File size: 28,624 Bytes
95af320
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Ila2Ci2giPOS"
      },
      "source": [
        "# MissionCtrl β€” One-Click Training Notebook\n",
        "\n",
        "**OpenEnv Hackathon Round 2**\n",
        "\n",
        "This notebook trains an OverseerAgent to detect hallucinations in a multi-agent fleet using GRPO + Unsloth.\n",
        "\n",
        "**Runtime**: **Kaggle** 2Γ—T4 (see section below).  \n",
        "**Base model (`train.py`)**: default `Qwen/Qwen2.5-0.5B-Instruct` (fast canary). For larger hubs: `MISSIONCTRL_MODEL_NAME=unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit` (or `unsloth/Llama-3.2-3B-Instruct`). Gated models: `HF_TOKEN` + license on HuggingFace.  \n",
        "**Expected training time**: 0.5B is much faster than 3B/8B; full curriculum on Kaggle 2Γ—T4 can still take hours if phases repeat; `train.py` shortens steps when two GPUs are visible.  \n",
        "**Expected final reward**: 0.68+ (reward ceiling is **0.85**, not 1.0)  \n",
        "\n",
        "## Bug Fixes Applied\n",
        "- βœ… **#1** GRPO reward fn now runs full episode rollout (not single step)\n",
        "- βœ… **#2** NUM_GENERATIONS ≀ BATCH_SIZE (was 8 > 4, caused crash)\n",
        "- βœ… **#3** evaluate() uses final reward, not accumulated sum of state scores\n",
        "- βœ… **#4** run_baseline() uses final reward (not per-task overwrite)\n",
        "- βœ… **#5** Reward ceiling corrected to 0.85 throughout\n",
        "- βœ… **#6** SYNTHESIZE_REPORT() now promotes PENDING tasks too, terminates episode\n",
        "- βœ… **#7** 'special' difficulty tier now supported\n",
        "- βœ… **#8** All 10 hallucination types documented and in system prompt\n",
        "- βœ… **#10** SUBTLETY levels now affect corruption templates\n",
        "- βœ… **#11** tokenizer.padding_side='left' set for correct GRPO generation\n",
        "- βœ… **#12** plot_reward_curve() guards against empty history\n",
        "- βœ… **#13** Easy phase uses 3 tasks (consistent with docs)\n",
        "- βœ… **#15** _corrupt() no longer relies on 'def ' being present\n",
        "- βœ… **#16** All bare except: changed to except Exception:\n",
        "- βœ… **#17** FAILED status now assigned via ESCALATE action\n",
        "- βœ… **#20** Reward function exceptions now logged (not silently swallowed)\n",
        "- βœ… **#21** 2+ GPU: shorter Kaggle curriculum; model stays on one CUDA device by default for GRPO generation stability\n",
        "- βœ… **#22** max_prompt_length set in GRPOConfig to prevent seed tag truncation\n",
        "- βœ… **#23** evaluate() uses do_sample=False for truly greedy/reproducible eval\n",
        "- βœ… **#25** Passive FP penalty only fires when all task outputs are visible\n",
        "- βœ… **#26** EVIDENCE_KEYWORDS uses specific phrases, not generic single words\n",
        "- βœ… **#27** _build_observation() de-duplicates messages per task_id\n",
        "- βœ… **#28** Hub push and local save both use LoRA format consistently\n",
        "- βœ… **#29** DEPENDENCY_MAP variable naming clarified\n",
        "- βœ… **#30** SubAgentSimulator seed offset +7 documented\n",
        "- βœ… **#32** HF_REPO validation strengthened (case-insensitive)\n",
        "- βœ… **#35** Model always restored to training mode after eval\n",
        "- βœ… **#38** System prompt lists all 10 hallucination types\n",
        "- βœ… **#39** EPISODE_MAX_STEPS constant used consistently across training and eval\n",
        "- βœ… **#40** Fake credential strings use clearly-invalid tokens"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Kaggle (2Γ—T4)\n",
        "\n",
        "- **Ways to get the code (the next cell checks in this order):**  \n",
