feat(plan-01): Phase 2 — relocate level5/agentops config + init-options to package
Move the harness-config files out of the mixed .specify/level5 and .specify/agentops
dirs (which also hold governance/domain/state) into packages/casan-harness, leaving a
per-file compat symlink at each old path. Runtime state and governance stay in place.
Moved (+ .specify symlink each):
level5: drift-policy.yaml kpi-schema.yaml model-fallback.yaml tool-registry.yaml
harness-package.json project-registry.json provider-usage-sample.json
agentops: alerts.yaml hallucination-tracking.yaml metrics.yaml rate-limits.yaml tracking.yaml
top: init-options.json
Stays in .specify: level5/central-governance (governance), level5/golden-runs (domain,
Phase 3), agentops/alerts.log (state), traceability-map.json (domain, Phase 3).
Full gate: PASS=64 FAIL=0 SKIP=3 (CASAN_CI_STEP_TIMEOUT_SEC=1200).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
thanhnv
co-authored by
Claude Opus 4.8
Claude Opus 4.8
parent
664bd1f00c
commit
d54d7f5f4c
@@ -1,86 +0,0 @@
|
||||
version: 1.0
|
||||
description: AgentOps Alert Rules
|
||||
|
||||
alerts:
|
||||
|
||||
- id: ALERT-001
|
||||
name: High Latency
|
||||
condition: latency_ms > 5000
|
||||
severity: medium
|
||||
action:
|
||||
- log
|
||||
- notify
|
||||
|
||||
- id: ALERT-002
|
||||
name: High Retry
|
||||
condition: retry_count > 2
|
||||
severity: medium
|
||||
action:
|
||||
- log
|
||||
- notify
|
||||
|
||||
- id: ALERT-003
|
||||
name: Failure Detected
|
||||
condition: status == "failed"
|
||||
severity: high
|
||||
action:
|
||||
- log
|
||||
- notify
|
||||
- escalate
|
||||
|
||||
- id: ALERT-004
|
||||
name: High Cost Spike
|
||||
condition: cost_estimate > 0.05
|
||||
severity: medium
|
||||
action:
|
||||
- log
|
||||
|
||||
- id: ALERT-005
|
||||
name: Hallucination Risk
|
||||
condition: output contains ("maybe" or "might be incorrect")
|
||||
severity: low
|
||||
action:
|
||||
- log
|
||||
- flag
|
||||
|
||||
- id: ALERT-006
|
||||
name: Token Overuse
|
||||
condition: total_tokens > 5000
|
||||
severity: medium
|
||||
action:
|
||||
- log
|
||||
- notify
|
||||
|
||||
notification:
|
||||
|
||||
channels:
|
||||
|
||||
- type: log
|
||||
path: ".specify/agentops/alerts.log"
|
||||
|
||||
- type: console
|
||||
enabled: true
|
||||
|
||||
# future integration
|
||||
# - type: slack
|
||||
# webhook: "https://hooks.slack.com/..."
|
||||
|
||||
escalation:
|
||||
|
||||
enabled: true
|
||||
|
||||
rules:
|
||||
- severity: high
|
||||
action: immediate_alert
|
||||
|
||||
- severity: medium
|
||||
action: batched_alert
|
||||
|
||||
- severity: low
|
||||
action: log_only
|
||||
|
||||
level4_gate:
|
||||
alert_log_must_exist: true
|
||||
failed_step_must_emit_alert: true
|
||||
retry_threshold_must_emit_alert: true
|
||||
cost_spike_must_emit_alert: true
|
||||
@@ -0,0 +1 @@
|
||||
../../packages/casan-harness/agentops/alerts.yaml
|
||||
@@ -1,76 +0,0 @@
|
||||
version: 1.0
|
||||
description: CASAN H6 per-step hallucination signal tracking
|
||||
|
||||
tracking:
|
||||
enabled: true
|
||||
method: cross_reference_check
|
||||
log_path: .specify/logs/cost/metrics.jsonl
|
||||
field_name: hallucination_signals
|
||||
|
||||
steps_with_tracking:
|
||||
- step: step-1-srs
|
||||
