19 Commits
Author SHA1 Message Date
robbond 152096d433 feat(task-023): improve generated context quality 2026-06-04 09:42:05 +01:00
robbond c72ad6995e feat(task-022): expand discovery coverage 2026-06-04 07:42:48 +01:00
robbond a0b28e7d8d feat(task-021): add context health reporting 2026-06-03 19:05:04 +01:00
robbond 5bad6ad0f8 feat(task-020): generate context from discovery answers 2026-06-03 18:19:25 +01:00
robbond 1c2faa3162 feat(task-018): add role-based context selection 2026-06-02 18:09:11 +01:00
robbond 34f7364c86 feat: support role-based agent prompts 2026-06-02 17:56:38 +01:00
robbond 3ccdea330a feat: add standard context file templates 2026-06-02 17:18:35 +01:00
robbond 6eef97582d feat: use telemetry in guardrails 2026-06-02 16:44:36 +01:00
robbond 2fcc822394 feat: record CLI command telemetry 2026-06-02 15:49:27 +01:00
robbond eb30450f34 feat: add telemetry foundation 2026-06-02 14:21:17 +01:00
robbond 7a1d36c03c feat: improve generated agent prompts 2026-06-02 12:49:55 +01:00
robbond aee13b045e chore: mark TASK-006 complete 2026-06-02 11:41:27 +01:00
robbond 21611b7c4e feat(TASK-005): wire project state and agent handoff into start/complete commands
- Add update_project_state() helper: updates Current Task + Last Updated
  in PROJECT_STATE.md via regex sub, preserving all surrounding formatting.
- Add update_agent_handoff() helper: updates Current Stage + Current Task
  sections in AGENT_HANDOFF.md, auto-detected from project_stage().
- Wire both helpers into rdb start TASK-ID and rdb complete TASK-ID CLI
  commands so task lifecycle transitions propagate to all control files.
- ADDING test_status.py with 5 tests: update_project_state task/timestamp
  updates, missing-file false return, agent handoff update and miss.

Acceptance criteria met:
- rdb start/complete now update PROJECT_STATE.md
- rdb start/complete now update AGENT_HANDOFF.md
- RUN_LOG.md already updated (pre-existing)
- Task formatting preserved (regex sub targets single line only)
2026-06-02 10:37:38 +01:00
robbond 39728667a7 feat: add read_discovery_answers, append_followup_answer, and ask-more command
- Add read_discovery_answers() to parse discovery-log.md rows into dicts
  with low_confidence and needs_followup boolean flags.
- Add append_followup_answer() to append follow-up rows linked to original Q-A IDs.
- Add 'ask-more' CLI command that detects Low-confidence and Follow-up-needed
  answers, prompts for additional details, and records them in the log.
- Add 6 tests: read_discovery_answers round-trip, empty-log handling,
  low-confidence detection, follow-up flag detection, and append_followup.
2026-06-02 09:57:02 +01:00
robbond 6430a16050 docs: add task for agent prompt generation 2026-06-02 06:44:03 +01:00
robbond 6211a391b5 chore: implement rdb init project structure 2026-06-02 06:13:43 +01:00
robbond 7cb7034704 chore: remove cached Python artifacts 2026-06-01 19:40:37 +01:00
robbond bc027a5423 fix: parse task headings with dash variants 2026-06-01 19:25:59 +01:00
robbond dede6ecc60 chore: bootstrap rdb-discovery 2026-06-01 17:43:02 +01:00