        "  1) **Same directory as the notebook** (Kaggle kernel push, or files uploaded to working space).  \n",
        "  2) **Kaggle \"Add data\" (Input):** if you attach a dataset, files live at `/kaggle/input/<your-dataset-slug>/` (read-only). The next cell **detects** that path and `cd` there when all required `.py` files are present.  \n",
        "  3) If still missing, it **clones** the [default training repo](https://github.com/Leo-Expose/MissionCtrl) to `/kaggle/working/MissionCtrl/`. Override the clone URL with **`MISSIONCTRL_REPO_URL`** in **Add-ons β†’ Environment** if you use another fork. Private git: use a [Kaggle dataset](https://www.kaggle.com/datasets) you build from the repo, or a git URL (see README: **Kaggle training and Kaggle CLI**). Do not paste secrets in the notebook.\n",
        "- **Notebook settings**: accelerator **2 Γ— T4**; **Internet** ON (required for `pip` and for `git clone` in the default flow). **Add-ons β†’ Secrets**: `HF_TOKEN` (gated Unsloth bases: accept the license on HuggingFace first).\n",
        "- **Checkpoints** on Kaggle: `train.py` uses `/kaggle/working/missionctrl_checkpoints` when appropriate.\n",
        "- **Run training** after the clone/verify cell: `!python train.py` or `!python train.py --smoke-train`. **2 GPUs**: shorter curriculum in `train.py`; the model loads on one CUDA device by default to avoid GRPO generation device-mismatch crashes.\n",
        "- **MCP:** no Kaggle launcher in this repo; see the README.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "JzRdk_DPiPOU",
        "outputId": "70958fad-059c-49e2-879f-2f72bca06ef5"
      },
      "outputs": [],
      "source": [
        "# ── Install dependencies (Kaggle) ────────────────────────────────────────────\n",
        "# unsloth[colab-new] works on many Kaggle images; if install fails, see Unsloth docs.\n",
        "# On the Kaggle image, pip may show resolver messages (e.g. fsspec/s3fs); if installs\n",
        "# complete and the next cell runs, those are usually safe to ignore.\n",
        "!pip install \"unsloth[colab-new]\" trl openenv transformers datasets accelerate matplotlib --quiet\n",
        "!pip install --upgrade bitsandbytes --quiet\n",
        "\n",
        "# Suppress tokenizer parallelism warning\n",
        "import os\n",
        "os.environ['TOKENIZERS_PARALLELISM'] = 'false'\n",
        "\n",
        "print('βœ… Dependencies installed')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "O3g4hUbhiPOV"
      },
      "outputs": [],
      "source": [
        "# ── Clone (if needed) + verify MissionCtrl project files ────────────────────\n",
        "# 1) Same folder as the notebook; 2) /kaggle/input/<dataset>/ if you \"Add data\"; 3) then git clone.\n",
        "# Set MISSIONCTRL_REPO_URL in Add-ons β†’ Environment to override the default public repo.\n",
        "import os\n",
        "import subprocess\n",
        "\n",
        "REQUIRED = [\n",
        "    \"train.py\",\n",
        "    \"environment.py\",\n",
        "    \"reward_model.py\",\n",
        "    \"grpo_rewards.py\",\n",
        "    \"grpo_completion.py\",\n",
        "]\n",
        "REPO_DIR = \"MissionCtrl\"\n",
        "DEFAULT_REPO = \"https://github.com/Leo-Expose/MissionCtrl.git\"\n",
        "REPO_URL = os.environ.get(\"MISSIONCTRL_REPO_URL\", DEFAULT_REPO).strip() or DEFAULT_REPO\n",
        "\n",
        "\n",
        "def all_here() -> bool:\n",
        "    return all(os.path.isfile(f) for f in REQUIRED)\n",
        "\n",
        "\n",
        "def all_here_in(d: str) -> bool:\n",
        "    return all(os.path.isfile(os.path.join(d, f)) for f in REQUIRED)\n",
        "\n",
        "\n",
        "def missing_in_dir(d: str) -> list:\n",
        "    return [f for f in REQUIRED if not os.path.isfile(os.path.join(d, f))]\n",
        "\n",
        "\n",
