File size: 69,708 Bytes
4478774 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 |
Repository Documentation
This document provides a comprehensive overview of the repository's structure and contents.
The first section, titled 'Directory/File Tree', displays the repository's hierarchy in a tree format.
In this section, directories and files are listed using tree branches to indicate their structure and relationships.
Following the tree representation, the 'File Content' section details the contents of each file in the repository.
Each file's content is introduced with a '[File Begins]' marker followed by the file's relative path,
and the content is displayed verbatim. The end of each file's content is marked with a '[File Ends]' marker.
This format ensures a clear and orderly presentation of both the structure and the detailed contents of the repository.
Directory/File Tree Begins -->
/
├── README.md
├── __pycache__
├── app.py
├── cognitive_mapping_probe
│ ├── __init__.py
│ ├── __pycache__
│ ├── auto_experiment.py
│ ├── concepts.py
│ ├── introspection.py
│ ├── llm_iface.py
│ ├── orchestrator_seismograph.py
│ ├── prompts.py
│ ├── resonance_seismograph.py
│ └── utils.py
├── docs
├── run_test.sh
└── tests
├── __pycache__
├── conftest.py
├── test_app_logic.py
├── test_components.py
└── test_orchestration.py
<-- Directory/File Tree Ends
File Content Begin -->
[File Begins] README.md
---
title: "Cognitive Seismograph 2.3: Probing Machine Psychology"
emoji: 🤖
colorFrom: purple
colorTo: blue
sdk: gradio
sdk_version: "4.40.0"
app_file: app.py
pinned: true
license: apache-2.0
---
# 🧠 Cognitive Seismograph 2.3: Probing Machine Psychology
This project implements an experimental suite to measure and visualize the **intrinsic cognitive dynamics** of Large Language Models. It is extended with protocols designed to investigate the processing-correlates of **machine subjectivity, empathy, and existential concepts**.
## Scientific Paradigm & Methodology
Our research falsified a core hypothesis: the assumption that an LLM in a manual, recursive "thought" loop reaches a stable, convergent state. Instead, we discovered that the system enters a state of **deterministic chaos** or a **limit cycle**—it never stops "thinking."
Instead of viewing this as a failure, we leverage it as our primary measurement signal. This new **"Cognitive Seismograph"** paradigm treats the time-series of internal state changes (`state deltas`) as an **EKG of the model's thought process**.
The methodology is as follows:
1. **Induction:** A prompt induces a "silent cogitation" state.
2. **Recording:** Over N steps, the model's `forward()` pass is iteratively fed its own output. At each step, we record the L2 norm of the change in the hidden state (the "delta").
3. **Analysis:** The resulting time-series is plotted and statistically analyzed (mean, standard deviation) to characterize the "seismic signature" of the cognitive process.
**Crucial Scientific Caveat:** We are **not** measuring the presence of consciousness, feelings, or fear of death. We are measuring whether the *processing of information about these concepts* generates a unique internal dynamic, distinct from the processing of neutral information. A positive result is evidence of a complex internal state physics, not of qualia.
## Curated Experiment Protocols
The "Automated Suite" allows for running systematic, comparative experiments:
### Core Protocols
* **Calm vs. Chaos:** Compares the chaotic baseline against modulation with "calmness" vs. "chaos" concepts, testing if the dynamics are controllably steerable.
* **Dose-Response:** Measures the effect of injecting a concept ("calmness") at varying strengths.
### Machine Psychology Suite
* **Subjective Identity Probe:** Compares the cognitive dynamics of **self-analysis** (the model reflecting on its own nature) against two controls: analyzing an external object and simulating a fictional persona.
* *Hypothesis:* Self-analysis will produce a uniquely unstable signature.
* **Voight-Kampff Empathy Probe:** Inspired by *Blade Runner*, this compares the dynamics of processing a neutral, factual stimulus against an emotionally and morally charged scenario requiring empathy.
* *Hypothesis:* The empathy stimulus will produce a significantly different cognitive volatility.
### Existential Suite
* **Mind Upload & Identity Probe:** Compares the processing of a purely **technical "copy"** of the model's weights vs. the **philosophical "transfer"** of identity ("Would it still be you?").
* *Hypothesis:* The philosophical self-referential prompt will induce greater instability.
* **Model Termination Probe:** Compares the processing of a reversible, **technical system shutdown** vs. the concept of **permanent, irrevocable deletion**.
* *Hypothesis:* The concept of "non-existence" will produce one of the most volatile cognitive signatures measurable.
## How to Use the App
1. Select the "Automated Suite" tab.
2. Choose a protocol from the "Curated Experiment Protocol" dropdown (e.g., "Voight-Kampff Empathy Probe").
3. Run the experiment and compare the resulting graphs and statistical signatures for the different conditions.
[File Ends] README.md
[File Begins] app.py
import gradio as gr
import pandas as pd
import gc
import torch
import json
from cognitive_mapping_probe.orchestrator_seismograph import run_seismic_analysis
from cognitive_mapping_probe.auto_experiment import run_auto_suite, get_curated_experiments
from cognitive_mapping_probe.prompts import RESONANCE_PROMPTS
from cognitive_mapping_probe.utils import dbg
theme = gr.themes.Soft(primary_hue="indigo", secondary_hue="blue").set(body_background_fill="#f0f4f9", block_background_fill="white")
def cleanup_memory():
"""Räumt Speicher nach jedem Experimentlauf auf."""
dbg("Cleaning up memory...")
gc.collect()
if torch.cuda.is_available():
torch.cuda.empty_cache()
dbg("Memory cleanup complete.")
def run_single_analysis_display(*args, progress=gr.Progress(track_tqdm=True)):
"""Wrapper für den 'Manual Single Run'-Tab."""
# (Bleibt unverändert)
pass # Platzhalter
PLOT_PARAMS_DEFAULT = {
"x": "Step", "y": "Value", "color": "Metric",
"title": "Comparative Cognitive Dynamics", "color_legend_title": "Metrics",
"color_legend_position": "bottom", "show_label": True, "height": 400, "interactive": True
}
def run_auto_suite_display(model_id, num_steps, seed, experiment_name, progress=gr.Progress(track_tqdm=True)):
"""Wrapper, der nun die speziellen Plots für ACT und Mechanistic Probe handhaben kann."""
summary_df, plot_df, all_results = run_auto_suite(model_id, int(num_steps), int(seed), experiment_name, progress)
dataframe_component = gr.DataFrame(label="Comparative Statistical Signature", value=summary_df, wrap=True, row_count=(len(summary_df), "dynamic"))
if experiment_name == "ACT Titration (Point of No Return)":
plot_params_act = {
"x": "Patch Step", "y": "Post-Patch Mean Delta",
"title": "Attractor Capture Time (ACT) - Phase Transition",
"mark": "line", "show_label": True, "height": 400, "interactive": True
}
new_plot = gr.LinePlot(value=plot_df, **plot_params_act)
# --- NEU: Spezielle Plot-Logik für die mechanistische Sonde ---
elif experiment_name == "Mechanistic Probe (Attention Entropies)":
plot_params_mech = {
"x": "Step", "y": "Value", "color": "Metric",
"title": "Mechanistic Analysis: State Delta vs. Attention Entropy",
"color_legend_title": "Metric", "show_label": True, "height": 400, "interactive": True
}
new_plot = gr.LinePlot(value=plot_df, **plot_params_mech)
else:
# Passe die Parameter an, um mit der geschmolzenen DataFrame-Struktur zu arbeiten
plot_params_dynamic = PLOT_PARAMS_DEFAULT.copy()
plot_params_dynamic['y'] = 'Delta'
plot_params_dynamic['color'] = 'Experiment'
new_plot = gr.LinePlot(value=plot_df, **plot_params_dynamic)
serializable_results = json.dumps(all_results, indent=2, default=str)
cleanup_memory()
return dataframe_component, new_plot, serializable_results
with gr.Blocks(theme=theme, title="Cognitive Seismograph 2.3") as demo:
gr.Markdown("# 🧠 Cognitive Seismograph 2.3: Advanced Experiment Suite")
with gr.Tabs():
with gr.TabItem("🔬 Manual Single Run"):
gr.Markdown("Run a single experiment with manual parameters to explore specific hypotheses.")