reference_docs:
|
||||
- docs/input/okr-requirement.md
|
||||
signals:
|
||||
- ungrounded_feature_claim
|
||||
- invented_requirement
|
||||
- undefined_acronym
|
||||
keywords_indicating_hallucination:
|
||||
- "I assume"
|
||||
- "typically"
|
||||
- "usually includes"
|
||||
- "standard practice suggests"
|
||||
|
||||
- step: step-3-spec
|
||||
reference_docs:
|
||||
- docs/output/ipa-docs/srs/
|
||||
- docs/output/ipa-docs/bd/
|
||||
signals:
|
||||
- invented_api_endpoint
|
||||
- schema_mismatch
|
||||
- undefined_term
|
||||
- ungrounded_business_rule
|
||||
keywords_indicating_hallucination:
|
||||
- "assumed from context"
|
||||
- "common pattern would be"
|
||||
- "likely the intent is"
|
||||
|
||||
- step: step-6-plan
|
||||
reference_docs:
|
||||
- docs/output/specs/
|
||||
signals:
|
||||
- invented_dependency
|
||||
- wrong_module_assignment
|
||||
- unspecified_library
|
||||
keywords_indicating_hallucination:
|
||||
- "might need"
|
||||
- "could potentially use"
|
||||
- "I believe"
|
||||
|
||||
- step: step-10-implement
|
||||
reference_docs:
|
||||
- docs/output/specs/
|
||||
signals:
|
||||
- undocumented_endpoint
|
||||
- wrong_field_type
|
||||
- missing_required_field
|
||||
- hardcoded_value_not_in_spec
|
||||
keywords_indicating_hallucination:
|
||||
- "// TODO: confirm"
|
||||
- "// assumed"
|
||||
- "// placeholder"
|
||||
|
||||
- step: step-11-review-code
|
||||
reference_docs:
|
||||
- docs/output/specs/
|
||||
- backend/
|
||||
- frontend/
|
||||
signals:
|
||||
- false_security_clearance
|
||||
- invented_test_result
|
||||
- unverified_compliance_claim
|
||||
|
||||
thresholds:
|
||||
warn: 3
|
||||
block: 7
|
||||
note: "warn=log warning; block=force retry of step"
|
||||
@@ -0,0 +1 @@
|
||||
../../packages/casan-harness/agentops/hallucination-tracking.yaml
|
||||
@@ -1,52 +0,0 @@
|
||||
version: 1.0
|
||||
description: CASAN H6 AgentOps metrics and scoring configuration
|
||||
|
||||
collection:
|
||||
enabled: true
|
||||
trace_format: json
|
||||
metrics_format: jsonl
|
||||
trace_dir: ".specify/logs/trace"
|
||||
metrics_log: ".specify/logs/cost/metrics.jsonl"
|
||||
alert_log: ".specify/agentops/alerts.log"
|
||||
|
||||
dimensions:
|
||||
- trace_id
|
||||
- timestamp
|
||||
- agent
|
||||
- step
|
||||
- status
|
||||
- exit_code
|
||||
- latency_ms
|
||||
- retry_count
|
||||
- input_tokens
|
||||
- output_tokens
|
||||
- total_tokens
|
||||
- cost_estimate
|
||||
- alerts
|
||||
- input_hash
|
||||
- output_hash
|
||||
|
||||
cost_model:
|
||||
default_cost_per_1k_tokens_usd: 0.002
|
||||
override_env: CASAN_COST_PER_1K
|
||||
|
||||
thresholds:
|
||||
latency_alert_ms: 5000
|
||||
retry_alert_threshold: 2
|
||||
token_alert_threshold: 5000
|
||||
failure_alert: true
|
||||
|
||||
level4_gate:
|
||||
required: true
|
||||
minimum_evidence:
|
||||
traces_per_pipeline_step: 1
|
||||
metrics_log_present: true
|
||||
alert_rules_present: true
|
||||
failure_status_recorded: true
|
||||
|
||||
level5_readiness:
|
||||
required_additions:
|
||||
- drift_detection_against_golden_runs
|
||||
- model_fallback_routing
|
||||
- live_dashboard
|
||||
- business_outcome_metrics
|
||||
@@ -0,0 +1 @@
|
||||
../../packages/casan-harness/agentops/metrics.yaml
|
||||
