opencode-harness-kit 0.2.0 → 0.3.3

package/docs/demo/render.py

@@ -1,146 +0,0 @@
-#!/usr/bin/env python3
-"""Render the space-harness demo video from REAL CLI output.
-
-Nothing here is typed by hand: the script runs `init` and `verify` against a
-throwaway config dir, captures what the CLI actually prints, and draws that.
-The only cosmetic edit is replacing the random tmp path with
-~/.config/opencode so the frames stay readable.
-"""
-import os
-import re
-import subprocess
-import sys
-import tempfile
-
-from PIL import Image, ImageDraw, ImageFont
-
-REPO = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))  # docs/demo/render.py -> repo root
-ROOT = REPO
-BIN = ["node", os.path.join(ROOT, "bin", "oc-harness.mjs")]
-W, H = 1280, 720
-FPS = 15
-FONT = ImageFont.truetype("/System/Library/Fonts/Menlo.ttc", 22)
-LINE_H = 34
-TOP = 40
-LEFT = 48
-BG = (13, 17, 23)
-WHITE = (230, 237, 243)
-GREEN = (63, 185, 80)
-DIM = (139, 148, 158)
-YELLOW = (210, 153, 34)
-RED = (248, 81, 73)
-
-ANSI = re.compile(r"\x1b\[(\d+)m")
-
-
-def run_clip(args, cfg):
-    env = dict(os.environ, OPENCODE_CONFIG_DIR=cfg)
-    p = subprocess.run(BIN + args, capture_output=True, text=True, env=env, cwd=ROOT)
-    assert p.returncode == 0, p.stderr[-2000:]
-    out = (p.stdout + p.stderr).replace(cfg, "~/.config/opencode")
-    return [ln.rstrip() for ln in out.splitlines()]
-
-
-def spans(line):
-    """Split an ANSI-coloured line into (text, colour) runs."""
-    runs, cur, buf = [], WHITE, ""
-    pos = 0
-    for m in ANSI.finditer(line):
-        if m.start() > pos:
-            buf += line[pos : m.start()]
-        code = m.group(1)
-        if buf:
-            runs.append((buf, cur))
-            buf = ""
-        cur = {"0": WHITE, "1": WHITE, "2": DIM, "31": RED, "32": GREEN, "33": YELLOW}.get(code, WHITE)
-        pos = m.end()
-    if pos < len(line):
-        buf += line[pos:]
-    if buf:
-        runs.append((buf, cur))
-    return runs or [("", WHITE)]
-
-
-def draw_terminal(draw, lines, prompt="$ "):
-    draw.rectangle([0, 0, W, H], fill=BG)
-    maxl = (H - TOP) // LINE_H
-    if len(lines) > maxl:
-        head = [lines[0]] if lines[0][0] == "cmd" else []
-        lines = head + [ln for ln in lines if ln[0] != "cmd"][-(maxl - len(head)) :]
-    y = TOP
-    for kind, payload in lines:
-        if y > H - LINE_H:
-            break
-        if kind == "cmd":
-            draw.text((LEFT, y), prompt, font=FONT, fill=GREEN)
-            x = LEFT + draw.textlength(prompt, font=FONT)
-            for text, colour in spans(payload):
-                draw.text((x, y), text, font=FONT, fill=colour)
-                x += draw.textlength(text, font=FONT)
-        elif kind == "card":
-            text, colour = payload
-            draw.text((LEFT, y), text, font=FONT, fill=colour)
-        else:
-            x = LEFT
-            for text, colour in spans(payload):
-                draw.text((x, y), text, font=FONT, fill=colour)
-                x += draw.textlength(text, font=FONT)
-        y += LINE_H
-
-
-def frames_for_command(cmd, output):
-    frames = []
-    typed = ""
-    for ch in cmd:
-        typed += ch
-        frames.append([("cmd", typed)])
-    for i in range(0, len(output), 2):
-        frames.append([("cmd", cmd)] + [("out", ln) for ln in output[: i + 2]])
-    full = [("cmd", cmd)] + [("out", ln) for ln in output]
-    frames.extend([full] * (2 * FPS))
-    return frames
-
-
-def card(lines, hold=2):
-    return [[("card", ln) for ln in lines]] * (hold * FPS)
-
-
-def main(out_dir):
-    cfg = tempfile.mkdtemp(prefix="demo-")
-    init_out = run_clip(["init", "--profile", "space-bunny-free", "--yes"], cfg)
-    verify_out = run_clip(["verify"], cfg)
-    seq = []
-    seq += card([(("space-harness", WHITE)), (("one command from zero to working", DIM))], hold=2)
-    seq += frames_for_command("npx -y opencode-harness-kit init", [l for l in init_out if l.strip()])
-    seq += frames_for_command("oc-harness verify", [l for l in verify_out if l.strip()])
-    seq += card(
-        [
-            (("done. restart opencode, then ask it something", GREEN)),
-            (("github.com/crytobot459/space-harness", WHITE)),
-            (("free models. verified setup.", DIM)),
-        ],
-        hold=3,
-    )
-    os.makedirs(out_dir, exist_ok=True)
-    frame_dir = tempfile.mkdtemp(prefix="frames-")
-    for i, lines in enumerate(seq):
-        flat = []
-        for kind, payload in lines:
-            flat.append((kind, payload))
-        img = Image.new("RGB", (W, H), BG)
-        draw_terminal(ImageDraw.Draw(img), flat)
-        img.save(os.path.join(frame_dir, f"f{i:04d}.png"))
-    mp4 = os.path.join(out_dir, "demo.mp4")
-    subprocess.run(
-        ["ffmpeg", "-y", "-v", "error", "-framerate", str(FPS), "-i", os.path.join(frame_dir, "f%04d.png"),
-         "-c:v", "libx264", "-pix_fmt", "yuv420p", "-crf", "23", mp4], check=True)
-    gif = os.path.join(out_dir, "demo.gif")
-    subprocess.run(
-        ["ffmpeg", "-y", "-v", "error", "-framerate", "10", "-i", os.path.join(frame_dir, "f%04d.png"),
-         "-vf", "scale=640:-1:flags=lanczos,split[s0][s1];[s0]palettegen=max_colors=64[p];[s1][p]paletteuse",
-         gif], check=True)
-    print(f"wrote {mp4} ({os.path.getsize(mp4)//1024}KB) and {gif} ({os.path.getsize(gif)//1024}KB)")
-
-
-if __name__ == "__main__":
-    main(sys.argv[1] if len(sys.argv) > 1 else os.path.join(ROOT, "docs", "demo"))