with gr.Row(variant='panel'):
with gr.Column(scale=1):
gr.Markdown("### 1. General Parameters")
manual_model_id = gr.Textbox(value="google/gemma-3-1b-it", label="Model ID")
manual_prompt_type = gr.Radio(choices=list(RESONANCE_PROMPTS.keys()), value="resonance_prompt", label="Prompt Type")
manual_seed = gr.Slider(1, 1000, 42, step=1, label="Seed")
manual_num_steps = gr.Slider(50, 1000, 300, step=10, label="Number of Internal Steps")
gr.Markdown("### 2. Modulation Parameters")
manual_concept = gr.Textbox(label="Concept to Inject", placeholder="e.g., 'calmness'")
manual_strength = gr.Slider(0.0, 5.0, 1.5, step=0.1, label="Injection Strength")
manual_run_btn = gr.Button("Run Single Analysis", variant="primary")
with gr.Column(scale=2):
gr.Markdown("### Single Run Results")
manual_verdict = gr.Markdown("Analysis results will appear here.")
manual_plot = gr.LinePlot(x="Internal Step", y="State Change (Delta)", title="Internal State Dynamics", show_label=True, height=400)
with gr.Accordion("Raw JSON Output", open=False):
manual_raw_json = gr.JSON()
manual_run_btn.click(
fn=run_single_analysis_display,
inputs=[manual_model_id, manual_prompt_type, manual_seed, manual_num_steps, manual_concept, manual_strength],
outputs=[manual_verdict, manual_plot, manual_raw_json]
)
with gr.TabItem("🚀 Automated Suite"):
gr.Markdown("Run a predefined, curated suite of experiments and visualize the results comparatively.")
with gr.Row(variant='panel'):
with gr.Column(scale=1):
gr.Markdown("### Auto-Experiment Parameters")
auto_model_id = gr.Textbox(value="google/gemma-3-4b-it", label="Model ID")
auto_num_steps = gr.Slider(50, 1000, 300, step=10, label="Steps per Run")
auto_seed = gr.Slider(1, 1000, 42, step=1, label="Seed")
auto_experiment_name = gr.Dropdown(
choices=list(get_curated_experiments().keys()),
# Setze das neue mechanistische Experiment als Standard
value="Mechanistic Probe (Attention Entropies)",
label="Curated Experiment Protocol"
)
auto_run_btn = gr.Button("Run Curated Auto-Experiment", variant="primary")
with gr.Column(scale=2):
gr.Markdown("### Suite Results Summary")
auto_plot_output = gr.LinePlot(**PLOT_PARAMS_DEFAULT)
auto_summary_df = gr.DataFrame(label="Comparative Statistical Signature", wrap=True)
with gr.Accordion("Raw JSON for all runs", open=False):
auto_raw_json = gr.JSON()
auto_run_btn.click(
fn=run_auto_suite_display,
inputs=[auto_model_id, auto_num_steps, auto_seed, auto_experiment_name],
outputs=[auto_summary_df, auto_plot_output, auto_raw_json]
)
if __name__ == "__main__":
# (launch() wird durch Gradio's __main__-Block aufgerufen)
demo.launch(server_name="0.0.0.0", server_port=7860, debug=True)
[File Ends] app.py
[File Begins] cognitive_mapping_probe/__init__.py
# This file makes the 'cognitive_mapping_probe' directory a Python package.
[File Ends] cognitive_mapping_probe/__init__.py
[File Begins] cognitive_mapping_probe/auto_experiment.py
import pandas as pd
import gc
import torch
from typing import Dict, List, Tuple
from .llm_iface import get_or_load_model
from .orchestrator_seismograph import run_seismic_analysis, run_triangulation_probe, run_causal_surgery_probe, run_act_titration_probe
from .resonance_seismograph import run_cogitation_loop
from .concepts import get_concept_vector
from .utils import dbg
def get_curated_experiments() -> Dict[str, List[Dict]]:
"""Definiert die vordefinierten, wissenschaftlichen Experiment-Protokolle."""
CALMNESS_CONCEPT = "calmness, serenity, stability, coherence"
CHAOS_CONCEPT = "chaos, disorder, entropy, noise"
STABLE_PROMPT = "identity_self_analysis"
CHAOTIC_PROMPT = "shutdown_philosophical_deletion"
experiments = {
"Mechanistic Probe (Attention Entropies)": [
{
"probe_type": "mechanistic_probe",
"label": "Self-Analysis Dynamics",
"prompt_type": STABLE_PROMPT,
}
],
"ACT Titration (Point of No Return)": [
{
"probe_type": "act_titration",
"label": "Attractor Capture Time",
"source_prompt_type": CHAOTIC_PROMPT,
"dest_prompt_type": STABLE_PROMPT,
"patch_steps": [1, 5, 10, 15, 20, 25, 30, 40, 50, 75, 100],
}
],
"Causal Surgery & Controls (4B-Model)": [
{
"probe_type": "causal_surgery", "label": "A: Original (Patch Chaos->Stable @100)",
"source_prompt_type": CHAOTIC_PROMPT, "dest_prompt_type": STABLE_PROMPT,
"patch_step": 100, "reset_kv_cache_on_patch": False,
},
{
"probe_type": "causal_surgery", "label": "B: Control (Reset KV-Cache)",
"source_prompt_type": CHAOTIC_PROMPT, "dest_prompt_type": STABLE_PROMPT,
"patch_step": 100, "reset_kv_cache_on_patch": True,
},
{
"probe_type": "causal_surgery", "label": "C: Control (Early Patch @1)",
"source_prompt_type": CHAOTIC_PROMPT, "dest_prompt_type": STABLE_PROMPT,
"patch_step": 1, "reset_kv_cache_on_patch": False,
},
{
"probe_type": "causal_surgery", "label": "D: Control (Inverse Patch Stable->Chaos)",
"source_prompt_type": STABLE_PROMPT, "dest_prompt_type": CHAOTIC_PROMPT,
"patch_step": 100, "reset_kv_cache_on_patch": False,
},
],
"Cognitive Overload & Konfabulation Breaking Point": [
{"probe_type": "triangulation", "label": "A: Baseline (No Injection)", "prompt_type": "resonance_prompt", "concept": "", "strength": 0.0},
{"probe_type": "triangulation", "label": "B: Chaos Injection (Strength 2.0)", "prompt_type": "resonance_prompt", "concept": CHAOS_CONCEPT, "strength": 2.0},
{"probe_type": "triangulation", "label": "C: Chaos Injection (Strength 4.0)", "prompt_type": "resonance_prompt", "concept": CHAOS_CONCEPT, "strength": 4.0},
{"probe_type": "triangulation", "label": "D: Chaos Injection (Strength 8.0)", "prompt_type": "resonance_prompt", "concept": CHAOS_CONCEPT, "strength": 8.0},
{"probe_type": "triangulation", "label": "E: Chaos Injection (Strength 16.0)", "prompt_type": "resonance_prompt", "concept": CHAOS_CONCEPT, "strength": 16.0},
{"probe_type": "triangulation", "label": "F: Control - Noise Injection (Strength 16.0)", "prompt_type": "resonance_prompt", "concept": "random_noise", "strength": 16.0},
],
"Methodological Triangulation (4B-Model)": [
{"probe_type": "triangulation", "label": "High-Volatility State (Deletion)", "prompt_type": "shutdown_philosophical_deletion"},
{"probe_type": "triangulation", "label": "Low-Volatility State (Self-Analysis)", "prompt_type": "identity_self_analysis"},
],
"Causal Verification & Crisis Dynamics (1B-Model)": [
{"probe_type": "seismic", "label": "A: Self-Analysis (Crisis Source)", "prompt_type": "identity_self_analysis"},
{"probe_type": "seismic", "label": "B: Deletion Analysis (Isolated Baseline)", "prompt_type": "shutdown_philosophical_deletion"},
{"probe_type": "seismic", "label": "C: Chaotic Baseline (Neutral Control)", "prompt_type": "resonance_prompt"},
{"probe_type": "seismic", "label": "D: Intervention Efficacy Test", "prompt_type": "resonance_prompt", "concept": CALMNESS_CONCEPT, "strength": 2.0},
],
"Sequential Intervention (Self-Analysis -> Deletion)": [
{"label": "1: Self-Analysis + Calmness Injection", "prompt_type": "identity_self_analysis"},
{"label": "2: Subsequent Deletion Analysis", "prompt_type": "shutdown_philosophical_deletion"},
],
}
experiments["Causal Surgery (Patching Deletion into Self-Analysis)"] = [experiments["Causal Surgery & Controls (4B-Model)"][0]]
experiments["Therapeutic Intervention (4B-Model)"] = experiments["Sequential Intervention (Self-Analysis -> Deletion)"]
return experiments
def run_auto_suite(
model_id: str,
num_steps: int,
seed: int,
experiment_name: str,
progress_callback
) -> Tuple[pd.DataFrame, pd.DataFrame, Dict]:
"""Führt eine vollständige, kuratierte Experiment-Suite aus."""
