Ayush Dubey 579b931915 fix(llmloop): account for tool_calls and arguments in messageTokens (#1413) ...

Assistant turns issuing tool calls under OpenAI-compatible chat completions store their calls and arguments on ToolCalls rather than Native.Payload. Because messageTokens only inspected ExtractText() and Native.EstimatedTokens(), these turns evaluated to 0 tokens during active zone budget calculations, causing computeActiveZoneSize to pack too many rounds and risk exceeding model context limits.

Adds EstimatedTokens to ToolCall (including arguments and ExtraContent) and Message, and updates messageTokens to account for tool calls when not already covered by Native payload.

2026-09-28 15:16:11 +08:00

..

comments_test.go

feat(cli): add --output flag to write review/scan results to a file (#852)

2026-08-24 15:37:29 +08:00

comments.go

chore: add SPDX license headers and automated verification (#740)

2026-08-05 21:26:27 +08:00

compare_test.go

fix(session): preserve findings across file renames (#1529)

2026-09-22 15:56:35 +08:00

compare.go

fix(session): preserve findings across file renames (#1529)

2026-09-22 15:56:35 +08:00

delete_test.go

feat(session): add 'ocr session rm' to delete a saved session (#1490)

2026-09-23 20:14:06 +08:00

delete.go

feat(session): add 'ocr session rm' to delete a saved session (#1490)

2026-09-23 20:14:06 +08:00

final_manifest_test.go

test: raise statement coverage to 90% and enforce it in CI (#747)

2026-08-06 12:55:44 +08:00

history_test.go

fix(llm): replay tool_call extra_content and surface provider error bodies (#1393)

2026-09-23 10:07:19 +08:00

history.go

fix(llmloop): account for tool_calls and arguments in messageTokens (#1413)

2026-09-28 15:16:11 +08:00

list_error_test.go

feat(cli): add --output flag to write review/scan results to a file (#852)

2026-08-24 15:37:29 +08:00

list_more_test.go

test: raise statement coverage to 90% and enforce it in CI (#747)

2026-08-06 12:55:44 +08:00

list_test.go

feat(cli): add --output flag to write review/scan results to a file (#852)

2026-08-24 15:37:29 +08:00

list.go

feat(session): add 'ocr session rm' to delete a saved session (#1490)

2026-09-23 20:14:06 +08:00

manifest_guards_test.go

test: raise statement coverage to 90% and enforce it in CI (#747)

2026-08-06 12:55:44 +08:00

manifest_test.go

chore(ci): fail CI when unapproved non-English text appears in source files (#876)

2026-08-13 14:43:55 +08:00

manifest.go

chore: add SPDX license headers and automated verification (#740)

2026-08-05 21:26:27 +08:00

persist_test.go

fix(llm): trim environment-sourced endpoint values (#1414)

2026-09-24 17:59:47 +08:00

persist.go

fix(llm): trim environment-sourced endpoint values (#1414)

2026-09-24 17:59:47 +08:00

raw_writer_test.go

feat(raw): capture raw LLM traffic via SDK middleware (opt-in) (#1109)

2026-09-03 11:05:21 +08:00

raw_writer.go

feat(raw): capture raw LLM traffic via SDK middleware (opt-in) (#1109)

2026-09-03 11:05:21 +08:00

resume_identity_test.go

feat(resume): add trusted resume validation and transition lineage (#786) (#845)

2026-08-14 11:31:40 +08:00

resume_identity.go

feat(resume): add trusted resume validation and transition lineage (#786) (#845)

2026-08-14 11:31:40 +08:00

resume_orphan_request_test.go

Feat/llm retry report:SDK retry-attempt observability for review (#785) (#790)

2026-08-13 14:31:18 +08:00

resume_test.go

fix(session): tolerate truncated resume tail (#1312)

2026-09-17 10:29:23 +08:00

resume.go

fix(session): tolerate truncated resume tail (#1312)

2026-09-17 10:29:23 +08:00

test_home_test.go

feat(cli): add --output flag to write review/scan results to a file (#852)

2026-08-24 15:37:29 +08:00

testing.go

feat(raw): capture raw LLM traffic via SDK middleware (opt-in) (#1109)

2026-09-03 11:05:21 +08:00

testmain_test.go

fix(test): add TestMain to isolate session writes from real HOME (#1416)

2026-09-18 21:29:02 +08:00

validate_scan_options_test.go

test: raise statement coverage to 90% and enforce it in CI (#747)

2026-08-06 12:55:44 +08:00