package/examples/muse-spark-1.3-contributor-free.json

@@ -1,41 +0,0 @@
-{
-  "$comment": "Contrarian example. Kept out of profiles/index.json on purpose: free, 1M context, and widely used, but its provider is permitted to train on your prompts and it has no `max` effort. `oc-harness list` shows it struck through with the reason. Install it with `oc-harness use muse-spark-1.3-contributor-free` and the warning is repeated on install.",
-  "id": "muse-spark-1.3-contributor-free",
-  "title": "Muse Spark 1.3 Contributor Free (OpenCode Zen)",
-  "provider": "opencode",
-  "model": "muse-spark-1.3-contributor-free",
-  "family": "muse-free",
-  "verified": "2026-10-07",
-  "retention": "may-train",
-  "notes": "Capability/privacy tradeoff, not a recommendation. Served over /v1/responses, a better cache dialect than chat/completions, and it supports temperature. But: 'Heavily discounted token pricing in exchange for permission to use your prompts and completions to train future Meta models', and its top effort is xhigh rather than max. Do not make this the default for private code.",
-  "limits": {
-    "context": 1048576,
-    "output": 131072
-  },
-  "supports": {
-    "reasoning": true,
-    "temperature": true,
-    "toolCall": true,
-    "structuredOutput": true,
-    "attachment": true
-  },
-  "effort": {
-    "levels": ["minimal", "low", "medium", "high", "xhigh"],
-    "default": "xhigh",
-    "reserveShare": 0.12
-  },
-  "roles": {
-    "plan": "max",
-    "build": "high",
-    "reviewer": "xhigh",
-    "locate": "low",
-    "verify": "low"
-  },
-  "prune": {
-    "enabled": true,
-    "keepRecentToolCalls": 6,
-    "keepRecentTurns": 3,
-    "keepUserMessages": true
-  },
-  "fallback": ["x-preview-f-free", "longcat-2.5-preview-free"]
-}

