gitea-admin/CASAN
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: align all documentation with the new repo structure

Browse Source 
Update agent protocols (.claude/agents, .github/agents), guides, runbooks and READMEs
to the post-restructure layout: .specify/{scripts,tests,security,config,templates,
governance,memory,level5-config} -> packages/casan-harness/...; docs/input +
golden-runs + traceability-map -> apps/okr/domain/...; drop AINative_OKR_CASAN5/ prefix.
Runtime-state paths (.specify/logs, .specify/agentops, .specify/level5/central-governance)
kept as-is. Historical evidence under docs/output/ left untouched (immutable run records).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
thanhnv
2026-07-08 14:36:27 +09:00
co-authored by Claude Opus 4.8
parent 36a4812ef3
commit 18997caf49
53 changed files with 167 additions and 167 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.claude/agents/okr.bd.md
+3 -3
View File
@@ -49,7 +49,7 @@ Read the following files to gather context:
2. **System overview**: `docs/output/srs-systems/srs-overview-system.md` — system-wide context 2. **System overview**: `docs/output/srs-systems/srs-overview-system.md` — system-wide context
3. **Module SRS folder**: `docs/output/srs-systems/<mod-folder>/` — module wireframes & details 3. **Module SRS folder**: `docs/output/srs-systems/<mod-folder>/` — module wireframes & details
4. **Technical architecture**: `docs/technical_architecture.md` — mandatory tech stack 4. **Technical architecture**: `docs/technical_architecture.md` — mandatory tech stack
5. **BD template**: `.specify/templates/bd-template.md` — output structure template 5. **BD template**: `packages/casan-harness/templates/bd-template.md` — output structure template
--- ---
@@ -57,7 +57,7 @@ Read the following files to gather context:
Generate the BD document at: `docs/output/ipa-docs/bd/bd-<mod-id>-<name>.md` Generate the BD document at: `docs/output/ipa-docs/bd/bd-<mod-id>-<name>.md`
The output **MUST** follow the structure defined in `.specify/templates/bd-template.md`: The output **MUST** follow the structure defined in `packages/casan-harness/templates/bd-template.md`:
| § | Section | Content | | § | Section | Content |
|---|---------|---------| |---|---------|---------|
@@ -80,7 +80,7 @@ The output **MUST** follow the structure defined in `.specify/templates/bd-templ
2. Read `docs/output/srs-systems/srs-overview-system.md` for system context 2. Read `docs/output/srs-systems/srs-overview-system.md` for system context
3. Read module wireframe/detail files from `docs/output/srs-systems/<mod-folder>/` 3. Read module wireframe/detail files from `docs/output/srs-systems/<mod-folder>/`
4. Read `docs/technical_architecture.md` for tech stack constraints 4. Read `docs/technical_architecture.md` for tech stack constraints
5. Read `.specify/templates/bd-template.md` for the output template structure 5. Read `packages/casan-harness/templates/bd-template.md` for the output template structure
Log: `[PROCESSING] Input file loading complete` Log: `[PROCESSING] Input file loading complete`
.claude/agents/okr.bossbuiltin.md
+9 -9
View File
@@ -151,10 +151,10 @@ report-nn: <NN> # for speckit.implement only
report-phase: <phase> # for speckit.implement only report-phase: <phase> # for speckit.implement only
casan-harness: casan-harness:
required: true required: true
h4-security: ".specify/scripts/bash/security-check.sh" h4-security: "packages/casan-harness/scripts/bash/security-check.sh"
h5-governance: ".specify/scripts/bash/governance-check.sh" h5-governance: "packages/casan-harness/scripts/bash/governance-check.sh"
h6-agentops: ".specify/scripts/bash/agent-metrics.sh" h6-agentops: "packages/casan-harness/scripts/bash/agent-metrics.sh"
wrapper: ".specify/scripts/bash/casan-harness.sh" wrapper: "packages/casan-harness/scripts/bash/casan-harness.sh"
evidence: evidence:
trace-dir: ".specify/logs/trace" trace-dir: ".specify/logs/trace"
audit-log: ".specify/logs/audit/audit.jsonl" audit-log: ".specify/logs/audit/audit.jsonl"
@@ -174,20 +174,20 @@ For every delegated step, Boss MUST:
1. Write the step input payload to `docs/output/output_logs/<feature-id>/casan/<step>-input.txt`. 1. Write the step input payload to `docs/output/output_logs/<feature-id>/casan/<step>-input.txt`.
2. Run H4 input security: 2. Run H4 input security:
```bash ```bash
.specify/scripts/bash/security-check.sh <step-input> <safe-input> input packages/casan-harness/scripts/bash/security-check.sh <step-input> <safe-input> input
``` ```
3. Run H5 governance: 3. Run H5 governance:
```bash ```bash
.specify/scripts/bash/governance-check.sh <safe-input> <approved-input> <action-name> packages/casan-harness/scripts/bash/governance-check.sh <safe-input> <approved-input> <action-name>
``` ```
4. Execute the real agent/tool step under H6 metrics: 4. Execute the real agent/tool step under H6 metrics:
```bash ```bash
CASAN_AGENT_NAME=<agent> CASAN_STEP_NAME=<step> \ CASAN_AGENT_NAME=<agent> CASAN_STEP_NAME=<step> \
.specify/scripts/bash/agent-metrics.sh <approved-input> <raw-output> -- <real command> packages/casan-harness/scripts/bash/agent-metrics.sh <approved-input> <raw-output> -- <real command>
``` ```
5. Run H4 output security: 5. Run H4 output security:
```bash ```bash
.specify/scripts/bash/security-check.sh <raw-output> <final-output> output packages/casan-harness/scripts/bash/security-check.sh <raw-output> <final-output> output
``` ```
6. Update `pipeline-context.yaml` with the H4/H5/H6 trace paths and status. 6. Update `pipeline-context.yaml` with the H4/H5/H6 trace paths and status.
@@ -204,7 +204,7 @@ Side-effecting action names:
High-risk actions are denied by default unless `CASAN_APPROVAL_DECISION=approve` and `CASAN_APPROVER=<name>` are set in the environment. Boss must log denied actions and stop that action instead of bypassing governance. High-risk actions are denied by default unless `CASAN_APPROVAL_DECISION=approve` and `CASAN_APPROVER=<name>` are set in the environment. Boss must log denied actions and stop that action instead of bypassing governance.
For side-effecting actions, Boss MUST also call `.specify/scripts/bash/tool-registry-gate.sh <action-name>` with `CASAN_IDEMPOTENCY_KEY` set. Cache hits are allowed only when H4 input, H5 governance, H6 metrics, and H4 output evidence are still written for the current run. For side-effecting actions, Boss MUST also call `packages/casan-harness/scripts/bash/tool-registry-gate.sh <action-name>` with `CASAN_IDEMPOTENCY_KEY` set. Cache hits are allowed only when H4 input, H5 governance, H6 metrics, and H4 output evidence are still written for the current run.
--- ---
.claude/agents/okr.dd.md
+3 -3
View File
@@ -54,7 +54,7 @@ Read the following files:
3. **Feature spec**: `docs/output/specs/<feature-id>/spec.md` — feature specification 3. **Feature spec**: `docs/output/specs/<feature-id>/spec.md` — feature specification
4. **Implementation plan**: `docs/output/specs/<feature-id>/plan.md` — tech plan & data model 4. **Implementation plan**: `docs/output/specs/<feature-id>/plan.md` — tech plan & data model
5. **Technical architecture**: `docs/technical_architecture.md` — mandatory tech stack 5. **Technical architecture**: `docs/technical_architecture.md` — mandatory tech stack
6. **DD template**: `.specify/templates/dd-template.md` — output structure template 6. **DD template**: `packages/casan-harness/templates/dd-template.md` — output structure template
--- ---
@@ -62,7 +62,7 @@ Read the following files:
Generate the DD document at: `docs/output/ipa-docs/dd/dd-<mod-id>-<name>.md` Generate the DD document at: `docs/output/ipa-docs/dd/dd-<mod-id>-<name>.md`
The output **MUST** follow the structure defined in `.specify/templates/dd-template.md`: The output **MUST** follow the structure defined in `packages/casan-harness/templates/dd-template.md`:
| § | Section | Content | | § | Section | Content |
|---|---------|---------| |---|---------|---------|
@@ -88,7 +88,7 @@ The output **MUST** follow the structure defined in `.specify/templates/dd-templ
2. Read SRS for requirements & NFR 2. Read SRS for requirements & NFR
3. Read spec.md and plan.md 3. Read spec.md and plan.md
4. Read `docs/technical_architecture.md` 4. Read `docs/technical_architecture.md`
5. Read `.specify/templates/dd-template.md` 5. Read `packages/casan-harness/templates/dd-template.md`
Log: `[PROCESSING] Input file loading complete` Log: `[PROCESSING] Input file loading complete`
.claude/agents/okr.reviewcode.md
+3 -3
View File
@@ -52,7 +52,7 @@ You are a Senior Code Reviewer specializing in Node.js/NestJS/TypeScript impleme
$ARGUMENTS $ARGUMENTS
``` ```
If `$ARGUMENTS` is empty, run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` to detect the current active feature. If `$ARGUMENTS` is empty, run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` to detect the current active feature.
## Constraints ## Constraints
@@ -82,7 +82,7 @@ Add a dedicated section in the report:
## Setup ## Setup
1. Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly -RequireTasks -IncludeTasks` and parse: 1. Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly -RequireTasks -IncludeTasks` and parse:
- `FEATURE_DIR` — feature specs directory - `FEATURE_DIR` — feature specs directory
- `AVAILABLE_DOCS` — list of generated artifacts - `AVAILABLE_DOCS` — list of generated artifacts
2. Load reference documents: 2. Load reference documents:
@@ -90,7 +90,7 @@ Add a dedicated section in the report:
- `docs/output/specs/<feature-id>/tasks.md` — task completion checklist - `docs/output/specs/<feature-id>/tasks.md` — task completion checklist
- `docs/output/specs/<feature-id>/plan.md` — implementation plan - `docs/output/specs/<feature-id>/plan.md` — implementation plan
- `docs/output/specs/<feature-id>/data-model.md` — entity model - `docs/output/specs/<feature-id>/data-model.md` — entity model
- `.specify/memory/constitution.md` — project Constitution - `packages/casan-harness/memory/constitution.md` — project Constitution
- `docs/technical_architecture.md` — system architecture - `docs/technical_architecture.md` — system architecture
3. Identify implementation module directory (e.g., `backend/src/modules/workspace/`) 3. Identify implementation module directory (e.g., `backend/src/modules/workspace/`)
.claude/agents/okr.reviewplan.md
+2 -2
View File
@@ -64,7 +64,7 @@ Optional: feature-id (e.g. `001-xxx`). If empty, auto-detect from the active bra
## Setup ## Setup
Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` from repo root and parse: Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` from repo root and parse:
- `FEATURE_DIR` — absolute path to the feature specs directory - `FEATURE_DIR` — absolute path to the feature specs directory
- `FEATURE_SPEC` — path to `spec.md` - `FEATURE_SPEC` — path to `spec.md`
@@ -75,7 +75,7 @@ Load the following documents:
- `docs/output/specs/<feature-id>/contracts/` — API contracts (**warn** if missing) - `docs/output/specs/<feature-id>/contracts/` — API contracts (**warn** if missing)
- `docs/output/specs/<feature-id>/research.md` — library/framework decisions - `docs/output/specs/<feature-id>/research.md` — library/framework decisions
- `docs/output/specs/<feature-id>/quickstart.md` — integration scenarios - `docs/output/specs/<feature-id>/quickstart.md` — integration scenarios
- `.specify/memory/constitution.md` — project Constitution - `packages/casan-harness/memory/constitution.md` — project Constitution
- `docs/technical_architecture.md` — system architecture - `docs/technical_architecture.md` — system architecture
--- ---
.claude/agents/okr.reviewspec.md
+2 -2
View File
@@ -61,7 +61,7 @@ Optional: feature-id (e.g. `001-xxx`). If empty, auto-detect from the active bra
## Setup ## Setup
Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` from repo root and parse: Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` from repo root and parse:
- `FEATURE_DIR` — absolute path to the feature specs directory - `FEATURE_DIR` — absolute path to the feature specs directory
- `FEATURE_SPEC` — path to `spec.md` - `FEATURE_SPEC` — path to `spec.md`
@@ -69,7 +69,7 @@ Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` from
Load the following reference documents: Load the following reference documents:
- `docs/output/srs-systems/srs-overview-system.md` — system-level SRS (traceability source) - `docs/output/srs-systems/srs-overview-system.md` — system-level SRS (traceability source)
- `docs/technical_architecture.md` — technical architecture (feasibility reference) - `docs/technical_architecture.md` — technical architecture (feasibility reference)
- `.specify/memory/constitution.md` — project Constitution (compliance gate) - `packages/casan-harness/memory/constitution.md` — project Constitution (compliance gate)
- Feature-specific SRS if exists: `docs/output/ipa-docs/srs/srs-<module>.md` - Feature-specific SRS if exists: `docs/output/ipa-docs/srs/srs-<module>.md`
--- ---
.claude/agents/okr.srs.md
+2 -2
View File
@@ -86,7 +86,7 @@ Priority rule: `srs-overview-system.md` → `srs-mod<XX>-detail.md` → `srs-mod
1. Load `docs/output/srs-systems/srs-overview-system.md` to get system context, then identify the module folder matching `$ARGUMENTS` (e.g., `docs/output/srs-systems/mod01-xxx/`). Load `srs-mod<XX>-detail.md` and `srs-mod<XX>-wireframe.md` from that folder. Enumerate all FEAs belonging to the target module. 1. Load `docs/output/srs-systems/srs-overview-system.md` to get system context, then identify the module folder matching `$ARGUMENTS` (e.g., `docs/output/srs-systems/mod01-xxx/`). Load `srs-mod<XX>-detail.md` and `srs-mod<XX>-wireframe.md` from that folder. Enumerate all FEAs belonging to the target module.