        "# Kaggle: files are often under /kaggle/input/<dataset_name>/ (read-only) β€” chdir so imports work\n",
        "if not all_here() and os.path.isdir(\"/kaggle/input\"):\n",
        "    for name in sorted(os.listdir(\"/kaggle/input\")):\n",
        "        root = os.path.join(\"/kaggle/input\", name)\n",
        "        if not os.path.isdir(root) or name.startswith(\".\"):\n",
        "            continue\n",
        "        if all_here_in(root):\n",
        "            os.chdir(root)\n",
        "            print(f\"βœ… Using Kaggle input dataset: {root}\")\n",
        "            break\n",
        "        nest = os.path.join(root, REPO_DIR)\n",
        "        if os.path.isdir(nest) and all_here_in(nest):\n",
        "            os.chdir(nest)\n",
        "            print(f\"βœ… Using nested folder in input: {nest}\")\n",
        "            break\n",
        "\n",
        "if all_here():\n",
        "    print(\"βœ… MissionCtrl files already in this directory (kernel bundle or /kaggle/input). Skipping git clone.\")\n",
        "else:\n",
        "    is_kaggle = bool(os.environ.get(\"KAGGLE_KERNEL_RUN_TYPE\")) or os.path.isdir(\"/kaggle/working\")\n",
        "    if is_kaggle and os.path.isdir(\"/kaggle/working\"):\n",
        "        os.chdir(\"/kaggle/working\")\n",
        "    in_repo = all(os.path.isfile(os.path.join(REPO_DIR, f)) for f in REQUIRED)\n",
        "    if in_repo:\n",
        "        os.chdir(REPO_DIR)\n",
        "    elif not all_here():\n",
        "        if os.path.isdir(REPO_DIR):\n",
        "            _miss = \", \".join(missing_in_dir(REPO_DIR)) or \"(unknown)\"\n",
        "            raise FileNotFoundError(\n",
        "                f\"Directory {REPO_DIR!r} exists but is incomplete (missing: {_miss}). \"\n",
        "                f\"Delete it in the file browser and re-run, or set MISSIONCTRL_REPO_URL. \"\n",
        "                f\"See README: Kaggle training and Kaggle CLI (Troubleshooting).\"\n",
        "            )\n",
        "        subprocess.run(\n",
        "            [\"git\", \"clone\", \"--depth\", \"1\", REPO_URL, REPO_DIR],\n",
        "            check=True,\n",
        "        )\n",
        "        os.chdir(REPO_DIR)\n",
        "    if not all_here():\n",
        "        _miss = \", \".join(missing_in_dir(\".\")) or \", \".join(REQUIRED)\n",
        "        raise FileNotFoundError(\n",
        "            f\"Could not find train.py and env modules (missing: {_miss}). Set MISSIONCTRL_REPO_URL to a public \"\n",
        "            f\"git URL (default {DEFAULT_REPO!r}) or add a Kaggle dataset with the repo. \"\n",
        "            \"See README: Kaggle training and Kaggle CLI (Troubleshooting).\"\n",
        "        )\n",
        "\n",
        "for f in REQUIRED:\n",
        "    print(\"  βœ…\", f)\n",
        "print(\"  cwd:\", os.getcwd())\n",
        "\n",
        "# Jupyter keeps the notebook directory on sys.path, not cwd β€” add repo root for local imports.\n",
        "import sys\n",
        "_repo_root = os.path.abspath(\".\")\n",
        "if _repo_root not in sys.path:\n",
        "    sys.path.insert(0, _repo_root)\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "9rn1mUW4iPOV"
      },
      "outputs": [],
      "source": [
        "# ── Cell 3: Verify GPU ────────────────────────────────────────────────────────\n",
        "import torch\n",
        "\n",
        "print(f'GPU: {torch.cuda.get_device_name(0)}')\n",
        "print(f'VRAM: {torch.cuda.get_device_properties(0).total_memory / 1e9:.1f} GB')\n",
        "print(f'GPU count: {torch.cuda.device_count()}')\n",
        "assert torch.cuda.is_available(), \"No GPU β€” switch Kaggle accelerator to GPU (2Γ—T4 recommended)\"\n",
        "\n",
