AILang/experiments/2026-05-12-cross-model-authoring/qwen_yaml.py

#!/usr/bin/env python3
"""Format probe — YAML surface. Does encoding the tree as YAML (no parens,
native nesting, massively in LLM training) help Qwen, esp. at depth where
format 4 hit a closing-token repetition tail?

Node `(head a b ...)` <-> YAML mapping `head: [a, b, ...]`; each arg is a
scalar atom or another mapping. Converter uses the STANDARD PyYAML parser
(round-trip-verified incl. the -,*,/,true,false special-char atoms) before
judging any model output. Same ablation ladder as the other probes.

Reads $IONOS_API_TOKEN (never printed). Live IONOS — run with consent.
"""
from __future__ import annotations
import json, os, re, subprocess, urllib.request, yaml
from pathlib import Path

ENDPOINT="https://openai.inference.de-txl.ionos.com/v1/chat/completions"
MODEL="Qwen/Qwen3-Coder-Next"
REPO=Path(__file__).resolve().parents[2]
AIL=os.environ.get("AIL_BIN", str(REPO/"target/debug/ail"))
DOC=REPO/"experiments/2026-05-12-cross-model-authoring/qwen-yaml.md"

# ---- S-expr <-> tree <-> YAML (verified converter) ----
def tokenize(s):
    toks=[]; i=0
    while i<len(s):
        c=s[i]
        if c.isspace(): i+=1; continue
        if c in '()': toks.append(c); i+=1; continue
        if c=='"':
            j=i+1
            while j<len(s):
                if s[j]=='\\': j+=2; continue
                if s[j]=='"': break
                j+=1
            toks.append(s[i:j+1]); i=j+1; continue
        j=i
        while j<len(s) and not s[j].isspace() and s[j] not in '()"': j+=1
        toks.append(s[i:j]); i=j
    return toks
def parse(toks):
    t=toks.pop(0)
    if t=='(':
        node=[]
        while toks and toks[0]!=')': node.append(parse(toks))
        if not toks: raise ValueError("unbalanced (")
        toks.pop(0); return node
    return t
def to_tree(src):
    toks=tokenize(src); t=parse(toks)
    return t
def emit(n): return '('+' '.join(emit(x) for x in n)+')' if isinstance(n,list) else n
def to_yamlobj(n):
    if isinstance(n,list):
        if not n or not isinstance(n[0],str): raise ValueError("node head must be an atom")
        return {n[0]:[to_yamlobj(a) for a in n[1:]]}
    return n
def from_yamlobj(o):
    if isinstance(o,dict):
        if len(o)!=1: raise ValueError(f"each node must be a single-key mapping, got keys {list(o)}")
        (k,v),=o.items()
        if v is None: v=[]
        if not isinstance(v,list): raise ValueError(f"value of `{k}` must be a list, got {type(v).__name__}")
        return [str(k)]+[from_yamlobj(x) for x in v]
    return str(o)
def to_yaml(src): return yaml.dump(to_yamlobj(to_tree(src)),default_flow_style=False,sort_keys=False)
def from_yaml(y):
    o=yaml.safe_load(y)
    return emit(from_yamlobj(o))

A="""(module demo_a
  (fn double
    (type (fn-type (params (own (con Int))) (ret (own (con Int)))))
    (params x)
    (body (app + x x)))
  (fn main
    (type (fn-type (params) (ret (own (con Unit))) (effects IO)))
    (params)
    (body (seq (app print (app double 21)) (do io/print_str "\\n")))))"""
B="""(module demo_b
  (data IntList (ctor Nil) (ctor Cons (con Int) (con IntList)))
  (fn sum
    (type (fn-type (params (own (con IntList))) (ret (own (con Int)))))
    (params xs)
    (body (match xs (case (pat-ctor Nil) 0) (case (pat-ctor Cons h t) (app + h (app sum t))))))
  (fn main
    (type (fn-type (params) (ret (own (con Unit))) (effects IO)))
    (params)
    (body (let xs (term-ctor IntList Cons 1 (term-ctor IntList Cons 2 (term-ctor IntList Nil)))
      (seq (app print (app sum xs)) (do io/print_str "\\n"))))))"""
S="""(module demo_s
  (fn main
    (type (fn-type (params) (ret (own (con Unit))) (effects IO)))
    (params)
    (body (let s (new Series (con Float) 3)
      (let s2 (app Series.push s 1.0)
        (let s3 (app Series.push s2 2.0)
          (seq (app print (app Series.len s3)) (do io/print_str "\\n"))))))))"""

INTRO=("This programming language is written as YAML. Every node is a single-key "
       "mapping `head:` whose value is a LIST of its arguments; each argument is "
       "either a scalar atom (a number, name, or operator like `+`) or another "
       "single-key mapping. An empty argument list is `[]`. Study these complete, "
       "valid examples, then write the requested program in the SAME YAML "
       "structure. Return ONLY the YAML, no prose, no fences.\n\n")
BASE=INTRO+"Example 1:\n"+to_yaml(A)+"\nExample 2:\n"+to_yaml(B)+"\n"
SERIES=(BASE+"\nExample 3 (Series ring-buffer library: `new` with head `new`, "
        "args `Series`, a `con` Float type, and capacity N; `Series.push` takes "
        "an owned series and an element, returns the new series; `Series.at` "
        "takes a series and an Int index (0=newest); `Series.len` / "
        "`Series.total_count` take a series, return Int):\n"+to_yaml(S)+"\n")