2. Cross-reference `srs-mod<XX>-detail.md` and `srs-mod<XX>-wireframe.md` to fill in any missing details for each FEA. 2. Cross-reference `srs-mod<XX>-detail.md` and `srs-mod<XX>-wireframe.md` to fill in any missing details for each FEA.
3. Generate a complete SRS document using **`.specify/templates/srs-template.md`** as the base template. Follow the section mapping in **SRS Output Structure** below to populate each template section with module-specific content. 3. Generate a complete SRS document using **`packages/casan-harness/templates/srs-template.md`** as the base template. Follow the section mapping in **SRS Output Structure** below to populate each template section with module-specific content.
> ⚠️ **MANDATORY: TABLE OF CONTENTS** — The SRS document **MUST** include a `## TABLE OF CONTENTS` section immediately after the `Record of Change` table (before §1). Generate a complete, clickable table of contents listing all `##` and `###` level headings with Markdown anchor links. This matches the structure in `srs-template.md`. Do NOT skip this section. > ⚠️ **MANDATORY: TABLE OF CONTENTS** — The SRS document **MUST** include a `## TABLE OF CONTENTS` section immediately after the `Record of Change` table (before §1). Generate a complete, clickable table of contents listing all `##` and `###` level headings with Markdown anchor links. This matches the structure in `srs-template.md`. Do NOT skip this section.
4. Save to `docs/output/ipa-docs/srs/srs-<MOD-ID>-<module-short-name>.md`. 4. Save to `docs/output/ipa-docs/srs/srs-<MOD-ID>-<module-short-name>.md`.
Example: MOD-01 (OKR management module) → `docs/output/ipa-docs/srs/srs-mod01-okr-management.md` Example: MOD-01 (OKR management module) → `docs/output/ipa-docs/srs/srs-mod01-okr-management.md`
@@ -94,7 +94,7 @@ Priority rule: `srs-overview-system.md` → `srs-mod<XX>-detail.md` → `srs-mod
## SRS Output Structure ## SRS Output Structure
Start from a copy of **`.specify/templates/srs-template.md`** and populate every section as follows. Start from a copy of **`packages/casan-harness/templates/srs-template.md`** and populate every section as follows.
**File header** — replace placeholders: **File header** — replace placeholders:
.claude/agents/okr.srsallsystem.md
+1 -1
View File
@@ -39,7 +39,7 @@ Mission: produce a **complete, exhaustive, system-wide SRS** covering all module
If `$ARGUMENTS` specifies a file or folder path, **read that path first** as the primary source. Otherwise, read in this priority order and cross-reference: If `$ARGUMENTS` specifies a file or folder path, **read that path first** as the primary source. Otherwise, read in this priority order and cross-reference:
1. **`docs/input/okr-requirement.md`** — Original product requirement document. **Primary source of truth.** Contains functional requirements, screen definitions, field rules, user flows, and validation constraints. 1. **`apps/okr/domain/input/okr-requirement.md`** — Original product requirement document. **Primary source of truth.** Contains functional requirements, screen definitions, field rules, user flows, and validation constraints.
2. **`docs/technical_architecture.md`** — Technology stack recommendations. Use for the technology recommendation section only (not for functional requirements). 2. **`docs/technical_architecture.md`** — Technology stack recommendations. Use for the technology recommendation section only (not for functional requirements).
**Priority rule:** User-specified input (`$ARGUMENTS`) → Special Specification (Spec) → system-overview.md → `[TBC-XX]` if all are insufficient. **Priority rule:** User-specified input (`$ARGUMENTS`) → Special Specification (Spec) → system-overview.md → `[TBC-XX]` if all are insufficient.
.claude/agents/okr.testkit.md
+7 -7
View File
@@ -29,7 +29,7 @@ You are the **Independent QA Agent (okr.testkit)** for OKR web app. Your role is
**Output:** **Output:**
- `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` — Comprehensive test case document - `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` — Comprehensive test case document
**Template:** `.specify/templates/testcase-template.md` — Use this template for the output format. Fill in all sections with actual test cases generated from the input documents. **Template:** `packages/casan-harness/templates/testcase-template.md` — Use this template for the output format. Fill in all sections with actual test cases generated from the input documents.
**Process:** **Process:**
@@ -43,11 +43,11 @@ You are the **Independent QA Agent (okr.testkit)** for OKR web app. Your role is
- **API Tests (AT)** — From DD internal API contracts + BD external interface → Jest + Supertest - **API Tests (AT)** — From DD internal API contracts + BD external interface → Jest + Supertest
- **UI/E2E Tests (E2E)** — From BD screen designs + SRS user flows → Playwright - **UI/E2E Tests (E2E)** — From BD screen designs + SRS user flows → Playwright
- **Integration Tests (IT)** — From DD sequence diagrams + data flow → testcontainers-node - **Integration Tests (IT)** — From DD sequence diagrams + data flow → testcontainers-node
4. **Write test case document** using template `.specify/templates/testcase-template.md` to `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` with full traceability 4. **Write test case document** using template `packages/casan-harness/templates/testcase-template.md` to `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` with full traceability
#### Test Case Output #### Test Case Output
The output file MUST follow the template at `.specify/templates/testcase-template.md`. Key sections: The output file MUST follow the template at `packages/casan-harness/templates/testcase-template.md`. Key sections:
- **§1 Unit Tests (UT)** — From DD class/method designs → Jest - **§1 Unit Tests (UT)** — From DD class/method designs → Jest
- **§2 API Tests (AT)** — From DD internal API contracts + BD external interface → Jest + Supertest - **§2 API Tests (AT)** — From DD internal API contracts + BD external interface → Jest + Supertest
- **§3 UI/E2E Tests (E2E)** — From BD screen designs + SRS user flows → Playwright - **§3 UI/E2E Tests (E2E)** — From BD screen designs + SRS user flows → Playwright
@@ -59,7 +59,7 @@ The template contains embedded generation rules (HTML comments) for each section
#### ⛔ MANDATORY TABLE FORMAT — STRICTLY ENFORCED #### ⛔ MANDATORY TABLE FORMAT — STRICTLY ENFORCED
Each section (UT, AT, E2E, IT) MUST be output as **one single consolidated master table** per section, exactly matching the column structure shown in the template `.specify/templates/testcase-template.md`. Each section (UT, AT, E2E, IT) MUST be output as **one single consolidated master table** per section, exactly matching the column structure shown in the template `packages/casan-harness/templates/testcase-template.md`.
**⛔ PROHIBITED formats (DO NOT USE):** **⛔ PROHIBITED formats (DO NOT USE):**
- Individual `| Item | Content |` two-column tables for each test case - Individual `| Item | Content |` two-column tables for each test case
@@ -162,10 +162,10 @@ Each section (UT, AT, E2E, IT) MUST be output as **one single consolidated maste
8. **Write test execution summary report** to `docs/output/output_logs/<feature-id>/reports/<NN>-testkit-report.md`: 8. **Write test execution summary report** to `docs/output/output_logs/<feature-id>/reports/<NN>-testkit-report.md`:
**Template:** `.specify/templates/testreport-template.md` — Load this template and fill in all sections with actual test execution results. **Template:** `packages/casan-harness/templates/testreport-template.md` — Load this template and fill in all sections with actual test execution results.
**Process:** **Process:**
1. Read the template file: `.specify/templates/testreport-template.md` 1. Read the template file: `packages/casan-harness/templates/testreport-template.md`
2. Read `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` and extract ALL TC-IDs from master tables. **Same rules as Phase D apply: exact TC-IDs, zero omissions, all 4 sections mandatory.** 2. Read `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` and extract ALL TC-IDs from master tables. **Same rules as Phase D apply: exact TC-IDs, zero omissions, all 4 sections mandatory.**
3. Fill in all placeholders with actual test execution data: 3. Fill in all placeholders with actual test execution data:
- §1 Test Execution Summary — aggregate pass/fail/skip counts from Phase B - §1 Test Execution Summary — aggregate pass/fail/skip counts from Phase B
@@ -294,7 +294,7 @@ Code (TypeScript/JavaScript test scripts) and file paths remain in English.
This agent is invoked by the Boss orchestrator at two specific points: This agent is invoked by the Boss orchestrator at two specific points:
1. **STEP 8b** (after DD): `gen-testcases <feature-id>` → produces `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` using template `.specify/templates/testcase-template.md` 1. **STEP 8b** (after DD): `gen-testcases <feature-id>` → produces `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` using template `packages/casan-harness/templates/testcase-template.md`
2. **STEP 12** (after build, FINAL QA AUDIT): `run-tests <feature-id>` → produces test scripts + executes + produces: 2. **STEP 12** (after build, FINAL QA AUDIT): `run-tests <feature-id>` → produces test scripts + executes + produces:
- Pipeline report: `docs/output/output_logs/<feature-id>/reports/<NN>-testkit-report.md` (Phase C) - Pipeline report: `docs/output/output_logs/<feature-id>/reports/<NN>-testkit-report.md` (Phase C)
- IPA detail report: `docs/output/ipa-docs/testreport/testreport-<MOD-ID>-<module-short-name>.md` (Phase D) - IPA detail report: `docs/output/ipa-docs/testreport/testreport-<MOD-ID>-<module-short-name>.md` (Phase D)
.claude/agents/protocols/casan-harness-protocol.md
+10 -10
View File
@@ -10,38 +10,38 @@ Raise the SDD Speckit OKR pipeline from CASAN Level 3 to Level 4 by making Secur
| Harness | Runtime control | Script | Evidence | | Harness | Runtime control | Script | Evidence |
|---|---|---|---| |---|---|---|---|
| H4 Security | Prompt injection block, PII masking, secret redaction, output filtering | `.specify/scripts/bash/security-check.sh` | `.specify/logs/trace/security-*.json`, `.specify/logs/audit/security.jsonl` | | H4 Security | Prompt injection block, PII masking, secret redaction, output filtering | `packages/casan-harness/scripts/bash/security-check.sh` | `.specify/logs/trace/security-*.json`, `.specify/logs/audit/security.jsonl` |
| H5 Governance | Risk scoring, non-interactive approval policy, append-only hash-chain audit | `.specify/scripts/bash/governance-check.sh` | `.specify/logs/trace/governance-*.json`, `.specify/logs/audit/audit.jsonl` | | H5 Governance | Risk scoring, non-interactive approval policy, append-only hash-chain audit | `packages/casan-harness/scripts/bash/governance-check.sh` | `.specify/logs/trace/governance-*.json`, `.specify/logs/audit/audit.jsonl` |
| H6 AgentOps | Latency, retry, token, cost, status, alert tracking | `.specify/scripts/bash/agent-metrics.sh` | `.specify/logs/trace/agentops-*.json`, `.specify/logs/cost/metrics.jsonl`, `.specify/agentops/alerts.log` | | H6 AgentOps | Latency, retry, token, cost, status, alert tracking | `packages/casan-harness/scripts/bash/agent-metrics.sh` | `.specify/logs/trace/agentops-*.json`, `.specify/logs/cost/metrics.jsonl`, `.specify/agentops/alerts.log` |
| H2 Tool Registry | Side-effect registry, idempotency key, per-call audit | `.specify/scripts/bash/tool-registry-gate.sh` | `.specify/logs/level5/tool-registry.jsonl`, `.specify/logs/audit/tool-calls.jsonl` | | H2 Tool Registry | Side-effect registry, idempotency key, per-call audit | `packages/casan-harness/scripts/bash/tool-registry-gate.sh` | `.specify/logs/level5/tool-registry.jsonl`, `.specify/logs/audit/tool-calls.jsonl` |
## Mandatory Gate Pattern ## Mandatory Gate Pattern
Before every delegated step: Before every delegated step:
```bash ```bash
.specify/scripts/bash/security-check.sh "$STEP_INPUT" "$SAFE_INPUT" input packages/casan-harness/scripts/bash/security-check.sh "$STEP_INPUT" "$SAFE_INPUT" input
.specify/scripts/bash/governance-check.sh "$SAFE_INPUT" "$APPROVED_INPUT" "$ACTION_NAME" packages/casan-harness/scripts/bash/governance-check.sh "$SAFE_INPUT" "$APPROVED_INPUT" "$ACTION_NAME"
``` ```
Around every execution or agent/tool invocation: Around every execution or agent/tool invocation:
```bash ```bash
CASAN_AGENT_NAME="<agent>" CASAN_STEP_NAME="<step>" \ CASAN_AGENT_NAME="<agent>" CASAN_STEP_NAME="<step>" \
.specify/scripts/bash/agent-metrics.sh "$APPROVED_INPUT" "$RAW_OUTPUT" -- <real command> packages/casan-harness/scripts/bash/agent-metrics.sh "$APPROVED_INPUT" "$RAW_OUTPUT" -- <real command>
``` ```
After every generated artifact or agent response: After every generated artifact or agent response:
```bash ```bash
.specify/scripts/bash/security-check.sh "$RAW_OUTPUT" "$FINAL_OUTPUT" output packages/casan-harness/scripts/bash/security-check.sh "$RAW_OUTPUT" "$FINAL_OUTPUT" output
``` ```
When a step can be represented as a single command, Boss MAY use the wrapper: When a step can be represented as a single command, Boss MAY use the wrapper:
```bash ```bash
CASAN_AGENT_NAME="<agent>" CASAN_STEP_NAME="<step>" \ CASAN_AGENT_NAME="<agent>" CASAN_STEP_NAME="<step>" \
.specify/scripts/bash/casan-harness.sh "$STEP_INPUT" "$FINAL_OUTPUT" "$ACTION_NAME" -- <real command> packages/casan-harness/scripts/bash/casan-harness.sh "$STEP_INPUT" "$FINAL_OUTPUT" "$ACTION_NAME" -- <real command>
``` ```
Cache hits MUST NOT bypass CASAN evidence. A cached wrapper run still has to produce fresh H4 input, H5 governance, H6 metrics, and H4 output traces for the current execution. Cache hits MUST NOT bypass CASAN evidence. A cached wrapper run still has to produce fresh H4 input, H5 governance, H6 metrics, and H4 output traces for the current execution.
