prizmkit 1.1.191 → 1.1.192

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (169) hide show
  1. package/bundled/VERSION.json +3 -3
  2. package/bundled/adapters/antigravity/skill-adapter.js +13 -4
  3. package/bundled/adapters/codex/skill-adapter.js +28 -8
  4. package/bundled/adapters/cursor/skill-adapter.js +13 -4
  5. package/bundled/adapters/pi/skill-adapter.js +28 -7
  6. package/bundled/dev-pipeline/.env.example +4 -12
  7. package/bundled/dev-pipeline/README.md +5 -10
  8. package/bundled/dev-pipeline/assets/skill-subagent-integration.md +3 -6
  9. package/bundled/dev-pipeline/prizmkit_runtime/atomic_io.py +48 -0
  10. package/bundled/dev-pipeline/prizmkit_runtime/checkpoint_state.py +66 -23
  11. package/bundled/dev-pipeline/prizmkit_runtime/cli.py +10 -7
  12. package/bundled/dev-pipeline/prizmkit_runtime/commands.py +2 -21
  13. package/bundled/dev-pipeline/prizmkit_runtime/config.py +24 -76
  14. package/bundled/dev-pipeline/prizmkit_runtime/daemon.py +125 -67
  15. package/bundled/dev-pipeline/prizmkit_runtime/gitops.py +77 -430
  16. package/bundled/dev-pipeline/prizmkit_runtime/heartbeat.py +93 -49
  17. package/bundled/dev-pipeline/prizmkit_runtime/interoperability.py +1 -3
  18. package/bundled/dev-pipeline/prizmkit_runtime/paths.py +0 -6
  19. package/bundled/dev-pipeline/prizmkit_runtime/platform_detection.py +36 -14
  20. package/bundled/dev-pipeline/prizmkit_runtime/processes.py +206 -151
  21. package/bundled/dev-pipeline/prizmkit_runtime/reset.py +2 -23
  22. package/bundled/dev-pipeline/prizmkit_runtime/reset_preserve.py +15 -134
  23. package/bundled/dev-pipeline/prizmkit_runtime/results.py +25 -0
  24. package/bundled/dev-pipeline/prizmkit_runtime/runner_bookkeeping.py +68 -83
  25. package/bundled/dev-pipeline/prizmkit_runtime/runner_classification.py +15 -5
  26. package/bundled/dev-pipeline/prizmkit_runtime/runner_models.py +1 -29
  27. package/bundled/dev-pipeline/prizmkit_runtime/runner_prompts.py +0 -2
  28. package/bundled/dev-pipeline/prizmkit_runtime/runner_status.py +7 -2
  29. package/bundled/dev-pipeline/prizmkit_runtime/runners.py +276 -217
  30. package/bundled/dev-pipeline/prizmkit_runtime/runtime_commit.py +124 -122
  31. package/bundled/dev-pipeline/prizmkit_runtime/runtime_helper.py +90 -9
  32. package/bundled/dev-pipeline/prizmkit_runtime/sessions.py +183 -130
  33. package/bundled/dev-pipeline/prizmkit_runtime/status.py +1 -3
  34. package/bundled/dev-pipeline/prizmkit_runtime/stream_progress.py +2780 -0
  35. package/bundled/dev-pipeline/prizmkit_runtime/task_checkout.py +27 -101
  36. package/bundled/dev-pipeline/prizmkit_runtime/test_result.py +58 -4
  37. package/bundled/dev-pipeline/scripts/check-session-status.py +43 -19
  38. package/bundled/dev-pipeline/scripts/continuation.py +6 -4
  39. package/bundled/dev-pipeline/scripts/detect-stuck.py +28 -28
  40. package/bundled/dev-pipeline/scripts/generate-bootstrap-prompt.py +7 -2
  41. package/bundled/dev-pipeline/scripts/generate-bugfix-prompt.py +7 -2
  42. package/bundled/dev-pipeline/scripts/init-bugfix-pipeline.py +10 -7
  43. package/bundled/dev-pipeline/scripts/init-change-artifact.py +8 -2
  44. package/bundled/dev-pipeline/scripts/init-pipeline.py +14 -69
  45. package/bundled/dev-pipeline/scripts/parse-stream-progress.py +31 -2616
  46. package/bundled/dev-pipeline/scripts/patch-completion-notes.py +4 -24
  47. package/bundled/dev-pipeline/scripts/prompt_framework.py +56 -9
  48. package/bundled/dev-pipeline/scripts/status_common.py +591 -0
  49. package/bundled/dev-pipeline/scripts/update-bug-status.py +85 -463
  50. package/bundled/dev-pipeline/scripts/update-checkpoint.py +227 -65
  51. package/bundled/dev-pipeline/scripts/update-feature-status.py +76 -509
  52. package/bundled/dev-pipeline/scripts/utils.py +5 -12
  53. package/bundled/dev-pipeline/templates/bootstrap-tier3.md +4 -4
  54. package/bundled/dev-pipeline/templates/bug-fix-list-schema.json +7 -0
  55. package/bundled/dev-pipeline/templates/bugfix-bootstrap-prompt.md +1 -1
  56. package/bundled/dev-pipeline/templates/sections/artifact-manifest.md +1 -1
  57. package/bundled/dev-pipeline/templates/sections/bugfix-phase-manual-verification.md +1 -1
  58. package/bundled/dev-pipeline/templates/sections/bugfix-phase-review.md +1 -1
  59. package/bundled/dev-pipeline/templates/sections/bugfix-phase-test.md +2 -1
