fix(feat): initial prd, then openspec specs, for clean room re-impl of augment as part of boost#3278
fix(feat): initial prd, then openspec specs, for clean room re-impl of augment as part of boost#3278gabemontero wants to merge 1 commit into
Conversation
…f augment as part of boost Signed-off-by: gabemontero <gmontero@redhat.com> Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Code Review by Qodo
1. Wrong workspace path
|
|
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #3278 +/- ##
=======================================
Coverage 53.62% 53.62%
=======================================
Files 2409 2409
Lines 86633 86633
Branches 23997 23997
=======================================
Hits 46457 46457
Misses 39894 39894
Partials 282 282
*This pull request uses carry forward flags. Click here to find out more. Continue to review full report in Codecov by Sentry.
🚀 New features to boost your workflow:
|
Review Summary by QodoBoost Agentic SDLC Platform: Complete Specification Suite with Security, Modularity, and Enterprise Operations
WalkthroughsDescription• Comprehensive specification suite for Boost agentic SDLC platform with 5 PRDs and 40+ OpenSpec change documents • **Security & Governance**: 16 fine-grained permissions with conditional rules, RFC 8693 token exchange, three security modes, safety shields, and resilience patterns • **Agent Creation & Discovery**: Four converging creation paths (no-code builder, Software Template, DevSpaces, import), catalog-first architecture with entity providers, MCP tool registration with 4-level auth chain • **Pluggable AI Platform**: Provider abstraction interface with normalized streaming, runtime hot-swap with rollback, multi-agent orchestration via Llama Stack, modular provider packaging as independent backend modules • **Platform Operations & Deployment**: Schema-driven runtime configuration with two-layer resolution (YAML + DB overrides), cache migration to Backstage cacheService, RAG knowledge pipelines with multi-source ingestion • **AI Chat Experience**: Streaming chat with phase indicators, RAG-grounded answers with citations, human-in-the-loop approval, conversation history, developer debugging tools, frontend composability with lazy loading • Design principles extracted from Augment reference prototype with clean-slate implementation approach and 12 lessons learned • Modular workspace structure with independently deployable packages (core, providers, entity providers) Diagramflowchart LR
PRD["5 Product Requirements<br/>Documents"]
SEC["Security & Governance<br/>16 Permissions + Token Exchange"]
AGENT["Agent Creation<br/>4 Paths + Catalog"]
PROV["Pluggable Providers<br/>Hot-Swap + Normalization"]
OPS["Platform Operations<br/>Schema Config + Caching"]
CHAT["Chat Experience<br/>Streaming + RAG + HITL"]
PRD --> SEC
PRD --> AGENT
PRD --> PROV
PRD --> OPS
PRD --> CHAT
SEC -- "Governs" --> AGENT
SEC -- "Protects" --> PROV
SEC -- "Secures" --> OPS
SEC -- "Enforces" --> CHAT
PROV -- "Powers" --> CHAT
AGENT -- "Enables" --> CHAT
OPS -- "Configures" --> PROV
OPS -- "Configures" --> AGENT
File Changes1. workspaces/boost/specifications/prd/security-safety-governance.md
|
rhdh-qodo-merge
Bot
added
the
documentation
ReviewFindingsMedium
Low
|
![fullsend-ai-review[bot]](https://avatars.githubusercontent.com/in/3478501?s=60&v=4){kind=small}
|
|
||
| Agents follow the 4-stage lifecycle from the start: Draft → Pending → Published → Archived. No legacy stage mappings or normalization layers — boost has no prior model to be compatible with. The `createdBy` field is set at registration and drives visibility filtering, action gating, and self-approval prevention. Cascading delete detects agent source and cleans up across corresponding stores. | ||
|
|
||
| ### Decision 6: Skills marketplace integration (consumer only) |
There was a problem hiding this comment.
[medium] naming-convention
All repository path references use 'rhdh-plugins/workspace/boost/plugins/' (singular 'workspace') but the actual directory is 'workspaces/' (plural). Error appears across 7+ occurrences in multiple files.
Suggested fix: Replace all occurrences of 'rhdh-plugins/workspace/boost/' with 'rhdh-plugins/workspaces/boost/'.
1 participant
Hey, I just made a Pull Request!
Working of the wealth of specifications, use case documentation, system diagrams, that have been cultivated as part of the augment workspace in rhdh-plugins, we are putting the new RHDH agentic sdlc system, including integration with fullsend, to work to see what kind of alternative implementation if comes up with.
This leveraged
✔️ Checklist