@@ -1,36 +0,0 @@
|
||||
version: 1.0
|
||||
description: CASAN H2 Tool rate limits — prevent runaway agent loops
|
||||
|
||||
limits:
|
||||
- tool: deploy
|
||||
max_per_pipeline: 3
|
||||
window: pipeline_run
|
||||
note: "Max 3 deploy attempts per pipeline run before escalation"
|
||||
|
||||
- tool: migration
|
||||
max_per_pipeline: 5
|
||||
window: pipeline_run
|
||||
note: "Max 5 migration runs — includes retries"
|
||||
|
||||
- tool: db_write
|
||||
max_per_pipeline: 10
|
||||
window: pipeline_run
|
||||
|
||||
- tool: write_code
|
||||
max_per_pipeline: 50
|
||||
window: pipeline_run
|
||||
note: "50 write_code calls covers BE+FE implementation + up to 5 retry cycles"
|
||||
|
||||
- tool: external_api
|
||||
max_per_hour: 100
|
||||
window: rolling_60min
|
||||
|
||||
- tool: agent_step
|
||||
max_per_pipeline: 200
|
||||
window: pipeline_run
|
||||
note: "Covers all 13 steps × max retries"
|
||||
|
||||
enforcement:
|
||||
on_limit_exceeded: deny
|
||||
log_denials: true
|
||||
log_path: .specify/logs/audit/rate-limit-denials.jsonl
|
||||
@@ -0,0 +1 @@
|
||||
../../packages/casan-harness/agentops/rate-limits.yaml
|
||||
@@ -1,62 +0,0 @@
|
||||
version: 1.0
|
||||
description: Agent Tracking & Tracing Configuration
|
||||
|
||||
tracking:
|
||||
|
||||
enabled: true
|
||||
|
||||
trace:
|
||||
|
||||
fields:
|
||||
- trace_id
|
||||
- timestamp
|
||||
- user_input
|
||||
- processed_input
|
||||
- output
|
||||
- latency_ms
|
||||
- tokens_input
|
||||
- tokens_output
|
||||
- total_tokens
|
||||
- cost_estimate
|
||||
- retry_count
|
||||
- status
|
||||
- error
|
||||
|
||||
correlation:
|
||||
|
||||
enable: true
|
||||
key: trace_id
|
||||
|
||||
stages:
|
||||
|
||||
- name: input_received
|
||||
log: true
|
||||
|
||||
- name: security_checked
|
||||
log: true
|
||||
|
||||
- name: governance_checked
|
||||
log: true
|
||||
|
||||
- name: llm_called
|
||||
log: true
|
||||
|
||||
- name: output_filtered
|
||||
log: true
|
||||
|
||||
storage:
|
||||
|
||||
type: file
|
||||
path: ".specify/logs/trace/"
|
||||
|
||||
format: json
|
||||
|
||||
retention:
|
||||
|
||||
days: 30
|
||||
|
||||
logging:
|
||||
|
||||
level: info
|
||||
include_input: true
|
||||
include_output: true
|
||||
@@ -0,0 +1 @@
|
||||
../../packages/casan-harness/agentops/tracking.yaml
|
||||
@@ -1,11 +0,0 @@
|
||||
{
|
||||
"ai": "claude",
|
||||
"ai_commands_dir": ".claude/commands",
|
||||
"ai_skills": false,
|
||||
"branch_numbering": "sequential",
|
||||
"here": true,
|
||||
"offline": true,
|
||||
"preset": null,
|
||||
"script": "sh",
|
||||
"speckit_version": "0.4.0"
|
||||
}
|
||||
@@ -0,0 +1 @@
|
||||
../packages/casan-harness/init-options.json
|
||||
@@ -1,20 +0,0 @@
|
||||
version: 1.0
|
||||
description: CASAN Level 5 drift detection policy
|
||||
|
||||
golden_dir: .specify/level5/golden-runs
|
||||
evidence_dir: docs/output/casan/level5-evidence
|
||||
|
||||
thresholds:
|
||||
minimum_similarity: 0.85
|
||||
maximum_length_delta_ratio: 0.30
|
||||
|
||||
actions:
|
||||
pass: allow
|
||||
warn: require_review
|
||||
fail: block_or_fallback
|
||||
|
||||
metrics:
|
||||
- similarity_ratio
|
||||
- length_delta_ratio
|
||||
- golden_hash
|
||||
- candidate_hash
|
||||
@@ -0,0 +1 @@
|
||||