  60. package/bundled/dev-pipeline/templates/sections/checkpoint-system.md +1 -1
  61. package/bundled/dev-pipeline/templates/sections/phase-browser-verification-auto.md +1 -1
  62. package/bundled/dev-pipeline/templates/sections/phase-browser-verification-opencli.md +2 -2
  63. package/bundled/dev-pipeline/templates/sections/phase-browser-verification.md +2 -2
  64. package/bundled/dev-pipeline/templates/sections/phase-prizmkit-test.md +2 -1
  65. package/bundled/dev-pipeline/templates/sections/phase-review-full.md +1 -1
  66. package/bundled/dev-pipeline/templates/sections/phase-specify-plan-full.md +3 -6
  67. package/bundled/dev-pipeline/templates/session-status-schema.json +2 -5
  68. package/bundled/dev-pipeline/tests/_helpers.py +418 -0
  69. package/bundled/dev-pipeline/tests/conftest.py +45 -1
  70. package/bundled/dev-pipeline/tests/test_auto_skip.py +4 -69
  71. package/bundled/dev-pipeline/tests/test_checkpoint_state.py +126 -1
  72. package/bundled/dev-pipeline/tests/test_daemon_and_scripts.py +257 -0
  73. package/bundled/dev-pipeline/tests/test_e2e_pipeline_run.py +500 -0
  74. package/bundled/dev-pipeline/tests/test_generate_bootstrap_prompt.py +59 -117
  75. package/bundled/dev-pipeline/tests/test_generate_bugfix_prompt.py +12 -10
  76. package/bundled/dev-pipeline/tests/test_python_runner_parity.py +431 -3099
  77. package/bundled/dev-pipeline/tests/test_recovery_workflow.py +7 -8
  78. package/bundled/dev-pipeline/tests/test_repository_bootstrap.py +0 -1
  79. package/bundled/dev-pipeline/tests/test_reset_modes.py +15 -27
  80. package/bundled/dev-pipeline/tests/test_reset_preserve.py +54 -139
  81. package/bundled/dev-pipeline/tests/test_runner_bookkeeping.py +766 -0
  82. package/bundled/dev-pipeline/tests/test_runner_lifecycle.py +1257 -0
  83. package/bundled/dev-pipeline/tests/test_runtime_helper.py +97 -20
  84. package/bundled/dev-pipeline/tests/test_session_launch.py +1101 -0
  85. package/bundled/dev-pipeline/tests/test_stream_progress.py +585 -0
  86. package/bundled/dev-pipeline/tests/test_unified_cli.py +155 -2034
  87. package/bundled/dev-pipeline/tests/test_utils.py +3 -3
  88. package/bundled/skills/_metadata.json +9 -63
  89. package/bundled/skills/app-planner/SKILL.md +32 -303
  90. package/bundled/skills/app-planner/references/app-design-guide.md +0 -4
  91. package/bundled/skills/app-planner/references/generated-plan-review.md +2 -1
  92. package/bundled/skills/app-planner/references/project-brief-guide.md +14 -0
  93. package/bundled/skills/app-planner/references/project-conventions-discovery.md +4 -6
  94. package/bundled/skills/app-planner/references/project-state-detection.md +2 -3
  95. package/bundled/skills/bug-fix-workflow/SKILL.md +1 -2
  96. package/bundled/skills/bug-fix-workflow/references/bug-diagnosis.md +4 -7
  97. package/bundled/skills/bug-planner/SKILL.md +54 -435
  98. package/bundled/skills/bug-planner/references/generated-plan-review.md +3 -2
  99. package/bundled/skills/bug-planner/references/input-formats.md +32 -0
  100. package/bundled/skills/bugfix-pipeline-launcher/SKILL.md +4 -6
  101. package/bundled/skills/bugfix-pipeline-launcher/references/configuration.md +4 -28
  102. package/bundled/skills/feature-pipeline-launcher/SKILL.md +4 -6
  103. package/bundled/skills/feature-pipeline-launcher/references/configuration.md +4 -28
  104. package/bundled/skills/feature-planner/SKILL.md +60 -439
  105. package/bundled/skills/feature-planner/assets/planning-guide.md +1 -1
  106. package/bundled/skills/feature-planner/references/completeness-review.md +34 -0
  107. package/bundled/skills/feature-planner/references/decomposition-patterns.md +2 -2
  108. package/bundled/skills/feature-planner/references/error-recovery.md +1 -1
  109. package/bundled/skills/feature-planner/references/generated-plan-review.md +3 -2
  110. package/bundled/skills/feature-planner/references/incremental-feature-planning.md +3 -1
  111. package/bundled/skills/feature-workflow/SKILL.md +1 -2
  112. package/bundled/skills/prizmkit/SKILL.md +7 -1
  113. package/bundled/skills/prizmkit-code-review/SKILL.md +14 -6
  114. package/bundled/skills/prizmkit-code-review/references/independent-code-review.md +7 -4
  115. package/bundled/skills/prizmkit-code-review/references/review-report-template.md +16 -0
