Skip to content

260602#33

Merged
tynab merged 1 commit into
mainfrom
develop
Jun 2, 2026
Merged

260602#33
tynab merged 1 commit into
mainfrom
develop

Conversation

@tynab

@tynab tynab commented Jun 2, 2026

Copy link
Copy Markdown
Owner

No description provided.

Copilot AI review requested due to automatic review settings June 2, 2026 13:35
@tynab tynab merged commit f32239c into main Jun 2, 2026
2 checks passed

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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 .env SDLC 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 thread .env
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 thread .env
Comment on lines +70 to +71
# │ MAX_LOADED_MODELS │ 1 │ 4 │ 2 │ 3 │
# │ CONTEXT_LENGTH │ 8192 │ 16384 │ 32768 │ 65536 │
Comment thread .env
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.
Comment thread .env
# 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
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants