Dhanji R. Prasanna b89d55a9ff Add characterization tests for stream_completion_with_tools ...

Add 32 blackbox characterization tests to lock down the behavior of the
stream_completion_with_tools function (1067 lines) before refactoring.

Tests cover key behaviors through stable boundaries:
- StreamingToolParser: tool call detection, incomplete detection, text accumulation
- Auto-continue logic: autonomous mode decisions, priority ordering
- Duplicate detection: sequential duplicates, cross-message duplicates
- Context window: token tracking, compaction threshold, history preservation
- Tool execution: read_file, shell, write_file, todo tools through Agent
- Streaming utilities: LLM token cleaning, duration formatting, truncation
- Parser sanitization: inline tool pattern handling, homoglyph replacement

These tests intentionally do NOT assert:
- Internal parser state or implementation details
- Specific timing values
- UI output formatting
- Provider-specific behavior

Agent: hopper

2026-01-13 16:25:33 +05:30

..

auto_continue_test.rs

Remove final_output tool and improve scout report handback

2026-01-10 13:43:04 +11:00

background_process_demo_test.rs

Remove legacy logs/ directory, consolidate all data under .g3/

2026-01-12 18:20:08 +05:30

code_search_test.rs

add context window monitor

2025-11-27 21:00:02 +11:00

compaction_behavior_test.rs

Add 72 integration tests for compaction, retry, tool execution, and error classification

2026-01-12 11:40:19 +05:30

duplicate_detection_test.rs

Fix panic on multi-byte chars in filter_json buffer truncation

2026-01-09 15:20:57 +11:00

end_of_turn_behavior_test.rs

Add comprehensive end-of-turn behavior tests for g3-core

2026-01-12 21:17:32 +05:30

error_classification_test.rs

Add 72 integration tests for compaction, retry, tool execution, and error classification

2026-01-12 11:40:19 +05:30

incomplete_tool_call_test.rs

Fix panic on multi-byte chars in filter_json buffer truncation

2026-01-09 15:20:57 +11:00

integration_blackbox_test.rs

Remove legacy logs/ directory, consolidate all data under .g3/

2026-01-12 18:20:08 +05:30

parser_sanitization_test.rs

Add characterization tests for UTF-8 truncation and parser sanitization

2026-01-13 11:22:46 +05:30

read_file_token_limit_test.rs

fix: remove allow_multiple_tool_calls config and simplify tool execution flow

2026-01-09 13:28:07 +11:00

read_image_test.rs

Enhance read_image tool with magic byte detection and multi-image support

2025-12-26 11:19:37 +11:00

retry_behavior_test.rs

Add 72 integration tests for compaction, retry, tool execution, and error classification

2026-01-12 11:40:19 +05:30

stream_completion_characterization_test.rs

Add characterization tests for stream_completion_with_tools

2026-01-13 16:25:33 +05:30

streaming_parser_test.rs

Fix panic on multi-byte chars in filter_json buffer truncation

2026-01-09 15:20:57 +11:00

test_acd_integration.rs

Fix ACD turn summary loss and add /dump command

2026-01-12 05:13:02 +05:30

test_agent_session_id.rs

fix agent-mode session resumption bug

2026-01-03 16:44:58 +11:00

test_context_thinning.rs

Move fixed_filter_json from g3-core to g3-cli

2025-12-22 10:32:21 +11:00

test_preflight_max_tokens.rs

agent mode resumption

2026-01-03 14:50:08 +11:00

test_reset_with_summary.rs

fix compaction to restore system message

2025-12-01 14:38:21 +11:00

test_session_continuation.rs

Remove legacy logs/ directory, consolidate all data under .g3/

2026-01-12 18:20:08 +05:30

test_system_message_loading.rs

test for system message

2025-12-02 14:45:12 +11:00

test_todo_completion.rs

test for resume unfinished todos

2025-12-02 11:07:13 +11:00

test_todo_context_thinning.rs

Move fixed_filter_json from g3-core to g3-cli

2025-12-22 10:32:21 +11:00

test_todo_persistence.rs

add context window monitor

2025-11-27 21:00:02 +11:00

test_token_counting.rs

use consistent naming for compaction

2026-01-08 12:54:03 +11:00

todo_staleness_test.rs

Remove final_output tool - let summaries stream naturally

2026-01-09 14:57:24 +11:00

tool_execution_roundtrip_test.rs

Add 72 integration tests for compaction, retry, tool execution, and error classification

2026-01-12 11:40:19 +05:30

tool_execution_test.rs

Remove final_output tool and improve scout report handback

2026-01-10 13:43:04 +11:00

utf8_truncation_test.rs

Add characterization tests for UTF-8 truncation and parser sanitization

2026-01-13 11:22:46 +05:30