  116. package/bundled/skills/prizmkit-code-review/scripts/render_review_report.py +58 -20
  117. package/bundled/skills/prizmkit-implement/SKILL.md +1 -1
  118. package/bundled/skills/prizmkit-init/SKILL.md +24 -127
  119. package/bundled/skills/prizmkit-init/assets/project-brief-template.md +3 -3
  120. package/bundled/skills/prizmkit-plan/SKILL.md +6 -8
  121. package/bundled/skills/prizmkit-plan/references/clarify-guide.md +1 -1
  122. package/bundled/skills/prizmkit-plan/references/independent-plan-review.md +5 -2
  123. package/bundled/skills/prizmkit-plan/references/review-plan-spec-loop.md +6 -5
  124. package/bundled/skills/prizmkit-prizm-docs/SKILL.md +1 -13
  125. package/bundled/skills/prizmkit-prizm-docs/references/op-update.md +1 -1
  126. package/bundled/skills/prizmkit-retrospective/SKILL.md +6 -4
  127. package/bundled/skills/prizmkit-test/SKILL.md +25 -133
  128. package/bundled/skills/prizmkit-test/references/independent-test-review.md +5 -2
  129. package/bundled/skills/prizmkit-test/references/test-coverage-model.md +6 -0
  130. package/bundled/skills/prizmkit-workflow/SKILL.md +2 -3
  131. package/bundled/skills/prizmkit-workflow/references/workflow-state-protocol.md +4 -3
  132. package/bundled/skills/recovery-workflow/SKILL.md +7 -7
  133. package/bundled/skills/recovery-workflow/evals/evals.json +1 -1
  134. package/bundled/skills/recovery-workflow/references/detection.md +1 -3
  135. package/bundled/skills/recovery-workflow/scripts/detect-recovery-state.py +0 -6
  136. package/bundled/templates/project-memory-template.md +1 -2
  137. package/package.json +1 -1
  138. package/src/scaffold.js +28 -7
  139. package/bundled/dev-pipeline/SCHEMA_ANALYSIS.md +0 -53
  140. package/bundled/dev-pipeline/scripts/generate-refactor-prompt.py +0 -649
  141. package/bundled/dev-pipeline/scripts/init-refactor-pipeline.py +0 -463
  142. package/bundled/dev-pipeline/scripts/update-refactor-status.py +0 -1512
  143. package/bundled/dev-pipeline/templates/refactor-bootstrap-prompt.md +0 -240
  144. package/bundled/dev-pipeline/templates/refactor-list-schema.json +0 -266
  145. package/bundled/dev-pipeline/templates/sections/refactor-critical-paths.md +0 -15
  146. package/bundled/dev-pipeline/templates/sections/refactor-mission.md +0 -9
  147. package/bundled/dev-pipeline/templates/sections/refactor-phase-commit-report.md +0 -24
  148. package/bundled/dev-pipeline/templates/sections/refactor-phase-implement.md +0 -16
  149. package/bundled/dev-pipeline/templates/sections/refactor-phase-init.md +0 -9
  150. package/bundled/dev-pipeline/templates/sections/refactor-phase-plan.md +0 -22
  151. package/bundled/dev-pipeline/templates/sections/refactor-phase-review.md +0 -19
  152. package/bundled/dev-pipeline/templates/sections/refactor-phase-test.md +0 -24
  153. package/bundled/dev-pipeline/templates/sections/refactor-reminders.md +0 -12
  154. package/bundled/dev-pipeline/templates/sections/refactor-session-context.md +0 -6
  155. package/bundled/dev-pipeline/templates/sections/refactor-task-contract.md +0 -52
  156. package/bundled/dev-pipeline/tests/test_generate_refactor_prompt.py +0 -478
  157. package/bundled/skills/feature-planner/assets/evaluation-guide.md +0 -44
  158. package/bundled/skills/refactor-pipeline-launcher/SKILL.md +0 -219
  159. package/bundled/skills/refactor-pipeline-launcher/references/configuration.md +0 -78
  160. package/bundled/skills/refactor-planner/SKILL.md +0 -467
  161. package/bundled/skills/refactor-planner/assets/planning-guide.md +0 -291
  162. package/bundled/skills/refactor-planner/references/behavior-preservation.md +0 -187
  163. package/bundled/skills/refactor-planner/references/error-recovery.md +0 -45
  164. package/bundled/skills/refactor-planner/references/fast-path.md +0 -59
  165. package/bundled/skills/refactor-planner/references/generated-plan-review.md +0 -107
  166. package/bundled/skills/refactor-planner/references/planning-phases.md +0 -172
  167. package/bundled/skills/refactor-planner/references/refactor-scoping-guide.md +0 -230
  168. package/bundled/skills/refactor-planner/scripts/validate-and-generate-refactor.py +0 -1120
  169. package/bundled/skills/refactor-workflow/SKILL.md +0 -205
@@ -0,0 +1,585 @@
1
+ """Focused tests for stream-json and progress parsing helpers."""
