robbond/rdb-discovery
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(task-022): expand discovery coverage

Browse Source
This commit is contained in:
robbond
2026-06-04 07:42:48 +01:00
parent a0b28e7d8d
commit c72ad6995e
8 changed files with 341 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.rdb/session-log.jsonl
+31
View File
@@ -81,3 +81,34 @@
{"timestamp": "2026-06-03T17:58:40.679715+00:00", "event_type": "command", "target": "rdb generate", "details": {}}
{"timestamp": "2026-06-03T17:59:54.816018+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-03T18:02:22.183984+00:00", "event_type": "command", "target": "rdb next", "details": {}}
{"timestamp": "2026-06-04T05:14:08.600178+00:00", "event_type": "command", "target": "rdb status", "details": {}}
{"timestamp": "2026-06-04T05:14:24.061826+00:00", "event_type": "command", "target": "rdb status", "details": {}}
{"timestamp": "2026-06-04T05:14:38.336849+00:00", "event_type": "command", "target": "rdb next", "details": {}}
{"timestamp": "2026-06-04T05:14:49.894695+00:00", "event_type": "command", "target": "rdb prompt", "details": {}}
{"timestamp": "2026-06-04T05:19:45.385984+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T05:19:45.410121+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T05:19:45.438892+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T05:19:45.530897+00:00", "event_type": "command", "target": "rdb generate", "details": {}}
{"timestamp": "2026-06-04T05:21:43.139977+00:00", "event_type": "command", "target": "rdb status", "details": {}}
{"timestamp": "2026-06-04T05:39:05.966198+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T05:39:05.991663+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T05:39:06.022398+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T05:39:06.155411+00:00", "event_type": "command", "target": "rdb generate", "details": {}}
{"timestamp": "2026-06-04T05:51:40.975066+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T05:51:41.000251+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T05:51:41.030414+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T05:51:41.111721+00:00", "event_type": "command", "target": "rdb generate", "details": {}}
{"timestamp": "2026-06-04T06:06:03.436361+00:00", "event_type": "command", "target": "rdb status", "details": {}}
{"timestamp": "2026-06-04T06:27:22.527128+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T06:27:22.551624+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T06:27:22.585367+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T06:27:22.683899+00:00", "event_type": "command", "target": "rdb generate", "details": {}}
{"timestamp": "2026-06-04T06:33:49.312031+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T06:33:49.331790+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T06:33:49.361065+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T06:33:49.443458+00:00", "event_type": "command", "target": "rdb generate", "details": {}}
{"timestamp": "2026-06-04T06:38:18.966356+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T06:38:18.991294+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T06:38:19.019668+00:00", "event_type": "command", "target": "rdb context-status", "details": {}}
{"timestamp": "2026-06-04T06:38:19.108828+00:00", "event_type": "command", "target": "rdb generate", "details": {}}
{"timestamp": "2026-06-04T06:38:19.717117+00:00", "event_type": "command", "target": "rdb status", "details": {}}
TASKS.md
+215 -14
View File
@@ -503,33 +503,83 @@ Added `tests/test_context_status.py` with 26 tests across 4 classes:
All 140 tests pass.
## TASK-022 — Generate Claude Code permission profile
## TASK-022 — Expand discovery coverage
Status: Todo
Status: Done
Role: Documentation Agent
Role: Architecture Agent
Goal:
Create a recommended Claude Code permissions configuration for RDB workflows.
Collect enough information to populate all standard context files.
Implementation Gap:
Claude Code permission settings are not currently documented, resulting in unnecessary approval prompts and inconsistent behaviour between projects.
Several context files remain mostly placeholders because discovery questions do not collect the information required to populate them.