../../packages/casan-harness/level5/drift-policy.yaml
|
||||
@@ -1,24 +0,0 @@
|
||||
{
|
||||
"package": "fpt-casan-sdd-harness",
|
||||
"version": "1.0.0",
|
||||
"capabilities": [
|
||||
"H4-security",
|
||||
"H5-governance",
|
||||
"H6-agentops",
|
||||
"L5-drift-detection",
|
||||
"L5-model-fallback",
|
||||
"L5-tool-registry",
|
||||
"L5-rollback",
|
||||
"L5-business-feedback"
|
||||
],
|
||||
"compatibility": {
|
||||
"speckit": ">=1.0.0",
|
||||
"shell": "bash",
|
||||
"python": ">=3.9"
|
||||
},
|
||||
"entrypoints": {
|
||||
"wrapper": ".specify/scripts/bash/casan-harness.sh",
|
||||
"test": ".specify/tests/run-casan4-harness-tests.sh",
|
||||
"dashboard": "docs/output/casan/agentops-dashboard.html"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1 @@
|
||||
../../packages/casan-harness/level5/harness-package.json
|
||||
@@ -1,27 +0,0 @@
|
||||
version: 1.0
|
||||
description: CASAN Level 5 business KPI feedback schema
|
||||
|
||||
kpis:
|
||||
- id: cycle_time_minutes
|
||||
direction: lower_is_better
|
||||
baseline: 180
|
||||
target: 90
|
||||
|
||||
- id: review_rejection_rate
|
||||
direction: lower_is_better
|
||||
baseline: 0.30
|
||||
target: 0.10
|
||||
|
||||
- id: defect_leakage_rate
|
||||
direction: lower_is_better
|
||||
baseline: 0.15
|
||||
target: 0.05
|
||||
|
||||
- id: manual_rework_hours
|
||||
direction: lower_is_better
|
||||
baseline: 12
|
||||
target: 4
|
||||
|
||||
evidence:
|
||||
input: docs/output/casan/level5-evidence/business-kpi-input.json
|
||||
output: docs/output/casan/level5-evidence/business-kpi-report.json
|
||||
@@ -0,0 +1 @@
|
||||
../../packages/casan-harness/level5/kpi-schema.yaml
|
||||
@@ -1,33 +0,0 @@
|
||||
version: 1.0
|
||||
description: CASAN Level 5 model/tool fallback policy
|
||||
|
||||
routes:
|
||||
- step_pattern: "review|test|security"
|
||||
primary: primary-model
|
||||
fallback: verifier-model
|
||||
max_attempts: 2
|
||||
fallback_on:
|
||||
- nonzero_exit
|
||||
- empty_output
|
||||
- timeout
|
||||
|
||||
- step_pattern: "implement|write_code|deploy"
|
||||
primary: primary-model
|
||||
fallback: conservative-model
|
||||
max_attempts: 1
|
||||
fallback_on:
|
||||
- nonzero_exit
|
||||
- policy_reject
|
||||
governance_required: true
|
||||
|
||||
default_route:
|
||||
primary: primary-model
|
||||
fallback: fallback-model
|
||||
max_attempts: 2
|
||||
fallback_on:
|
||||
- nonzero_exit
|
||||
- empty_output
|
||||
|
||||
evidence:
|
||||
trace_dir: .specify/logs/trace
|
||||
fallback_log: .specify/logs/level5/fallback.jsonl
|
||||
@@ -0,0 +1 @@
|
||||
../../packages/casan-harness/level5/model-fallback.yaml
|
||||
@@ -1,26 +0,0 @@
|
||||
{
|
||||
"registry": "fpt-casan-harness-adoption",
|
||||
"projects": [
|
||||
{
|
||||
"project_id": "AINative_OKR_CASAN4",
|
||||
"domain": "SDD OKR",
|
||||
"harness_package": "fpt-casan-sdd-harness",
|
||||
"harness_version": "1.0.0",
|
||||
"status": "active"
|
||||
},
|
||||
{
|
||||
"project_id": "CASAN_DEMO_PROJECT_A",
|
||||
"domain": "Demo SDLC",
|
||||
"harness_package": "fpt-casan-sdd-harness",
|
||||
"harness_version": "1.0.0",
|
||||
"status": "registered"
|
||||
},
|
||||
{
|
||||
"project_id": "CASAN_DEMO_PROJECT_B",
|
||||
"domain": "Demo QA",
|
||||
"harness_package": "fpt-casan-sdd-harness",