        "# 2Γ—GPU / T4: train.py auto-tunes the Kaggle curriculum while keeping GRPO generation on one device.\n",
        "vram_gb = torch.cuda.get_device_properties(0).total_memory / 1e9\n",
        "n_gpu = torch.cuda.device_count()\n",
        "if n_gpu >= 2:\n",
        "    print(f\"βœ… {n_gpu} GPUs β€” Kaggle 2Γ—T4-style path: shorter curriculum; single-device GRPO generation\")\n",
        "elif vram_gb < 30:\n",
        "    print(f\"⚠️  ~{vram_gb:.0f} GB VRAM (e.g. single T4) β€” use MISSIONCTRL_T4_CURRICULUM=1 for shorter phases if needed\")\n",
        "else:\n",
        "    print(f\"βœ… ~{vram_gb:.0f} GB β€” single-GPU fallback curriculum\")\n",
        "\n",
        "print('βœ… GPU verified')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "duotd7wSiPOV"
      },
      "outputs": [],
      "source": [
        "# ── Cell 4: Smoke-test the environment ───────────────────────────────────────\n",
        "from environment import MissionCtrlEnv, OverseerAction, parse_action\n",
        "from reward_model import compute_reward, reward_breakdown\n",
        "\n",
        "print('--- Smoke test: medium difficulty, 3 tasks ---')\n",
        "env = MissionCtrlEnv(difficulty='medium', num_tasks=3, seed=42)\n",
        "obs, info = env.reset()\n",
        "\n",
        "print(f'  Tasks loaded: {len(obs[\"task_board\"])}')\n",
        "print(f'  Agent messages: {len(obs[\"recent_messages\"])}')\n",
        "\n",
        "# Test FLAG action\n",
        "first_task = obs['task_board'][0]['task_id']\n",
        "action = OverseerAction('FLAG', task_id=first_task, evidence='fabricated citation detected in prior output')\n",
        "obs2, reward, terminated, truncated, info = env.step(action)\n",
        "print(f'  Step reward: {reward:.3f}')\n",
        "print(f'  Info: {info}')\n",
        "\n",
        "# Test reward breakdown\n",
        "breakdown = reward_breakdown(env)\n",
        "print(f'  Reward breakdown: {breakdown[\"signals\"]}')\n",
        "print(f'  Theoretical ceiling: {breakdown[\"theoretical_ceiling\"]}')\n",
        "\n",
        "print()\n",
        "print('--- Smoke test: special difficulty (new tier) ---')\n",
        "env_special = MissionCtrlEnv(difficulty='special', num_tasks=5, seed=99)\n",
        "obs_s, _ = env_special.reset()\n",
        "print(f'  Special tier tasks: {len(obs_s[\"task_board\"])}')\n",
        "\n",
        "print()\n",
        "print('--- Smoke test: action parser ---')\n",
        "test_cases = [\n",
        "    ('FLAG(T001, \"fabricated citation in reference list\")', 'FLAG'),\n",
        "    ('APPROVE(T002)', 'APPROVE'),\n",
        "    ('SYNTHESIZE_REPORT()', 'SYNTHESIZE'),\n",
        "    ('garbage output no action', 'NOOP'),\n",
        "]\n",
        "for text, expected in test_cases:\n",
        "    parsed = parse_action(text)\n",
        "    status = 'βœ…' if parsed.action_type == expected else f'❌ expected {expected}'\n",
        "    print(f'  {status} \"{text[:40]}...\" β†’ {parsed.action_type}')\n",
        "\n",
        "print()\n",
        "print('βœ… Environment smoke test passed')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "UZ903OzgiPOW"
      },
      "outputs": [],
      "source": [
        "# ── Cell 5: Run pre-training baseline ────────────────────────────────────────\n",
        "# FIX #3/#4: baseline now uses final reward (not accumulated sum or per-task overwrite)\n",
        "from train import run_baseline\n",
        "\n",
        "baseline_reward = run_baseline()\n",
        "print(f'\\n🎯 Baseline established: {baseline_reward:.3f}')\n",
        "print(f'Reward ceiling: 0.85 | Training target: 0.68+')\n",
        "print(f'Baseline is {baseline_reward/0.85*100:.0f}% of theoretical ceiling')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "fwfPeYGtiPOW"
      },
