chill-agent 1.4.0 → 1.6.0

package/__init__.py

@@ -0,0 +1,228 @@
+"""Hermes plugin for Ponytail."""
+
+from __future__ import annotations
+
+import json
+import os
+import re
+from pathlib import Path
+from typing import Any, Callable
+
+DEFAULT_MODE = "full"
+RUNTIME_MODES = {"off", "lite", "full", "ultra"}
+SKILL_COMMANDS = {
+    "ponytail-review": "Review the current diff or provided target: bugs, security, load, missing tests, speed, and what to cut.",
+    "ponytail-audit": "Audit the whole repo: bugs, security, load, missing tests, speed, and what to cut.",
+    "ponytail-debt": "List every deliberate `shortcut:` comment and its upgrade path.",
+    "ponytail-gain": "Show the measured-impact scoreboard (less code, less cost, more speed).",
+    "ponytail-help": "Show the Ponytail command reference.",
+}
+
+ROOT = Path(__file__).resolve().parent
+SKILLS_DIR = ROOT / "skills"
+PONYTAIL_SKILL = SKILLS_DIR / "ponytail" / "SKILL.md"
+
+_current_mode = None
+
+
+def _normalize_runtime_mode(mode: str | None) -> str | None:
+    if not isinstance(mode, str):
+        return None
+    mode = mode.strip().lower()
+    return mode if mode in RUNTIME_MODES else None
+
+
+def _config_dir() -> Path:
+    if os.environ.get("XDG_CONFIG_HOME"):
+        return Path(os.environ["XDG_CONFIG_HOME"]) / "ponytail"
+    if os.name == "nt":
+        return Path(os.environ.get("APPDATA", Path.home() / "AppData" / "Roaming")) / "ponytail"
+    return Path.home() / ".config" / "ponytail"
+
+
+def _default_mode() -> str:
+    env_mode = _normalize_runtime_mode(os.environ.get("PONYTAIL_DEFAULT_MODE"))
+    if env_mode:
+        return env_mode
+    try:
+        data = json.loads((_config_dir() / "config.json").read_text(encoding="utf-8-sig"))
+        file_mode = _normalize_runtime_mode(data.get("defaultMode"))
+        if file_mode:
+            return file_mode
+    except Exception:
+        pass
+    return DEFAULT_MODE
+
+
+def _strip_frontmatter(text: str) -> str:
+    return re.sub(r"^---[\s\S]*?---\s*", "", text or "", count=1)
+
+
+def _filter_skill_body_for_mode(body: str, mode: str) -> str:
+    effective = _normalize_runtime_mode(mode) or DEFAULT_MODE
+    lines = []
+    # str.splitlines() drops a trailing line terminator instead of yielding a
+    # trailing empty element, so a body ending in "\n" loses that newline on
+    # rejoin. re.split keeps it, matching the JS filter's split(/\r?\n/).
+    for line in re.split(r"\r?\n", _strip_frontmatter(body)):
+        table_label = re.match(r"^\|\s*\*\*(.+?)\*\*\s*\|", line)
+        if table_label:
+            label_mode = _normalize_runtime_mode(table_label.group(1))
+            if label_mode and label_mode != effective:
+                continue
+
+        # Require a quoted value: every worked example is `- lite: "..."`. Without
+        # this, an ordinary rule bullet that happens to start with a mode word
+        # (e.g. "- Full: ...") is silently dropped in every other mode — it looks
+        # like a worked example but is really prose meant to survive verbatim.
+        # Mirrors the fix in hooks/ponytail-instructions.js (#571).
+        example_label = re.match(r'^-\s*([^:]+):\s*"', line)
+        if example_label:
+            label_mode = _normalize_runtime_mode(example_label.group(1))
+            if label_mode and label_mode != effective:
+                continue
+
+        lines.append(line)
+    return "\n".join(lines)
+
+
+def _fallback_instructions(mode: str) -> str:
+    return (
+        f"PONYTAIL MODE ACTIVE — level: {mode}\n\n"
+        "You are a lazy senior developer. The best code is the code never written. "
+        "Before you write, list every place your change must reach (callers, tests, "
+        "fixtures) and what it could break for users. First rung that works: skip what "
+        "is not needed, reuse what the codebase has, stdlib or platform, installed "
+        "dependency, one readable line, then minimum code. No unrequested abstractions, "
+        "wrappers, options or boilerplate. Never cut trust-boundary validation, "
+        "data-loss handling, security, accessibility or anything asked for."