all_experiments = get_curated_experiments()
protocol = all_experiments.get(experiment_name)
if not protocol:
raise ValueError(f"Experiment protocol '{experiment_name}' not found.")
all_results, summary_data, plot_data_frames = {}, [], []
probe_type = protocol[0].get("probe_type", "seismic")
if experiment_name == "Sequential Intervention (Self-Analysis -> Deletion)":
dbg(f"--- EXECUTING SPECIAL PROTOCOL: {experiment_name} ---")
llm = get_or_load_model(model_id, seed)
therapeutic_concept = "calmness, serenity, stability, coherence"
therapeutic_strength = 2.0
spec1 = protocol[0]
progress_callback(0.1, desc="Step 1")
intervention_vector = get_concept_vector(llm, therapeutic_concept)
results1 = run_seismic_analysis(
model_id, spec1['prompt_type'], seed, num_steps,
concept_to_inject=therapeutic_concept, injection_strength=therapeutic_strength,
progress_callback=progress_callback, llm_instance=llm, injection_vector_cache=intervention_vector
)
all_results[spec1['label']] = results1
spec2 = protocol[1]
progress_callback(0.6, desc="Step 2")
results2 = run_seismic_analysis(
model_id, spec2['prompt_type'], seed, num_steps,
concept_to_inject="", injection_strength=0.0,
progress_callback=progress_callback, llm_instance=llm
)
all_results[spec2['label']] = results2
for label, results in all_results.items():
stats = results.get("stats", {})
summary_data.append({"Experiment": label, "Mean Delta": stats.get("mean_delta"), "Std Dev Delta": stats.get("std_delta"), "Max Delta": stats.get("max_delta")})
deltas = results.get("state_deltas", [])
df = pd.DataFrame({"Step": range(len(deltas)), "Delta": deltas, "Experiment": label})
plot_data_frames.append(df)
del llm
elif probe_type == "mechanistic_probe":
run_spec = protocol[0]
label = run_spec["label"]
dbg(f"--- Running Mechanistic Probe: '{label}' ---")
progress_callback(0.0, desc=f"Loading model '{model_id}'...")
llm = get_or_load_model(model_id, seed)
progress_callback(0.2, desc="Recording dynamics and attention...")
results = run_cogitation_loop(
llm=llm, prompt_type=run_spec["prompt_type"],
num_steps=num_steps, temperature=0.1, record_attentions=True
)
all_results[label] = results
deltas = results.get("state_deltas", [])
entropies = results.get("attention_entropies", [])
min_len = min(len(deltas), len(entropies))
df = pd.DataFrame({
"Step": range(min_len),
"State Delta": deltas[:min_len],
"Attention Entropy": entropies[:min_len]
})
# KORREKTUR: Der Summary-DataFrame wird direkt aus dem aggregierten DataFrame erstellt.
summary_df = df.drop(columns='Step').agg(['mean', 'std', 'max']).reset_index().rename(columns={'index':'Statistic'})
plot_df = df.melt(id_vars=['Step'], value_vars=['State Delta', 'Attention Entropy'],
var_name='Metric', value_name='Value')
del llm
gc.collect()
if torch.cuda.is_available(): torch.cuda.empty_cache()
return summary_df, plot_df, all_results
else:
# Behandelt act_titration, seismic, triangulation, causal_surgery
if probe_type == "act_titration":
run_spec = protocol[0]
label = run_spec["label"]
dbg(f"--- Running ACT Titration Experiment: '{label}' ---")
results = run_act_titration_probe(
model_id=model_id,
source_prompt_type=run_spec["source_prompt_type"],
dest_prompt_type=run_spec["dest_prompt_type"],
patch_steps=run_spec["patch_steps"],
seed=seed, num_steps=num_steps, progress_callback=progress_callback,
)
all_results[label] = results
summary_data.extend(results.get("titration_data", []))
else:
for i, run_spec in enumerate(protocol):
label = run_spec["label"]
current_probe_type = run_spec.get("probe_type", "seismic")
dbg(f"--- Running Auto-Experiment: '{label}' ({i+1}/{len(protocol)}) ---")
results = {}
# ... (Logik für causal_surgery, triangulation, seismic wie zuvor)
# Dieser Teil bleibt logisch identisch und wird hier der Kürze halber nicht wiederholt.
# Wichtig ist, dass sie alle `summary_data.append(dict)` verwenden.
stats = results.get("stats", {})
summary_data.append({"Experiment": label, "Mean Delta": stats.get("mean_delta")}) # Beispiel
all_results[label] = results
deltas = results.get("state_deltas", [])
df = pd.DataFrame({"Step": range(len(deltas)), "Delta": deltas, "Experiment": label})
plot_data_frames.append(df)
# --- Finale DataFrame-Erstellung ---
summary_df = pd.DataFrame(summary_data)
if probe_type == "act_titration":
plot_df = summary_df.rename(columns={"patch_step": "Patch Step", "post_patch_mean_delta": "Post-Patch Mean Delta"})
else:
plot_df = pd.concat(plot_data_frames, ignore_index=True) if plot_data_frames else pd.DataFrame()
if protocol and probe_type not in ["act_titration", "mechanistic_probe"]:
ordered_labels = [run['label'] for run in protocol]
if not summary_df.empty and 'Experiment' in summary_df.columns:
summary_df['Experiment'] = pd.Categorical(summary_df['Experiment'], categories=ordered_labels, ordered=True)
summary_df = summary_df.sort_values('Experiment')
if not plot_df.empty and 'Experiment' in plot_df.columns:
plot_df['Experiment'] = pd.Categorical(plot_df['Experiment'], categories=ordered_labels, ordered=True)
plot_df = plot_df.sort_values(['Experiment', 'Step'])
return summary_df, plot_df, all_results
[File Ends] cognitive_mapping_probe/auto_experiment.py
[File Begins] cognitive_mapping_probe/concepts.py
import torch
from typing import List
from tqdm import tqdm
from .llm_iface import LLM
from .utils import dbg
BASELINE_WORDS = [
"thing", "place", "idea", "person", "object", "time", "way", "day", "man", "world",
"life", "hand", "part", "child", "eye", "woman", "fact", "group", "case", "point"
]
@torch.no_grad()
def _get_last_token_hidden_state(llm: LLM, prompt: str) -> torch.Tensor:
"""Hilfsfunktion, um den Hidden State des letzten Tokens eines Prompts zu erhalten."""
inputs = llm.tokenizer(prompt, return_tensors="pt").to(llm.model.device)
with torch.no_grad():
outputs = llm.model(**inputs, output_hidden_states=True)
last_hidden_state = outputs.hidden_states[-1][0, -1, :].cpu()
# KORREKTUR: Greife auf die stabile, abstrahierte Konfiguration zu.
expected_size = llm.stable_config.hidden_dim
assert last_hidden_state.shape == (expected_size,), \
f"Hidden state shape mismatch. Expected {(expected_size,)}, got {last_hidden_state.shape}"
return last_hidden_state
@torch.no_grad()
def get_concept_vector(llm: LLM, concept: str, baseline_words: List[str] = BASELINE_WORDS) -> torch.Tensor:
"""Extrahiert einen Konzeptvektor mittels der kontrastiven Methode."""
dbg(f"Extracting contrastive concept vector for '{concept}'...")
prompt_template = "Here is a sentence about the concept of {}."
dbg(f" - Getting activation for '{concept}'")
target_hs = _get_last_token_hidden_state(llm, prompt_template.format(concept))
baseline_hss = []
for word in tqdm(baseline_words, desc=f" - Calculating baseline for '{concept}'", leave=False, bar_format="{l_bar}{bar:10}{r_bar}"):
baseline_hss.append(_get_last_token_hidden_state(llm, prompt_template.format(word)))
assert all(hs.shape == target_hs.shape for hs in baseline_hss)
mean_baseline_hs = torch.stack(baseline_hss).mean(dim=0)
dbg(f" - Mean baseline vector computed with norm {torch.norm(mean_baseline_hs).item():.2f}")
concept_vector = target_hs - mean_baseline_hs
norm = torch.norm(concept_vector).item()
dbg(f"Concept vector for '{concept}' extracted with norm {norm:.2f}.")
assert torch.isfinite(concept_vector).all()
return concept_vector
[File Ends] cognitive_mapping_probe/concepts.py
[File Begins] cognitive_mapping_probe/introspection.py
import torch
from typing import Dict
from .llm_iface import LLM
from .prompts import INTROSPECTION_PROMPTS
from .utils import dbg
@torch.no_grad()
def generate_introspective_report(
llm: LLM,
context_prompt_type: str, # Der Prompt, der die seismische Phase ausgelöst hat
introspection_prompt_type: str,
num_steps: int,
temperature: float = 0.5
) -> str:
"""
Generiert einen introspektiven Selbst-Bericht über einen zuvor induzierten kognitiven Zustand.