@@ -105,4 +105,4 @@ Boss orchestrator also enforces:
1. **Self-Security Audit:** Every agent reads `protocols/agent-self-security-rules.md` before output is accepted. 1. **Self-Security Audit:** Every agent reads `protocols/agent-self-security-rules.md` before output is accepted.
2. **Self-Governance Audit:** Every agent reads `protocols/governance-risk-policy.md` before high-risk action planning. 2. **Self-Governance Audit:** Every agent reads `protocols/governance-risk-policy.md` before high-risk action planning.
3. **Hallucination Checklist:** Every review agent reads `protocols/hallucination-prevention-checklist.md` during review gates. 3. **Hallucination Checklist:** Every review agent reads `protocols/hallucination-prevention-checklist.md` during review gates.
4. **Tool Registry Policy:** Every side-effecting tool is checked against `protocols/tool-registry-policy.md` and `.specify/level5/tool-registry.yaml`. 4. **Tool Registry Policy:** Every side-effecting tool is checked against `protocols/tool-registry-policy.md` and `packages/casan-harness/level5/tool-registry.yaml`.
.claude/agents/protocols/hallucination-prevention-checklist.md
+1 -1
View File
@@ -4,7 +4,7 @@ Giao thức này cung cấp bộ checklist bắt buộc để các Review Agents
## 1. Nguyên lý đối chiếu chéo (Grounding) ## 1. Nguyên lý đối chiếu chéo (Grounding)
- Không có bất kỳ chi tiết thiết kế hoặc logic code nào được phép tự ý phát minh nếu không có cơ sở chứng cứ rõ ràng từ: - Không có bất kỳ chi tiết thiết kế hoặc logic code nào được phép tự ý phát minh nếu không có cơ sở chứng cứ rõ ràng từ:
- Tài liệu Yêu cầu nghiệp vụ (`docs/input/okr-requirement.md`). - Tài liệu Yêu cầu nghiệp vụ (`apps/okr/domain/input/okr-requirement.md`).
- Bản vẽ thiết kế Basic Design (`bd-*.md`) hoặc Detail Design (`dd-*.md`). - Bản vẽ thiết kế Basic Design (`bd-*.md`) hoặc Detail Design (`dd-*.md`).
- Tệp thông tin Context hiện tại (`pipeline-context.yaml`). - Tệp thông tin Context hiện tại (`pipeline-context.yaml`).
.claude/agents/protocols/pipeline-context.md
+6 -6
View File
@@ -32,22 +32,22 @@ tech-stack:
casan-harness: casan-harness:
level-target: 5 level-target: 5
h4-security: h4-security:
policy: .specify/security/prompt-filter.yaml policy: packages/casan-harness/security/prompt-filter.yaml
output-policy: .specify/security/output-policy.yaml output-policy: packages/casan-harness/security/output-policy.yaml
audit-log: .specify/logs/audit/security.jsonl audit-log: .specify/logs/audit/security.jsonl
h5-governance: h5-governance:
approval-flow: .specify/governance/approval-flow.yaml approval-flow: packages/casan-harness/governance/approval-flow.yaml
risk-registry: .specify/governance/risk-registry.yaml risk-registry: packages/casan-harness/governance/risk-registry.yaml
audit-log: .specify/logs/audit/audit.jsonl audit-log: .specify/logs/audit/audit.jsonl
h6-agentops: h6-agentops:
metrics-policy: .specify/agentops/metrics.yaml metrics-policy: .specify/agentops/metrics.yaml
metrics-log: .specify/logs/cost/metrics.jsonl metrics-log: .specify/logs/cost/metrics.jsonl
alert-log: .specify/agentops/alerts.log alert-log: .specify/agentops/alerts.log
h2-tool-registry: h2-tool-registry:
registry: .specify/level5/tool-registry.yaml registry: packages/casan-harness/level5/tool-registry.yaml
audit-log: .specify/logs/level5/tool-registry.jsonl audit-log: .specify/logs/level5/tool-registry.jsonl
h7-drift: h7-drift:
golden-dir: .specify/level5/golden-runs/ golden-dir: apps/okr/domain/golden-runs/
drift-log: .specify/logs/level5/drift.jsonl drift-log: .specify/logs/level5/drift.jsonl
rollback: rollback:
transactions-log: .specify/logs/level5/rollback-transactions.jsonl transactions-log: .specify/logs/level5/rollback-transactions.jsonl
.claude/agents/protocols/tool-registry-policy.md
+1 -1
View File
@@ -7,7 +7,7 @@ Giao thức này quy định danh sách trắng các công cụ và câu lệnh
### A. Boss Orchestrator (okr.bossbuiltin) ### A. Boss Orchestrator (okr.bossbuiltin)
Được phép điều phối và chạy toàn bộ các chuỗi công cụ chuẩn bị và kiểm thử: Được phép điều phối và chạy toàn bộ các chuỗi công cụ chuẩn bị và kiểm thử:
- `Read`, `Write`, `Edit`, `Glob`, `Grep` (IDE Tools) - `Read`, `Write`, `Edit`, `Glob`, `Grep` (IDE Tools)
- Các script hỗ trợ: `.specify/scripts/bash/casan-harness.sh`, `security-check.sh`, `governance-check.sh`, `agent-metrics.sh` - Các script hỗ trợ: `packages/casan-harness/scripts/bash/casan-harness.sh`, `security-check.sh`, `governance-check.sh`, `agent-metrics.sh`
- CLI Commands: `npm install`, `npm run build`, `npm run start:dev`, `docker compose` - CLI Commands: `npm install`, `npm run build`, `npm run start:dev`, `docker compose`
### B. Special Design/Specification Agents (srs, bd, specify, plan, dd, tasks) ### B. Special Design/Specification Agents (srs, bd, specify, plan, dd, tasks)
.claude/agents/speckit.analyze.md
+3 -3
View File
@@ -26,13 +26,13 @@ Identify inconsistencies, duplications, ambiguities, and underspecified items ac
**STRICTLY READ-ONLY**: Do **not** modify any files. Output a structured analysis report. Offer an optional remediation plan (user must explicitly approve before any follow-up editing commands would be invoked manually). **STRICTLY READ-ONLY**: Do **not** modify any files. Output a structured analysis report. Offer an optional remediation plan (user must explicitly approve before any follow-up editing commands would be invoked manually).
**Constitution Authority**: The project constitution (`.specify/memory/constitution.md`) is **non-negotiable** within this analysis scope. Constitution conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle. If a principle itself needs to change, that must occur in a separate, explicit constitution update outside `/speckit.analyze`. **Constitution Authority**: The project constitution (`packages/casan-harness/memory/constitution.md`) is **non-negotiable** within this analysis scope. Constitution conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle. If a principle itself needs to change, that must occur in a separate, explicit constitution update outside `/speckit.analyze`.
## Execution Steps ## Execution Steps
### 1. Initialize Analysis Context ### 1. Initialize Analysis Context
Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks` once from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive absolute paths: Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks` once from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive absolute paths:
- SPEC = FEATURE_DIR/spec.md - SPEC = FEATURE_DIR/spec.md
- PLAN = FEATURE_DIR/plan.md - PLAN = FEATURE_DIR/plan.md
@@ -70,7 +70,7 @@ Load only the minimal necessary context from each artifact:
**From constitution:** **From constitution:**
- Load `.specify/memory/constitution.md` for principle validation - Load `packages/casan-harness/memory/constitution.md` for principle validation
### 3. Build Semantic Models ### 3. Build Semantic Models
.claude/agents/speckit.checklist.md
+2 -2
View File
@@ -41,7 +41,7 @@ You **MUST** consider the user input before proceeding (if not empty).
## Execution Steps ## Execution Steps
1. **Setup**: Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json` from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS list. 1. **Setup**: Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json` from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS list.
- All file paths must be absolute. - All file paths must be absolute.
- For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). - For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
@@ -212,7 +212,7 @@ You **MUST** consider the user input before proceeding (if not empty).
- ✅ "Are [edge cases/scenarios] addressed in requirements?" - ✅ "Are [edge cases/scenarios] addressed in requirements?"
- ✅ "Does the spec define [missing aspect]?" - ✅ "Does the spec define [missing aspect]?"
6. **Structure Reference**: Generate the checklist following the canonical template in `.specify/templates/checklist-template.md` for title, meta section, category headings, and ID formatting. If template is unavailable, use: H1 title, purpose/created meta lines, `##` category sections containing `- [ ] CHK### <requirement item>` lines with globally incrementing IDs starting at CHK001. 6. **Structure Reference**: Generate the checklist following the canonical template in `packages/casan-harness/templates/checklist-template.md` for title, meta section, category headings, and ID formatting. If template is unavailable, use: H1 title, purpose/created meta lines, `##` category sections containing `- [ ] CHK### <requirement item>` lines with globally incrementing IDs starting at CHK001.
7. **Report**: Output full path to checklist file, item count, and summarize whether the run created a new file or appended to an existing one. Summarize: 7. **Report**: Output full path to checklist file, item count, and summarize whether the run created a new file or appended to an existing one. Summarize:
- Focus areas selected - Focus areas selected
.claude/agents/speckit.clarify.md
+1 -1
View File
@@ -58,7 +58,7 @@ Note: This clarification workflow is expected to run (and be completed) BEFORE i
Execution steps: Execution steps:
1. Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` from repo root **once** (combined `--json --paths-only` mode / `-Json -PathsOnly`). Parse minimal JSON payload fields: 1. Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` from repo root **once** (combined `--json --paths-only` mode / `-Json -PathsOnly`). Parse minimal JSON payload fields:
- `FEATURE_DIR` - `FEATURE_DIR`
- `FEATURE_SPEC` - `FEATURE_SPEC`
- (Optionally capture `IMPL_PLAN`, `TASKS` for future chained flows.) - (Optionally capture `IMPL_PLAN`, `TASKS` for future chained flows.)
.claude/agents/speckit.constitution.md
+9 -9
View File
@@ -20,13 +20,13 @@ You **MUST** consider the user input before proceeding (if not empty).
