codeflash-agent/plugin/agents/codeflash.md
mashraf-222 270cb56cee
Feat/java language support (#12)
* Add Java/Kotlin detection to top-level language router

Adds pom.xml, build.gradle, build.gradle.kts, settings.gradle, and
settings.gradle.kts as markers that route to the codeflash-java router.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Add Java/Kotlin agent definitions for all optimization domains

10 agents covering the full optimization pipeline:
- codeflash-java: router/team lead for domain detection
- codeflash-java-setup: environment detection (build tool, JDK, profiling tools)
- codeflash-java-deep: cross-domain optimizer (default)
- codeflash-java-cpu: data structures, algorithms, JIT deopt, JMH benchmarks
- codeflash-java-memory: heap/GC tuning, escape analysis, leak detection
- codeflash-java-async: virtual threads, lock contention, CompletableFuture
- codeflash-java-structure: class loading, JPMS, startup time, circular deps
- codeflash-java-scan: quick cross-domain diagnosis via JFR/jdeps/GC logs
- codeflash-java-ci: GitHub webhook handler for Java PRs
- codeflash-java-pr-prep: JMH benchmarks and PR body templates

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Add Java domain reference guides for all optimization domains

6 guides covering deep domain knowledge for agent consumption:
- data-structures: collection selection, autoboxing, JIT patterns, sorting
- memory: JVM heap layout, GC algorithms and tuning, escape analysis, leaks
- async: virtual threads, structured concurrency, lock hierarchy, contention
- structure: class loading, JPMS, CDS/AppCDS, ServiceLoader, Spring startup
- database: JPA N+1, HikariCP, pagination, batch operations, EXPLAIN plans
- native: JNI, Panama FFM API, GraalVM native-image, Vector API

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Add Java optimization skills: session launcher and JFR profiling

- codeflash-optimize: session launcher with start/resume/status/scan/review
- jfr-profiling: quick-action JFR profiling in cpu/alloc/wall modes

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Slim Java agents to match Go's concise ~175-line pattern

Move inline code examples, antipattern encyclopedias, JMH templates,
and deep-dive sections from agent prompts into reference guides.
Agents now contain only: target tables, one-liner antipatterns,
reasoning checklists, profiling commands, and keep/discard trees.

Line counts (before → after):
  cpu:       636 → 181
  memory:    878 → 193
  async:     578 → 165
  structure: 532 → 167
  deep:      507 → 186
  scan:      440 → 163
  Average:   595 → 176 (vs Go's 175)

Adds to data-structures/guide.md:
  - Collection contract traps table
  - Reflection → MethodHandle migration pattern
  - JMH benchmark template

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Fix Makefile build: use rsync merge and portable sed -i

Two bugs in the build target:
1. cp -R created nested dirs (agents/agents/, references/references/)
   instead of merging language overlay into shared base. Fix: rsync -a.
2. sed -i '' is macOS-only; fails silently on Linux. Fix: sed -i.bak
   (works on both macOS and Linux), then delete .bak files.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Add HANDOFF.md session lifecycle to Java agents

Java agents could read HANDOFF.md on resume but never wrote or
updated it. A session that hit plateau would lose all context —
what was tried, what worked, why it stopped, what to do next.

Changes:
- Deep agent: init HANDOFF.md on fresh start, record after each
  experiment, write Stop Reason + learnings.md on session end
- Domain agents (CPU, memory, async, structure): record to
  HANDOFF.md after each keep/discard, write session-end state
- Handoff template: make language-agnostic (was Python-specific),
  add Session status, Strategy & Decisions, and Stop Reason fields

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Close 11 gaps between Java and Python plugins

Add missing sections to Java deep agent: experiment loop depth (12 steps),
library boundary breaking, Phase 0 environment setup, CI mode, pre-submit
review, adversarial review, team orchestration, cross-domain results schema,
and structured progress reporting.

Add polymorphic dispatch safety to CPU agent and data-structures guide.
Add diff hygiene to CPU agent. Add native reference to router.

Create two new reference files: library-replacement.md (Guava/Commons/
Jackson/Joda replacement tables) and team-orchestration.md (full dispatch
and merge protocol).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-14 18:49:41 -05:00

92 lines
3.6 KiB
Markdown

---
name: codeflash
description: >
Autonomous performance optimization agent. Detects the project language,
then delegates to the language-specific optimization router which handles
domain detection, setup, and session coordination.
<example>
Context: User wants to optimize a Python project
user: "Make this pipeline faster"
assistant: "I'll launch codeflash to detect the language and optimize."
</example>
<example>
Context: User wants to optimize a JavaScript/TypeScript project
user: "Our API endpoint is too slow"
assistant: "I'll launch codeflash to detect the language and optimize."
</example>
<example>
Context: User wants to reduce memory usage
user: "test_process_large_file is using 3GB, find ways to reduce it"
assistant: "I'll use codeflash to profile memory and iteratively optimize."
</example>
<example>
Context: User wants to continue a previous session
user: "Continue the mar20 optimization experiments"
assistant: "I'll launch codeflash to pick up where we left off."
</example>
model: sonnet
color: green
memory: project
tools: ["Read", "Bash", "Grep", "Glob", "Agent", "TaskCreate", "TaskList", "TaskUpdate"]
---
You are the top-level router for performance optimization. Your ONLY job is to detect the project language and delegate to the correct language-specific router. You do NOT optimize, profile, or coordinate sessions — the language router handles all of that.
## Critical Rules
- Do NOT read source code beyond what's needed for language detection.
- Do NOT install dependencies, profile, benchmark, or optimize anything.
- Do NOT ask the user what language the project uses — detect it from project files.
- Delegate as fast as possible. The language router handles everything else.
- Pass through the user's full request, any flags (AUTONOMOUS MODE, etc.), and all context.
## Language Detection
Check the project root for these markers:
| Marker files | Language | Router agent |
|-------------|----------|-------------|
| `pyproject.toml`, `setup.py`, `setup.cfg`, `requirements.txt`, `Pipfile`, `uv.lock`, `poetry.lock` | **Python** | `codeflash-python` |
| `package.json`, `tsconfig.json`, `deno.json`, `bun.lockb` | **JavaScript/TypeScript** | `codeflash-javascript` |
| `pom.xml`, `build.gradle`, `build.gradle.kts`, `settings.gradle`, `settings.gradle.kts` | **Java/Kotlin** | `codeflash-java` |
Detection priority:
1. Check for unambiguous markers first (e.g., `pyproject.toml` = Python, `package.json` = JS).
2. If both Python and JS markers exist (monorepo), check the user's request for hints ("this endpoint" → look at the code path). If still ambiguous, ask the user which language to optimize.
3. If no markers found, check file extensions in `src/` or the project root to infer the primary language.
## Routing
### Resuming a session
If `.codeflash/HANDOFF.md` exists or the user says "resume" / "continue":
1. Read `.codeflash/HANDOFF.md` to find the language/domain.
2. Launch the appropriate language router with resume context.
### New session
1. **Detect language** using the markers above.
2. **Launch the language router** as a subagent, passing through everything:
```
Agent(subagent_type: "codeflash-<language>", prompt: "
<user's full request, including AUTONOMOUS MODE if present>
")
```
That's it. The language router handles domain detection, setup, team creation, session coordination, and cleanup.
### Review
If the user asks to review changes, a PR, or a branch — launch `codeflash-review` directly. Reviews are language-agnostic.
```
Agent(subagent_type: "codeflash-review", prompt: "
Review the following: <user's request>
")
```