2
+
3
+ from __future__ import annotations
4
+
5
+ import json
6
+ import sys
7
+
8
+ import pytest
9
+
10
+ from _helpers import PIPELINE_ROOT, load_progress_parser_module as _load_progress_parser_module
11
+
12
+ sys.path.insert(0, str(PIPELINE_ROOT))
13
+
14
+
15
+ def test_progress_parser_adds_required_metadata(tmp_path):
16
+ import importlib.util
17
+
18
+ parser_path = PIPELINE_ROOT / "scripts" / "parse-stream-progress.py"
19
+ spec = importlib.util.spec_from_file_location("parse_stream_progress", parser_path)
20
+ module = importlib.util.module_from_spec(spec)
21
+ assert spec.loader is not None
22
+ spec.loader.exec_module(module)
23
+
24
+ tracker = module.ProgressTracker()
25
+ tracker.process_event({"type": "system", "subtype": "init", "session_id": "claude-session", "cwd": str(tmp_path)})
26
+ tracker.process_event({"type": "assistant", "message": {"content": [{"type": "text", "text": "working"}]}})
27
+ tracker.process_event({"type": "result", "subtype": "success", "stop_reason": "end_turn", "usage": {"input_tokens": 1}, "result": "done"})
28
+ tracker.process_event({"type": "error", "error": {"message": "permission denied by user"}})
29
+ data = tracker.to_dict()
30
+
31
+ assert data["event_type_counts"]["system"] == 1
32
+ assert data["event_type_counts"]["assistant"] == 1
33
+ assert data["claude_session_id"] == "claude-session"
34
+ assert data["result_subtype"] == "success"
35
+ assert data["stop_reason"] == "end_turn"
36
+ assert data["has_usage"] is True
37
+ assert data["permission_denial_count"] == 1
38
+
39
+
40
+
41
+ def test_progress_parser_normalizes_pi_json_events():
42
+ module = _load_progress_parser_module()
43
+ tracker = module.ProgressTracker()
44
+ tracker.process_event({"type": "session", "version": 3, "id": "pi-session", "cwd": "/tmp/project"})
45
+ tracker.process_event({"type": "agent_start"})
46
+ tracker.process_event({"type": "turn_start"})
47
+ tracker.process_event({
48
+ "type": "message_update",
49
+ "assistantMessageEvent": {"type": "text_delta", "delta": "Running prizmkit-implement"},
50
+ })
51
+ tracker.process_event({"type": "tool_execution_start", "toolName": "edit", "args": {"path": "src/a.js"}})
52
+ tracker.process_event({"type": "tool_execution_end", "toolName": "edit", "result": {"ok": True}, "isError": False})
53
+ tracker.process_event({"type": "compaction_start", "reason": "threshold"})
54
+ tracker.process_event({"type": "compaction_end", "reason": "threshold", "aborted": False, "willRetry": False})
55
+ tracker.process_event({"type": "agent_end", "messages": []})
56
+ data = tracker.to_dict()
57
+ assert data["event_format"] == "pi-json"
58
+ assert data["message_count"] == 1
59
+ assert data["total_tool_calls"] == 1
60
+ assert {item["name"]: item["count"] for item in data["tool_calls"]}["edit"] == 1
61
+ assert data["current_phase"] == "implement"
62
+ assert data["is_active"] is False
63
+ assert data["result_subtype"] == "success"
64
+ assert data["terminal_success_at"]
65
+
66
+
67
+ def test_progress_parser_does_not_mark_failed_pi_agent_end_as_success():
68
+ module = _load_progress_parser_module()
69
+ tracker = module.ProgressTracker()
70
+ tracker.process_event({"type": "session", "version": 3, "id": "pi-session", "cwd": "/tmp/project"})
71
+ tracker.process_event({"type": "agent_start"})
72
+ tracker.process_event({
73
+ "type": "message_end",
74
+ "message": {
75
+ "role": "assistant",
76
+ "content": [],
77
+ "stopReason": "error",
78
+ "errorMessage": "provider request failed",
79
+ },
80
+ })
81
+ tracker.process_event({"type": "agent_end", "messages": []})
82
+
83
+ data = tracker.to_dict()
84
+
85
+ assert data["event_format"] == "pi-json"
86
+ assert data["is_active"] is False
87
+ assert data["result_subtype"] == "error"
88
+ assert data["stop_reason"] == "error"
89
+ assert data["last_result_is_error"] is True
90
+ assert data["terminal_success_at"] == ""
91
+ assert "provider request failed" in data["errors"]
92
+
93
+
94
+ def test_progress_parser_keeps_pi_length_as_nonfatal_diagnostic_metadata():
95
+ module = _load_progress_parser_module()
96
+ tracker = module.ProgressTracker()
97
+ tracker.process_event({"type": "session", "version": 3, "id": "pi-session", "cwd": "/tmp/project"})
98
+ tracker.process_event({"type": "agent_start"})
99
+ message = {
100
+ "role": "assistant",
101
+ "content": [{"type": "thinking", "thinking": "Planning the next test"}],
102
+ "stopReason": "length",
103
+ }
104
+ tracker.process_event({"type": "message_end", "message": message})
105
+ tracker.process_event({"type": "agent_end", "willRetry": False, "messages": [message]})
106
+
107
+ data = tracker.to_dict()
108
+
109
+ assert data["result_subtype"] == "success"
110
+ assert data["stop_reason"] == "length"
111
+ assert data["last_result_is_error"] is False
112
+ assert data["api_error_code"] == ""
113
+ assert data["fatal_error_code"] == ""
114
+ assert data["terminal_success_at"]
115
+
116
+
117
+ @pytest.mark.parametrize("role", ("assistant", "toolResult"))
118
+ def test_progress_parser_does_not_promote_pi_diagnostic_content_to_fatal_error(role):
119
+ module = _load_progress_parser_module()
120
+ tracker = module.ProgressTracker()
121
+ tracker.process_event({"type": "session", "version": 3, "id": "pi-session", "cwd": "/tmp/project"})