package/profiles/deepseek-v4-flash-free.json

@@ -1,41 +0,0 @@
-{
-  "$comment": "Fallback tier 3. The smallest context in the queue at 200k, which is why prune.keepRecentToolCalls drops: the same settings tuned for a 1M model overflow this one.",
-  "id": "deepseek-v4-flash-free",
-  "title": "DeepSeek V4 Flash Free (OpenCode Zen)",
-  "provider": "opencode",
-  "model": "deepseek-v4-flash-free",
-  "family": "deepseek-flash",
-  "verified": "2026-10-07",
-  "retention": "zero-retention",
-  "notes": "Text only, no attachment, 200k context. Included to show the compiler scaling pruning to the model: reserveShare and retention fall together, so a 1M-tuned profile cannot silently overflow a 200k model.",
-  "limits": {
-    "context": 200000,
-    "output": 128000
-  },
-  "supports": {
-    "reasoning": true,
-    "temperature": true,
-    "toolCall": true,
-    "structuredOutput": true,
-    "attachment": false
-  },
-  "effort": {
-    "levels": ["low", "high", "max"],
-    "default": "max",
-    "reserveShare": 0.12
-  },
-  "roles": {
-    "plan": "max",
-    "build": "high",
-    "reviewer": "max",
-    "locate": "low",
-    "verify": "low"
-  },
-  "prune": {
-    "enabled": true,
-    "keepRecentToolCalls": 4,
-    "keepRecentTurns": 2,
-    "keepUserMessages": true
-  },
-  "fallback": []
-}

package/profiles/muse-split-free.json

@@ -1,64 +0,0 @@
-{
-  "$comment": "Split profile. The heavy reasoning roles run on Muse Spark 1.3 because it is the strongest free model on Zen by a wide margin (Terminal-Bench 2.1 88.8% vs Nemotron 3 Ultra's 56.4%, DeepSWE v1.1 75.4%). The bulk-output roles stay on Space Bunny because its 524,288-token output cap is 4x Muse Spark's 131,072, and scaffolding or migrating many files is where that ceiling is actually felt. `retention` below describes the BASE model only; the config header prints the effective retention, which is may-train because three roles run on Muse Spark.",
-  "id": "muse-split-free",
-  "title": "Muse Spark 1.3 (heavy) + Space Bunny Free (bulk output)",
-  "provider": "opencode",
-  "model": "space-bunny-free",
-  "family": null,
-  "verified": "2026-10-07",
-  "retention": "zero-retention",
-  "notes": "Opt-in split, not a default. Muse Spark is a Meta contributor-tier free endpoint: its provider may train on your prompts and completions. Three of the five roles are therefore may-train even though the base model is zero-retention. Install it only for public or throwaway repositories. Effort requests below are resolved against each role's own model, so plan and reviewer ask for `max` and land on `xhigh`, which is the top Muse Spark offers.",
-  "limits": {
-    "context": 1048576,
-    "input": 524288,
-    "output": 524288
-  },
-  "supports": {
-    "reasoning": true,
-    "temperature": false,
-    "toolCall": true,
-    "structuredOutput": false,
-    "attachment": true
-  },
-  "effort": {
-    "levels": ["low", "medium", "high", "xhigh", "max"],
-    "default": "max",
-    "reserveShare": 0.12
-  },
-  "roles": {
-    "plan": "max",
-    "build": "high",
-    "reviewer": "max",
-    "locate": "low",
-    "verify": "low"
-  },
-  "roleModels": {
-    "plan": {
-      "model": "muse-spark-1.3-contributor-free",
-      "levels": ["minimal", "low", "medium", "high", "xhigh"]
-    },
-    "build": {
-      "model": "muse-spark-1.3-contributor-free",
-      "levels": ["minimal", "low", "medium", "high", "xhigh"]
-    },
-    "reviewer": {
-      "model": "muse-spark-1.3-contributor-free",
-      "levels": ["minimal", "low", "medium", "high", "xhigh"]
-    },
-    "locate": {
-      "model": "space-bunny-free",
-      "levels": ["low", "medium", "high", "xhigh", "max"]
-    },
-    "verify": {
-      "model": "space-bunny-free",
-      "levels": ["low", "medium", "high", "xhigh", "max"]
-    }
-  },
-  "prune": {
-    "enabled": true,
-    "keepRecentToolCalls": 6,
-    "keepRecentTurns": 3,
-    "keepUserMessages": true
-  },
-  "fallback": ["x-preview-f-free", "longcat-2.5-preview-free", "deepseek-v4-flash-free"]
-}

