chore: add deployment issue board with all pre-deploy tasks#32
Merged
chore: add deployment issue board with all pre-deploy tasks#32
Conversation
Co-authored-by: Tpypan <155002057+Tpypan@users.noreply.github.com>
Author
|
Just as a heads up, I was blocked by some firewall rules while working on your feedback. Expand below for details. Warning Firewall rules blocked me from connecting to one or more addresses (expand for details)I tried to connect to the following addresses, but was blocked by firewall rules:
If you need me to access, download, or install something from one of these locations, you can either:
|
Copilot
AI
changed the title
[WIP] Add planning documentation for deployment improvements
chore: add deployment issue board with all pre-deploy tasks
Mar 16, 2026
There was a problem hiding this comment.
Pull request overview
Adds an in-repo deployment checklist (“issue board”) consolidating pre-deploy tasks from the deployment PRD and review discussions, to make the deployment plan actionable as a phase/priority-driven checklist.
Changes:
- Introduces
plan/ISSUE_BOARD.mdwith 71 tasks organized by phase and priority (P0–P2). - Adds a P0-only summary table intended as the minimum viable pre-deploy checklist.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| - [ ] **#8** `[P0]` Delete junk scrapers: `eonet.py`, `eonet_db.py`, `social_scraper.py`, `reddit.py`, `reddit_classifier.py`, `reddit_db.py`, `reddit_schema.sql`, `Reddit Scraper/`, `natural-disasters/`, `ryan_scrapers/` | ||
| - [ ] **#9** `[P0]` Move remaining hackathon scrapers (`gdelt.py`, `kalshi.py`, `polymarket.py`, `acled/`) into a `scrapers/_reference/` directory — kept as design inspiration only | ||
| - [ ] **#10** `[P0]` Remove duplicate `content_repository.py` (exists in both `repositories/` and `ingestion/`) — consolidate into one | ||
| - [ ] **#11** `[P0]` Remove all Cloudinary and legacy S3 media code — delete `utils/mediaConfig.ts`, remove `@cloudinary/react` and `@cloudinary/url-gen` from frontend, remove `cloudinary` and `boto3` from backend, drop `image_url` and `s3_url` columns from `content_table`, remove all `CLOUDINARY_*` and `AWS_*`/`S3_*` env vars. **Note (from review):** team confirmed S3 *will* be used for media storage, so keep `image_url` (repurposed as the S3 URL column) but drop `s3_url` as a duplicate. |
| ## Environment & Configuration | ||
|
|
||
| - [ ] **#70** `[P0]` Set `DATABASE_URL` to `postgresql://user:pass@host:5432/dbname` (no `+asyncpg` suffix) — both psycopg2 and asyncpg consume it as a standard libpq DSN. Update all documentation and `.env.example` to reflect this. | ||
| - [ ] **#71** `[P0]` Add all required environment variables to `.env.example` with comments: `DATABASE_URL`, `GEMINI_API_KEY`, `GEMINI_MODEL`, `OPENAI_API_KEY` (until local embeddings), `ACLED_API_KEY`, `ELEVENLABS_API_KEY` (optional). Remove any `CLOUDINARY_*`, `AWS_*`, `S3_*` examples. |
Comment on lines
+146
to
+158
| ## P0 Summary — Must Complete Before First Deploy | ||
|
|
||
| The following P0 items are the minimum required to go live: | ||
|
|
||
| | # | Task | | ||
| |---|------| | ||
| | 1 | Backend Dockerfile | | ||
| | 2 | Frontend Dockerfile | | ||
| | 3 | docker-compose.yml | | ||
| | 4 | .dockerignore files | | ||
| | 5 | GitHub Actions CI | | ||
| | 8 | Delete junk scrapers | | ||
| | 10 | Consolidate duplicate content_repository.py | |
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.
PR #29 contained a phased deployment PRD (66 tickets) and architecture context file, but no consolidated task list actionable as a checklist. Review discussions also surfaced several tasks not captured in the PRD.
Changes
plan/ISSUE_BOARD.md— 71 tasks extracted fromPRD.mdand PR review threads, organized by phase/priority with a P0-only summary table at the bottom for the minimum viable deploy checklistExtra tasks surfaced from review (beyond PRD's 66)
pg_try_advisory_lockor Redis) to prevent zombie cron runs/content/pointsto avoid massive JSON payloadsmax_sizemust be set explicitly; default of 10 will cause "too many connections" under loadcontent.py) to async — docs claimed async-only but code wasn'tDATABASE_URLmust usepostgresql://notpostgresql+asyncpg://; both psycopg2 and asyncpg reject the SQLAlchemy-style schemeimage_urlas the S3 URL column, drops3_urlonly📱 Kick off Copilot coding agent tasks wherever you are with GitHub Mobile, available on iOS and Android.