122
+ tracker.process_event({"type": "agent_start"})
123
+ tracker.process_event({
124
+ "type": "message_end",
125
+ "message": {
126
+ "role": role,
127
+ "content": [{
128
+ "type": "text",
129
+ "text": 'continuation_reason = "context_overflow"\nerror = _error_text(result)',
130
+ }],
131
+ "stopReason": "toolUse",
132
+ },
133
+ })
134
+
135
+ data = tracker.to_dict()
136
+
137
+ assert data["api_error_code"] == ""
138
+ assert data["fatal_error_code"] == ""
139
+ assert data["last_result_is_error"] is False
140
+
141
+
142
+ def test_progress_parser_recovers_from_retrying_pi_attempt_before_final_success():
143
+ module = _load_progress_parser_module()
144
+ tracker = module.ProgressTracker()
145
+ tracker.process_event({"type": "session", "version": 3, "id": "pi-session", "cwd": "/tmp/project"})
146
+ tracker.process_event({"type": "agent_start"})
147
+ tracker.process_event({
148
+ "type": "message_end",
149
+ "message": {
150
+ "role": "assistant",
151
+ "content": [],
152
+ "stopReason": "error",
153
+ "errorMessage": "Error Code internal_server_error: unexpected EOF",
154
+ },
155
+ })
156
+ tracker.process_event({"type": "agent_end", "willRetry": True, "messages": []})
157
+ tracker.process_event({
158
+ "type": "auto_retry_start",
159
+ "attempt": 1,
160
+ "delayMs": 2000,
161
+ "errorMessage": "Error Code internal_server_error: unexpected EOF",
162
+ })
163
+ tracker.process_event({"type": "agent_start"})
164
+ tracker.process_event({"type": "auto_retry_end", "attempt": 1})
165
+ tracker.process_event({
166
+ "type": "message_end",
167
+ "message": {
168
+ "role": "assistant",
169
+ "content": [{"type": "text", "text": "WORKFLOW_COMPLETED"}],
170
+ "stopReason": "stop",
171
+ },
172
+ })
173
+ tracker.process_event({
174
+ "type": "agent_end",
175
+ "willRetry": False,
176
+ "messages": [{
177
+ "role": "assistant",
178
+ "content": [{"type": "text", "text": "WORKFLOW_COMPLETED"}],
179
+ "stopReason": "stop",
180
+ }],
181
+ })
182
+
183
+ data = tracker.to_dict()
184
+
185
+ assert data["result_subtype"] == "success"
186
+ assert data["last_result_is_error"] is False
187
+ assert data["stop_reason"] == "stop"
188
+ assert data["fatal_error_code"] == ""
189
+ assert data["terminal_success_at"]
190
+ assert any("unexpected EOF" in str(error) for error in data["errors"])
191
+
192
+
193
+ def test_progress_parser_keeps_final_error_after_internal_retry_exhausts():
194
+ module = _load_progress_parser_module()
195
+ tracker = module.ProgressTracker()
196
+ tracker.process_event({"type": "session", "id": "pi-session"})
197
+ tracker.process_event({"type": "agent_start"})
198
+ tracker.process_event({
199
+ "type": "message_end",
200
+ "message": {"role": "assistant", "content": [], "stopReason": "error", "errorMessage": "temporary error"},
201
+ })
202
+ tracker.process_event({"type": "agent_end", "willRetry": True, "messages": []})
203
+ tracker.process_event({"type": "auto_retry_start", "attempt": 1, "errorMessage": "temporary error"})
204
+ tracker.process_event({"type": "agent_start"})
205
+ tracker.process_event({
206
+ "type": "message_end",
207
+ "message": {"role": "assistant", "content": [], "stopReason": "error", "errorMessage": "final error"},
208
+ })
209
+ tracker.process_event({
210
+ "type": "agent_end",
211
+ "willRetry": False,
212
+ "messages": [{"role": "assistant", "content": [], "stopReason": "error", "errorMessage": "final error"}],
213
+ })
214
+
215
+ data = tracker.to_dict()
216
+
217
+ assert data["result_subtype"] == "error"
218
+ assert data["last_result_is_error"] is True
219
+ assert data["stop_reason"] == "error"
220
+ assert data["terminal_success_at"] == ""
221
+ assert "final error" in data["terminal_result_text"]
222
+
223
+
224
+ def test_progress_parser_clears_retrying_fatal_marker_on_new_pi_attempt():
225
+ module = _load_progress_parser_module()
226
+ tracker = module.ProgressTracker()
227
+ tracker.process_event({"type": "session", "id": "pi-session"})
228
+ tracker.process_event({"type": "agent_start"})
229
+ tracker.process_event({
230
+ "type": "message_end",
231
+ "message": {
232
+ "role": "assistant",
233
+ "content": [],
234
+ "stopReason": "error",
235
+ "errorMessage": "API Error: Your input exceeds the context window",
236
+ },
237
+ })
238
+ tracker.process_event({"type": "agent_end", "willRetry": True, "messages": []})
239
+ failed_attempt = tracker.to_dict()
240
+
241
+ tracker.process_event({"type": "agent_start"})
242
+ next_attempt = tracker.to_dict()
243
+
244
+ assert failed_attempt["fatal_error_code"] == "context_overflow"
245
+ assert failed_attempt["last_result_is_error"] is True
246
+ assert next_attempt["fatal_error_code"] == ""
247
+ assert next_attempt["result_subtype"] == ""
248
+ assert next_attempt["last_result_is_error"] is False
249
+ assert any("context window" in str(error) for error in next_attempt["errors"])
250
+ assert next_attempt["is_active"] is True
251
+
252
+
253
+ def test_semantic_log_normalizer_compacts_pi_cumulative_stream():
254
+ module = _load_progress_parser_module()
255
+ normalizer = module.SemanticLogNormalizer()
256
+ events = [
257
+ {"type": "session", "id": "session-1"},
258
+ {"type": "message_start", "message": {"role": "user"}},
259
+ {"type": "message_end", "message": {"role": "user", "content": [{"type": "text", "text": "SECRET PROMPT"}]}},