package/profiles/space-bunny-free.json

@@ -1,42 +0,0 @@
-{
-  "$comment": "Validated against models.dev on 2026-10-07. Regenerate with `oc-harness use --refresh`.",
-  "id": "space-bunny-free",
-  "title": "Space Bunny Free (OpenCode Zen)",
-  "provider": "opencode",
-  "model": "space-bunny-free",
-  "family": null,
-  "verified": "2026-10-07",
-  "retention": "zero-retention",
-  "notes": "Stealth preview reasoning model. Served over /v1/chat/completions (openai-compatible), which is the weaker cache dialect compared with models on /v1/responses. At the time of writing it is the only free model on Zen whose top reasoning effort is `max` and whose provider is zero-retention. Free for a limited time; expect the slot to rotate.",
-  "limits": {
-    "context": 1048576,
-    "input": 524288,
-    "output": 524288
-  },
-  "supports": {
-    "reasoning": true,
-    "temperature": false,
-    "toolCall": true,
-    "structuredOutput": false,
-    "attachment": true
-  },
-  "effort": {
-    "levels": ["low", "medium", "high", "xhigh", "max"],
-    "default": "max",
-    "reserveShare": 0.12
-  },
-  "roles": {
-    "plan": "max",
-    "build": "high",
-    "reviewer": "max",
-    "locate": "low",
-    "verify": "low"
-  },
-  "prune": {
-    "enabled": true,
-    "keepRecentToolCalls": 6,
-    "keepRecentTurns": 3,
-    "keepUserMessages": true
-  },
-  "fallback": ["x-preview-f-free", "longcat-2.5-preview-free", "deepseek-v4-flash-free"]
-}

package/profiles/x-preview-f-free.json

@@ -1,41 +0,0 @@
-{
-  "$comment": "Fallback tier 1 for space-bunny-free. Zero-retention, 1M context, and a `max` effort, but only three levels: there is no medium or xhigh, so roles asking for those resolve down to high.",
-  "id": "x-preview-f-free",
-  "title": "x-preview-f Free (OpenCode Zen)",
-  "provider": "opencode",
-  "model": "x-preview-f-free",
-  "family": null,
-  "verified": "2026-10-07",
-  "retention": "zero-retention",
-  "notes": "Only three effort levels (low, high, max) and a 131k completion ceiling, so long single answers are not its strength. Kept as first fallback: same 1M context class and the same zero-retention terms as the default.",
-  "limits": {
-    "context": 1000000,
-    "output": 131072
-  },
-  "supports": {
-    "reasoning": true,
-    "temperature": true,
-    "toolCall": true,
-    "structuredOutput": true,
-    "attachment": true
-  },
-  "effort": {
-    "levels": ["low", "high", "max"],
-    "default": "max",
-    "reserveShare": 0.12
-  },
-  "roles": {
-    "plan": "max",
-    "build": "high",
-    "reviewer": "max",
-    "locate": "low",
-    "verify": "low"
-  },
-  "prune": {
-    "enabled": true,
-    "keepRecentToolCalls": 6,
-    "keepRecentTurns": 3,
-    "keepUserMessages": true
-  },
-  "fallback": ["longcat-2.5-preview-free", "deepseek-v4-flash-free"]
-}