5 promotion/finalize workflows. Co-authored-by: Seongho Bae <seonghobae@users.noreply.github.com>
|
Caution Review failedAn error occurred during the review process. Please try again later. 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 review |
|
Scope
This Draft PR implements Task 4 only: server-authoritative email/thread/recipient context construction for the writing-review workflow. It excludes contextual-orchestrator/model execution, Candidate/Judge semantics, review API, Inkspan editor integration, sending, policy publication, and release behavior.
The service keeps owner/organization authorization, canonical thread membership and chronology, complete-message budgeting, recipient-role derivation from persisted headers, trust labels for untrusted content, and fail-closed handling for oversized selected content. It does not infer importance, tone, actionability, or intent from keywords, sender domains, recipient counts, language names, nearest-text search, or positional heuristics.
Live stack state — 2026-09-01
Direct parent #1328 is
ea61b9de9cd26a26209da36e858510a31486531a. This Task-4 head is64d1f746723616b0111eb40b130d6f07ed413a86and contains that exact parent through an ordinary non-destructive two-parent merge. No force-push or destructive rebase was used.Its unique Task-4 delta remains the context TDD workflow,
email_writing_context_service.py, and the two focused context-service test modules. Current root design documents are inherited through the stack and are not Task-4-owned semantic delta. All predecessor-head evidence is stale after this movement.Authorization/privacy contract retained
Evidence and continuation
Fresh exact-head authorization/isolation, Python 3.14, coverage/docstrings, SAST/security/dependency/package/provenance and review/thread evidence must be regenerated for
64d1f746723616b0111eb40b130d6f07ed413a86. Child #1356 is reconciled onto this exact Task-4 head asbeb28466573b2163df97b027a6d3ac3776773869; later task-owned descendants have likewise been advanced in dependency order. No predecessor evidence transfers.Merge boundary
Keep Draft while current-head evidence is regenerated. Merge only on an unchanged head satisfying live rulesets/protection, every applicable exact-head gate, zero valid unresolved findings, and any qualifying independent approval actually required after the last push. Pending/queued/skipped-required/cancelled/neutral/failed/absent/stale/predecessor/synthetic/model-only/status-only/author-only evidence is non-passing.
No writing-guidance feature is shipped by this context slice; editing and sending remain available.