260
+ {"type": "turn_start"},
261
+ {"type": "message_update", "assistantMessageEvent": {"type": "thinking_start", "contentIndex": 0}},
262
+ {"type": "message_update", "assistantMessageEvent": {"type": "thinking_delta", "contentIndex": 0, "delta": "Inspecting"}},
263
+ {"type": "message_update", "assistantMessageEvent": {"type": "thinking_delta", "contentIndex": 0, "delta": " state"}},
264
+ {"type": "message_update", "assistantMessageEvent": {"type": "thinking_end", "contentIndex": 0, "content": "Inspecting state"}},
265
+ {"type": "tool_execution_start", "toolCallId": "call-1", "toolName": "bash", "args": {"command": "printf ABC"}},
266
+ {"type": "tool_execution_update", "toolCallId": "call-1", "toolName": "bash", "partialResult": {"content": [{"type": "text", "text": "A"}]}},
267
+ {"type": "tool_execution_update", "toolCallId": "call-1", "toolName": "bash", "partialResult": {"content": [{"type": "text", "text": "AB"}]}},
268
+ {"type": "tool_execution_update", "toolCallId": "call-1", "toolName": "bash", "partialResult": {"content": [{"type": "text", "text": "ABC"}]}},
269
+ {"type": "tool_execution_end", "toolCallId": "call-1", "toolName": "bash", "result": {"content": [{"type": "text", "text": "ABC"}]}, "isError": False},
270
+ {"type": "message_start", "message": {"role": "toolResult"}},
271
+ {"type": "message_end", "message": {"role": "toolResult", "toolCallId": "call-1", "toolName": "bash", "content": [{"type": "text", "text": "ABC"}]}},
272
+ {"type": "message_update", "assistantMessageEvent": {"type": "text_start", "contentIndex": 1}},
273
+ {"type": "message_update", "assistantMessageEvent": {"type": "text_delta", "contentIndex": 1, "delta": "Done"}},
274
+ {"type": "message_update", "assistantMessageEvent": {"type": "text_end", "contentIndex": 1, "content": "Done"}},
275
+ {"type": "message_end", "message": {"role": "assistant", "content": [{"type": "text", "text": "Done"}], "stopReason": "stop"}},
276
+ {"type": "turn_end", "message": {"role": "assistant", "content": [{"type": "text", "text": "Done"}], "stopReason": "stop"}},
277
+ {"type": "agent_end", "willRetry": False, "messages": [{"role": "assistant", "content": [{"type": "text", "text": "Done"}], "stopReason": "stop"}]},
278
+ {"type": "agent_settled"},
279
+ ]
280
+
281
+ rendered = "".join(normalizer.process_event(event) for event in events) + normalizer.finish()
282
+
283
+ assert rendered.count("[THINK]") == 1
284
+ assert "[THINK] Inspecting state\n" in rendered
285
+ assert rendered.count("[ACTION]") == 1
286
+ assert "bash" in rendered and "printf ABC" in rendered
287
+ assert rendered.count("[OBSERVATION]") == 1
288
+ assert "[OBSERVATION] ABC\n" in rendered
289
+ assert rendered.count("[FINAL]") == 1
290
+ assert "[FINAL] Done\n" in rendered
291
+ assert rendered.count("[SESSION_END]") == 1
292
+ assert "message_update" not in rendered
293
+ assert "SECRET PROMPT" not in rendered
294
+
295
+
296
+ def test_semantic_log_normalizer_ignores_user_prompt_but_keeps_nested_tool_results():
297
+ module = _load_progress_parser_module()
298
+ normalizer = module.SemanticLogNormalizer()
299
+ rendered = normalizer.process_event({
300
+ "type": "user",
301
+ "message": {
302
+ "content": [
303
+ {"type": "text", "text": "SECRET PROMPT"},
304
+ {"type": "tool_result", "tool_use_id": "tool-1", "content": "tool output"},
305
+ ]
306
+ },
307
+ })
308
+ rendered += normalizer.finish()
309
+
310
+ assert "SECRET PROMPT" not in rendered
311
+ assert "[OBSERVATION] tool output" in rendered
312
+
313
+
314
+ def test_semantic_log_normalizer_preserves_repeated_plain_and_tool_output_records():
315
+ module = _load_progress_parser_module()
316
+ normalizer = module.SemanticLogNormalizer()
317
+ rendered = normalizer.process_text("same\n")
318
+ rendered += normalizer.process_text("same\n")
319
+ rendered += normalizer.process_event({"type": "function_call_result", "id": "one", "output": "same result"})
320
+ rendered += normalizer.process_event({"type": "function_call_result", "id": "two", "output": "same result"})
321
+ rendered += normalizer.finish()
322
+
323
+ assert rendered.count("[OUTPUT] same") == 2
324
+ assert rendered.count("[OBSERVATION] same result") == 2
325
+
326
+
327
+ def test_semantic_log_normalizer_emits_terminal_metadata_once():
328
+ module = _load_progress_parser_module()
329
+ normalizer = module.SemanticLogNormalizer()
330
+ rendered = normalizer.process_event({"type": "turn.completed"})
331
+ rendered += normalizer.process_event({"type": "result", "subtype": "success", "result": "Done"})
332
+ rendered += normalizer.finish()
333
+
334
+ assert rendered.count("[SESSION_END]") == 1
335
+ assert "[FINAL] Done" in rendered
336
+
337
+
338
+ def test_semantic_log_normalizer_does_not_promote_pi_length_to_context_overflow():
339
+ module = _load_progress_parser_module()
340
+ normalizer = module.SemanticLogNormalizer()
341
+ rendered = normalizer.process_event({
342
+ "type": "agent_end",
343
+ "willRetry": False,
344
+ "messages": [{"role": "assistant", "content": [], "stopReason": "length"}],
345
+ })
346
+ rendered += normalizer.finish()
347
+
348
+ assert rendered.count("[SESSION_END]") == 1
349
+ assert "status=success stop_reason=length" in rendered
350