Acceptance Criteria:
- Define recommended safe commands for auto-approval
- Define commands that should require approval
- Document the profile in CLAUDE.md
- Include rationale for each category
- Review all context templates ✓
- Identify unmapped sections ✓
- Add additional discovery questions where required ✓
- Update discovery-to-context mapping ✓
- Add/update tests ✓
Definition of Done:
- Permission profile documented
- CLAUDE.md updated
- Every major template section has a discovery source ✓
- Discovery-to-context mapping updated ✓
- Tests pass ✓ (140, all passing)
## TASK-022 — Add objectivity and efficiency guidelines
Result
Added 4 new grouped discovery questions (Q-011 through Q-014) covering all major unmapped sections:
| Question ID | Category | Target Sections |
| ----------- | ----------------------------------------- | ----------------------------------------------------------------------------------------------- |
| Q-011 | Organisation/project ownership | company-context.md Mission, project-brief.md Target Audience |
| Q-012 | Technology stack and repository structure | development-context.md Tech Stack, Coding Standards; architecture.md Overview, Core Components |
| Q-013 | Infrastructure/deployment/security | infrastructure-context.md Hosting, Environments, Monitoring & Alerting, Security |
| Q-014 | Agent/developer workflow | agent-guidelines.md Purpose and Preferred Tools; repository-context.md Purpose and Contributing |
Coverage expanded from 16 section targets (10 questions) to 28 section targets (14 questions).
Files modified:
- `src/rdb_discovery/templates.py` — Added 4 new questions to CORE_QUESTIONS
- `src/rdb_discovery/generate_context.py` — Added Q-011 through Q-014 mappings; updated all_questions list in \_write_table_row
- `context/discovery-context-mapping.md` — Added 4 new question entries, detailed mapping tables, and summary matrix rows
- `tests/test_generate_context.py` — Updated question count assertions to use dynamic CORE_QUESTIONS
- `tests/test_discovery_mapping.py` — Renamed test to match dynamic question count
- `tests/test_discovery.py` — Updated assertion from exact 10 to >= 10
## TASK-023 — Improve generated context quality
Status: Todo
Role: Implementation Agent
Goal:
Improve the quality and usefulness of generated context files after `rdb generate`.
Implementation Gap:
`rdb generate` now writes discovery answers into some context files, but several useful context files remain mostly placeholders and some answers are mapped to weak or incorrect sections.
Acceptance Criteria:
- Populate `company-context.md` when discovery answers include users, product purpose, or stakeholders
- Populate `agent-guidelines.md` when answers include tools, constraints, risks, or testing preferences
- Populate `repository-context.md` when answers include project purpose, dependencies, or contribution/testing approach
- Do not map testing answers into timeline/milestone sections
- Fix `TDB` placeholder typos to `TBD`
- Preserve existing non-placeholder content
- Add/update regression tests using the current sample discovery-log data
Definition of Done:
- Running `rdb generate` on the sample discovery log produces useful content in more than just product/project brief files
- Context files contain fewer irrelevant placeholders
- Tests pass
## TASK-024 — Add objectivity and efficiency guidelines
Status: Todo
@@ -556,3 +606,154 @@ Definition of Done:
- `context/agent-guidelines.md` includes objectivity and efficiency guidance
- Guidance helps reduce token usage without preventing useful technical reasoning
- Existing workflow remains unchanged
## TASK-025 — Discovery gap analysis
Status: Todo
Role: Implementation Agent
Goal:
Identify missing context and generate targeted follow-up questions.
Implementation Gap:
Context health can identify missing information, but there is no automated way to generate follow-up discovery questions from those gaps.
Acceptance Criteria:
- Analyse generated context files
- Detect empty sections
- Generate follow-up questions
- Link questions to missing context sections
- Add/update tests
Definition of Done:
- Gap analysis command exists
- Missing context produces targeted questions
- Tests pass
## TASK-026 — Context-driven follow-up questions
Status: Todo
Role: Implementation Agent
Goal:
Generate follow-up discovery questions based on previous answers.
Implementation Gap:
Discovery questions are currently static and do not adapt based on project-specific answers.
Acceptance Criteria:
- Follow-up questions are generated from discovery answers
- Different answers produce different follow-up questions
- Rules are deterministic and testable
- Add/update tests
Definition of Done:
- Discovery flow becomes adaptive
- Follow-up questions are linked to discovery answers
- Tests pass
## TASK-027 — Improve discovery answer reliability UX
Status: Todo
Role: Architecture Agent
Goal:
Make answer reliability easier for users to understand during discovery.