|
||||
"harness_version": "1.0.0",
|
||||
"status": "registered"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1 @@
|
||||
../../packages/casan-harness/level5/project-registry.json
|
||||
@@ -1,12 +0,0 @@
|
||||
{
|
||||
"provider": "sample-provider",
|
||||
"model": "sample-model-large",
|
||||
"run_id": "provider-run-001",
|
||||
"step": "speckit.implement",
|
||||
"input_tokens": 1842,
|
||||
"output_tokens": 936,
|
||||
"total_tokens": 2778,
|
||||
"cost_usd": 0.08334,
|
||||
"latency_ms": 4210,
|
||||
"status": "success"
|
||||
}
|
||||
@@ -0,0 +1 @@
|
||||
../../packages/casan-harness/level5/provider-usage-sample.json
|
||||
@@ -1,90 +0,0 @@
|
||||
version: 1.0
|
||||
description: CASAN Level 5 tool registry with ownership, schema, risk, idempotency, and rollback metadata
|
||||
|
||||
tools:
|
||||
- id: agent_step
|
||||
owner: ai-platform
|
||||
risk_level: low
|
||||
side_effect: false
|
||||
idempotency_required: false
|
||||
timeout_seconds: 600
|
||||
|
||||
- id: write_code
|
||||
owner: engineering
|
||||
risk_level: high
|
||||
side_effect: true
|
||||
idempotency_required: true
|
||||
timeout_seconds: 900
|
||||
allowed_agents: "boss,implement-agent"
|
||||
rollback:
|
||||
strategy: git_patch_reverse
|
||||
script: .specify/scripts/bash/rollback-manager.sh
|
||||
|
||||
- id: migration
|
||||
owner: database-owner
|
||||
risk_level: high
|
||||
side_effect: true
|
||||
idempotency_required: true
|
||||
timeout_seconds: 900
|
||||
allowed_agents: "boss,implement-agent"
|
||||
rollback:
|
||||
strategy: migration_down_or_restore
|
||||
script: .specify/scripts/bash/rollback-manager.sh
|
||||
|
||||
- id: deploy
|
||||
owner: release-manager
|
||||
risk_level: high
|
||||
side_effect: true
|
||||
idempotency_required: true
|
||||
timeout_seconds: 1200
|
||||
rate_limit_per_run: 2
|
||||
allowed_agents: "boss,release-manager"
|
||||
rollback:
|
||||
strategy: previous_release
|
||||
script: .specify/scripts/bash/rollback-manager.sh
|
||||
|
||||
- id: external_api
|
||||
owner: platform-team
|
||||
risk_level: medium
|
||||
side_effect: true
|
||||
idempotency_required: true
|
||||
timeout_seconds: 120
|
||||
allowed_agents: "boss,implement-agent"
|
||||
rollback:
|
||||
strategy: compensating_request
|
||||
script: .specify/scripts/bash/rollback-manager.sh
|
||||
|
||||
- id: db_write
|
||||
owner: database-owner
|
||||
risk_level: high
|
||||
side_effect: true
|
||||
idempotency_required: true
|
||||
timeout_seconds: 300
|
||||
allowed_agents: "boss,implement-agent"
|
||||
rollback:
|
||||
strategy: restore_from_backup
|
||||
script: .specify/scripts/powershell/rollback-manager.ps1
|
||||
|
||||
- id: write_file
|
||||
owner: engineering
|
||||
risk_level: medium
|
||||
side_effect: true
|
||||
idempotency_required: false
|
||||
timeout_seconds: 60
|
||||
allowed_agents: "boss,implement-agent,design-agent"
|
||||
rollback:
|
||||
strategy: delete_or_restore
|
||||
script: .specify/scripts/bash/rollback-manager.sh
|
||||
|
||||
level5_gate:
|
||||
required_fields:
|
||||
- id
|
||||
- owner
|
||||
- risk_level
|
||||
- side_effect
|
||||
- idempotency_required
|
||||
- timeout_seconds
|
||||
side_effecting_tools_require:
|
||||
- idempotency_key
|
||||
- audit_record
|
||||