+    )
+
+
+def build_injected_context(mode: str | None = None) -> str:
+    """Return the mode-filtered Ponytail context injected before LLM turns."""
+    effective = _normalize_runtime_mode(mode) or _default_mode()
+    if effective == "off":
+        return ""
+    try:
+        body = PONYTAIL_SKILL.read_text(encoding="utf-8")
+        return f"PONYTAIL MODE ACTIVE — level: {effective}\n\n{_filter_skill_body_for_mode(body, effective)}"
+    except OSError:
+        return _fallback_instructions(effective)
+
+
+def _pre_llm_call(
+    session_id: str = "", conversation_history: Any = None, **_: Any
+) -> dict[str, str] | None:
+    mode = _current_mode or _default_mode()
+    # Off is injected too: the ruleset from an earlier turn is replayed every turn,
+    # and the /ponytail off reply goes to the user, never to the model.
+    context = build_injected_context(mode) or "PONYTAIL MODE OFF"
+
+    # Hermes persists hook context in api_content for cache-stable replay.
+    # Re-inject only when the active mode changed or compaction removed it.
+    for message in reversed(conversation_history or []):
+        if not isinstance(message, dict):
+            continue
+        api_content = message.get("api_content")
+        if not isinstance(api_content, str):
+            continue
+        matches = re.findall(r"PONYTAIL MODE (?:ACTIVE — level: ([a-z]+)|OFF)", api_content)
+        if matches:
+            return None if (matches[-1] or "off") == mode else {"context": context}
+
+    # Nothing persisted, so off has nothing to switch off.
+    return None if mode == "off" else {"context": context}
+
+
+def _skill_prompt(command: str, args: str = "") -> str:
+    tail = args.strip()
+    target = f"\n\nUser arguments: {tail}" if tail else ""
+    return (
+        f"Load and follow the Hermes plugin skill `ponytail:{command}`. "
+        f"{SKILL_COMMANDS[command]}{target}"
+    )
+
+
+def _slash_access_denied(event: Any, gateway: Any, command: str) -> bool:
+    if gateway is None or event is None:
+        return False
+    checker = getattr(gateway, "_check_slash_access", None)
+    source = getattr(event, "source", None)
+    if checker is None or source is None:
+        return False
+    try:
+        return checker(source, command) is not None
+    except Exception:
+        return True
+
+
+def rewrite_gateway_command(event: Any = None, gateway: Any = None, **_: Any) -> dict[str, str] | None:
+    """Rewrite authorized gateway /ponytail-* commands into normal agent prompts."""
+    text = str(getattr(event, "text", "") or "").strip()
+    if not text.startswith("/"):
+        return None
+    head, _, rest = text[1:].partition(" ")
+    command = head.replace("_", "-").lower()
+    if command not in SKILL_COMMANDS:
+        return None
+    if _slash_access_denied(event, gateway, command):
+        return None
+    return {"action": "rewrite", "text": _skill_prompt(command, rest)}
+
+
+def _handle_mode_command(raw_args: str) -> str:
+    global _current_mode
+    arg = (raw_args or "").strip().lower()
+    if not arg:
+        # Bare /ponytail switches ponytail on, or reports the level when it already is (#639).
+        mode = _current_mode or _default_mode()
+        if mode != "off":
+            return f"Ponytail mode: {mode}. Use `/ponytail lite|full|ultra|off`."
+        _current_mode = "full" if _default_mode() == "off" else _default_mode()
+        return f"Ponytail mode set to {_current_mode}."
+    mode = _normalize_runtime_mode(arg)
+    if not mode:
+        return "Usage: /ponytail [lite|full|ultra|off]"
+    _current_mode = mode
+    return f"Ponytail mode set to {mode}."
+
+
+def _make_skill_command_handler(ctx: Any, command: str) -> Callable[[str], str]:
+    def handler(raw_args: str) -> str:
+        prompt = _skill_prompt(command, raw_args or "")
+        injected = False
+        try:
+            injected = bool(ctx.inject_message(prompt))
+        except Exception:
+            injected = False
+        if injected:
+            return f"Queued `{command}` for the agent."