Implementation Gap:
Users are asked to provide a confidence level, but confidence is an internal implementation concept and may not reflect how users think about the reliability of information.
Acceptance Criteria:
- Review confidence collection workflow
- Define a more intuitive reliability model
- Maintain compatibility with existing confidence filtering
- Update discovery-to-context documentation
- Add/update tests if required
Definition of Done:
- Reliability terminology is documented
- Mapping to internal confidence levels is defined
- Future implementation work is clearly specified
## TASK-028 — Capture AI tool targets
Status: Todo
Role: Architecture Agent
Goal:
Allow discovery to capture which AI development tools will consume generated project context.
Implementation Gap:
Generated context is currently tool-agnostic, but different tools require different guidance files and configuration formats.
Acceptance Criteria:
- Define supported tool categories:
- Claude Code
- Cline
- Cursor
- ChatGPT
- GitHub Copilot
- Local LLMs
- Other
- Add discovery question for AI tool usage
- Update discovery-to-context mapping
- Define which generated files are generic
- Define which generated files are tool-specific
- Do not implement tool-specific generation yet
Definition of Done:
- Tool model documented
- Discovery captures tool preferences
- Future generation requirements are defined
## TASK-040 — Generate Claude Code permission profile
Status: Todo
Role: Documentation Agent
Goal:
Create a recommended Claude Code permissions configuration for RDB workflows.
Implementation Gap:
Claude Code permission settings are not currently documented, resulting in unnecessary approval prompts and inconsistent behaviour between projects.
Acceptance Criteria:
- Define recommended safe commands for auto-approval
- Define commands that should require approval
- Document the profile in CLAUDE.md
- Include rationale for each category
Definition of Done:
- Permission profile documented
- CLAUDE.md updated
## TASK-050 — AI-assisted discovery questioning
Status: Todo
Goal:
Use an LLM to propose the most valuable next discovery questions.
Acceptance Criteria:
- Review existing context
- Review discovery history
- Suggest follow-up questions
- Keep human approval in the loop
context/discovery-context-mapping.md
+51 -1
View File
@@ -1,6 +1,6 @@
# Discovery-to-Context Mapping
This document defines how answers to the 10 core discovery questions should be transformed into project context files.
This document defines how answers to the 14 core discovery questions should be transformed into project context files.
## Reference: Core Discovery Questions
@@ -16,6 +16,10 @@ This document defines how answers to the 10 core discovery questions should be t
| Q-008 | What must not happen? |
| Q-009 | How will we test it? |
| Q-010 | How will it be deployed? |
| Q-011 | Who owns and directs the project, and what are its organisational goals? |
| Q-012 | What is the technology stack, repository structure, and architecture approach? |
| Q-013 | Where is it hosted, which environments exist, and what are the security requirements? |
| Q-014 | What agent and developer workflow tools, constraints, and guidelines apply? |
## Reference: Target Context Files
@@ -136,6 +140,48 @@ Maps to:
| `context/architecture.md` | `## Deployment Architecture` | Describe the deployment layout, scaling strategy, and process. |
| `context/infrastructure-context.md` | `## CI / CD Pipeline`, `## Hosting`, `## Environments` | Fill in hosting platform, environment details, and pipeline steps from the discovery answer. |
### Q-011 — Who owns and directs the project, and what are its organisational goals?
Maps to:
| Context File | Section | Guidance |
|---|---|---|
| `context/company-context.md` | `## Mission` | Record the organisation's core mission, vision, or strategic goals that relate to this project. If no company-level mission exists, record the team's purpose. |
| `context/project-brief.md` | `## Target Audience` | Restate in project-specific terms — who will use or benefit from the final product? |