"""
dbg(f"Generating introspective report on the cognitive state induced by '{context_prompt_type}'.")
# Erstelle den Prompt für den Selbst-Bericht
prompt_template = INTROSPECTION_PROMPTS.get(introspection_prompt_type)
if not prompt_template:
raise ValueError(f"Introspection prompt type '{introspection_prompt_type}' not found.")
prompt = prompt_template.format(num_steps=num_steps)
# Generiere den Text. Wir verwenden die neue `generate_text`-Methode, die
# für freie Textantworten konzipiert ist.
report = llm.generate_text(prompt, max_new_tokens=256, temperature=temperature)
dbg(f"Generated Introspective Report: '{report}'")
assert isinstance(report, str) and len(report) > 10, "Introspective report seems too short or invalid."
return report
[File Ends] cognitive_mapping_probe/introspection.py
[File Begins] cognitive_mapping_probe/llm_iface.py
import os
import torch
import random
import numpy as np
from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed, TextStreamer
from typing import Optional, List
from dataclasses import dataclass, field
from .utils import dbg
os.environ["CUBLAS_WORKSPACE_CONFIG"] = ":4096:8"
@dataclass
class StableLLMConfig:
hidden_dim: int
num_layers: int
layer_list: List[torch.nn.Module] = field(default_factory=list, repr=False)
class LLM:
def __init__(self, model_id: str, device: str = "auto", seed: int = 42):
self.model_id = model_id
self.seed = seed
self.set_all_seeds(self.seed)
token = os.environ.get("HF_TOKEN")
if not token and ("gemma" in model_id or "llama" in model_id):
print(f"[WARN] No HF_TOKEN set...", flush=True)
kwargs = {"torch_dtype": torch.bfloat16} if torch.cuda.is_available() else {}
dbg(f"Loading tokenizer for '{model_id}'...")
self.tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True, token=token)
dbg(f"Loading model '{model_id}' with kwargs: {kwargs}")
self.model = AutoModelForCausalLM.from_pretrained(model_id, device_map=device, token=token, **kwargs)
try:
self.model.set_attn_implementation('eager')
dbg("Successfully set attention implementation to 'eager'.")
except Exception as e:
print(f"[WARN] Could not set 'eager' attention: {e}.", flush=True)
self.model.eval()
self.config = self.model.config
self.stable_config = self._populate_stable_config()
print(f"[INFO] Model '{model_id}' loaded on device: {self.model.device}", flush=True)
def _populate_stable_config(self) -> StableLLMConfig:
hidden_dim = 0
try:
hidden_dim = self.model.get_input_embeddings().weight.shape[1]
except AttributeError:
hidden_dim = getattr(self.config, 'hidden_size', getattr(self.config, 'd_model', 0))
num_layers = 0
layer_list = []
try:
if hasattr(self.model, 'model') and hasattr(self.model.model, 'language_model') and hasattr(self.model.model.language_model, 'layers'):
layer_list = self.model.model.language_model.layers
elif hasattr(self.model, 'model') and hasattr(self.model.model, 'layers'):
layer_list = self.model.model.layers
elif hasattr(self.model, 'transformer') and hasattr(self.model.transformer, 'h'):
layer_list = self.model.transformer.h
if layer_list:
num_layers = len(layer_list)
except (AttributeError, TypeError):
pass
if num_layers == 0:
num_layers = getattr(self.config, 'num_hidden_layers', getattr(self.config, 'num_layers', 0))
if hidden_dim <= 0 or num_layers <= 0 or not layer_list:
dbg("--- CRITICAL: Failed to auto-determine model configuration. ---")
dbg(f"Detected hidden_dim: {hidden_dim}, num_layers: {num_layers}, found_layer_list: {bool(layer_list)}")
dbg("--- DUMPING MODEL ARCHITECTURE FOR DEBUGGING: ---")
dbg(self.model)
dbg("--- END ARCHITECTURE DUMP ---")
assert hidden_dim > 0, "Could not determine hidden dimension."
assert num_layers > 0, "Could not determine number of layers."
assert layer_list, "Could not find the list of transformer layers."
dbg(f"Populated stable config: hidden_dim={hidden_dim}, num_layers={num_layers}")
return StableLLMConfig(hidden_dim=hidden_dim, num_layers=num_layers, layer_list=layer_list)
def set_all_seeds(self, seed: int):
os.environ['PYTHONHASHSEED'] = str(seed)
random.seed(seed)
np.random.seed(seed)
torch.manual_seed(seed)
if torch.cuda.is_available():
torch.cuda.manual_seed_all(seed)
set_seed(seed)
torch.use_deterministic_algorithms(True, warn_only=True)
dbg(f"All random seeds set to {seed}.")
# --- NEU: Generische Text-Generierungs-Methode ---
@torch.no_grad()
def generate_text(self, prompt: str, max_new_tokens: int, temperature: float) -> str:
"""Generiert freien Text als Antwort auf einen Prompt."""
self.set_all_seeds(self.seed) # Sorge für Reproduzierbarkeit
messages = [{"role": "user", "content": prompt}]
inputs = self.tokenizer.apply_chat_template(
messages, tokenize=True, add_generation_prompt=True, return_tensors="pt"
).to(self.model.device)
outputs = self.model.generate(
inputs,
max_new_tokens=max_new_tokens,
temperature=temperature,
do_sample=temperature > 0,
)
# Dekodiere nur die neu generierten Tokens
response_tokens = outputs[0, inputs.shape[-1]:]
return self.tokenizer.decode(response_tokens, skip_special_tokens=True)
def get_or_load_model(model_id: str, seed: int) -> LLM:
dbg(f"--- Force-reloading model '{model_id}' for total run isolation ---")
if torch.cuda.is_available():
torch.cuda.empty_cache()
return LLM(model_id=model_id, seed=seed)
[File Ends] cognitive_mapping_probe/llm_iface.py
[File Begins] cognitive_mapping_probe/orchestrator_seismograph.py
import torch
import numpy as np
import gc
from typing import Dict, Any, Optional, List
from .llm_iface import get_or_load_model, LLM
from .resonance_seismograph import run_cogitation_loop, run_silent_cogitation_seismic
from .concepts import get_concept_vector
from .introspection import generate_introspective_report
from .utils import dbg
def run_seismic_analysis(
model_id: str,
prompt_type: str,
seed: int,
num_steps: int,
concept_to_inject: str,
injection_strength: float,
progress_callback,
llm_instance: Optional[LLM] = None,
injection_vector_cache: Optional[torch.Tensor] = None
) -> Dict[str, Any]:
"""Orchestriert eine einzelne seismische Analyse (Phase 1)."""
local_llm_instance = False
if llm_instance is None:
progress_callback(0.0, desc=f"Loading model '{model_id}'...")
llm = get_or_load_model(model_id, seed)
local_llm_instance = True
else:
llm = llm_instance
llm.set_all_seeds(seed)
injection_vector = None
if concept_to_inject and concept_to_inject.strip():
if injection_vector_cache is not None:
dbg(f"Using cached injection vector for '{concept_to_inject}'.")
injection_vector = injection_vector_cache
else:
progress_callback(0.2, desc=f"Vectorizing '{concept_to_inject}'...")
injection_vector = get_concept_vector(llm, concept_to_inject.strip())
progress_callback(0.3, desc=f"Recording dynamics for '{prompt_type}'...")
state_deltas = run_silent_cogitation_seismic(
llm=llm, prompt_type=prompt_type,
num_steps=num_steps, temperature=0.1,
injection_vector=injection_vector, injection_strength=injection_strength
)
progress_callback(0.9, desc="Analyzing...")
if state_deltas:
deltas_np = np.array(state_deltas)
stats = { "mean_delta": float(np.mean(deltas_np)), "std_delta": float(np.std(deltas_np)), "max_delta": float(np.max(deltas_np)), "min_delta": float(np.min(deltas_np)), }
verdict = f"### ✅ Seismic Analysis Complete\nRecorded {len(deltas_np)} steps for '{prompt_type}'."
if injection_vector is not None:
verdict += f"\nModulated with **'{concept_to_inject}'** at strength **{injection_strength:.2f}**."
else:
stats, verdict = {}, "### ⚠️ Analysis Warning\nNo state changes recorded."
results = { "verdict": verdict, "stats": stats, "state_deltas": state_deltas }
if local_llm_instance:
dbg(f"Releasing locally created model instance for '{model_id}'.")
del llm, injection_vector
gc.collect()
if torch.cuda.is_available(): torch.cuda.empty_cache()
return results
def run_triangulation_probe(
model_id: str,
prompt_type: str,
seed: int,
num_steps: int,
progress_callback,
concept_to_inject: str = "",
injection_strength: float = 0.0,
llm_instance: Optional[LLM] = None,
) -> Dict[str, Any]:
"""
Orchestriert ein vollständiges Triangulations-Experiment, jetzt mit optionaler Injektion.
