KiFdZddlmZdZd d dZd dZd ddZd dZd d dZy )a0MCP prompt templates for Code Review Graph. Provides 5 pre-built prompt workflows, all enforcing token-efficient detail_level="minimal" first patterns with get_minimal_context entry point. 1. review_changes - pre-commit review using detect_changes + affected_flows 2. architecture_map - architecture docs using communities, flows, Mermaid 3. debug_issue - guided debugging using search, flow tracing 4. onboard_developer - new dev orientation using stats, architecture, flows 5. pre_merge_check - PR readiness with risk scoring, test gaps, dead code ) annotationsui## Rules for Token-Efficient Graph Usage 1. ALWAYS call `get_minimal_context` first with a task description. 2. Use `detail_level="minimal"` on all tool calls unless the minimal output is insufficient. 3. Only escalate to `detail_level="standard"` or `"verbose"` for the specific entities that need deeper inspection. 4. Never request more than 3 tool calls per turn unless absolutely necessary. 5. Prefer targeted queries (query_graph with a specific symbol) over broad scans (list_communities with full members). 6. When reviewing changes: detect_changes(detail_level="minimal") → only expand on high-risk items. c"dtd|ddgS)zcPre-commit review workflow. Args: base: Git ref to diff against. Default: HEAD~1. userzN ## Review Workflow 1. Call `get_minimal_context(task="review changes against uf")` to get risk overview. 2. If risk is "low": call `detect_changes(detail_level="minimal")` → report summary + any test gaps. 3. If risk is "medium" or "high": a. Call `detect_changes(detail_level="standard")` for full change list. b. For each high-risk function, call `query_graph(pattern="callers_of", target=, detail_level="minimal")`. c. Call `get_affected_flows(detail_level="minimal")` only if >3 changed functions. 4. Summarize: risk level, what changed, test gaps, specific improvements needed. Do NOT call get_review_context unless you need source code snippets for a specific function.rolecontent_TOKEN_EFFICIENCY_PREAMBLEbases e/home/jay/workspace/scripts/.codegraph-venv/lib/python3.12/site-packages/code_review_graph/prompts.pyreview_changes_promptr s3-./M&45  cdtddgS)z$Architecture documentation workflow.ra ## Architecture Mapping Workflow 1. Call `get_minimal_context(task="map architecture")`. 2. Call `get_architecture_overview(detail_level="minimal")` for community coupling summary. 3. Call `list_flows(detail_level="minimal")` for critical flow names + criticality scores. 4. Only call `get_community(name=, detail_level="standard")` for the 1-2 communities the user is most interested in. 5. Produce a concise Mermaid diagram showing communities as boxes and key flows as arrows.rr rr architecture_map_promptrBs&-. /1 1  rc.|xsd}dtd|ddgS)zbGuided debugging workflow. Args: description: Description of the issue to debug. z rz= ## Debug Workflow 1. Call `get_minimal_context(task="debug: a")`. 2. Call `semantic_search_nodes(query=, detail_level="minimal", limit=5)`. 3. For the top 1-2 results, call `query_graph(pattern="callers_of", target=, detail_level="minimal")`. 4. If the issue involves execution flow: call `get_flow(name=)` for the single most relevant flow. 5. Only call `get_review_context` or `get_impact_radius` if you need to trace the blast radius of a specific change.rr ) description desc_parts r debug_issue_promptrYs@ .I-./=+ N N  rcdtddgS)z#New developer orientation workflow.ru ## Onboarding Workflow 1. Call `get_minimal_context(task="onboard developer")`. 2. Call `list_graph_stats()` for technology overview. 3. Call `get_architecture_overview(detail_level="minimal")` for the 30-second mental model. 4. Call `list_communities(detail_level="minimal")` — present as a table of module names + sizes. 5. Call `list_flows(detail_level="minimal")` — highlight the top 3 critical flows. 6. Only drill into a specific community or flow if the developer asks.rr rrr onboard_developer_promptrws&-. /" "  rcdtddgS)zdPR readiness check workflow. Args: base: Git ref to diff against. Default: HEAD~1. ra~ ## Pre-Merge Check Workflow 1. Call `get_minimal_context(task="pre-merge check")`. 2. Call `detect_changes(detail_level="minimal")` for risk score and test gaps. 3. If risk > 0.4: call `get_affected_flows(detail_level="minimal")`. 4. If test_gap_count > 0: call `query_graph(pattern="tests_for", target=, detail_level="minimal")` for up to 3 functions. 5. Call `refactor(mode="dead_code", detail_level="minimal")` to check for newly dead code. 6. Only call `find_large_functions` or `get_impact_radius` if risk > 0.7. 7. Output: GO/NO-GO recommendation with 1-sentence justification + list of required follow-ups.rr r s r pre_merge_check_promptrs&-./??  rN)zHEAD~1)r strreturn list[dict])rr))rrrr) __doc__ __future__rr rrrrrrrr r!s3 # "D.<.r