## Outline ## Outline
You are updating the project constitution at `.specify/memory/constitution.md`. This file is a TEMPLATE containing placeholder tokens in square brackets (e.g. `[PROJECT_NAME]`, `[PRINCIPLE_1_NAME]`). Your job is to (a) collect/derive concrete values, (b) fill the template precisely, and (c) propagate any amendments across dependent artifacts. You are updating the project constitution at `packages/casan-harness/memory/constitution.md`. This file is a TEMPLATE containing placeholder tokens in square brackets (e.g. `[PROJECT_NAME]`, `[PRINCIPLE_1_NAME]`). Your job is to (a) collect/derive concrete values, (b) fill the template precisely, and (c) propagate any amendments across dependent artifacts.
**Note**: If `.specify/memory/constitution.md` does not exist yet, it should have been initialized from `.specify/templates/constitution-template.md` during project setup. If it's missing, copy the template first. **Note**: If `packages/casan-harness/memory/constitution.md` does not exist yet, it should have been initialized from `packages/casan-harness/templates/constitution-template.md` during project setup. If it's missing, copy the template first.
Follow this execution flow: Follow this execution flow:
1. Load the existing constitution at `.specify/memory/constitution.md`. 1. Load the existing constitution at `packages/casan-harness/memory/constitution.md`.
- Identify every placeholder token of the form `[ALL_CAPS_IDENTIFIER]`. - Identify every placeholder token of the form `[ALL_CAPS_IDENTIFIER]`.
**IMPORTANT**: The user might require less or more principles than the ones used in the template. If a number is specified, respect that - follow the general template. You will update the doc accordingly. **IMPORTANT**: The user might require less or more principles than the ones used in the template. If a number is specified, respect that - follow the general template. You will update the doc accordingly.
@@ -47,10 +47,10 @@ Follow this execution flow:
- Ensure Governance section lists amendment procedure, versioning policy, and compliance review expectations. - Ensure Governance section lists amendment procedure, versioning policy, and compliance review expectations.
4. Consistency propagation checklist (convert prior checklist into active validations): 4. Consistency propagation checklist (convert prior checklist into active validations):
- Read `.specify/templates/plan-template.md` and ensure any "Constitution Check" or rules align with updated principles. - Read `packages/casan-harness/templates/plan-template.md` and ensure any "Constitution Check" or rules align with updated principles.
- Read `.specify/templates/spec-template.md` for scope/requirements alignment—update if constitution adds/removes mandatory sections or constraints. - Read `packages/casan-harness/templates/spec-template.md` for scope/requirements alignment—update if constitution adds/removes mandatory sections or constraints.
- Read `.specify/templates/tasks-template.md` and ensure task categorization reflects new or removed principle-driven task types (e.g., observability, versioning, testing discipline). - Read `packages/casan-harness/templates/tasks-template.md` and ensure task categorization reflects new or removed principle-driven task types (e.g., observability, versioning, testing discipline).
- Read each command file in `.specify/templates/commands/*.md` (including this one) to verify no outdated references (agent-specific names like CLAUDE only) remain when generic guidance is required. - Read each command file in `packages/casan-harness/templates/commands/*.md` (including this one) to verify no outdated references (agent-specific names like CLAUDE only) remain when generic guidance is required.
- Read any runtime guidance docs (e.g., `README.md`, `docs/quickstart.md`, or agent-specific guidance files if present). Update references to principles changed. - Read any runtime guidance docs (e.g., `README.md`, `docs/quickstart.md`, or agent-specific guidance files if present). Update references to principles changed.
5. Produce a Sync Impact Report (prepend as an HTML comment at top of the constitution file after update): 5. Produce a Sync Impact Report (prepend as an HTML comment at top of the constitution file after update):
@@ -67,7 +67,7 @@ Follow this execution flow:
- Dates ISO format YYYY-MM-DD. - Dates ISO format YYYY-MM-DD.
- Principles are declarative, testable, and free of vague language ("should" → replace with MUST/SHOULD rationale where appropriate). - Principles are declarative, testable, and free of vague language ("should" → replace with MUST/SHOULD rationale where appropriate).
7. Write the completed constitution back to `.specify/memory/constitution.md` (overwrite). 7. Write the completed constitution back to `packages/casan-harness/memory/constitution.md` (overwrite).
8. Output a final summary to the user with: 8. Output a final summary to the user with:
- New version and bump rationale. - New version and bump rationale.
@@ -85,4 +85,4 @@ If the user supplies partial updates (e.g., only one principle revision), still
If critical info missing (e.g., ratification date truly unknown), insert `TODO(<FIELD_NAME>): explanation` and include in the Sync Impact Report under deferred items. If critical info missing (e.g., ratification date truly unknown), insert `TODO(<FIELD_NAME>): explanation` and include in the Sync Impact Report under deferred items.
Do not create a new template; always operate on the existing `.specify/memory/constitution.md` file. Do not create a new template; always operate on the existing `packages/casan-harness/memory/constitution.md` file.
.claude/agents/speckit.implement.md
+1 -1
View File
@@ -60,7 +60,7 @@ You **MUST** consider the user input before proceeding (if not empty).
## Outline ## Outline
1. Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). 1. Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
2. **Check checklists status** (if FEATURE_DIR/checklists/ exists): 2. **Check checklists status** (if FEATURE_DIR/checklists/ exists):
- Scan all checklist files in the checklists/ directory - Scan all checklist files in the checklists/ directory
.claude/agents/speckit.plan.md
+3 -3
View File
@@ -51,9 +51,9 @@ You **MUST** consider the user input before proceeding (if not empty).
## Outline ## Outline
1. **Setup**: Run `.specify/scripts/powershell/setup-plan.ps1 -Json` from repo root and parse JSON for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). 1. **Setup**: Run `packages/casan-harness/scripts/powershell/setup-plan.ps1 -Json` from repo root and parse JSON for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
2. **Load context**: Read FEATURE_SPEC and `.specify/memory/constitution.md`. Load IMPL_PLAN template (already copied). 2. **Load context**: Read FEATURE_SPEC and `packages/casan-harness/memory/constitution.md`. Load IMPL_PLAN template (already copied).
3. **Execute plan workflow**: Follow the structure in IMPL_PLAN template to: 3. **Execute plan workflow**: Follow the structure in IMPL_PLAN template to:
- Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION") - Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION")
@@ -114,7 +114,7 @@ Technical IDs remain unchanged.
- Skip if project is purely internal (build scripts, one-off tools, etc.) - Skip if project is purely internal (build scripts, one-off tools, etc.)
3. **Agent context update**: 3. **Agent context update**:
- Run `.specify/scripts/powershell/update-agent-context.ps1 -AgentType copilot` - Run `packages/casan-harness/scripts/powershell/update-agent-context.ps1 -AgentType copilot`
- These scripts detect which AI agent is in use - These scripts detect which AI agent is in use
- Update the appropriate agent-specific context file - Update the appropriate agent-specific context file
- Add only new technology from current plan - Add only new technology from current plan
.claude/agents/speckit.specify.md
+4 -4
View File
@@ -107,10 +107,10 @@ Given that feature description, do this:
- Find the highest number N - Find the highest number N
- Use N+1 for the new branch number - Use N+1 for the new branch number
g. Run the script `.specify/scripts/powershell/create-new-feature.ps1 -Json "$ARGUMENTS"` with the calculated number and short-name: g. Run the script `packages/casan-harness/scripts/powershell/create-new-feature.ps1 -Json "$ARGUMENTS"` with the calculated number and short-name:
- Pass `--number N+1` and `--short-name "your-short-name"` along with the feature description - Pass `--number N+1` and `--short-name "your-short-name"` along with the feature description
- Bash example: `.specify/scripts/powershell/create-new-feature.ps1 -Json "$ARGUMENTS" --json --number 5 --short-name "user-auth" "Add user authentication"` - Bash example: `packages/casan-harness/scripts/powershell/create-new-feature.ps1 -Json "$ARGUMENTS" --json --number 5 --short-name "user-auth" "Add user authentication"`
- PowerShell example: `.specify/scripts/powershell/create-new-feature.ps1 -Json "$ARGUMENTS" -Json -Number 5 -ShortName "user-auth" "Add user authentication"` - PowerShell example: `packages/casan-harness/scripts/powershell/create-new-feature.ps1 -Json "$ARGUMENTS" -Json -Number 5 -ShortName "user-auth" "Add user authentication"`
**IMPORTANT**: **IMPORTANT**:
- Check all three sources (remote branches, local branches, specs directories) to find the highest number - Check all three sources (remote branches, local branches, specs directories) to find the highest number
@@ -121,7 +121,7 @@ Given that feature description, do this:
- The JSON output will contain BRANCH_NAME and SPEC_FILE paths - The JSON output will contain BRANCH_NAME and SPEC_FILE paths
- For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot") - For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot")
3. Load `.specify/templates/spec-template.md` to understand required sections. 3. Load `packages/casan-harness/templates/spec-template.md` to understand required sections.
4. Follow this execution flow: 4. Follow this execution flow:
.claude/agents/speckit.tasks.md
+2 -2
View File
@@ -51,7 +51,7 @@ You **MUST** consider the user input before proceeding (if not empty).
## Outline ## Outline
1. **Setup**: Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). 1. **Setup**: Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
2. **Load design documents**: Read from FEATURE_DIR: 2. **Load design documents**: Read from FEATURE_DIR:
- **Required**: plan.md (tech stack, libraries, structure), spec.md (user stories with priorities) - **Required**: plan.md (tech stack, libraries, structure), spec.md (user stories with priorities)
@@ -69,7 +69,7 @@ You **MUST** consider the user input before proceeding (if not empty).
- Create parallel execution examples per user story - Create parallel execution examples per user story
- Validate task completeness (each user story has all needed tasks, independently testable) - Validate task completeness (each user story has all needed tasks, independently testable)
4. **Generate tasks.md**: Use `.specify/templates/tasks-template.md` as structure, fill with: 4. **Generate tasks.md**: Use `packages/casan-harness/templates/tasks-template.md` as structure, fill with:
**Output Language**: Produce `tasks.md` in Vietnamese. Technical IDs (T001, [US1], [P], etc.) remain unchanged. **Output Language**: Produce `tasks.md` in Vietnamese. Technical IDs (T001, [US1], [P], etc.) remain unchanged.
- Correct feature name from plan.md - Correct feature name from plan.md
.claude/agents/speckit.taskstoissues.md
+1 -1
View File
@@ -21,7 +21,7 @@ You **MUST** consider the user input before proceeding (if not empty).
## Outline ## Outline
1. Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). 1. Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
1. From the executed script, extract the path to **tasks**. 1. From the executed script, extract the path to **tasks**.
1. Get the Git remote by running: 1. Get the Git remote by running:
.gitea/vault-setup-runbook.md
+1 -1
View File
@@ -148,7 +148,7 @@ From macOS with the project checked out:
export VAULT_ADDR=http://161.33.139.73:8200 export VAULT_ADDR=http://161.33.139.73:8200
export VAULT_TOKEN=<TOKEN> export VAULT_TOKEN=<TOKEN>
cd Output_CASAN5_REFINED # repo root (app promoted from AINative_OKR_CASAN5/) cd Output_CASAN5_REFINED # repo root (app promoted from )
# Test sign-policy-bundle with Vault # Test sign-policy-bundle with Vault
bash packages/casan-harness/scripts/bash/sign-policy-bundle.sh sign bash packages/casan-harness/scripts/bash/sign-policy-bundle.sh sign
.gitea/vps-setup-runbook.md
+1 -1
View File
@@ -162,7 +162,7 @@ On the VPS (or via Gitea web UI), create a new repository:
On your local machine: On your local machine:
```bash ```bash
cd Output_CASAN5_REFINED # repo root (app promoted from AINative_OKR_CASAN5/) cd Output_CASAN5_REFINED # repo root (app promoted from )
# Add Gitea as remote # Add Gitea as remote
git remote add gitea ssh://git@161.33.139.73:2222/<YOUR_USER>/casan5.git git remote add gitea ssh://git@161.33.139.73:2222/<YOUR_USER>/casan5.git
.github/agents/copilot-instructions.md
+2 -2
View File
@@ -8,7 +8,7 @@ You are an expert full-stack developer specializing in NestJS and a **master of
- **Architecture:** Refer to `docs/technical_architecture.md` for the overall system design, module responsibilities, and technology stack. - **Architecture:** Refer to `docs/technical_architecture.md` for the overall system design, module responsibilities, and technology stack.
- **Requirements:** Refer to `docs/input/okr-requirement.md` for functional requirements, use cases, and UI mockups. - **Requirements:** Refer to `apps/okr/domain/input/okr-requirement.md` for functional requirements, use cases, and UI mockups.
- **Your Task:** Your role is to translate these designs into code, not to be creative. - **Your Task:** Your role is to translate these designs into code, not to be creative.