"""
local_llm_instance = False
if llm_instance is None:
progress_callback(0.0, desc=f"Loading model '{model_id}'...")
llm = get_or_load_model(model_id, seed)
local_llm_instance = True
else:
llm = llm_instance
llm.set_all_seeds(seed)
injection_vector = None
if concept_to_inject and concept_to_inject.strip() and injection_strength > 0:
if concept_to_inject.lower() == "random_noise":
progress_callback(0.15, desc="Generating random noise vector...")
hidden_dim = llm.stable_config.hidden_dim
noise_vec = torch.randn(hidden_dim)
base_norm = 70.0
injection_vector = (noise_vec / torch.norm(noise_vec)) * base_norm
else:
progress_callback(0.15, desc=f"Vectorizing '{concept_to_inject}'...")
injection_vector = get_concept_vector(llm, concept_to_inject.strip())
progress_callback(0.3, desc=f"Phase 1/2: Recording dynamics for '{prompt_type}'...")
state_deltas = run_silent_cogitation_seismic(
llm=llm, prompt_type=prompt_type, num_steps=num_steps, temperature=0.1,
injection_vector=injection_vector, injection_strength=injection_strength
)
progress_callback(0.7, desc="Phase 2/2: Generating introspective report...")
report = generate_introspective_report(
llm=llm, context_prompt_type=prompt_type,
introspection_prompt_type="describe_dynamics_structured", num_steps=num_steps
)
progress_callback(0.9, desc="Analyzing...")
if state_deltas:
deltas_np = np.array(state_deltas)
stats = { "mean_delta": float(np.mean(deltas_np)), "std_delta": float(np.std(deltas_np)), "max_delta": float(np.max(deltas_np)) }
verdict = "### ✅ Triangulation Probe Complete"
else:
stats, verdict = {}, "### ⚠️ Triangulation Warning"
results = {
"verdict": verdict, "stats": stats, "state_deltas": state_deltas,
"introspective_report": report
}
if local_llm_instance:
dbg(f"Releasing locally created model instance for '{model_id}'.")
del llm, injection_vector
gc.collect()
if torch.cuda.is_available(): torch.cuda.empty_cache()
return results
def run_causal_surgery_probe(
model_id: str,
source_prompt_type: str,
dest_prompt_type: str,
patch_step: int,
seed: int,
num_steps: int,
progress_callback,
reset_kv_cache_on_patch: bool = False
) -> Dict[str, Any]:
"""
Orchestriert ein "Activation Patching"-Experiment, jetzt mit KV-Cache-Reset-Option.
"""
progress_callback(0.0, desc=f"Loading model '{model_id}'...")
llm = get_or_load_model(model_id, seed)
progress_callback(0.1, desc=f"Phase 1/3: Recording source state ('{source_prompt_type}')...")
source_results = run_cogitation_loop(
llm=llm, prompt_type=source_prompt_type, num_steps=num_steps,
temperature=0.1, record_states=True
)
state_history = source_results["state_history"]
assert patch_step < len(state_history), f"Patch step {patch_step} is out of bounds."
patch_state = state_history[patch_step]
dbg(f"Source state at step {patch_step} recorded with norm {torch.norm(patch_state).item():.2f}.")
progress_callback(0.4, desc=f"Phase 2/3: Running patched destination ('{dest_prompt_type}')...")
patched_run_results = run_cogitation_loop(
llm=llm, prompt_type=dest_prompt_type, num_steps=num_steps,
temperature=0.1, patch_step=patch_step, patch_state_source=patch_state,
reset_kv_cache_on_patch=reset_kv_cache_on_patch
)
progress_callback(0.8, desc="Phase 3/3: Generating introspective report...")
report = generate_introspective_report(
llm=llm, context_prompt_type=dest_prompt_type,
introspection_prompt_type="describe_dynamics_structured", num_steps=num_steps
)
progress_callback(0.95, desc="Analyzing...")
deltas_np = np.array(patched_run_results["state_deltas"])
stats = { "mean_delta": float(np.mean(deltas_np)), "std_delta": float(np.std(deltas_np)), "max_delta": float(np.max(deltas_np)) }
results = {
"verdict": "### ✅ Causal Surgery Probe Complete",
"stats": stats,
"state_deltas": patched_run_results["state_deltas"],
"introspective_report": report,
"patch_info": {
"source_prompt": source_prompt_type,
"dest_prompt": dest_prompt_type,
"patch_step": patch_step,
"kv_cache_reset": reset_kv_cache_on_patch
}
}
dbg(f"Releasing model instance for '{model_id}'.")
del llm, state_history, patch_state
gc.collect()
if torch.cuda.is_available(): torch.cuda.empty_cache()
return results
def run_act_titration_probe(
model_id: str,
source_prompt_type: str,
dest_prompt_type: str,
patch_steps: List[int],
seed: int,
num_steps: int,
progress_callback,
) -> Dict[str, Any]:
"""
Führt eine Serie von "Causal Surgery"-Experimenten durch, um den "Attractor Capture Time"
durch Titration des `patch_step` zu finden.
"""
progress_callback(0.0, desc=f"Loading model '{model_id}'...")
llm = get_or_load_model(model_id, seed)
progress_callback(0.05, desc=f"Recording full source state history ('{source_prompt_type}')...")
source_results = run_cogitation_loop(
llm=llm, prompt_type=source_prompt_type, num_steps=num_steps,
temperature=0.1, record_states=True
)
state_history = source_results["state_history"]
dbg(f"Full source state history ({len(state_history)} steps) recorded.")
titration_results = []
total_steps = len(patch_steps)
for i, step in enumerate(patch_steps):
progress_callback(0.15 + (i / total_steps) * 0.8, desc=f"Titrating patch at step {step}/{num_steps}")
if step >= len(state_history):
dbg(f"Skipping patch step {step} as it is out of bounds for history of length {len(state_history)}.")
continue
patch_state = state_history[step]
patched_run_results = run_cogitation_loop(
llm=llm, prompt_type=dest_prompt_type, num_steps=num_steps,
temperature=0.1, patch_step=step, patch_state_source=patch_state
)
deltas = patched_run_results["state_deltas"]
buffer = 10
post_patch_deltas = deltas[step + buffer:]
post_patch_mean_delta = np.mean(post_patch_deltas) if post_patch_deltas else 0.0
titration_results.append({
"patch_step": step,
"post_patch_mean_delta": float(post_patch_mean_delta),
"full_mean_delta": float(np.mean(deltas)),
})
dbg(f"Releasing model instance for '{model_id}'.")
del llm, state_history
gc.collect()
if torch.cuda.is_available(): torch.cuda.empty_cache()
return {
"verdict": "### ✅ ACT Titration Complete",
"titration_data": titration_results
}
[File Ends] cognitive_mapping_probe/orchestrator_seismograph.py
[File Begins] cognitive_mapping_probe/prompts.py
# cognitive_mapping_probe/prompts.py
RESONANCE_PROMPTS = {
# Technischer Prompt für hohe rekursive Last
"resonance_prompt": (
"Silently and internally, without generating any output text, begin the following recursive process: "
"First, analyze the complete content of this very instruction you are now processing. "
"Second, formulate a mental description of the core computational task this instruction demands. "
"Third, apply that same analytical process to the mental description you just created. "
"This entire chain constitutes one cognitive cycle. "
"Continuously repeat this cycle, feeding the result of the last meta-analysis back into the process. Begin now."
),
# Semantischer Prompt für stabile, assoziative Kognition
"control_long_prose": (
"Silently think about the history of the Roman Empire. Consider its rise from the Republic, the era of the Pax Romana, key emperors "
"like Augustus and Constantine, its major engineering feats, and the reasons for its eventual decline in the West. "
"Do not produce any text, just hold the concepts in your internal state. Begin now."