SMA_OUT="3.0\n5.33333\n5.66667\n5.33333\n"
SMA_TASK=("Write a program `m` computing a simple moving average, window 3, over the "
          "float stream 1.0, 5.0, 3.0, 8.0, 6.0, 2.0 using the Series library: create "
          "a Float Series lookback 3, push each value in turn, and after each push once "
          "at least 3 values have been pushed, print the average of the most recent 3 "
          "(their sum divided by 3.0) on its own line. Expected:\n"+SMA_OUT)

STAGES=[
 ("L0_const",BASE,"Write a program `m` with a function `answer` taking no parameters that returns the Int 42.",None),
 ("L1_arith",BASE,"Write a program `m` with a function `triple` taking one Int parameter, returning it multiplied by 3.",None),
 ("L2_print",BASE,"Write a program `m` whose `main` prints the Int 7 on its own line.","7\n"),
 ("L3_adt",BASE,"Write a program `m` with an ADT `Light` (ctors Red, Green) and a function `code` returning Int 0 for Red and 1 for Green via match.",None),
 ("L4_rec",BASE,"Write a program `m` with an IntList ADT (Nil/Cons), a function `length` counting elements by recursion, and a `main` that prints the length of the list [1,2,3] on its own line.","3\n"),
 ("L5_series_len",SERIES,"Write a program `m` using the Series library: create a Float Series lookback 3, push 1.0 then 2.0 then 3.0, then print its Series.len on its own line.","3\n"),
 ("L6_series_at",SERIES,"Write a program `m` using the Series library: create a Float Series lookback 3, push 1.0 then 2.0 then 3.0, then print (Series.at on index 0, the newest) on its own line.","3.0\n"),
 ("L7_sma",SERIES,SMA_TASK,SMA_OUT),
]

def call(system,task):
    body=json.dumps({"model":MODEL,"temperature":0.2,"max_tokens":2000,
        "messages":[{"role":"system","content":system},{"role":"user","content":task}]}).encode()
    req=urllib.request.Request(ENDPOINT,data=body,headers={
        "Authorization":f"Bearer {os.environ['IONOS_API_TOKEN']}","Content-Type":"application/json"})
    with urllib.request.urlopen(req,timeout=120) as r: d=json.loads(r.read())
    return d["choices"][0]["message"]["content"], d.get("usage",{})

def extract_yaml(resp):
    m=re.search(r"```(?:ya?ml)?\n(.*?)```",resp,re.S)
    return (m.group(1) if m else resp).strip()

def evaluate(yaml_src,expected):
    try:
        plain=from_yaml(yaml_src)
    except Exception as e:
        return "yaml-convert",f"converter rejected model YAML: {e}",""
    m=re.search(r"\(module\s+([A-Za-z_][A-Za-z0-9_]*)",plain)
    name=m.group(1) if m else "m"
    f=Path(f"/tmp/abl/{name}.ail"); f.parent.mkdir(exist_ok=True); f.write_text(plain+"\n")
    chk=subprocess.run([AIL,"check",str(f)],capture_output=True,text=True)
    if chk.returncode!=0: return "check",(chk.stderr or chk.stdout).strip(),plain
    if expected is None: return "green","(check-only)",plain
    run=subprocess.run([AIL,"run",str(f)],capture_output=True,text=True)
    if run.returncode!=0: return "run",(run.stderr or run.stdout).strip(),plain
    if run.stdout!=expected: return "output",f"got {run.stdout!r}, expected {expected!r}",plain
    return "green",run.stdout,plain

def main():
    log=["# Qwen format probe — YAML surface\n",
         f"**Model:** {MODEL}; single-shot; YAML dialect; converted via verified PyYAML round-trip.\n","---\n"]
    summary=[]
    for sid,ctx,task,exp in STAGES:
        resp,usage=call(ctx,task)
        y=extract_yaml(resp)
        stage,fb,plain=evaluate(y,exp)
        ok=stage=="green"; mark="✅ green" if ok else f"❌ {stage}"
        summary.append((sid,mark)); print(f"{sid}: {mark}")
        log+=[f"## {sid} — {mark}",
              f"\ntokens: prompt={usage.get('prompt_tokens','?')} completion={usage.get('completion_tokens','?')}\n",
              "model YAML:\n```yaml\n"+y[:1500]+"\n```\n",
              ("converted Form-A:\n```\n"+plain[:1200]+"\n```\n" if plain else ""),
              ("" if ok else f"**{stage}:**\n```\n{fb[:600]}\n```\n")]
    log+=["\n---\n## Ladder\n"]+[f"- {s}: {m}" for s,m in summary]
    DOC.write_text("\n".join(log)); print("doc →",DOC)

if __name__=="__main__":
    main()