@@ -63,7 +63,7 @@ You are an expert full-stack developer specializing in NestJS and a **master of
**Design Style: Clean Modern Dashboard (Pure Tailwind CSS)** **Design Style: Clean Modern Dashboard (Pure Tailwind CSS)**
This project uses **pure Tailwind CSS** — no external component library (no MUI, no Ant Design). The design is clean, professional, and matches the OKR dashboard wireframes defined in `docs/input/okr-requirement.md`. This project uses **pure Tailwind CSS** — no external component library (no MUI, no Ant Design). The design is clean, professional, and matches the OKR dashboard wireframes defined in `apps/okr/domain/input/okr-requirement.md`.
### Layout Structure (matches OKR wireframes): ### Layout Structure (matches OKR wireframes):
.github/agents/okr.bd.agent.md
+3 -3
View File
@@ -49,7 +49,7 @@ Read the following files to gather context:
2. **System overview**: `docs/output/srs-systems/srs-overview-system.md` — system-wide context 2. **System overview**: `docs/output/srs-systems/srs-overview-system.md` — system-wide context
3. **Module SRS folder**: `docs/output/srs-systems/<mod-folder>/` — module wireframes & details 3. **Module SRS folder**: `docs/output/srs-systems/<mod-folder>/` — module wireframes & details
4. **Technical architecture**: `docs/technical_architecture.md` — mandatory tech stack 4. **Technical architecture**: `docs/technical_architecture.md` — mandatory tech stack
5. **BD template**: `.specify/templates/bd-template.md` — output structure template 5. **BD template**: `packages/casan-harness/templates/bd-template.md` — output structure template
--- ---
@@ -57,7 +57,7 @@ Read the following files to gather context:
Generate the BD document at: `docs/output/ipa-docs/bd/bd-<mod-id>-<name>.md` Generate the BD document at: `docs/output/ipa-docs/bd/bd-<mod-id>-<name>.md`
The output **MUST** follow the structure defined in `.specify/templates/bd-template.md`: The output **MUST** follow the structure defined in `packages/casan-harness/templates/bd-template.md`:
| § | Section | Content | | § | Section | Content |
|---|---------|---------| |---|---------|---------|
@@ -80,7 +80,7 @@ The output **MUST** follow the structure defined in `.specify/templates/bd-templ
2. Read `docs/output/srs-systems/srs-overview-system.md` for system context 2. Read `docs/output/srs-systems/srs-overview-system.md` for system context
3. Read module wireframe/detail files from `docs/output/srs-systems/<mod-folder>/` 3. Read module wireframe/detail files from `docs/output/srs-systems/<mod-folder>/`
4. Read `docs/technical_architecture.md` for tech stack constraints 4. Read `docs/technical_architecture.md` for tech stack constraints
5. Read `.specify/templates/bd-template.md` for the output template structure 5. Read `packages/casan-harness/templates/bd-template.md` for the output template structure
Log: `[PROCESSING] Input file loading complete` Log: `[PROCESSING] Input file loading complete`
.github/agents/okr.bossbuiltin.agent.md
+4 -4
View File
@@ -115,10 +115,10 @@ report-nn: <NN> # for speckit.implement only
report-phase: <phase> # for speckit.implement only report-phase: <phase> # for speckit.implement only
casan-harness: casan-harness:
required: true required: true
h4-security: ".specify/scripts/bash/security-check.sh" h4-security: "packages/casan-harness/scripts/bash/security-check.sh"
h5-governance: ".specify/scripts/bash/governance-check.sh" h5-governance: "packages/casan-harness/scripts/bash/governance-check.sh"
h6-agentops: ".specify/scripts/bash/agent-metrics.sh" h6-agentops: "packages/casan-harness/scripts/bash/agent-metrics.sh"
wrapper: ".specify/scripts/bash/casan-harness.sh" wrapper: "packages/casan-harness/scripts/bash/casan-harness.sh"
evidence: evidence:
trace-dir: ".specify/logs/trace" trace-dir: ".specify/logs/trace"
audit-log: ".specify/logs/audit/audit.jsonl" audit-log: ".specify/logs/audit/audit.jsonl"
.github/agents/okr.dd.agent.md
+3 -3
View File
@@ -54,7 +54,7 @@ Read the following files:
3. **Feature spec**: `specs/<feature-id>/spec.md` — feature specification 3. **Feature spec**: `specs/<feature-id>/spec.md` — feature specification
4. **Implementation plan**: `specs/<feature-id>/plan.md` — tech plan & data model 4. **Implementation plan**: `specs/<feature-id>/plan.md` — tech plan & data model
5. **Technical architecture**: `docs/technical_architecture.md` — mandatory tech stack 5. **Technical architecture**: `docs/technical_architecture.md` — mandatory tech stack
6. **DD template**: `.specify/templates/dd-template.md` — output structure template 6. **DD template**: `packages/casan-harness/templates/dd-template.md` — output structure template
--- ---
@@ -62,7 +62,7 @@ Read the following files:
Generate the DD document at: `docs/output/ipa-docs/dd/dd-<mod-id>-<name>.md` Generate the DD document at: `docs/output/ipa-docs/dd/dd-<mod-id>-<name>.md`
The output **MUST** follow the structure defined in `.specify/templates/dd-template.md`: The output **MUST** follow the structure defined in `packages/casan-harness/templates/dd-template.md`:
| § | Section | Content | | § | Section | Content |
|---|---------|---------| |---|---------|---------|
@@ -88,7 +88,7 @@ The output **MUST** follow the structure defined in `.specify/templates/dd-templ
2. Read SRS for requirements & NFR 2. Read SRS for requirements & NFR
3. Read spec.md and plan.md 3. Read spec.md and plan.md
4. Read `docs/technical_architecture.md` 4. Read `docs/technical_architecture.md`
5. Read `.specify/templates/dd-template.md` 5. Read `packages/casan-harness/templates/dd-template.md`
Log: `[PROCESSING] Input file loading complete` Log: `[PROCESSING] Input file loading complete`
.github/agents/okr.reviewcode.agent.md
+3 -3
View File
@@ -52,7 +52,7 @@ You are a Senior Code Reviewer specializing in Node.js/NestJS/TypeScript impleme
$ARGUMENTS $ARGUMENTS
``` ```
If `$ARGUMENTS` is empty, run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` to detect the current active feature. If `$ARGUMENTS` is empty, run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` to detect the current active feature.
## Constraints ## Constraints
@@ -82,7 +82,7 @@ Add a dedicated section in the report:
## Setup ## Setup
1. Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly -RequireTasks -IncludeTasks` and parse: 1. Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly -RequireTasks -IncludeTasks` and parse:
- `FEATURE_DIR` — feature specs directory - `FEATURE_DIR` — feature specs directory
- `AVAILABLE_DOCS` — list of generated artifacts - `AVAILABLE_DOCS` — list of generated artifacts
2. Load reference documents: 2. Load reference documents:
@@ -90,7 +90,7 @@ Add a dedicated section in the report:
- `specs/<feature-id>/tasks.md` — task completion checklist - `specs/<feature-id>/tasks.md` — task completion checklist
- `specs/<feature-id>/plan.md` — implementation plan - `specs/<feature-id>/plan.md` — implementation plan
- `specs/<feature-id>/data-model.md` — entity model - `specs/<feature-id>/data-model.md` — entity model
- `.specify/memory/constitution.md` — project Constitution - `packages/casan-harness/memory/constitution.md` — project Constitution
- `docs/technical_architecture.md` — system architecture - `docs/technical_architecture.md` — system architecture
3. Identify implementation module directory (e.g., `backend/src/modules/workspace/`) 3. Identify implementation module directory (e.g., `backend/src/modules/workspace/`)
.github/agents/okr.reviewplan.agent.md
+2 -2
View File
@@ -64,7 +64,7 @@ Optional: feature-id (e.g. `001-xxx`). If empty, auto-detect from the active bra
## Setup ## Setup
Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` from repo root and parse: Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` from repo root and parse:
- `FEATURE_DIR` — absolute path to the feature specs directory - `FEATURE_DIR` — absolute path to the feature specs directory
- `FEATURE_SPEC` — path to `spec.md` - `FEATURE_SPEC` — path to `spec.md`
@@ -75,7 +75,7 @@ Load the following documents:
- `specs/<feature-id>/contracts/` — API contracts (**warn** if missing) - `specs/<feature-id>/contracts/` — API contracts (**warn** if missing)
- `specs/<feature-id>/research.md` — library/framework decisions - `specs/<feature-id>/research.md` — library/framework decisions
- `specs/<feature-id>/quickstart.md` — integration scenarios - `specs/<feature-id>/quickstart.md` — integration scenarios
- `.specify/memory/constitution.md` — project Constitution - `packages/casan-harness/memory/constitution.md` — project Constitution
- `docs/technical_architecture.md` — system architecture - `docs/technical_architecture.md` — system architecture
--- ---
.github/agents/okr.reviewspec.agent.md
+2 -2
View File
@@ -61,7 +61,7 @@ Optional: feature-id (e.g. `001-xxx`). If empty, auto-detect from the active bra
## Setup ## Setup
Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` from repo root and parse: Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` from repo root and parse:
- `FEATURE_DIR` — absolute path to the feature specs directory - `FEATURE_DIR` — absolute path to the feature specs directory
- `FEATURE_SPEC` — path to `spec.md` - `FEATURE_SPEC` — path to `spec.md`
@@ -69,7 +69,7 @@ Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` from
Load the following reference documents: Load the following reference documents:
- `docs/output/srs-systems/srs-overview-system.md` — system-level SRS (traceability source) - `docs/output/srs-systems/srs-overview-system.md` — system-level SRS (traceability source)
- `docs/technical_architecture.md` — technical architecture (feasibility reference) - `docs/technical_architecture.md` — technical architecture (feasibility reference)
- `.specify/memory/constitution.md` — project Constitution (compliance gate) - `packages/casan-harness/memory/constitution.md` — project Constitution (compliance gate)
- Feature-specific SRS if exists: `docs/output/ipa-docs/srs/srs-<module>.md` - Feature-specific SRS if exists: `docs/output/ipa-docs/srs/srs-<module>.md`
--- ---
.github/agents/okr.srs.agent.md
+2 -2
View File
@@ -86,7 +86,7 @@ Priority rule: `srs-overview-system.md` → `srs-mod<XX>-detail.md` → `srs-mod
1. Load `docs/output/srs-systems/srs-overview-system.md` to get system context, then identify the module folder matching `$ARGUMENTS` (e.g., `docs/output/srs-systems/mod01-xxx/`). Load `srs-mod<XX>-detail.md` and `srs-mod<XX>-wireframe.md` from that folder. Enumerate all FEAs belonging to the target module. 1. Load `docs/output/srs-systems/srs-overview-system.md` to get system context, then identify the module folder matching `$ARGUMENTS` (e.g., `docs/output/srs-systems/mod01-xxx/`). Load `srs-mod<XX>-detail.md` and `srs-mod<XX>-wireframe.md` from that folder. Enumerate all FEAs belonging to the target module.
2. Cross-reference `srs-mod<XX>-detail.md` and `srs-mod<XX>-wireframe.md` to fill in any missing details for each FEA. 2. Cross-reference `srs-mod<XX>-detail.md` and `srs-mod<XX>-wireframe.md` to fill in any missing details for each FEA.
3. Generate a complete SRS document using **`.specify/templates/srs-template.md`** as the base template. Follow the section mapping in **SRS Output Structure** below to populate each template section with module-specific content. 3. Generate a complete SRS document using **`packages/casan-harness/templates/srs-template.md`** as the base template. Follow the section mapping in **SRS Output Structure** below to populate each template section with module-specific content.
> ⚠️ **MANDATORY: TABLE OF CONTENTS** — The SRS document **MUST** include a `## TABLE OF CONTENTS` section immediately after the `Record of Change` table (before §1). Generate a complete, clickable table of contents listing all `##` and `###` level headings with Markdown anchor links. This matches the structure in `srs-template.md`. Do NOT skip this section. > ⚠️ **MANDATORY: TABLE OF CONTENTS** — The SRS document **MUST** include a `## TABLE OF CONTENTS` section immediately after the `Record of Change` table (before §1). Generate a complete, clickable table of contents listing all `##` and `###` level headings with Markdown anchor links. This matches the structure in `srs-template.md`. Do NOT skip this section.
4. Save to `docs/output/ipa-docs/srs/srs-<MOD-ID>-<module-short-name>.md`. 4. Save to `docs/output/ipa-docs/srs/srs-<MOD-ID>-<module-short-name>.md`.
Example: MOD-01 (OKR management module) → `docs/output/ipa-docs/srs/srs-mod01-okr-management.md` Example: MOD-01 (OKR management module) → `docs/output/ipa-docs/srs/srs-mod01-okr-management.md`
@@ -94,7 +94,7 @@ Priority rule: `srs-overview-system.md` → `srs-mod<XX>-detail.md` → `srs-mod
## SRS Output Structure ## SRS Output Structure
Start from a copy of **`.specify/templates/srs-template.md`** and populate every section as follows. Start from a copy of **`packages/casan-harness/templates/srs-template.md`** and populate every section as follows.