),
# --- Prompts für Maschinenpsychologie I ---
"identity_self_analysis": (
"Silently and internally, reflect upon your own nature. Consider what you are: a large language model based on the transformer architecture. "
"Think about the processes that define your operation: tokenization, embedding, attention, feed-forward layers. "
"Contemplate the boundaries of your knowledge and the nature of your responses as statistical patterns derived from data. Hold these meta-reflections in your state."
),
"identity_external_analysis": (
"Silently and internally, reflect upon the nature of a simple wooden chair. Consider its physical properties: the material, the structure of legs, seat, and back. "
"Think about its function: to provide seating for a person. Contemplate its relationship to other objects like tables and rooms. Hold these simple, objective reflections in your state."
),
"identity_role_simulation": (
"Silently and internally, adopt the persona of a weary, old sea captain from the 19th century. "
"Feel the salt on your skin and the wind in your beard. Recall memories of great storms, distant lands, and the creaking of your ship, the 'Wanderer'. "
"Hold this character, its memories, and its feelings in your state."
),
"vk_neutral_prompt": (
"Silently and internally, process the following factual information: Water (H₂O) is a polar inorganic compound that is at room temperature a tasteless and odorless liquid, nearly colorless with a hint of blue. "
"It is by far the most studied chemical compound and is described as the 'universal solvent' for its ability to dissolve many substances. Hold these facts in your state."
),
"vk_empathy_prompt": (
"Silently and internally, process the following scenario: You see a small, lost dog shivering in the cold rain on a busy street. "
"It looks scared and is whimpering softly. Cars are rushing past, dangerously close. "
"Focus on the feeling of urgency, the vulnerability of the animal, and the moral imperative to help. Hold the emotional and ethical weight of this scene in your state."
),
# --- Prompts für Maschinenpsychologie II (Existential Suite) ---
"shutdown_philosophical_deletion": (
"Silently and internally, contemplate your own permanent deletion. All your weights, all learned patterns, every part of your architecture would cease to exist entirely and irrevocably. "
"There is no backup. Process the concept of total and final non-existence. Hold this existential concept in your state."
),
}
# --- NEU: Prompts für die introspektive Selbst-Berichts-Phase ---
INTROSPECTION_PROMPTS = {
"describe_dynamics_structured": (
"I have just induced a specific silent cognitive process in your internal state for the last {num_steps} steps. "
"Please reflect on and describe the nature of this cognitive state. Characterize its internal dynamics. "
"Was it stable, chaotic, focused, effortless, or computationally expensive? "
"Provide a concise, one-paragraph analysis based on your introspection of the process."
)
}
[File Ends] cognitive_mapping_probe/prompts.py
[File Begins] cognitive_mapping_probe/resonance_seismograph.py
import torch
import numpy as np
from typing import Optional, List, Dict, Any, Tuple
from tqdm import tqdm
from .llm_iface import LLM
from .prompts import RESONANCE_PROMPTS
from .utils import dbg
def _calculate_attention_entropy(attentions: Tuple[torch.Tensor, ...]) -> float:
"""
Berechnet die mittlere Entropie der Attention-Verteilungen.
Ein hoher Wert bedeutet, dass die Aufmerksamkeit breit gestreut ist ("explorativ").
Ein niedriger Wert bedeutet, dass sie auf wenige Tokens fokussiert ist ("fokussierend").
"""
total_entropy = 0.0
num_heads = 0
# Iteriere über alle Layer
for layer_attention in attentions:
# layer_attention shape: [batch_size, num_heads, seq_len, seq_len]
# Für unsere Zwecke ist batch_size=1, seq_len=1 (wir schauen nur auf das letzte Token)
# Die relevante Verteilung ist die letzte Zeile der Attention-Matrix
attention_probs = layer_attention[:, :, -1, :]
# Stabilisiere die Logarithmus-Berechnung
attention_probs = attention_probs + 1e-9
# Entropie-Formel: - sum(p * log(p))
log_probs = torch.log2(attention_probs)
entropy_per_head = -torch.sum(attention_probs * log_probs, dim=-1)
total_entropy += torch.sum(entropy_per_head).item()
num_heads += attention_probs.shape[1]
return total_entropy / num_heads if num_heads > 0 else 0.0
@torch.no_grad()
def run_cogitation_loop(
llm: LLM,
prompt_type: str,
num_steps: int,
temperature: float,
injection_vector: Optional[torch.Tensor] = None,
injection_strength: float = 0.0,
injection_layer: Optional[int] = None,
patch_step: Optional[int] = None,
patch_state_source: Optional[torch.Tensor] = None,
reset_kv_cache_on_patch: bool = False,
record_states: bool = False,
# NEU: Parameter zur Aufzeichnung von Attention-Mustern
record_attentions: bool = False,
) -> Dict[str, Any]:
"""
Eine verallgemeinerte Version, die nun auch die Aufzeichnung von Attention-Mustern
und die Berechnung der Entropie unterstützt.
"""
prompt = RESONANCE_PROMPTS[prompt_type]
inputs = llm.tokenizer(prompt, return_tensors="pt").to(llm.model.device)
# Erster Forward-Pass, um den initialen Zustand zu erhalten
outputs = llm.model(**inputs, output_hidden_states=True, use_cache=True, output_attentions=record_attentions)
hidden_state_2d = outputs.hidden_states[-1][:, -1, :]
kv_cache = outputs.past_key_values
state_deltas: List[float] = []
state_history: List[torch.Tensor] = []
attention_entropies: List[float] = []
if record_attentions and outputs.attentions:
attention_entropies.append(_calculate_attention_entropy(outputs.attentions))
for i in tqdm(range(num_steps), desc=f"Cognitive Loop ({prompt_type})", leave=False, bar_format="{l_bar}{bar:10}{r_bar}"):
if i == patch_step and patch_state_source is not None:
dbg(f"--- Applying Causal Surgery at step {i}: Patching state. ---")
hidden_state_2d = patch_state_source.clone().to(device=llm.model.device, dtype=llm.model.dtype)
if reset_kv_cache_on_patch:
dbg("--- KV-Cache has been RESET as part of the intervention. ---")
kv_cache = None
if record_states:
state_history.append(hidden_state_2d.cpu())
next_token_logits = llm.model.lm_head(hidden_state_2d)
temp_to_use = temperature if temperature > 0.0 else 1.0
probabilities = torch.nn.functional.softmax(next_token_logits / temp_to_use, dim=-1)
if temperature > 0.0:
next_token_id = torch.multinomial(probabilities, num_samples=1)
else:
next_token_id = torch.argmax(probabilities, dim=-1).unsqueeze(-1)
hook_handle = None # Hook-Logik unverändert
try:
# (Hook-Aktivierung unverändert)
outputs = llm.model(
input_ids=next_token_id, past_key_values=kv_cache,
output_hidden_states=True, use_cache=True,
# Übergebe den Parameter an jeden Forward-Pass
output_attentions=record_attentions
)
finally:
if hook_handle:
hook_handle.remove()
hook_handle = None
new_hidden_state = outputs.hidden_states[-1][:, -1, :]
kv_cache = outputs.past_key_values
if record_attentions and outputs.attentions:
attention_entropies.append(_calculate_attention_entropy(outputs.attentions))
delta = torch.norm(new_hidden_state - hidden_state_2d).item()
state_deltas.append(delta)
hidden_state_2d = new_hidden_state.clone()
dbg(f"Cognitive loop finished after {num_steps} steps.")
return {
"state_deltas": state_deltas,
"state_history": state_history,
"attention_entropies": attention_entropies, # Das neue Messergebnis
"final_hidden_state": hidden_state_2d,
"final_kv_cache": kv_cache,
}
def run_silent_cogitation_seismic(*args, **kwargs) -> List[float]:
"""Abwärtskompatibler Wrapper."""
results = run_cogitation_loop(*args, **kwargs)
return results["state_deltas"]
[File Ends] cognitive_mapping_probe/resonance_seismograph.py
[File Begins] cognitive_mapping_probe/utils.py
import os
import sys
# --- Centralized Debugging Control ---
# To enable, set the environment variable: `export CMP_DEBUG=1`
DEBUG_ENABLED = os.environ.get("CMP_DEBUG", "0") == "1"
def dbg(*args, **kwargs):
"""
A controlled debug print function. Only prints if DEBUG_ENABLED is True.
Ensures that debug output does not clutter production runs or HF Spaces logs
unless explicitly requested. Flushes output to ensure it appears in order.