+ assert "status=context_overflow" not in rendered
351
+
352
+
353
+ def test_semantic_log_normalizer_preserves_identical_text_from_distinct_turns():
354
+ module = _load_progress_parser_module()
355
+ normalizer = module.SemanticLogNormalizer()
356
+ events = [
357
+ {"type": "turn_start"},
358
+ {"type": "message_end", "message": {"role": "assistant", "content": [{"type": "text", "text": "Done"}], "stopReason": "stop"}},
359
+ {"type": "turn_start"},
360
+ {"type": "message_end", "message": {"role": "assistant", "content": [{"type": "text", "text": "Done"}], "stopReason": "stop"}},
361
+ ]
362
+
363
+ rendered = "".join(normalizer.process_event(event) for event in events) + normalizer.finish()
364
+
365
+ assert rendered.count("[FINAL] Done") == 2
366
+
367
+
368
+ def test_semantic_log_normalizer_size_tracks_unique_cumulative_content():
369
+ module = _load_progress_parser_module()
370
+ normalizer = module.SemanticLogNormalizer()
371
+ chunks = []
372
+ payload = ""
373
+ chunks.append(normalizer.process_event({"type": "tool_execution_start", "toolCallId": "call-1", "toolName": "read", "args": {"path": "sample"}}))
374
+ for index in range(1, 501):
375
+ payload += chr(64 + ((index - 1) % 26) + 1)
376
+ chunks.append(normalizer.process_event({
377
+ "type": "tool_execution_update",
378
+ "toolCallId": "call-1",
379
+ "toolName": "read",
380
+ "partialResult": {"content": [{"type": "text", "text": payload}]},
381
+ }))
382
+ assert sum(len(value) for value in normalizer._snapshots.values()) == len(payload)
383
+ assert not any(stream_id.startswith("tool:call-1:output") for stream_id in normalizer._stream_buffers)
384
+ chunks.append(normalizer.process_event({
385
+ "type": "tool_execution_end",
386
+ "toolCallId": "call-1",
387
+ "toolName": "read",
388
+ "result": {"content": [{"type": "text", "text": payload}]},
389
+ "isError": False,
390
+ }))
391
+ rendered = "".join(chunks) + normalizer.finish()
392
+
393
+ assert rendered.count(payload) == 1
394
+ assert len(rendered.encode("utf-8")) <= len(payload.encode("utf-8")) + 256
395
+
396
+
397
+ @pytest.mark.parametrize(
398
+ ("events", "expected_labels"),
399
+ [
400
+ (
401
+ [
402
+ {"type": "assistant", "message": {"content": [{"type": "text", "text": "Answer"}, {"type": "tool_use", "id": "tool-1", "name": "Read", "input": {"path": "a"}}]}},
403
+ {"type": "user", "message": {"content": [{"type": "tool_result", "tool_use_id": "tool-1", "content": "result"}]}},
404
+ {"type": "result", "subtype": "success", "stop_reason": "end_turn", "result": "Answer"},
405
+ ],
406
+ {"[FINAL]", "[ACTION]", "[OBSERVATION]", "[SESSION_END]"},
407
+ ),
408
+ (
409
+ [
410
+ {"type": "message", "sessionId": "cb-1", "role": "assistant", "content": [{"type": "text", "text": "Answer"}]},
411
+ {"type": "function_call", "sessionId": "cb-1", "id": "call-1", "name": "read", "arguments": "{\"path\":\"a\"}"},
412
+ {"type": "function_call_result", "sessionId": "cb-1", "id": "call-1", "output": "result"},
413
+ {"type": "result", "subtype": "success", "result": "Answer"},
414
+ ],
415
+ {"[FINAL]", "[ACTION]", "[OBSERVATION]", "[SESSION_END]"},
416
+ ),
417
+ (
418
+ [
419
+ {"type": "turn.started"},
420
+ {"type": "item.completed", "item": {"id": "reason-1", "type": "reasoning", "text": "Think"}},
421
+ {"type": "item.started", "item": {"id": "cmd-1", "type": "command_execution", "command": "printf result"}},
422
+ {"type": "item.completed", "item": {"id": "cmd-1", "type": "command_execution", "command": "printf result", "aggregated_output": "result", "status": "completed"}},
423
+ {"type": "item.completed", "item": {"id": "answer-1", "type": "agent_message", "text": "Answer"}},
424
+ {"type": "turn.completed", "usage": {"input_tokens": 1}},
425
+ ],
426
+ {"[THINK]", "[FINAL]", "[ACTION]", "[OBSERVATION]", "[SESSION_END]"},
427
+ ),
428
+ ],
429
+ )
430
+ def test_semantic_log_normalizer_has_cross_format_contract(events, expected_labels):
431
+ module = _load_progress_parser_module()
432
+ normalizer = module.SemanticLogNormalizer()
433
+
434
+ rendered = "".join(normalizer.process_event(event) for event in events) + normalizer.finish()
435
+
436
+ for label in expected_labels:
437
+ assert label in rendered
438
+ assert not any(json.dumps(event, ensure_ascii=False) in rendered for event in events)
439
+
440
+
441
+ def test_progress_parser_normalizes_claude_subagents_without_double_counting(tmp_path):
442
+ module = _load_progress_parser_module()
443
+ tracker = module.ProgressTracker()
444
+
445
+ tracker.process_event({"type": "system", "subtype": "init", "session_id": "claude-session", "cwd": str(tmp_path)})
446
+ tracker.process_event({
447
+ "type": "assistant",
448
+ "message": {"content": [{
449
+ "type": "tool_use",
450
+ "id": "tool-1",
451
+ "name": "Agent",
452
+ "input": {"description": "review code", "prompt": "check", "subagent_type": "reviewer"},
453
+ }]},
454
+ })
455
+ tracker.process_event({
456
+ "type": "system",
457
+ "subtype": "task_started",
458
+ "task_id": "task-1",
459
+ "tool_use_id": "tool-1",
460
+ "task_type": "in_process_teammate",
461
+ "subagent_type": "reviewer",
462
+ "description": "review code",
463
+ })
464
+ tracker.process_event({"type": "assistant", "parent_tool_use_id": "tool-1", "message": {"content": [{"type": "text", "text": "child activity"}]}})
