refactor: implement _summary_list_field function to streamline handling of summary fields in coach summary; enhance payload processing and validation for string and list types

refactor: add functions for JSON payload extraction and validation in coach summary; streamline summary key handling and improve error reporting

refactor: introduce compact representation functions for metrics, issues, and knowledge cards; enhance summary evidence generation and improve error handling in JSON extraction

refactor: enhance JSON response handling in coach summary generation; update response format instructions and improve error reporting for invalid JSON outputs

refactor: enhance _encode_bt709_output and _encode_bt709_command for improved audio stream handling and code clarity

refactor: remove sample_pose_cache module and streamline pose processing in pipeline

refactor: change default delegate to CPU in MediaPipePoseBackend and update tests accordingly

refactor: update artifact URLs and improve router device handling for better classification performance

refactor(mediapipe): simplify GPU delegate preference logic and remove unused CUDA visibility check

refactor(mediapipe): enhance MediaPipePoseBackend to prefer tasks on GPU and improve delegate handling

feat: load external coach knowledge packs

fix(hf-spaces): install mediapipe native libraries

fix(hf-spaces): avoid pickling analysis progress callbacks

feat(pose)!: use coco17 3d router features

Implement grounded coach summary with HF SLM

feat(hf): use ZeroGPU for analysis

perf(pose): read dense video frames sequentially

Merge branch 'main' into NLag/issue4

refactor(mediapipe): improve code readability and add CPU delegate option

Avoid OpenCV H264 writer fallback errors

feat(report): add annotated issue clips

Merge branch 'main' into NLag/issue4

fix(renderer): preserve video colors in annotations

refactor(exercises): route pipeline through exercise objects

Implement frame-level issue markers

Merge branch 'main' into NLag/issue4

refactor(exercises): introduce exercise strategies

Merge branch 'main' into NLag/issue4

fix(rep-analysis): split exercise analyzers

Merge branch 'main' into NLag/issue4

Merge main into issue 4 branch

Implement exercise classifier router

Merge branch 'main' into issue-6-rep-analysis-variation

Detect exercise variations from rep metrics

Implement pose-derived rep metrics

feat(rep_counter): implement exercise-specific rep counters for push-ups, shoulder presses, and squats; add dependency on fastapi

feat(pose): add pluggable pose backends

fix(rep): ignore noisy extrema in squat cycle segmentation

refactor(ui): clarify mocked downstream analysis

fix(renderer): prefer web-friendly video codecs

feat(pose): use dense frames for real pose extraction

fix(classifier): default auto routing to squat

feat(renderer): generate annotated pose videos

fix(rep): clamp mock analysis scores for long sets

feat(pipeline): persist rep debug artifacts

feat(rep): implement deterministic exercise rep segmentation

feat(rep): add shared signal and state machine utilities

refactor(exercises): centralize exercise definitions

feat(pose): add pluggable pose backends

feat(video): add intake quality gate