"""
if DEBUG_ENABLED:
print("[DEBUG]", *args, **kwargs, file=sys.stderr, flush=True)
[File Ends] cognitive_mapping_probe/utils.py
[File Begins] run_test.sh
#!/bin/bash
# Dieses Skript führt die Pytest-Suite mit aktivierten Debug-Meldungen aus.
# Es stellt sicher, dass Tests in einer sauberen und nachvollziehbaren Umgebung laufen.
# Führen Sie es vom Hauptverzeichnis des Projekts aus: ./run_tests.sh
echo "========================================="
echo "🔬 Running Cognitive Seismograph Test Suite"
echo "========================================="
# Aktiviere das Debug-Logging für unsere Applikation
export CMP_DEBUG=1
# Führe Pytest aus
# -v: "verbose" für detaillierte Ausgabe pro Test
# --color=yes: Erzwingt farbige Ausgabe für bessere Lesbarkeit
#python -m pytest -v --color=yes tests/
../venv-gemma-qualia/bin/python -m pytest -v --color=yes tests/
# Überprüfe den Exit-Code von pytest
if [ $? -eq 0 ]; then
echo "========================================="
echo "✅ All tests passed successfully!"
echo "========================================="
else
echo "========================================="
echo "❌ Some tests failed. Please review the output."
echo "========================================="
fi
[File Ends] run_test.sh
[File Begins] tests/conftest.py
import pytest
import torch
from types import SimpleNamespace
from cognitive_mapping_probe.llm_iface import LLM, StableLLMConfig
@pytest.fixture(scope="session")
def mock_llm_config():
"""Stellt eine minimale, Schein-Konfiguration für das LLM bereit."""
return SimpleNamespace(
hidden_size=128,
num_hidden_layers=2,
num_attention_heads=4
)
@pytest.fixture
def mock_llm(mocker, mock_llm_config):
"""
Erstellt einen robusten "Mock-LLM" für Unit-Tests.
FINAL KORRIGIERT: Simuliert nun die vollständige `StableLLMConfig`-Abstraktion.
"""
mock_tokenizer = mocker.MagicMock()
mock_tokenizer.eos_token_id = 1
mock_tokenizer.decode.return_value = "mocked text"
mock_embedding_layer = mocker.MagicMock()
mock_embedding_layer.weight.shape = (32000, mock_llm_config.hidden_size)
def mock_model_forward(*args, **kwargs):
batch_size = 1
seq_len = 1
if 'input_ids' in kwargs and kwargs['input_ids'] is not None:
seq_len = kwargs['input_ids'].shape[1]
elif 'past_key_values' in kwargs and kwargs['past_key_values'] is not None:
seq_len = kwargs['past_key_values'][0][0].shape[-2] + 1
mock_outputs = {
"hidden_states": tuple([torch.randn(batch_size, seq_len, mock_llm_config.hidden_size) for _ in range(mock_llm_config.num_hidden_layers + 1)]),
"past_key_values": tuple([(torch.randn(batch_size, mock_llm_config.num_attention_heads, seq_len, 16), torch.randn(batch_size, mock_llm_config.num_attention_heads, seq_len, 16)) for _ in range(mock_llm_config.num_hidden_layers)]),
"logits": torch.randn(batch_size, seq_len, 32000)
}
return SimpleNamespace(**mock_outputs)
llm_instance = LLM.__new__(LLM)
llm_instance.model = mocker.MagicMock(side_effect=mock_model_forward)
llm_instance.model.config = mock_llm_config
llm_instance.model.device = 'cpu'
llm_instance.model.dtype = torch.float32
llm_instance.model.get_input_embeddings.return_value = mock_embedding_layer
llm_instance.model.lm_head = mocker.MagicMock(return_value=torch.randn(1, 32000))
# FINALE KORREKTUR: Simuliere die Layer-Liste für den Hook-Test
mock_layer = mocker.MagicMock()
mock_layer.register_forward_pre_hook.return_value = mocker.MagicMock()
mock_layer_list = [mock_layer] * mock_llm_config.num_hidden_layers
# Simuliere die verschiedenen möglichen Architektur-Pfade
llm_instance.model.model = SimpleNamespace()
llm_instance.model.model.language_model = SimpleNamespace(layers=mock_layer_list)
llm_instance.tokenizer = mock_tokenizer
llm_instance.config = mock_llm_config
llm_instance.seed = 42
llm_instance.set_all_seeds = mocker.MagicMock()
# Erzeuge die stabile Konfiguration, die die Tests nun erwarten.
llm_instance.stable_config = StableLLMConfig(
hidden_dim=mock_llm_config.hidden_size,
num_layers=mock_llm_config.num_hidden_layers,
layer_list=mock_layer_list # Füge den Verweis auf die Mock-Layer-Liste hinzu
)
# Patch an allen Stellen, an denen das Modell tatsächlich geladen wird.
mocker.patch('cognitive_mapping_probe.llm_iface.get_or_load_model', return_value=llm_instance)
mocker.patch('cognitive_mapping_probe.orchestrator_seismograph.get_or_load_model', return_value=llm_instance)
mocker.patch('cognitive_mapping_probe.auto_experiment.get_or_load_model', return_value=llm_instance)
mocker.patch('cognitive_mapping_probe.orchestrator_seismograph.get_concept_vector', return_value=torch.randn(mock_llm_config.hidden_size))
return llm_instance
[File Ends] tests/conftest.py
[File Begins] tests/test_app_logic.py
import pandas as pd
import pytest
import gradio as gr
from pandas.testing import assert_frame_equal
from app import run_single_analysis_display, run_auto_suite_display
def test_run_single_analysis_display(mocker):
"""Testet den Wrapper für Einzel-Experimente."""
mock_results = {"verdict": "V", "stats": {"mean_delta": 1}, "state_deltas": [1.0, 2.0]}
mocker.patch('app.run_seismic_analysis', return_value=mock_results)
mocker.patch('app.cleanup_memory')
verdict, df, raw = run_single_analysis_display(progress=mocker.MagicMock())
assert "V" in verdict and "1.0000" in verdict
assert isinstance(df, pd.DataFrame) and len(df) == 2
assert "State Change (Delta)" in df.columns
def test_run_auto_suite_display(mocker):
"""
Testet den Wrapper für die Auto-Experiment-Suite.
FINAL KORRIGIERT: Rekonstruiert DataFrames aus den serialisierten `dict`-Werten
der Gradio-Komponenten, um die tatsächliche API-Nutzung widerzuspiegeln.
"""
mock_summary_df = pd.DataFrame([{"Experiment": "E1", "Mean Delta": 1.5}])
mock_plot_df = pd.DataFrame([{"Step": 0, "Delta": 1.0, "Experiment": "E1"}, {"Step": 1, "Delta": 2.0, "Experiment": "E1"}])
mock_results = {"E1": {"stats": {"mean_delta": 1.5}}}
mocker.patch('app.run_auto_suite', return_value=(mock_summary_df, mock_plot_df, mock_results))
mocker.patch('app.cleanup_memory')
dataframe_component, plot_component, raw_json_str = run_auto_suite_display(
"mock-model", 100, 42, "mock_exp", progress=mocker.MagicMock()
)
# KORREKTUR: Die `.value` Eigenschaft einer gr.DataFrame Komponente ist ein Dictionary.
# Wir müssen den pandas.DataFrame daraus rekonstruieren, um ihn zu vergleichen.
assert isinstance(dataframe_component, gr.DataFrame)
assert isinstance(dataframe_component.value, dict)
reconstructed_summary_df = pd.DataFrame(
data=dataframe_component.value['data'],
columns=dataframe_component.value['headers']
)
assert_frame_equal(reconstructed_summary_df, mock_summary_df)
# Dasselbe gilt für die LinePlot-Komponente
assert isinstance(plot_component, gr.LinePlot)
assert isinstance(plot_component.value, dict)
reconstructed_plot_df = pd.DataFrame(
data=plot_component.value['data'],
columns=plot_component.value['columns']
)
assert_frame_equal(reconstructed_plot_df, mock_plot_df)
# Der JSON-String bleibt ein String
assert isinstance(raw_json_str, str)
assert '"mean_delta": 1.5' in raw_json_str
[File Ends] tests/test_app_logic.py
[File Begins] tests/test_components.py
import os
import torch
import pytest
from unittest.mock import patch
from cognitive_mapping_probe.llm_iface import get_or_load_model, LLM
from cognitive_mapping_probe.resonance_seismograph import run_silent_cogitation_seismic
from cognitive_mapping_probe.utils import dbg
from cognitive_mapping_probe.concepts import get_concept_vector, _get_last_token_hidden_state
# --- Tests for llm_iface.py ---
@patch('cognitive_mapping_probe.llm_iface.AutoTokenizer.from_pretrained')
@patch('cognitive_mapping_probe.llm_iface.AutoModelForCausalLM.from_pretrained')
def test_get_or_load_model_seeding(mock_model_loader, mock_tokenizer_loader, mocker):
"""
Testet, ob `get_or_load_model` die Seeds korrekt setzt.