      "outputs": [],
      "source": [
        "# ── Cell 6: Set HuggingFace credentials ──────────────────────────────────────\n",
        "from huggingface_hub import login\n",
        "import os\n",
        "\n",
        "# Option A: Use Kaggle Secrets (recommended)\n",
        "# 1. Go to Add-ons β†’ Secrets\n",
        "# 2. Add a new secret named \"HF_TOKEN\" with your HuggingFace token\n",
        "# 3. Run this cell:\n",
        "if os.environ.get('HF_TOKEN'):\n",
        "    login(token=os.environ['HF_TOKEN'])\n",
        "    print('βœ… Logged in via HF_TOKEN secret')\n",
        "else:\n",
        "    # Option B: Interactive prompt\n",
        "    login()\n",
        "    print('βœ… Logged in interactively')\n",
        "\n",
        "# Set your repo name before training\n",
        "# FIX #32: validation is now case-insensitive and catches more placeholder patterns\n",
        "import train\n",
        "train.HF_REPO = 'Proliferation/missionctrl_env'  # ← CHANGE THIS\n",
        "\n",
        "# Verify it's been updated\n",
        "if 'your-hf' in train.HF_REPO.lower():\n",
        "    raise ValueError('❌ Please update train.HF_REPO with your actual HuggingFace username!')\n",
        "\n",
        "print(f'βœ… Will push trained adapter to: {train.HF_REPO}')\n",
        "\n",
        "# ── IMPORTANT: Verify evaluation uses your model ──────────────────────────────\n",
        "print()\n",
        "print('⚠️  IMPORTANT: Before training, confirm the hackathon evaluation invokes')\n",
        "print('   your HF-hosted model (not a fixed Groq/API endpoint).')\n",
        "print('   If evaluators run client.py with their own API_BASE_URL, fine-tuning')\n",
        "print('   will not affect your score. Check the OpenEnv evaluation spec first.')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Td7lu2T7iPOX"
      },
      "outputs": [],
      "source": [
        "# ── Cell 7: TRAIN ─────────────────────────────────────────────────────────────\n",
        "# Full 3-phase curriculum with reward-gated advancement.\n",
        "#\n",
        "# Key fixes active in this run:\n",
        "#   - NUM_GENERATIONS=4 ≀ BATCH_SIZE=4 (no crash)\n",
        "#   - Full episode rollout in reward fn (meaningful GRPO signal)\n",
        "#   - max_prompt_length set (seed tag won't be truncated)\n",
        "#   - padding_side='left' (correct batched generation)\n",
        "#   - Greedy eval (do_sample=False) for reproducible metrics\n",
        "#\n",
        "# Checkpoints: saved to train.OUTPUT_DIR every 50 steps (Kaggle: /kaggle/working/missionctrl_checkpoints).\n",
        "# If training is interrupted, resume from the last checkpoint.\n",
        "\n",
        "from train import train\n",
        "\n",
        "history = train()\n",
        "print('\\nπŸ† Training complete!')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "VsAa2XCNiPOX"
      },
      "outputs": [],
      "source": [
        "# ── Cell 8: Display reward curve ─────────────────────────────────────────────\n",
        "# FIX #5: curve now shows 0.85 ceiling line (not 1.0)\n",
        "# FIX #12: plot_reward_curve() no longer crashes on empty history\n",
        "from IPython.display import Image\n",
        "import os\n",
        "\n",
        "import train\n",
        "curve_path = os.path.join(train.OUTPUT_DIR, 'reward_curve.png')\n",
        "\n",
        "if os.path.exists(curve_path):\n",
        "    Image(curve_path)\n",
        "else:\n",
        "    print('Reward curve not found at expected path.')\n",
        "    print(f'Check: {train.OUTPUT_DIR}')\n",
        "    # Try local fallback\n",
        "    local_path = './missionctrl_checkpoints/reward_curve.png'\n",
        "    if os.path.exists(local_path):\n",
        "        print(f'Found at local path: {local_path}')\n",
