daax-dev / daax-dev/agentic-retrospective
Multi-repo support for team retrospectives
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 3
- Forks
- 2
- PR merge metrics
- No merged PRs in 30d
Description
Context
Teams typically work across multiple repositories. A sprint retrospective that only covers one repo gives an incomplete picture — you miss cross-repo rework chains, scattered hotspots, and skewed fix-to-feature ratios.
Currently, the tool is single-repo scoped:
GitAnalyzerruns git commands againstprocess.cwd()GitHubAnalyzerusesghagainst the current repoRetroConfighas no concept of repo identity- No way to attribute commits, hotspots, or PRs to a specific repo
Proposal
Add optional multi-repo support via a .retro.toml config file, following the TOML config pattern used elsewhere in the daax-dev org (e.g. daax-cli.toml).
Config file
# .retro.toml — drop in workspace root or any repo
[retrospective]
sprint_id = "sprint-42"
output_dir = "docs/retrospectives"
# Omit [[repos]] entirely for single-repo (current behaviour)
[[repos]]
path = "."
label = "frontend"
[[repos]]
path = "../api"
label = "api"
[[repos]]
path = "../infra"
label = "infra"
Behaviour
- No
.retro.toml+ no--repoflags → current behaviour,cwdis the repo. Zero breaking changes. --repo ../other→ analyse that single repo instead of cwd.--repo ./a --repo ./b→ multi-repo mode with per-repo sections + unified summary..retro.tomlfound → loads repo list from config.--repoflags override it.
CLI additions
# Single repo (unchanged)
agentic-retrospective
# Explicit repos
agentic-retrospective --repo ../frontend --repo ../api
# Config-driven
agentic-retrospective # picks up .retro.toml automatically
Report changes
- Per-repo sections for commits, hotspots, PRs
- Unified executive summary aggregating across all repos
- Repo label attribution on commits and findings
Implementation sketch
- Add optional
repostoRetroConfig RetroRunnerloops per-repo, passing repo path to analyzersGitAnalyzerandGitHubAnalyzeraccept an optionalcwdparameter instead of usingprocess.cwd()- Report generator gets per-repo sections + aggregate summary
- Config file discovery: walk up from cwd looking for
.retro.toml
Non-goals (for this issue)
- GitHub org auto-discovery (
--github-org) — could be a follow-up - Cross-repo dependency analysis
- Monorepo sub-path support
Compatibility
- No breaking changes — single-repo default preserved
- Complements #18 (trend tracking becomes more useful across repos)
- Orthogonal to #16 (headless mode)
Happy to contribute this. Keen to hear if this aligns with where the project is heading before starting implementation.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the existing GitAnalyzer, GitHubAnalyzer, RetroConfig, RetroRunner, and report generator entry points, then trace how the CLI currently handles cwd and options. Define the .retro.toml discovery and --repo override flow before implementing it. Done means preserving single-repo behavior while producing per-repo sections, labels, and a unified summary for configured or explicit repositories.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- cli, tooling
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100