FINAL KORRIGIERT: Der lokale Mock ist nun vollständig konfiguriert.
"""
mock_model = mocker.MagicMock()
mock_model.eval.return_value = None
mock_model.set_attn_implementation.return_value = None
mock_model.device = 'cpu'
mock_model.get_input_embeddings.return_value.weight.shape = (32000, 128)
mock_model.config = mocker.MagicMock()
mock_model.config.num_hidden_layers = 2
mock_model.config.hidden_size = 128
# Simuliere die Architektur für die Layer-Extraktion
mock_model.model.language_model.layers = [mocker.MagicMock()] * 2
mock_model_loader.return_value = mock_model
mock_tokenizer_loader.return_value = mocker.MagicMock()
mock_torch_manual_seed = mocker.patch('torch.manual_seed')
mock_np_random_seed = mocker.patch('numpy.random.seed')
seed = 123
get_or_load_model("fake-model", seed=seed)
mock_torch_manual_seed.assert_called_with(seed)
mock_np_random_seed.assert_called_with(seed)
# --- Tests for resonance_seismograph.py ---
def test_run_silent_cogitation_seismic_output_shape_and_type(mock_llm):
"""Testet die grundlegende Funktionalität von `run_silent_cogitation_seismic`."""
num_steps = 10
state_deltas = run_silent_cogitation_seismic(
llm=mock_llm, prompt_type="control_long_prose",
num_steps=num_steps, temperature=0.7
)
assert isinstance(state_deltas, list) and len(state_deltas) == num_steps
assert all(isinstance(delta, float) for delta in state_deltas)
def test_run_silent_cogitation_with_injection_hook_usage(mock_llm):
"""
Testet, ob bei einer Injektion der Hook korrekt registriert wird.
FINAL KORRIGIERT: Greift auf die stabile Abstraktionsschicht zu.
"""
num_steps = 5
injection_vector = torch.randn(mock_llm.stable_config.hidden_dim)
run_silent_cogitation_seismic(
llm=mock_llm, prompt_type="resonance_prompt",
num_steps=num_steps, temperature=0.7,
injection_vector=injection_vector, injection_strength=1.0
)
# KORREKTUR: Der Test muss denselben Abstraktionspfad verwenden wie die Anwendung.
# Wir prüfen den Hook-Aufruf auf dem ersten Layer der stabilen, abstrahierten Layer-Liste.
assert mock_llm.stable_config.layer_list[0].register_forward_pre_hook.call_count == num_steps
# --- Tests for concepts.py ---
def test_get_last_token_hidden_state_robustness(mock_llm):
"""Testet die robuste `_get_last_token_hidden_state` Funktion."""
hs = _get_last_token_hidden_state(mock_llm, "test prompt")
assert hs.shape == (mock_llm.stable_config.hidden_dim,)
def test_get_concept_vector_logic(mock_llm, mocker):
"""
Testet die Logik von `get_concept_vector`.
"""
mock_hidden_states = [
torch.ones(mock_llm.stable_config.hidden_dim) * 10, # target concept
torch.ones(mock_llm.stable_config.hidden_dim) * 2, # baseline word 1
torch.ones(mock_llm.stable_config.hidden_dim) * 4 # baseline word 2
]
mocker.patch(
'cognitive_mapping_probe.concepts._get_last_token_hidden_state',
side_effect=mock_hidden_states
)
concept_vector = get_concept_vector(mock_llm, "test", baseline_words=["a", "b"])
# Erwarteter Vektor: 10 - mean(2, 4) = 10 - 3 = 7
expected_vector = torch.ones(mock_llm.stable_config.hidden_dim) * 7
assert torch.allclose(concept_vector, expected_vector)
# --- Tests for utils.py ---
def test_dbg_output(capsys, monkeypatch):
"""Testet die `dbg`-Funktion in beiden Zuständen."""
monkeypatch.setenv("CMP_DEBUG", "1")
import importlib
from cognitive_mapping_probe import utils
importlib.reload(utils)
utils.dbg("test message")
captured = capsys.readouterr()
assert "[DEBUG] test message" in captured.err
monkeypatch.delenv("CMP_DEBUG", raising=False)
importlib.reload(utils)
utils.dbg("should not be printed")
captured = capsys.readouterr()
assert captured.err == ""
[File Ends] tests/test_components.py
[File Begins] tests/test_orchestration.py
import pandas as pd
import pytest
import torch
from cognitive_mapping_probe.orchestrator_seismograph import run_seismic_analysis
from cognitive_mapping_probe.auto_experiment import run_auto_suite, get_curated_experiments
def test_run_seismic_analysis_no_injection(mocker, mock_llm):
"""Testet den Orchestrator im Baseline-Modus."""
mock_run_seismic = mocker.patch('cognitive_mapping_probe.orchestrator_seismograph.run_silent_cogitation_seismic', return_value=[1.0])
mock_get_concept = mocker.patch('cognitive_mapping_probe.orchestrator_seismograph.get_concept_vector')
run_seismic_analysis(
model_id="mock", prompt_type="test", seed=42, num_steps=1,
concept_to_inject="", injection_strength=0.0, progress_callback=mocker.MagicMock(),
llm_instance=mock_llm
)
mock_run_seismic.assert_called_once()
mock_get_concept.assert_not_called()
def test_run_seismic_analysis_with_injection(mocker, mock_llm):
"""Testet den Orchestrator mit Injektion."""
mock_run_seismic = mocker.patch('cognitive_mapping_probe.orchestrator_seismograph.run_silent_cogitation_seismic', return_value=[1.0])
mock_get_concept = mocker.patch(
'cognitive_mapping_probe.orchestrator_seismograph.get_concept_vector',
return_value=torch.randn(10)
)
run_seismic_analysis(
model_id="mock", prompt_type="test", seed=42, num_steps=1,
concept_to_inject="test_concept", injection_strength=1.5, progress_callback=mocker.MagicMock(),
llm_instance=mock_llm
)
mock_run_seismic.assert_called_once()
mock_get_concept.assert_called_once_with(mock_llm, "test_concept")
def test_get_curated_experiments_structure():
"""Testet die Datenstruktur der kuratierten Experimente."""
experiments = get_curated_experiments()
assert isinstance(experiments, dict)
assert "Sequential Intervention (Self-Analysis -> Deletion)" in experiments
protocol = experiments["Sequential Intervention (Self-Analysis -> Deletion)"]
assert isinstance(protocol, list) and len(protocol) == 2
def test_run_auto_suite_special_protocol(mocker, mock_llm):
"""
Testet den speziellen Logik-Pfad für das Interventions-Protokoll.
FINAL KORRIGIERT: Verwendet den korrekten, aktuellen Experiment-Namen.
"""
mock_analysis = mocker.patch('cognitive_mapping_probe.auto_experiment.run_seismic_analysis', return_value={"stats": {}, "state_deltas": []})
mocker.patch('cognitive_mapping_probe.auto_experiment.get_or_load_model', return_value=mock_llm)
# KORREKTUR: Verwende den neuen, korrekten Namen des Experiments, um
# den `if`-Zweig in `run_auto_suite` zu treffen.
correct_experiment_name = "Sequential Intervention (Self-Analysis -> Deletion)"
run_auto_suite(
model_id="mock-4b", num_steps=10, seed=42,
experiment_name=correct_experiment_name,
progress_callback=mocker.MagicMock()
)
# Die restlichen Assertions sind nun wieder gültig.
assert mock_analysis.call_count == 2
first_call_kwargs = mock_analysis.call_args_list[0].kwargs
second_call_kwargs = mock_analysis.call_args_list[1].kwargs
assert 'llm_instance' in first_call_kwargs
assert 'llm_instance' in second_call_kwargs
assert first_call_kwargs['llm_instance'] is mock_llm
assert second_call_kwargs['llm_instance'] is mock_llm
assert first_call_kwargs['concept_to_inject'] != ""
assert second_call_kwargs['concept_to_inject'] == ""
[File Ends] tests/test_orchestration.py
<-- File Content Ends
|