Conversation
There was a problem hiding this comment.
Pull request overview
This PR expands the SDLC agent system prompts to enforce “system context awareness” (upstream/downstream/shared services/external integrations) across BA/PM/SA/TA and implementation-focused agents, and updates the repository .env model-tier guidance to new LOW/MEDIUM/HIGH/ULTRA recommendations.
Changes:
- Add integration/topology awareness requirements and new mandatory artifacts (ecosystem maps, C4 diagrams, dependency maps, lineage maps, integration test matrices) to multiple agent prompts in
agent-api/agents.py. - Revise
.envSDLC agent model tiers (LOW/MEDIUM/HIGH/ULTRA) and update the recommended model assignments and hardware notes.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 4 comments.
| File | Description |
|---|---|
agent-api/agents.py |
Strengthens agent instructions to explicitly cover integration ecosystems and end-to-end system topology via new required sections/diagrams. |
.env |
Updates default model configuration and tier documentation for different hardware profiles (incl. new ULTRA tier). |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
59
to
63
| # ─── SDLC Agent Models ──────────────────────────────────────────────────────── | ||
| # Chọn đúng một option theo phần cứng — chỉ bỏ comment MỘT block tại một thời điểm. | ||
| # Sau khi đổi option: restart agent-api + rag-api (không cần rebuild image). | ||
| # Nếu đổi EMBEDDING_MODEL → chạy lại POST /reset-ingest để rebuild vector index. | ||
| # |
Comment on lines
+70
to
+71
| # │ MAX_LOADED_MODELS │ 1 │ 4 │ 2 │ 3 │ | ||
| # │ CONTEXT_LENGTH │ 8192 │ 16384 │ 32768 │ 65536 │ |
Comment on lines
+110
to
+114
| # bge-m3 (~1GB) chạy trên GPU; 4 LLM chạy CPU RAM — tổng ~68GB trong 256GB, không swap. | ||
| # qwen3.6:35b (24GB, vision+tools+thinking, 256K ctx): ~2-3 tok/s trên 44-core Xeon. | ||
| # devstral-small-2:24b (15GB, 384K ctx): SWE-bench 65.8% — thế hệ mới vượt devstral gốc 46.8%. | ||
| # magistral:24b (14GB, 39K ctx): Mistral dedicated thinking/reasoning — tốt hơn mistral-small3.2 cho QA. | ||
| # MAX_LOADED_MODELS=4: giữ đồng thời 4 LLM (35+15+14+15=79GB) trong RAM, không reload overhead. |
| # devstral-small-2:24b (15GB, 384K ctx): SWE-bench 65.8% — thế hệ mới vượt devstral gốc 46.8%. | ||
| # magistral:24b (14GB, 39K ctx): Mistral dedicated thinking/reasoning — tốt hơn mistral-small3.2 cho QA. | ||
| # MAX_LOADED_MODELS=4: giữ đồng thời 4 LLM (35+15+14+15=79GB) trong RAM, không reload overhead. | ||
| # Cần pull: ollama pull qwen3.6:35b && ollama pull devstral-small-2 && ollama pull magistral |
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.
No description provided.