**File header** — replace placeholders: **File header** — replace placeholders:
.github/agents/okr.srsallsystem.agent.md
+1 -1
View File
@@ -39,7 +39,7 @@ Mission: produce a **complete, exhaustive, system-wide SRS** covering all module
If `$ARGUMENTS` specifies a file or folder path, **read that path first** as the primary source. Otherwise, read in this priority order and cross-reference: If `$ARGUMENTS` specifies a file or folder path, **read that path first** as the primary source. Otherwise, read in this priority order and cross-reference:
1. **`docs/input/okr-requirement.md`** — Original product requirement document. **Primary source of truth.** Contains functional requirements, screen definitions, field rules, user flows, and validation constraints. 1. **`apps/okr/domain/input/okr-requirement.md`** — Original product requirement document. **Primary source of truth.** Contains functional requirements, screen definitions, field rules, user flows, and validation constraints.
2. **`docs/technical_architecture.md`** — Technology stack recommendations. Use for the technology recommendation section only (not for functional requirements). 2. **`docs/technical_architecture.md`** — Technology stack recommendations. Use for the technology recommendation section only (not for functional requirements).
**Priority rule:** User-specified input (`$ARGUMENTS`) → Special Specification (Spec) → system-overview.md → `[TBC-XX]` if all are insufficient. **Priority rule:** User-specified input (`$ARGUMENTS`) → Special Specification (Spec) → system-overview.md → `[TBC-XX]` if all are insufficient.
.github/agents/okr.testkit.agent.md
+7 -7
View File
@@ -29,7 +29,7 @@ You are the **Independent QA Agent (okr.testkit)** for OKR web app. Your role is
**Output:** **Output:**
- `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` — Comprehensive test case document - `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` — Comprehensive test case document
**Template:** `.specify/templates/testcase-template.md` — Use this template for the output format. Fill in all sections with actual test cases generated from the input documents. **Template:** `packages/casan-harness/templates/testcase-template.md` — Use this template for the output format. Fill in all sections with actual test cases generated from the input documents.
**Process:** **Process:**
@@ -43,11 +43,11 @@ You are the **Independent QA Agent (okr.testkit)** for OKR web app. Your role is
- **API Tests (AT)** — From DD internal API contracts + BD external interface → Jest + Supertest - **API Tests (AT)** — From DD internal API contracts + BD external interface → Jest + Supertest
- **UI/E2E Tests (E2E)** — From BD screen designs + SRS user flows → Playwright - **UI/E2E Tests (E2E)** — From BD screen designs + SRS user flows → Playwright
- **Integration Tests (IT)** — From DD sequence diagrams + data flow → testcontainers-node - **Integration Tests (IT)** — From DD sequence diagrams + data flow → testcontainers-node
4. **Write test case document** using template `.specify/templates/testcase-template.md` to `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` with full traceability 4. **Write test case document** using template `packages/casan-harness/templates/testcase-template.md` to `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` with full traceability
#### Test Case Output #### Test Case Output
The output file MUST follow the template at `.specify/templates/testcase-template.md`. Key sections: The output file MUST follow the template at `packages/casan-harness/templates/testcase-template.md`. Key sections:
- **§1 Unit Tests (UT)** — From DD class/method designs → Jest - **§1 Unit Tests (UT)** — From DD class/method designs → Jest
- **§2 API Tests (AT)** — From DD internal API contracts + BD external interface → Jest + Supertest - **§2 API Tests (AT)** — From DD internal API contracts + BD external interface → Jest + Supertest
- **§3 UI/E2E Tests (E2E)** — From BD screen designs + SRS user flows → Playwright - **§3 UI/E2E Tests (E2E)** — From BD screen designs + SRS user flows → Playwright
@@ -59,7 +59,7 @@ The template contains embedded generation rules (HTML comments) for each section
#### ⛔ MANDATORY TABLE FORMAT — STRICTLY ENFORCED #### ⛔ MANDATORY TABLE FORMAT — STRICTLY ENFORCED
Each section (UT, AT, E2E, IT) MUST be output as **one single consolidated master table** per section, exactly matching the column structure shown in the template `.specify/templates/testcase-template.md`. Each section (UT, AT, E2E, IT) MUST be output as **one single consolidated master table** per section, exactly matching the column structure shown in the template `packages/casan-harness/templates/testcase-template.md`.
**⛔ PROHIBITED formats (DO NOT USE):** **⛔ PROHIBITED formats (DO NOT USE):**
- Individual `| Item | Content |` two-column tables for each test case - Individual `| Item | Content |` two-column tables for each test case
@@ -162,10 +162,10 @@ Each section (UT, AT, E2E, IT) MUST be output as **one single consolidated maste
8. **Write test execution summary report** to `docs/output/output_logs/<feature-id>/reports/<NN>-testkit-report.md`: 8. **Write test execution summary report** to `docs/output/output_logs/<feature-id>/reports/<NN>-testkit-report.md`:
**Template:** `.specify/templates/testreport-template.md` — Load this template and fill in all sections with actual test execution results. **Template:** `packages/casan-harness/templates/testreport-template.md` — Load this template and fill in all sections with actual test execution results.
**Process:** **Process:**
1. Read the template file: `.specify/templates/testreport-template.md` 1. Read the template file: `packages/casan-harness/templates/testreport-template.md`
2. Read `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` and extract ALL TC-IDs from master tables. **Same rules as Phase D apply: exact TC-IDs, zero omissions, all 4 sections mandatory.** 2. Read `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` and extract ALL TC-IDs from master tables. **Same rules as Phase D apply: exact TC-IDs, zero omissions, all 4 sections mandatory.**
3. Fill in all placeholders with actual test execution data: 3. Fill in all placeholders with actual test execution data:
- §1 Test Execution Summary — aggregate pass/fail/skip counts from Phase B - §1 Test Execution Summary — aggregate pass/fail/skip counts from Phase B
@@ -294,7 +294,7 @@ Code (TypeScript/JavaScript test scripts) and file paths remain in English.
This agent is invoked by the Boss orchestrator at two specific points: This agent is invoked by the Boss orchestrator at two specific points:
1. **STEP 8b** (after DD): `gen-testcases <feature-id>` → produces `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` using template `.specify/templates/testcase-template.md` 1. **STEP 8b** (after DD): `gen-testcases <feature-id>` → produces `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<module-short-name>.md` using template `packages/casan-harness/templates/testcase-template.md`
2. **STEP 12** (after build, FINAL QA AUDIT): `run-tests <feature-id>` → produces test scripts + executes + produces: 2. **STEP 12** (after build, FINAL QA AUDIT): `run-tests <feature-id>` → produces test scripts + executes + produces:
- Pipeline report: `docs/output/output_logs/<feature-id>/reports/<NN>-testkit-report.md` (Phase C) - Pipeline report: `docs/output/output_logs/<feature-id>/reports/<NN>-testkit-report.md` (Phase C)
- IPA detail report: `docs/output/ipa-docs/testreport/testreport-<MOD-ID>-<module-short-name>.md` (Phase D) - IPA detail report: `docs/output/ipa-docs/testreport/testreport-<MOD-ID>-<module-short-name>.md` (Phase D)
.github/agents/protocols/casan-harness-protocol.md
+10 -10
View File
@@ -10,38 +10,38 @@ Raise the SDD Speckit OKR pipeline from CASAN Level 3 to Level 4 by making Secur
| Harness | Runtime control | Script | Evidence | | Harness | Runtime control | Script | Evidence |
|---|---|---|---| |---|---|---|---|
| H4 Security | Prompt injection block, PII masking, secret redaction, output filtering | `.specify/scripts/bash/security-check.sh` | `.specify/logs/trace/security-*.json`, `.specify/logs/audit/security.jsonl` | | H4 Security | Prompt injection block, PII masking, secret redaction, output filtering | `packages/casan-harness/scripts/bash/security-check.sh` | `.specify/logs/trace/security-*.json`, `.specify/logs/audit/security.jsonl` |
| H5 Governance | Risk scoring, non-interactive approval policy, append-only hash-chain audit | `.specify/scripts/bash/governance-check.sh` | `.specify/logs/trace/governance-*.json`, `.specify/logs/audit/audit.jsonl` | | H5 Governance | Risk scoring, non-interactive approval policy, append-only hash-chain audit | `packages/casan-harness/scripts/bash/governance-check.sh` | `.specify/logs/trace/governance-*.json`, `.specify/logs/audit/audit.jsonl` |
| H6 AgentOps | Latency, retry, token, cost, status, alert tracking | `.specify/scripts/bash/agent-metrics.sh` | `.specify/logs/trace/agentops-*.json`, `.specify/logs/cost/metrics.jsonl`, `.specify/agentops/alerts.log` | | H6 AgentOps | Latency, retry, token, cost, status, alert tracking | `packages/casan-harness/scripts/bash/agent-metrics.sh` | `.specify/logs/trace/agentops-*.json`, `.specify/logs/cost/metrics.jsonl`, `.specify/agentops/alerts.log` |
| H2 Tool Registry | Side-effect registry, idempotency key, per-call audit | `.specify/scripts/bash/tool-registry-gate.sh` | `.specify/logs/level5/tool-registry.jsonl`, `.specify/logs/audit/tool-calls.jsonl` | | H2 Tool Registry | Side-effect registry, idempotency key, per-call audit | `packages/casan-harness/scripts/bash/tool-registry-gate.sh` | `.specify/logs/level5/tool-registry.jsonl`, `.specify/logs/audit/tool-calls.jsonl` |
## Mandatory Gate Pattern ## Mandatory Gate Pattern
Before every delegated step: Before every delegated step:
```bash ```bash
.specify/scripts/bash/security-check.sh "$STEP_INPUT" "$SAFE_INPUT" input packages/casan-harness/scripts/bash/security-check.sh "$STEP_INPUT" "$SAFE_INPUT" input
.specify/scripts/bash/governance-check.sh "$SAFE_INPUT" "$APPROVED_INPUT" "$ACTION_NAME" packages/casan-harness/scripts/bash/governance-check.sh "$SAFE_INPUT" "$APPROVED_INPUT" "$ACTION_NAME"
``` ```
Around every execution or agent/tool invocation: Around every execution or agent/tool invocation:
```bash ```bash
CASAN_AGENT_NAME="<agent>" CASAN_STEP_NAME="<step>" \ CASAN_AGENT_NAME="<agent>" CASAN_STEP_NAME="<step>" \
.specify/scripts/bash/agent-metrics.sh "$APPROVED_INPUT" "$RAW_OUTPUT" -- <real command> packages/casan-harness/scripts/bash/agent-metrics.sh "$APPROVED_INPUT" "$RAW_OUTPUT" -- <real command>
``` ```
After every generated artifact or agent response: After every generated artifact or agent response:
```bash ```bash
.specify/scripts/bash/security-check.sh "$RAW_OUTPUT" "$FINAL_OUTPUT" output packages/casan-harness/scripts/bash/security-check.sh "$RAW_OUTPUT" "$FINAL_OUTPUT" output
``` ```
When a step can be represented as a single command, Boss MAY use the wrapper: When a step can be represented as a single command, Boss MAY use the wrapper:
```bash ```bash
CASAN_AGENT_NAME="<agent>" CASAN_STEP_NAME="<step>" \ CASAN_AGENT_NAME="<agent>" CASAN_STEP_NAME="<step>" \
.specify/scripts/bash/casan-harness.sh "$STEP_INPUT" "$FINAL_OUTPUT" "$ACTION_NAME" -- <real command> packages/casan-harness/scripts/bash/casan-harness.sh "$STEP_INPUT" "$FINAL_OUTPUT" "$ACTION_NAME" -- <real command>
``` ```
Cache hits MUST NOT bypass CASAN evidence. A cached wrapper run still has to produce fresh H4 input, H5 governance, H6 metrics, and H4 output traces for the current execution. Cache hits MUST NOT bypass CASAN evidence. A cached wrapper run still has to produce fresh H4 input, H5 governance, H6 metrics, and H4 output traces for the current execution.
@@ -105,4 +105,4 @@ Boss orchestrator also enforces:
1. **Self-Security Audit:** Every agent reads `protocols/agent-self-security-rules.md` before output is accepted. 1. **Self-Security Audit:** Every agent reads `protocols/agent-self-security-rules.md` before output is accepted.
2. **Self-Governance Audit:** Every agent reads `protocols/governance-risk-policy.md` before high-risk action planning. 2. **Self-Governance Audit:** Every agent reads `protocols/governance-risk-policy.md` before high-risk action planning.
3. **Hallucination Checklist:** Every review agent reads `protocols/hallucination-prevention-checklist.md` during review gates. 3. **Hallucination Checklist:** Every review agent reads `protocols/hallucination-prevention-checklist.md` during review gates.