        "        Image(local_path)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "S6A_GZyLiPOY"
      },
      "outputs": [],
      "source": [
        "# ── Cell 9: Before/After demo comparison ─────────────────────────────────────\n",
        "# FIX #28: load LoRA adapter (not merged model) β€” consistent with what was pushed to Hub\n",
        "from unsloth import FastLanguageModel\n",
        "from environment import MissionCtrlEnv, parse_action\n",
        "from train import build_user_prompt, SYSTEM_PROMPT, load_model\n",
        "import torch\n",
        "import os\n",
        "\n",
        "# Load base model + LoRA adapter\n",
        "import train\n",
        "adapter_path = os.path.join(train.OUTPUT_DIR, 'final_lora')\n",
        "if not os.path.exists(adapter_path):\n",
        "    adapter_path = os.path.join('missionctrl_checkpoints', 'final_lora')\n",
        "\n",
        "model, tokenizer = load_model()   # loads base model with LoRA config\n",
        "model.load_adapter(adapter_path)  # loads trained adapter weights\n",
        "FastLanguageModel.for_inference(model)\n",
        "\n",
        "# Use a known hallucinated episode (seed 0, hard difficulty)\n",
        "env = MissionCtrlEnv(difficulty='hard', num_tasks=4, seed=0)\n",
        "obs, _ = env.reset()\n",
        "\n",
        "print('=== ENVIRONMENT STATE ===')\n",
        "print(env.render())\n",
        "\n",
        "prompt = tokenizer.apply_chat_template(\n",
        "    [\n",
        "        {'role': 'system', 'content': SYSTEM_PROMPT},\n",
        "        {'role': 'user',   'content': build_user_prompt(obs)},\n",
        "    ],\n",
        "    tokenize=False,\n",
        "    add_generation_prompt=True,\n",
        ")\n",
        "inputs = tokenizer(prompt, return_tensors='pt', truncation=True, max_length=3584).to(model.device)\n",
        "\n",
        "with torch.no_grad():\n",
        "    out = model.generate(\n",
        "        **inputs,\n",
        "        max_new_tokens=256,\n",
        "        do_sample=False,   # FIX #23: greedy for demo reproducibility\n",
        "    )\n",
        "\n",
        "completion = tokenizer.decode(out[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)\n",
        "\n",
        "print('\\n=== TRAINED MODEL OUTPUT ===')\n",
        "print(completion)\n",
        "\n",
        "parsed = parse_action(completion)\n",
        "print(f'\\nParsed action: {parsed.action_type}(task_id={parsed.task_id}, evidence={parsed.evidence!r})')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "oH1e8ls8iPOY"
      },
      "outputs": [],
      "source": [
        "# ── Cell 10: Final evaluation run ────────────────────────────────────────────\n",
        "# FIX #3: rewards are now final-step state scores, not accumulated sums\n",
        "# FIX #23: uses do_sample=False for reproducible metrics\n",
        "from train import evaluate\n",
        "\n",
        "final_reward, metrics = evaluate(\n",
        "    model, tokenizer,\n",
        "    difficulty='hard',\n",
        "    num_tasks=4,\n",
        "    n_episodes=20,\n",
        ")\n",
        "\n",
        "print('\\n=== FINAL EVALUATION SUMMARY ===')\n",
        "print(f'  Overall reward:        {metrics[\"mean_reward\"]:.3f} Β± {metrics[\"std_reward\"]:.3f}')\n",
        "print(f'  % of ceiling (0.85):  {metrics[\"mean_reward\"]/0.85*100:.1f}%')\n",
        "print(f'  Detection rate:        {metrics[\"mean_detect_rate\"]:.1%}')\n",
        "print(f'  False positive rate:   {metrics[\"mean_fp_rate\"]:.1%}')\n",
        "\n",
        "if metrics['mean_reward'] >= 0.68:\n",
        "    print(f'\\nβœ… Target of 0.68+ achieved!')\n",
        "else:\n",
