lee/graphify
1
0
Fork 0
mirror of https://github.com/safishamsi/graphify.git synced 2026-09-23 05:55:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

perf: larger chunks + code-only fast path + timing estimates

Browse Source 
- Semantic extraction chunks: 12-15 → 20-25 files (fewer subagent round trips)
- Code-only corpora skip semantic dispatch entirely (AST covers it)
- Print estimated time before extraction so the wait feels intentional
This commit is contained in:
Safi
2026-04-06 16:06:31 +01:00
parent 0f4de8e47f
commit ef8c2fef50
2 changed files with 16 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
graphify/skill.md
+8 -5
View File
@@ -124,12 +124,15 @@ else:
#### Part B - Semantic extraction (parallel subagents)
**Fast path:** If detection found zero docs, papers, and images (code-only corpus), skip Part B entirely and go straight to Part C. AST handles code - there is nothing for semantic subagents to do.
**MANDATORY: You MUST use the Agent tool here. Reading files yourself one-by-one is forbidden - it is 5-10x slower. If you do not use the Agent tool you are doing this wrong.**
Before dispatching subagents, print a cost estimate:
- Load `total_words` from `.graphify_detect.json`
- Estimate: ~(total_words / 750) input tokens per file on average, output ~20% of that
- Print: "Semantic extraction: ~N files, estimated ~X input tokens"
Before dispatching subagents, print a timing estimate:
- Load `total_words` and file counts from `.graphify_detect.json`
- Estimate agents needed: `ceil(uncached_non_code_files / 22)` (chunk size is 20-25)
- Estimate time: ~45s per agent batch (they run in parallel, so total ≈ 45s × ceil(agents/parallel_limit))
- Print: "Semantic extraction: ~N files → X agents, estimated ~Ys"
**Step B0 - Check extraction cache first**
@@ -157,7 +160,7 @@ Only dispatch subagents for files listed in `.graphify_uncached.txt`. If all fil
**Step B1 - Split into chunks**
Load files from `.graphify_uncached.txt`. Split into chunks of 12-15 files each. Each image gets its own chunk (vision needs separate context).
Load files from `.graphify_uncached.txt`. Split into chunks of 20-25 files each. Each image gets its own chunk (vision needs separate context).
**Step B2 - Dispatch ALL subagents in a single message**
skills/graphify/skill.md
+8 -5
View File
@@ -124,12 +124,15 @@ else:
#### Part B - Semantic extraction (parallel subagents)
**Fast path:** If detection found zero docs, papers, and images (code-only corpus), skip Part B entirely and go straight to Part C. AST handles code - there is nothing for semantic subagents to do.
**MANDATORY: You MUST use the Agent tool here. Reading files yourself one-by-one is forbidden - it is 5-10x slower. If you do not use the Agent tool you are doing this wrong.**
Before dispatching subagents, print a cost estimate:
- Load `total_words` from `.graphify_detect.json`
- Estimate: ~(total_words / 750) input tokens per file on average, output ~20% of that
- Print: "Semantic extraction: ~N files, estimated ~X input tokens"
Before dispatching subagents, print a timing estimate:
- Load `total_words` and file counts from `.graphify_detect.json`
- Estimate agents needed: `ceil(uncached_non_code_files / 22)` (chunk size is 20-25)
- Estimate time: ~45s per agent batch (they run in parallel, so total ≈ 45s × ceil(agents/parallel_limit))
- Print: "Semantic extraction: ~N files → X agents, estimated ~Ys"
**Step B0 - Check extraction cache first**
@@ -157,7 +160,7 @@ Only dispatch subagents for files listed in `.graphify_uncached.txt`. If all fil
**Step B1 - Split into chunks**
Load files from `.graphify_uncached.txt`. Split into chunks of 12-15 files each. Each image gets its own chunk (vision needs separate context).
Load files from `.graphify_uncached.txt`. Split into chunks of 20-25 files each. Each image gets its own chunk (vision needs separate context).
**Step B2 - Dispatch ALL subagents in a single message**