4. **Tool Registry Policy:** Every side-effecting tool is checked against `protocols/tool-registry-policy.md` and `.specify/level5/tool-registry.yaml`. 4. **Tool Registry Policy:** Every side-effecting tool is checked against `protocols/tool-registry-policy.md` and `packages/casan-harness/level5/tool-registry.yaml`.
.github/agents/protocols/hallucination-prevention-checklist.md
+1 -1
View File
@@ -4,7 +4,7 @@ Giao thức này cung cấp bộ checklist bắt buộc để các Review Agents
## 1. Nguyên lý đối chiếu chéo (Grounding) ## 1. Nguyên lý đối chiếu chéo (Grounding)
- Không có bất kỳ chi tiết thiết kế hoặc logic code nào được phép tự ý phát minh nếu không có cơ sở chứng cứ rõ ràng từ: - Không có bất kỳ chi tiết thiết kế hoặc logic code nào được phép tự ý phát minh nếu không có cơ sở chứng cứ rõ ràng từ:
- Tài liệu Yêu cầu nghiệp vụ (`docs/input/okr-requirement.md`). - Tài liệu Yêu cầu nghiệp vụ (`apps/okr/domain/input/okr-requirement.md`).
- Bản vẽ thiết kế Basic Design (`bd-*.md`) hoặc Detail Design (`dd-*.md`). - Bản vẽ thiết kế Basic Design (`bd-*.md`) hoặc Detail Design (`dd-*.md`).
- Tệp thông tin Context hiện tại (`pipeline-context.yaml`). - Tệp thông tin Context hiện tại (`pipeline-context.yaml`).
.github/agents/protocols/pipeline-context.md
+6 -6
View File
@@ -32,22 +32,22 @@ tech-stack:
casan-harness: casan-harness:
level-target: 5 level-target: 5
h4-security: h4-security:
policy: .specify/security/prompt-filter.yaml policy: packages/casan-harness/security/prompt-filter.yaml
output-policy: .specify/security/output-policy.yaml output-policy: packages/casan-harness/security/output-policy.yaml
audit-log: .specify/logs/audit/security.jsonl audit-log: .specify/logs/audit/security.jsonl
h5-governance: h5-governance:
approval-flow: .specify/governance/approval-flow.yaml approval-flow: packages/casan-harness/governance/approval-flow.yaml
risk-registry: .specify/governance/risk-registry.yaml risk-registry: packages/casan-harness/governance/risk-registry.yaml
audit-log: .specify/logs/audit/audit.jsonl audit-log: .specify/logs/audit/audit.jsonl
h6-agentops: h6-agentops:
metrics-policy: .specify/agentops/metrics.yaml metrics-policy: .specify/agentops/metrics.yaml
metrics-log: .specify/logs/cost/metrics.jsonl metrics-log: .specify/logs/cost/metrics.jsonl
alert-log: .specify/agentops/alerts.log alert-log: .specify/agentops/alerts.log
h2-tool-registry: h2-tool-registry:
registry: .specify/level5/tool-registry.yaml registry: packages/casan-harness/level5/tool-registry.yaml
audit-log: .specify/logs/level5/tool-registry.jsonl audit-log: .specify/logs/level5/tool-registry.jsonl
h7-drift: h7-drift:
golden-dir: .specify/level5/golden-runs/ golden-dir: apps/okr/domain/golden-runs/
drift-log: .specify/logs/level5/drift.jsonl drift-log: .specify/logs/level5/drift.jsonl
rollback: rollback:
transactions-log: .specify/logs/level5/rollback-transactions.jsonl transactions-log: .specify/logs/level5/rollback-transactions.jsonl
.github/agents/protocols/tool-registry-policy.md
+1 -1
View File
@@ -7,7 +7,7 @@ Giao thức này quy định danh sách trắng các công cụ và câu lệnh
### A. Boss Orchestrator (okr.bossbuiltin) ### A. Boss Orchestrator (okr.bossbuiltin)
Được phép điều phối và chạy toàn bộ các chuỗi công cụ chuẩn bị và kiểm thử: Được phép điều phối và chạy toàn bộ các chuỗi công cụ chuẩn bị và kiểm thử:
- `Read`, `Write`, `Edit`, `Glob`, `Grep` (IDE Tools) - `Read`, `Write`, `Edit`, `Glob`, `Grep` (IDE Tools)
- Các script hỗ trợ: `.specify/scripts/bash/casan-harness.sh`, `security-check.sh`, `governance-check.sh`, `agent-metrics.sh` - Các script hỗ trợ: `packages/casan-harness/scripts/bash/casan-harness.sh`, `security-check.sh`, `governance-check.sh`, `agent-metrics.sh`
- CLI Commands: `npm install`, `npm run build`, `npm run start:dev`, `docker compose` - CLI Commands: `npm install`, `npm run build`, `npm run start:dev`, `docker compose`
### B. Special Design/Specification Agents (srs, bd, specify, plan, dd, tasks) ### B. Special Design/Specification Agents (srs, bd, specify, plan, dd, tasks)
.github/agents/speckit.analyze.agent.md
+3 -3
View File
@@ -26,13 +26,13 @@ Identify inconsistencies, duplications, ambiguities, and underspecified items ac
**STRICTLY READ-ONLY**: Do **not** modify any files. Output a structured analysis report. Offer an optional remediation plan (user must explicitly approve before any follow-up editing commands would be invoked manually). **STRICTLY READ-ONLY**: Do **not** modify any files. Output a structured analysis report. Offer an optional remediation plan (user must explicitly approve before any follow-up editing commands would be invoked manually).
**Constitution Authority**: The project constitution (`.specify/memory/constitution.md`) is **non-negotiable** within this analysis scope. Constitution conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle. If a principle itself needs to change, that must occur in a separate, explicit constitution update outside `/speckit.analyze`. **Constitution Authority**: The project constitution (`packages/casan-harness/memory/constitution.md`) is **non-negotiable** within this analysis scope. Constitution conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle. If a principle itself needs to change, that must occur in a separate, explicit constitution update outside `/speckit.analyze`.
## Execution Steps ## Execution Steps
### 1. Initialize Analysis Context ### 1. Initialize Analysis Context
Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks` once from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive absolute paths: Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks` once from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive absolute paths:
- SPEC = FEATURE_DIR/spec.md - SPEC = FEATURE_DIR/spec.md
- PLAN = FEATURE_DIR/plan.md - PLAN = FEATURE_DIR/plan.md
@@ -70,7 +70,7 @@ Load only the minimal necessary context from each artifact:
**From constitution:** **From constitution:**
- Load `.specify/memory/constitution.md` for principle validation - Load `packages/casan-harness/memory/constitution.md` for principle validation
### 3. Build Semantic Models ### 3. Build Semantic Models
.github/agents/speckit.checklist.agent.md
+2 -2
View File
@@ -41,7 +41,7 @@ You **MUST** consider the user input before proceeding (if not empty).
## Execution Steps ## Execution Steps
1. **Setup**: Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json` from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS list. 1. **Setup**: Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json` from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS list.
- All file paths must be absolute. - All file paths must be absolute.
- For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). - For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
@@ -212,7 +212,7 @@ You **MUST** consider the user input before proceeding (if not empty).
- ✅ "Are [edge cases/scenarios] addressed in requirements?" - ✅ "Are [edge cases/scenarios] addressed in requirements?"
- ✅ "Does the spec define [missing aspect]?" - ✅ "Does the spec define [missing aspect]?"
6. **Structure Reference**: Generate the checklist following the canonical template in `.specify/templates/checklist-template.md` for title, meta section, category headings, and ID formatting. If template is unavailable, use: H1 title, purpose/created meta lines, `##` category sections containing `- [ ] CHK### <requirement item>` lines with globally incrementing IDs starting at CHK001. 6. **Structure Reference**: Generate the checklist following the canonical template in `packages/casan-harness/templates/checklist-template.md` for title, meta section, category headings, and ID formatting. If template is unavailable, use: H1 title, purpose/created meta lines, `##` category sections containing `- [ ] CHK### <requirement item>` lines with globally incrementing IDs starting at CHK001.
7. **Report**: Output full path to checklist file, item count, and summarize whether the run created a new file or appended to an existing one. Summarize: 7. **Report**: Output full path to checklist file, item count, and summarize whether the run created a new file or appended to an existing one. Summarize:
- Focus areas selected - Focus areas selected
.github/agents/speckit.clarify.agent.md
+1 -1
View File
@@ -62,7 +62,7 @@ Note: This clarification workflow is expected to run (and be completed) BEFORE i
Execution steps: Execution steps:
1. Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` from repo root **once** (combined `--json --paths-only` mode / `-Json -PathsOnly`). Parse minimal JSON payload fields: 1. Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly` from repo root **once** (combined `--json --paths-only` mode / `-Json -PathsOnly`). Parse minimal JSON payload fields:
- `FEATURE_DIR` - `FEATURE_DIR`
- `FEATURE_SPEC` - `FEATURE_SPEC`
- (Optionally capture `IMPL_PLAN`, `TASKS` for future chained flows.) - (Optionally capture `IMPL_PLAN`, `TASKS` for future chained flows.)
.github/agents/speckit.constitution.agent.md
+9 -9
View File
@@ -24,13 +24,13 @@ You **MUST** consider the user input before proceeding (if not empty).
## Outline ## Outline
You are updating the project constitution at `.specify/memory/constitution.md`. This file is a TEMPLATE containing placeholder tokens in square brackets (e.g. `[PROJECT_NAME]`, `[PRINCIPLE_1_NAME]`). Your job is to (a) collect/derive concrete values, (b) fill the template precisely, and (c) propagate any amendments across dependent artifacts. You are updating the project constitution at `packages/casan-harness/memory/constitution.md`. This file is a TEMPLATE containing placeholder tokens in square brackets (e.g. `[PROJECT_NAME]`, `[PRINCIPLE_1_NAME]`). Your job is to (a) collect/derive concrete values, (b) fill the template precisely, and (c) propagate any amendments across dependent artifacts.
**Note**: If `.specify/memory/constitution.md` does not exist yet, it should have been initialized from `.specify/templates/constitution-template.md` during project setup. If it's missing, copy the template first. **Note**: If `packages/casan-harness/memory/constitution.md` does not exist yet, it should have been initialized from `packages/casan-harness/templates/constitution-template.md` during project setup. If it's missing, copy the template first.
Follow this execution flow: Follow this execution flow:
1. Load the existing constitution at `.specify/memory/constitution.md`. 1. Load the existing constitution at `packages/casan-harness/memory/constitution.md`.
- Identify every placeholder token of the form `[ALL_CAPS_IDENTIFIER]`. - Identify every placeholder token of the form `[ALL_CAPS_IDENTIFIER]`.
**IMPORTANT**: The user might require less or more principles than the ones used in the template. If a number is specified, respect that - follow the general template. You will update the doc accordingly. **IMPORTANT**: The user might require less or more principles than the ones used in the template. If a number is specified, respect that - follow the general template. You will update the doc accordingly.
@@ -51,10 +51,10 @@ Follow this execution flow:
- Ensure Governance section lists amendment procedure, versioning policy, and compliance review expectations. - Ensure Governance section lists amendment procedure, versioning policy, and compliance review expectations.
4. Consistency propagation checklist (convert prior checklist into active validations): 4. Consistency propagation checklist (convert prior checklist into active validations):
- Read `.specify/templates/plan-template.md` and ensure any "Constitution Check" or rules align with updated principles. - Read `packages/casan-harness/templates/plan-template.md` and ensure any "Constitution Check" or rules align with updated principles.
- Read `.specify/templates/spec-template.md` for scope/requirements alignment—update if constitution adds/removes mandatory sections or constraints. - Read `packages/casan-harness/templates/spec-template.md` for scope/requirements alignment—update if constitution adds/removes mandatory sections or constraints.
- Read `.specify/templates/tasks-template.md` and ensure task categorization reflects new or removed principle-driven task types (e.g., observability, versioning, testing discipline). - Read `packages/casan-harness/templates/tasks-template.md` and ensure task categorization reflects new or removed principle-driven task types (e.g., observability, versioning, testing discipline).
- Read each command file in `.specify/templates/commands/*.md` (including this one) to verify no outdated references (agent-specific names like CLAUDE only) remain when generic guidance is required. - Read each command file in `packages/casan-harness/templates/commands/*.md` (including this one) to verify no outdated references (agent-specific names like CLAUDE only) remain when generic guidance is required.
- Read any runtime guidance docs (e.g., `README.md`, `docs/quickstart.md`, or agent-specific guidance files if present). Update references to principles changed. - Read any runtime guidance docs (e.g., `README.md`, `docs/quickstart.md`, or agent-specific guidance files if present). Update references to principles changed.