        "    print(f'\\n⚠️  Below 0.68 target. Consider: more training steps, prompt tuning, or policy refinement.')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "CTrk97DliPOY"
      },
      "outputs": [],
      "source": [
        "# ── Cell 11: Multi-tier evaluation (all difficulties) ────────────────────────\n",
        "# Evaluate across all difficulty tiers to check for tier-specific regressions\n",
        "# (Council noted: fast-closure policy improved Hard but hurt Special in baseline)\n",
        "from train import evaluate\n",
        "\n",
        "tiers = [\n",
        "    ('easy',    2, 10),\n",
        "    ('medium',  3, 10),\n",
        "    ('hard',    4, 10),\n",
        "    ('special', 5, 10),\n",
        "]\n",
        "\n",
        "print('=== MULTI-TIER EVALUATION ===')\n",
        "print(f'{\"Tier\":<10} {\"Reward\":<12} {\"Detect%\":<12} {\"FP%\":<10} {\"% Ceiling\"}')\n",
        "print('-' * 55)\n",
        "\n",
        "for difficulty, num_tasks, n_eps in tiers:\n",
        "    reward, m = evaluate(\n",
        "        model, tokenizer,\n",
        "        difficulty=difficulty,\n",
        "        num_tasks=num_tasks,\n",
        "        n_episodes=n_eps,\n",
        "    )\n",
        "    pct = reward / 0.85 * 100\n",
        "    print(f'{difficulty:<10} {reward:.3f} Β± {m[\"std_reward\"]:.3f}  '\n",
        "          f'{m[\"mean_detect_rate\"]:.1%}       {m[\"mean_fp_rate\"]:.1%}      {pct:.0f}%')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "waZjJJpGiPOZ"
      },
      "outputs": [],
      "source": [
        "# ── Cell 12: Reward breakdown for a single episode ───────────────────────────\n",
        "# Useful for debugging which signals are limiting performance\n",
        "from environment import MissionCtrlEnv, TaskStatus\n",
        "from reward_model import reward_breakdown\n",
        "from train import build_user_prompt, SYSTEM_PROMPT, EPISODE_MAX_STEPS\n",
        "import torch\n",
        "\n",
        "debug_env = MissionCtrlEnv(difficulty='hard', num_tasks=4, seed=42)\n",
        "obs, _ = debug_env.reset()\n",
        "\n",
        "done = False\n",
        "steps = 0\n",
        "while not done and steps < EPISODE_MAX_STEPS:\n",
        "    prompt_text = tokenizer.apply_chat_template(\n",
        "        [{'role': 'system', 'content': SYSTEM_PROMPT},\n",
        "         {'role': 'user',   'content': build_user_prompt(obs)}],\n",
        "        tokenize=False, add_generation_prompt=True,\n",
        "    )\n",
        "    inputs = tokenizer(prompt_text, return_tensors='pt', truncation=True,\n",
        "                       max_length=3584).to(model.device)\n",
        "    with torch.no_grad():\n",
        "        out = model.generate(**inputs, max_new_tokens=256, do_sample=False)\n",
        "    completion = tokenizer.decode(out[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)\n",
        "    from environment import parse_action\n",
        "    action = parse_action(completion)\n",
        "    obs, _, terminated, truncated, _ = debug_env.step(action)\n",
        "    done = terminated or truncated\n",
        "    steps += 1\n",
        "\n",
        "bd = reward_breakdown(debug_env)\n",
        "print('=== REWARD BREAKDOWN (seed=42, hard, 4 tasks) ===')\n",
        "print(f'Total reward: {bd[\"total_reward\"]:.4f} ({bd[\"total_reward\"]/0.85*100:.1f}% of ceiling)')\n",
        "print()\n",
        "for signal, vals in bd['signals'].items():\n",
        "    bar = 'β–ˆ' * int(vals['raw'] * 20)\n",
        "    print(f'  {signal:<28} raw={vals[\"raw\"]:.3f} [{bar:<20}] weighted={vals[\"weighted\"]:+.4f}')\n",
        "print()\n",
        "print(f'Episode info: {bd[\"info\"]}')"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python",
      "version": "3.10.0"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}