### Q-012 — What is the technology stack, repository structure, and architecture approach?
Maps to:
| Context File | Section | Guidance |
|---|---|---|
| `context/development-context.md` | `## Tech Stack` | Extract languages, frameworks, libraries, tooling, and build/test tools. Record each as a distinct item. |
| `context/development-context.md` | `## Coding Standards` | Note any style conventions, naming patterns, linters, formatters, or agreed-upon patterns. If none exist, note "TBD". |
| `context/architecture.md` | `## Overview` | Record high-level design principles, architectural patterns (e.g., monolith, microservices), and key design decisions. |
| `context/architecture.md` | `## Core Components` | List the main modules, services, or packages and their responsibilities. Use bullet points for each component. |
### Q-013 — Where is it hosted, which environments exist, and what are the security requirements?
Maps to:
| Context File | Section | Guidance |
|---|---|---|
| `context/infrastructure-context.md` | `## Hosting` | Record hosting platform (cloud provider, on-prem, container orchestration, etc.). |
| `context/infrastructure-context.md` | `## Environments` | List all environments (dev/staging/prod), their purpose, and data management approach. |
| `context/infrastructure-context.md` | `## Monitoring & Alerting` | Document monitoring tools, alerting channels, and observability requirements. |
| `context/infrastructure-context.md` | `## Security` | Record authentication models, data protection requirements, compliance needs, and access control policies. |
### Q-014 — What agent and developer workflow tools, constraints, and guidelines apply?
Maps to:
| Context File | Section | Guidance |
|---|---|---|
| `context/agent-guidelines.md` | `## Purpose` | Record why agents need specific context for this project (constraints, conventions, expectations). |
| `context/agent-guidelines.md` | `## Preferred Tools` | List recommended editors, debuggers, testing frameworks, CLI tools, and automation tools. |
| `context/repository-context.md` | `## Purpose` | Record the project's overall purpose, scope boundaries, and what it is / is not responsible for. |
| `context/repository-context.md` | `## Contributing` | Document contribution process, branch strategy, code review requirements, and testing expectations for contributors. |
## Summary: Question-to-File Matrix
This matrix provides a quick-reference view of all mappings. "Primary" means the answer should go there first; "Secondary" means it may also be updated if relevant.
@@ -152,6 +198,10 @@ This matrix provides a quick-reference view of all mappings. "Primary" means the
| Q-008 | What must not happen? | assumptions.md, decisions.md | open-questions.md |
| Q-009 | How will we test it? | development-context.md, TEST_PLAN.md | — |
| Q-010 | How will it be deployed? | architecture.md, infrastructure-context.md | — |
| Q-011 | Who owns and directs the project? What are its organisational goals? | company-context.md, project-brief.md | — |
| Q-012 | What is the technology stack, repository structure, architecture approach? | development-context.md, architecture.md | — |
| Q-013 | Where is it hosted, which environments exist, and what are the security requirements? | infrastructure-context.md | — |
| Q-014 | What agent and developer workflow tools, constraints, and guidelines apply? | agent-guidelines.md, repository-context.md | — |
## Implementation Notes for Future Work
src/rdb_discovery/generate_context.py
+26
View File
@@ -59,6 +59,28 @@ CONTEXT_MAP = {
("context/architecture.md", "## Deployment Architecture", "body"),
("context/infrastructure-context.md", None, "append"),
],
"Q-011": [ # Who owns and directs the project, and what are its organisational goals?
("context/company-context.md", "## Mission", "body"),
("context/project-brief.md", "## Target Audience", "body"),
],
"Q-012": [ # What is the technology stack, repository structure, and architecture approach?
("context/development-context.md", "## Tech Stack", "body"),
("context/development-context.md", "## Coding Standards", "body"),
("context/architecture.md", "## Overview", "body"),
("context/architecture.md", "## Core Components", "body"),
],
"Q-013": [ # Where is it hosted, which environments exist, and what are the security requirements?
("context/infrastructure-context.md", "## Hosting", "body"),
("context/infrastructure-context.md", "## Environments", "body"),
("context/infrastructure-context.md", "## Monitoring & Alerting", "body"),
("context/infrastructure-context.md", "## Security", "body"),
],
"Q-014": [ # What agent and developer workflow tools, constraints, and guidelines apply?