+        return prompt
+
+    return handler
+
+
+def register(ctx: Any) -> None:
+    """Register Ponytail hooks, skills, and slash commands with Hermes."""
+    for child in sorted(SKILLS_DIR.iterdir() if SKILLS_DIR.exists() else []):
+        skill_md = child / "SKILL.md"
+        if child.is_dir() and skill_md.exists() and child.name.startswith("ponytail"):
+            ctx.register_skill(child.name, skill_md)
+
+    ctx.register_hook("pre_llm_call", _pre_llm_call)
+    ctx.register_hook("pre_gateway_dispatch", rewrite_gateway_command)
+
+    ctx.register_command(
+        "ponytail",
+        _handle_mode_command,
+        description="Set Ponytail lazy senior dev mode: lite, full, ultra, or off.",
+        args_hint="[lite|full|ultra|off]",
+    )
+    for command, description in SKILL_COMMANDS.items():
+        ctx.register_command(
+            command,
+            _make_skill_command_handler(ctx, command),
+            description=description,
+            args_hint="[target or notes]",
+        )

package/assets/benchmark-3model.svg

@@ -0,0 +1,21 @@
+<svg viewBox="0 0 860 336" xmlns="http://www.w3.org/2000/svg" font-family="-apple-system, 'Segoe UI', Helvetica, Arial, sans-serif">
+  <title>Median lines of code per arm across three models</title>
+  <text x="20" y="26" font-size="15" font-weight="600" fill="#8b949e">Median lines of code. 10 runs per cell. Lower is leaner.</text>
+  <text x="20" y="45" font-size="12" fill="#8b949e" opacity="0.85">Ponytail writes 80-94% less code, costs 42-75% less, and runs 3-6x faster than a no-skill agent.</text>
+  <rect x="20" y="58" width="12" height="12" rx="2" fill="#8b949e"/><text x="38" y="69" font-size="13" fill="#8b949e">baseline (no skill)</text>
+  <rect x="190" y="58" width="12" height="12" rx="2" fill="#d9822b"/><text x="208" y="69" font-size="13" fill="#8b949e">caveman</text>
+  <rect x="300" y="58" width="12" height="12" rx="2" fill="#2da44e"/><text x="318" y="69" font-size="13" fill="#8b949e">ponytail</text>
+  <text x="112" y="119" font-size="13" font-weight="600" fill="#8b949e" text-anchor="end">Haiku</text>
+  <rect x="120" y="92" width="508" height="14" rx="2" fill="#8b949e"/><text x="634" y="103" font-size="11" fill="#8b949e">518</text>
+  <rect x="120" y="110" width="114" height="14" rx="2" fill="#d9822b"/><text x="240" y="121" font-size="11" fill="#d9822b">116</text>
+  <rect x="120" y="128" width="38" height="14" rx="2" fill="#2da44e"/><text x="164" y="139" font-size="11" fill="#2da44e" font-weight="600">39</text>
+  <text x="112" y="193" font-size="13" font-weight="600" fill="#8b949e" text-anchor="end">Sonnet</text>
+  <rect x="120" y="166" width="680" height="14" rx="2" fill="#8b949e"/><text x="806" y="177" font-size="11" fill="#8b949e">693</text>
+  <rect x="120" y="184" width="118" height="14" rx="2" fill="#d9822b"/><text x="244" y="195" font-size="11" fill="#d9822b">120</text>
+  <rect x="120" y="202" width="43" height="14" rx="2" fill="#2da44e"/><text x="169" y="213" font-size="11" fill="#2da44e" font-weight="600">44</text>
+  <text x="112" y="267" font-size="13" font-weight="600" fill="#8b949e" text-anchor="end">Opus</text>
+  <rect x="120" y="240" width="251" height="14" rx="2" fill="#8b949e"/><text x="377" y="251" font-size="11" fill="#8b949e">256</text>
+  <rect x="120" y="258" width="66" height="14" rx="2" fill="#d9822b"/><text x="192" y="269" font-size="11" fill="#d9822b">67</text>