5. Produce a Sync Impact Report (prepend as an HTML comment at top of the constitution file after update): 5. Produce a Sync Impact Report (prepend as an HTML comment at top of the constitution file after update):
@@ -71,7 +71,7 @@ Follow this execution flow:
- Dates ISO format YYYY-MM-DD. - Dates ISO format YYYY-MM-DD.
- Principles are declarative, testable, and free of vague language ("should" → replace with MUST/SHOULD rationale where appropriate). - Principles are declarative, testable, and free of vague language ("should" → replace with MUST/SHOULD rationale where appropriate).
7. Write the completed constitution back to `.specify/memory/constitution.md` (overwrite). 7. Write the completed constitution back to `packages/casan-harness/memory/constitution.md` (overwrite).
8. Output a final summary to the user with: 8. Output a final summary to the user with:
- New version and bump rationale. - New version and bump rationale.
@@ -89,4 +89,4 @@ If the user supplies partial updates (e.g., only one principle revision), still
If critical info missing (e.g., ratification date truly unknown), insert `TODO(<FIELD_NAME>): explanation` and include in the Sync Impact Report under deferred items. If critical info missing (e.g., ratification date truly unknown), insert `TODO(<FIELD_NAME>): explanation` and include in the Sync Impact Report under deferred items.
Do not create a new template; always operate on the existing `.specify/memory/constitution.md` file. Do not create a new template; always operate on the existing `packages/casan-harness/memory/constitution.md` file.
.github/agents/speckit.implement.agent.md
+1 -1
View File
@@ -60,7 +60,7 @@ You **MUST** consider the user input before proceeding (if not empty).
## Outline ## Outline
1. Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). 1. Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
2. **Check checklists status** (if FEATURE_DIR/checklists/ exists): 2. **Check checklists status** (if FEATURE_DIR/checklists/ exists):
- Scan all checklist files in the checklists/ directory - Scan all checklist files in the checklists/ directory
.github/agents/speckit.plan.agent.md
+3 -3
View File
@@ -59,9 +59,9 @@ You **MUST** consider the user input before proceeding (if not empty).
## Outline ## Outline
1. **Setup**: Run `.specify/scripts/powershell/setup-plan.ps1 -Json` from repo root and parse JSON for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). 1. **Setup**: Run `packages/casan-harness/scripts/powershell/setup-plan.ps1 -Json` from repo root and parse JSON for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
2. **Load context**: Read FEATURE_SPEC and `.specify/memory/constitution.md`. Load IMPL_PLAN template (already copied). 2. **Load context**: Read FEATURE_SPEC and `packages/casan-harness/memory/constitution.md`. Load IMPL_PLAN template (already copied).
3. **Execute plan workflow**: Follow the structure in IMPL_PLAN template to: 3. **Execute plan workflow**: Follow the structure in IMPL_PLAN template to:
- Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION") - Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION")
@@ -122,7 +122,7 @@ Technical IDs remain unchanged.
- Skip if project is purely internal (build scripts, one-off tools, etc.) - Skip if project is purely internal (build scripts, one-off tools, etc.)
3. **Agent context update**: 3. **Agent context update**:
- Run `.specify/scripts/powershell/update-agent-context.ps1 -AgentType copilot` - Run `packages/casan-harness/scripts/powershell/update-agent-context.ps1 -AgentType copilot`
- These scripts detect which AI agent is in use - These scripts detect which AI agent is in use
- Update the appropriate agent-specific context file - Update the appropriate agent-specific context file
- Add only new technology from current plan - Add only new technology from current plan
.github/agents/speckit.specify.agent.md
+4 -4
View File
@@ -115,10 +115,10 @@ Given that feature description, do this:
- Find the highest number N - Find the highest number N
- Use N+1 for the new branch number - Use N+1 for the new branch number
g. Run the script `.specify/scripts/powershell/create-new-feature.ps1 -Json "$ARGUMENTS"` with the calculated number and short-name: g. Run the script `packages/casan-harness/scripts/powershell/create-new-feature.ps1 -Json "$ARGUMENTS"` with the calculated number and short-name:
- Pass `--number N+1` and `--short-name "your-short-name"` along with the feature description - Pass `--number N+1` and `--short-name "your-short-name"` along with the feature description
- Bash example: `.specify/scripts/powershell/create-new-feature.ps1 -Json "$ARGUMENTS" --json --number 5 --short-name "user-auth" "Add user authentication"` - Bash example: `packages/casan-harness/scripts/powershell/create-new-feature.ps1 -Json "$ARGUMENTS" --json --number 5 --short-name "user-auth" "Add user authentication"`
- PowerShell example: `.specify/scripts/powershell/create-new-feature.ps1 -Json "$ARGUMENTS" -Json -Number 5 -ShortName "user-auth" "Add user authentication"` - PowerShell example: `packages/casan-harness/scripts/powershell/create-new-feature.ps1 -Json "$ARGUMENTS" -Json -Number 5 -ShortName "user-auth" "Add user authentication"`
**IMPORTANT**: **IMPORTANT**:
- Check all three sources (remote branches, local branches, specs directories) to find the highest number - Check all three sources (remote branches, local branches, specs directories) to find the highest number
@@ -129,7 +129,7 @@ Given that feature description, do this:
- The JSON output will contain BRANCH_NAME and SPEC_FILE paths - The JSON output will contain BRANCH_NAME and SPEC_FILE paths
- For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot") - For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot")
3. Load `.specify/templates/spec-template.md` to understand required sections. 3. Load `packages/casan-harness/templates/spec-template.md` to understand required sections.
4. Follow this execution flow: 4. Follow this execution flow:
.github/agents/speckit.tasks.agent.md
+2 -2
View File
@@ -60,7 +60,7 @@ You **MUST** consider the user input before proceeding (if not empty).
## Outline ## Outline
1. **Setup**: Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). 1. **Setup**: Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
2. **Load design documents**: Read from FEATURE_DIR: 2. **Load design documents**: Read from FEATURE_DIR:
- **Required**: plan.md (tech stack, libraries, structure), spec.md (user stories with priorities) - **Required**: plan.md (tech stack, libraries, structure), spec.md (user stories with priorities)
@@ -78,7 +78,7 @@ You **MUST** consider the user input before proceeding (if not empty).
- Create parallel execution examples per user story - Create parallel execution examples per user story
- Validate task completeness (each user story has all needed tasks, independently testable) - Validate task completeness (each user story has all needed tasks, independently testable)
4. **Generate tasks.md**: Use `.specify/templates/tasks-template.md` as structure, fill with: 4. **Generate tasks.md**: Use `packages/casan-harness/templates/tasks-template.md` as structure, fill with:
**Output Language**: Produce `tasks.md` in Vietnamese. Technical IDs (T001, [US1], [P], etc.) remain unchanged. **Output Language**: Produce `tasks.md` in Vietnamese. Technical IDs (T001, [US1], [P], etc.) remain unchanged.
- Correct feature name from plan.md - Correct feature name from plan.md
.github/agents/speckit.taskstoissues.agent.md
+1 -1
View File
@@ -21,7 +21,7 @@ You **MUST** consider the user input before proceeding (if not empty).
## Outline ## Outline
1. Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). 1. Run `packages/casan-harness/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
1. From the executed script, extract the path to **tasks**. 1. From the executed script, extract the path to **tasks**.
1. Get the Git remote by running: 1. Get the Git remote by running:
.github/prompts/demo-promt.md
+2 -2
View File
@@ -2,7 +2,7 @@
## step 1: gen wide system srs ## step 1: gen wide system srs
- use agent: 　okr.srsallsystem - use agent: 　okr.srsallsystem
- Prompt - Prompt
> Generate system-wide SRS (Full Module Requirements Definition) for the OKR web app base on input at docs/input/okr-requirement.md > Generate system-wide SRS (Full Module Requirements Definition) for the OKR web app base on input at apps/okr/domain/input/okr-requirement.md
## step 2: chọn module sẽ tạo ## step 2: chọn module sẽ tạo
### a. Case run from vscode ### a. Case run from vscode
@@ -18,4 +18,4 @@
# II. Change spec # II. Change spec
## step 3: thực hiện CR cho 1 module ## step 3: thực hiện CR cho 1 module
- Prompt - Prompt
> execute an UPDATE pipeline for change requests at docs/input/change-request/change-0405.md for MOD-02: Workspace & Dashboard > execute an UPDATE pipeline for change requests at apps/okr/domain/input/change-request/change-0405.md for MOD-02: Workspace & Dashboard
apps/okr/domain/README.md
+3 -3
View File
@@ -4,6 +4,6 @@ OKR-domain data consumed by the CASAN harness, kept separate from the reusable h
Populated in Plan-01 Phase 5. Referenced by scripts via `CASAN_DOMAIN_ROOT` (default this dir). Populated in Plan-01 Phase 5. Referenced by scripts via `CASAN_DOMAIN_ROOT` (default this dir).
Planned contents (moved from `.specify/` / `docs/` in Phase 5): Planned contents (moved from `.specify/` / `docs/` in Phase 5):
- `golden-runs/` — golden baselines for drift/H7 (from `.specify/level5/golden-runs/`) - `golden-runs/` — golden baselines for drift/H7 (from `apps/okr/domain/golden-runs/`)
- `input/` — requirement/architecture specs (from `docs/input/`) - `input/` — requirement/architecture specs (from `apps/okr/domain/input/`)
- `corpus/` — redteam + benign corpora (from `.specify/security/redteam-*.jsonl`, `benign-corpus/`) - `corpus/` — redteam + benign corpora (from `packages/casan-harness/security/redteam-*.jsonl`, `benign-corpus/`)
infra/local-prod/README.md
+4 -4
View File
@@ -18,10 +18,10 @@ CASAN Tier 2 from "needs infra" to locally testable production-like controls.
## Commands ## Commands
```bash ```bash
bash .specify/scripts/bash/infra-lab.sh start bash packages/casan-harness/scripts/bash/infra-lab.sh start
bash .specify/scripts/bash/infra-lab.sh verify bash packages/casan-harness/scripts/bash/infra-lab.sh verify
bash .specify/scripts/bash/infra-lab.sh env bash packages/casan-harness/scripts/bash/infra-lab.sh env
bash .specify/scripts/bash/infra-lab.sh stop bash packages/casan-harness/scripts/bash/infra-lab.sh stop
``` ```
This is a lab, not a compliance claim. AWS S3 Object Lock, real enterprise IdP, This is a lab, not a compliance claim. AWS S3 Object Lock, real enterprise IdP,
packages/casan-harness/memory/constitution.md
+4 -4
View File
@@ -5,10 +5,10 @@ Modified principles: placeholder principle 1 -> I. Requirement-First Definition;
Added sections: Product Scope Constraints; Delivery Workflow and Quality Gates Added sections: Product Scope Constraints; Delivery Workflow and Quality Gates
Removed sections: none Removed sections: none
Templates requiring updates: Templates requiring updates:
- ✅ .specify/templates/spec-template.md - ✅ packages/casan-harness/templates/spec-template.md
- ✅ .specify/templates/plan-template.md - ✅ packages/casan-harness/templates/plan-template.md
- ✅ .specify/templates/tasks-template.md - ✅ packages/casan-harness/templates/tasks-template.md
- ⚠ pending none in .specify/templates/commands because that directory does not exist in this repository - ⚠ pending none in packages/casan-harness/templates/commands because that directory does not exist in this repository
- ✅ README.md - ✅ README.md
Follow-up TODOs: none Follow-up TODOs: none
--> -->
packages/casan-harness/scripts/bash/guideH4-H5-H6.md
+2 -2
View File
@@ -15,11 +15,11 @@ LOG + TRACE + METRICS + AUDIT
Unified wrapper: Unified wrapper:
```bash ```bash
.specify/scripts/bash/casan-harness.sh input.txt output.txt agent_step packages/casan-harness/scripts/bash/casan-harness.sh input.txt output.txt agent_step
``` ```
Verification: Verification:
```bash ```bash
bash .specify/tests/run-casan4-harness-tests.sh bash packages/casan-harness/tests/run-casan4-harness-tests.sh
``` ```
packages/casan-harness/templates/plan-template.md
+1 -1
View File
@@ -3,7 +3,7 @@
**Branch**: `[###-feature-name]` | **Date**: [DATE] | **Spec**: [link] **Branch**: `[###-feature-name]` | **Date**: [DATE] | **Spec**: [link]
**Input**: Feature specification from `/specs/[###-feature-name]/spec.md` **Input**: Feature specification from `/specs/[###-feature-name]/spec.md`
**Note**: This template is filled in by the `/speckit.plan` command. See `.specify/templates/plan-template.md` for the execution workflow. **Note**: This template is filled in by the `/speckit.plan` command. See `packages/casan-harness/templates/plan-template.md` for the execution workflow.
## Summary ## Summary