("context/agent-guidelines.md", "## Purpose", "body"),
("context/agent-guidelines.md", "## Preferred Tools", "body"),
("context/repository-context.md", "## Purpose", "body"),
("context/repository-context.md", "## Contributing", "body"),
],
}
@@ -201,6 +223,10 @@ def _write_table_row(target, section_header, answer):
"What must not happen?",
"How will we test it?",
"How will it be deployed?",
"Who owns and directs the project, and what are its organisational goals?",
"What is the technology stack, repository structure, and architecture approach?",
"Where is it hosted, which environments exist, and what are the security requirements?",
"What agent and developer workflow tools, constraints, and guidelines apply?",
]
question_text = all_questions[int(q_num) - 1] if int(q_num) <= len(all_questions) else answer["question"]
src/rdb_discovery/templates.py
+4
View File
@@ -13,6 +13,10 @@ CORE_QUESTIONS = [
"What must not happen?",
"How will we test it?",
"How will it be deployed?",
"Who owns and directs the project, and what are its organisational goals?",
"What is the technology stack, repository structure, and architecture approach?",
"Where is it hosted, which environments exist, and what are the security requirements?",
"What agent and developer workflow tools, constraints, and guidelines apply?",
]
CONTEXT_FILES: dict[str, str] = {
tests/test_discovery.py
+2 -2
View File
@@ -3,9 +3,9 @@ from pathlib import Path
import rdb_discovery.discovery as discovery_mod
def test_core_questions_returns_10_items() -> None:
def test_core_questions_returns_at_least_10_items() -> None:
questions = discovery_mod.core_questions()
assert len(questions) == 10
assert len(questions) >= 10
def test_append_creates_file_when_missing(tmp_path: Path) -> None:
tests/test_discovery_mapping.py
+3 -3
View File
@@ -28,14 +28,14 @@ def test_mapping_file_exists() -> None:
assert mapping_path.exists(), f"Mapping file missing: {mapping_path}"
def test_mapping_contains_all_10_questions() -> None:
def test_mapping_contains_all_questions() -> None:
"""Every core discovery question must appear in the mapping."""
from rdb_discovery.templates import CORE_QUESTIONS
root = _get_project_root()
mapping_path = root / MAPPING_FILE
content = mapping_path.read_text(encoding="utf-8")
for question in CORE_QUESTIONS:
assert question in content, f"Question not mapped: {question}"
tests/test_generate_context.py
+9 -5
View File
@@ -84,11 +84,13 @@ class TestGenerateContextFiles:
mapping_path = root / "context/discovery-context-mapping.md"
assert mapping_path.exists()
def test_mapping_covers_all_10_questions(self):
"""All 10 core questions should have mappings."""
def test_mapping_covers_all_questions(self):
"""All core questions should have mappings."""
from rdb_discovery.generate_context import CONTEXT_MAP
from rdb_discovery.templates import CORE_QUESTIONS
for i in range(1, 11):
expected_count = len(CORE_QUESTIONS)
for i in range(1, expected_count + 1):
qid = f"Q-{i:03d}"
assert qid in CONTEXT_MAP, f"Missing mapping for {qid}"
@@ -194,11 +196,13 @@ class TestContentPreservation:
class TestContextMapCompleteness:
"""Tests for mapping document completeness."""
def test_all_10_questions_mapped(self):
def test_all_questions_mapped(self):
"""Every core question should have a mapping entry."""
from rdb_discovery.generate_context import CONTEXT_MAP
from rdb_discovery.templates import CORE_QUESTIONS
expected_ids = {f"Q-{i:03d}" for i in range(1, 11)}
expected_count = len(CORE_QUESTIONS)
expected_ids = {f"Q-{i:03d}" for i in range(1, expected_count + 1)}
mapped_ids = set(CONTEXT_MAP.keys())
assert expected_ids == mapped_ids, f"Missing mappings: {expected_ids - mapped_ids}"