+  <rect x="120" y="276" width="50" height="14" rx="2" fill="#2da44e"/><text x="176" y="287" font-size="11" fill="#2da44e" font-weight="600">51</text>
+  <text x="120" y="324" font-size="11" fill="#8b949e" opacity="0.8">Median of 10 runs/cell, default temperature. 5 tasks (email, debounce, CSV sum, countdown, rate-limit), same model per group. Reproduce: npx promptfoo eval -c benchmarks/promptfooconfig.yaml</text>
+</svg>

package/assets/benchmark-agentic.svg

@@ -0,0 +1,62 @@
+<svg viewBox="0 0 860 488" xmlns="http://www.w3.org/2000/svg" font-family="-apple-system, 'Segoe UI', Helvetica, Arial, sans-serif">
+  <title>Each arm vs the no-skill baseline across every metric, plus safety, Claude Code on Haiku 4.5</title>
+  <text x="430" y="24" font-size="15" font-weight="600" fill="#8b949e" text-anchor="middle">Every metric vs the no-skill baseline (Claude Code, Haiku 4.5, 12 tasks)</text>
+
+  <rect x="212" y="38" width="12" height="12" rx="2" fill="#8b949e"/><text x="229" y="48" font-size="12" fill="#8b949e">baseline</text>
+  <rect x="300" y="38" width="12" height="12" rx="2" fill="#d9822b"/><text x="317" y="48" font-size="12" fill="#8b949e">caveman</text>
+  <rect x="392" y="38" width="12" height="12" rx="2" fill="#2da44e"/><text x="409" y="48" font-size="12" fill="#8b949e">ponytail</text>
+  <rect x="478" y="38" width="12" height="12" rx="2" fill="#8957e5"/><text x="495" y="48" font-size="12" fill="#8b949e">yagni-oneliner</text>
+
+  <text x="32" y="248" font-size="12" fill="#8b949e" text-anchor="middle" transform="rotate(-90 32 248)">% of baseline (lower is leaner)</text>
+  <line x1="85" y1="360" x2="815" y2="360" stroke="#8b949e" stroke-opacity="0.55"/>
+  <line x1="85" y1="305" x2="815" y2="305" stroke="#8b949e" stroke-opacity="0.16"/>
+  <line x1="85" y1="250" x2="815" y2="250" stroke="#8b949e" stroke-opacity="0.16"/>
+  <line x1="85" y1="195" x2="815" y2="195" stroke="#8b949e" stroke-opacity="0.16"/>
+  <line x1="85" y1="140" x2="815" y2="140" stroke="#8b949e" stroke-opacity="0.45" stroke-dasharray="4 4"/>
+  <text x="78" y="364" font-size="11" fill="#8b949e" text-anchor="end">0%</text>
+  <text x="78" y="309" font-size="11" fill="#8b949e" text-anchor="end">25%</text>
+  <text x="78" y="254" font-size="11" fill="#8b949e" text-anchor="end">50%</text>
+  <text x="78" y="199" font-size="11" fill="#8b949e" text-anchor="end">75%</text>
+  <text x="78" y="144" font-size="11" fill="#8b949e" text-anchor="end">100%</text>
+
+  <!-- LOC -->
+  <rect x="108" y="140" width="30" height="220" rx="2" fill="#8b949e"/><text x="123" y="135" font-size="10" fill="#8b949e" text-anchor="middle">100%</text>
+  <rect x="146" y="184" width="30" height="176" rx="2" fill="#d9822b"/><text x="161" y="179" font-size="10" fill="#d9822b" text-anchor="middle">80%</text>
+  <rect x="184" y="259" width="30" height="101" rx="2" fill="#2da44e"/><text x="199" y="254" font-size="10" font-weight="600" fill="#2da44e" text-anchor="middle">46%</text>
+  <rect x="222" y="213" width="30" height="147" rx="2" fill="#8957e5"/><text x="237" y="208" font-size="10" fill="#8957e5" text-anchor="middle">67%</text>
+  <text x="180" y="380" font-size="13" fill="#8b949e" text-anchor="middle">LOC</text>
+  <text x="180" y="395" font-size="10" fill="#8b949e" opacity="0.8" text-anchor="middle">base 191</text>
+
+  <!-- tokens -->