465
+ tracker.process_event({"type": "system", "subtype": "task_started", "task_id": "bash-1", "task_type": "local_bash", "description": "ls"})
466
+ tracker.process_event({"type": "system", "subtype": "task_notification", "task_id": "task-1", "tool_use_id": "tool-1", "status": "completed", "summary": "done"})
467
+
468
+ data = tracker.to_dict()
469
+
470
+ statistics = data["subagent_statistics"]
471
+ assert statistics["source"] == "session_log"
472
+ assert statistics["spawned"] == 1
473
+ assert statistics["active"] == 0
474
+ assert statistics["states"] == [{"status": "completed", "count": 1}]
475
+ assert "task-1" in statistics["observed_ids"]
476
+ assert "tool-1" in statistics["parent_activity_ids"]
477
+ assert all("bash" not in record["id"] for record in data["subagent_statistics"]["records"])
478
+
479
+
480
+ def test_progress_parser_normalizes_codebuddy_agent_tools_with_deduplication():
481
+ module = _load_progress_parser_module()
482
+ tracker = module.ProgressTracker()
483
+ args = {"prompt": "inspect", "description": "inspect", "subagent_type": "Explore"}
484
+
485
+ tracker.process_event({
486
+ "type": "message",
487
+ "sessionId": "cb-session",
488
+ "cwd": "/tmp/project",
489
+ "role": "assistant",
490
+ "content": [{"type": "tool_use", "id": "call-1", "name": "Agent", "input": args}],
491
+ })
492
+ tracker.process_event({
493
+ "type": "function_call",
494
+ "sessionId": "cb-session",
495
+ "cwd": "/tmp/project",
496
+ "id": "call-1",
497
+ "name": "Agent",
498
+ "arguments": json.dumps(args),
499
+ })
500
+ tracker.process_event({
501
+ "type": "function_call",
502
+ "sessionId": "cb-session",
503
+ "cwd": "/tmp/project",
504
+ "id": "task-call",
505
+ "name": "TaskCreate",
506
+ "arguments": json.dumps({"description": "background", "subject": "status"}),
507
+ })
508
+
509
+ data = tracker.to_dict()
510
+
511
+ assert data["cb_session_id"] == "cb-session"
512
+ statistics = data["subagent_statistics"]
513
+ assert statistics["providers"] == ["codebuddy"]
514
+ assert statistics["spawned"] == 1
515
+ assert statistics["active"] == 1
516
+ assert {item["status"] for item in statistics["states"]} == {"running"}
517
+ assert len(statistics["records"]) == 1
518
+ assert data["subagent_statistics"]["records"][0]["metadata"]["tool"] == "Agent"
519
+
520
+
521
+ def test_progress_parser_normalizes_codex_collab_metadata_with_missing_fields():
522
+ module = _load_progress_parser_module()
523
+ tracker = module.ProgressTracker()
524
+
525
+ tracker.process_event({"type": "thread.started", "thread_id": "parent"})
526
+ tracker.process_event({
527
+ "type": "item.started",
528
+ "item": {
529
+ "type": "collab_tool_call",
530
+ "tool": "delegate",
531
+ "receiver_thread_ids": ["thread-a", "thread-b"],
532
+ "agents_states": {
533
+ "thread-a": {"status": "running", "message": "working"},
534
+ "thread-b": {"status": "completed", "message": "done"},
535
+ },
536
+ },
537
+ })
538
+ tracker.process_event({"type": "item.completed", "item": {"type": "collab_tool_call", "tool": "delegate"}})
539
+ tracker.process_event({"type": "turn.completed", "usage": {"input_tokens": 1}})
540
+
541
+ data = tracker.to_dict()
542
+
543
+ assert data["event_format"] == "codex-json"
544
+ assert data["result_subtype"] == "success"
545
+ assert data["stop_reason"] == "completed"
546
+ assert data["is_active"] is False
547
+ assert data["child_thread_ids"] == ["thread-a", "thread-b"]
548
+ statistics = data["subagent_statistics"]
549
+ assert statistics["spawned"] == 2
550
+ assert statistics["active"] == 1
551
+ assert {state["status"]: state["count"] for state in statistics["states"]} == {"running": 1, "completed": 1}
552
+ assert statistics["child_activity_source"] == "filesystem_liveness_only"
553
+
554
+
555
+ def test_progress_parser_keeps_child_files_liveness_only(tmp_path, monkeypatch):
556
+ module = _load_progress_parser_module()
557
+ claude_home = tmp_path / "claude"
558
+ project_key = str(tmp_path).replace("\\", "-").replace("/", "-").replace(":", "")
559
+ subagents_dir = claude_home / "projects" / project_key / "parent-session" / "subagents"
560
+ subagents_dir.mkdir(parents=True)
561
+ child_log = subagents_dir / "agent-child.jsonl"
562
+ child_log.write_text("child activity", encoding="utf-8")
563
+ monkeypatch.setenv("CLAUDE_HOME", str(claude_home))
564
+
565
+ tracker = module.ProgressTracker()
566
+ tracker.process_event({"type": "system", "subtype": "init", "session_id": "parent-session", "cwd": str(tmp_path)})
567
+ tracker.process_event({
568
+ "type": "system",
569
+ "subtype": "task_started",
570
+ "task_id": "task-1",
571
+ "tool_use_id": "tool-1",
572
+ "task_type": "in_process_teammate",
573
+ "description": "agent",
574
+ })
575
+ first = tracker.to_dict()
576
+ child_log.write_text("child activity grew", encoding="utf-8")
577
+ tracker.refresh_child_session_activity(force=True)
578
+ second = tracker.to_dict()
579
+
580
+ assert first["subagent_statistics"]["spawned"] == 1
581
+ assert second["subagent_statistics"]["spawned"] == 1
582
+ assert second["child_total_bytes"] > first["child_total_bytes"]
583
+ assert second["child_session_files"]
584
+ assert second["child_activity_source"] == "filesystem_liveness_only"
585
+ assert second["subagent_statistics"]["source"] == "session_log"