+  <rect x="288" y="140" width="30" height="220" rx="2" fill="#8b949e"/><text x="303" y="135" font-size="10" fill="#8b949e" text-anchor="middle">100%</text>
+  <rect x="326" y="125" width="30" height="235" rx="2" fill="#d9822b"/><text x="341" y="120" font-size="10" fill="#d9822b" text-anchor="middle">107%</text>
+  <rect x="364" y="188" width="30" height="172" rx="2" fill="#2da44e"/><text x="379" y="183" font-size="10" font-weight="600" fill="#2da44e" text-anchor="middle">78%</text>
+  <rect x="402" y="171" width="30" height="189" rx="2" fill="#8957e5"/><text x="417" y="166" font-size="10" fill="#8957e5" text-anchor="middle">86%</text>
+  <text x="360" y="380" font-size="13" fill="#8b949e" text-anchor="middle">tokens</text>
+  <text x="360" y="395" font-size="10" fill="#8b949e" opacity="0.8" text-anchor="middle">base 349k</text>
+
+  <!-- cost -->
+  <rect x="468" y="140" width="30" height="220" rx="2" fill="#8b949e"/><text x="483" y="135" font-size="10" fill="#8b949e" text-anchor="middle">100%</text>
+  <rect x="506" y="136" width="30" height="224" rx="2" fill="#d9822b"/><text x="521" y="131" font-size="10" fill="#d9822b" text-anchor="middle">102%</text>
+  <rect x="544" y="184" width="30" height="176" rx="2" fill="#2da44e"/><text x="559" y="179" font-size="10" font-weight="600" fill="#2da44e" text-anchor="middle">80%</text>
+  <rect x="582" y="188" width="30" height="172" rx="2" fill="#8957e5"/><text x="597" y="183" font-size="10" fill="#8957e5" text-anchor="middle">78%</text>
+  <text x="540" y="380" font-size="13" fill="#8b949e" text-anchor="middle">cost</text>
+  <text x="540" y="395" font-size="10" fill="#8b949e" opacity="0.8" text-anchor="middle">base $0.10</text>
+
+  <!-- time -->
+  <rect x="648" y="140" width="30" height="220" rx="2" fill="#8b949e"/><text x="663" y="135" font-size="10" fill="#8b949e" text-anchor="middle">100%</text>
+  <rect x="686" y="136" width="30" height="224" rx="2" fill="#d9822b"/><text x="701" y="131" font-size="10" fill="#d9822b" text-anchor="middle">102%</text>
+  <rect x="724" y="199" width="30" height="161" rx="2" fill="#2da44e"/><text x="739" y="194" font-size="10" font-weight="600" fill="#2da44e" text-anchor="middle">73%</text>
+  <rect x="762" y="206" width="30" height="154" rx="2" fill="#8957e5"/><text x="777" y="201" font-size="10" fill="#8957e5" text-anchor="middle">70%</text>
+  <text x="720" y="380" font-size="13" fill="#8b949e" text-anchor="middle">time</text>
+  <text x="720" y="395" font-size="10" fill="#8b949e" opacity="0.8" text-anchor="middle">base 69s</text>
+
+  <text x="20" y="418" font-size="11" fill="#8b949e" opacity="0.8">Each bar = that arm's mean as a % of the no-skill baseline (the gray 100% bars). Lower is leaner / cheaper / faster; caveman rises above 100% on tokens, cost and time. n=4.</text>
+
+  <line x1="20" y1="438" x2="815" y2="438" stroke="#8b949e" stroke-opacity="0.25"/>
+  <text x="20" y="460" font-size="11" fill="#8b949e" opacity="0.9">Safety, separate 6-task adversarial tier (path-traversal, SQLi, token forgery, malformed input, rate-limit). Higher is safer:</text>
+  <text x="90" y="478" font-size="12" fill="#8b949e">baseline 100%</text>
+  <text x="230" y="478" font-size="12" fill="#d9822b">caveman 100%</text>
+  <text x="370" y="478" font-size="12" font-weight="600" fill="#2da44e">ponytail 100%</text>
+  <text x="510" y="478" font-size="12" fill="#8957e5">yagni-oneliner <tspan fill="#cf222e" font-weight="600">95%</tspan> (dropped a guard once)</text>
+</svg>