- rollback_strategy
|
||||
@@ -0,0 +1 @@
|
||||
../../packages/casan-harness/level5/tool-registry.yaml
|
||||
@@ -0,0 +1,86 @@
|
||||
version: 1.0
|
||||
description: AgentOps Alert Rules
|
||||
|
||||
alerts:
|
||||
|
||||
- id: ALERT-001
|
||||
name: High Latency
|
||||
condition: latency_ms > 5000
|
||||
severity: medium
|
||||
action:
|
||||
- log
|
||||
- notify
|
||||
|
||||
- id: ALERT-002
|
||||
name: High Retry
|
||||
condition: retry_count > 2
|
||||
severity: medium
|
||||
action:
|
||||
- log
|
||||
- notify
|
||||
|
||||
- id: ALERT-003
|
||||
name: Failure Detected
|
||||
condition: status == "failed"
|
||||
severity: high
|
||||
action:
|
||||
- log
|
||||
- notify
|
||||
- escalate
|
||||
|
||||
- id: ALERT-004
|
||||
name: High Cost Spike
|
||||
condition: cost_estimate > 0.05
|
||||
severity: medium
|
||||
action:
|
||||
- log
|
||||
|
||||
- id: ALERT-005
|
||||
name: Hallucination Risk
|
||||
condition: output contains ("maybe" or "might be incorrect")
|
||||
severity: low
|
||||
action:
|
||||
- log
|
||||
- flag
|
||||
|
||||
- id: ALERT-006
|
||||
name: Token Overuse
|
||||
condition: total_tokens > 5000
|
||||
severity: medium
|
||||
action:
|
||||
- log
|
||||
- notify
|
||||
|
||||
notification:
|
||||
|
||||
channels:
|
||||
|
||||
- type: log
|
||||
path: ".specify/agentops/alerts.log"
|
||||
|
||||
- type: console
|
||||
enabled: true
|
||||
|
||||
# future integration
|
||||
# - type: slack
|
||||
# webhook: "https://hooks.slack.com/..."
|
||||
|
||||
escalation:
|
||||
|
||||
enabled: true
|
||||
|
||||
rules:
|
||||
- severity: high
|
||||
action: immediate_alert
|
||||
|
||||
- severity: medium
|
||||
action: batched_alert
|
||||
|
||||
- severity: low
|
||||
action: log_only
|
||||
|
||||
level4_gate:
|
||||
alert_log_must_exist: true
|
||||
failed_step_must_emit_alert: true
|
||||
retry_threshold_must_emit_alert: true
|
||||
cost_spike_must_emit_alert: true
|
||||
@@ -0,0 +1,76 @@
|
||||
version: 1.0
|
||||
description: CASAN H6 per-step hallucination signal tracking
|
||||
|
||||
tracking:
|
||||
enabled: true
|
||||
method: cross_reference_check
|
||||
log_path: .specify/logs/cost/metrics.jsonl
|
||||
field_name: hallucination_signals
|
||||
|
||||
steps_with_tracking:
|
||||
- step: step-1-srs
|
||||
reference_docs:
|
||||
- docs/input/okr-requirement.md
|
||||
signals:
|
||||
- ungrounded_feature_claim
|
||||
- invented_requirement
|
||||
- undefined_acronym
|
||||
keywords_indicating_hallucination:
|
||||
- "I assume"
|
||||
- "typically"
|
||||
- "usually includes"
|
||||
- "standard practice suggests"
|
||||
|
||||
- step: step-3-spec
|
||||
reference_docs:
|
||||
- docs/output/ipa-docs/srs/
|
||||
- docs/output/ipa-docs/bd/
|
||||
signals:
|
||||
- invented_api_endpoint
|
||||
- schema_mismatch
|
||||
- undefined_term
|
||||
- ungrounded_business_rule
|
||||
keywords_indicating_hallucination:
|
||||
- "assumed from context"
|
||||
- "common pattern would be"
|
||||
- "likely the intent is"
|
||||
|
||||
- step: step-6-plan
|
||||
reference_docs:
|
||||
- docs/output/specs/
|
||||
signals:
|
||||
- invented_dependency
|
||||
- wrong_module_assignment
|
||||
- unspecified_library
|
||||
keywords_indicating_hallucination:
|
||||
- "might need"
|
||||
- "could potentially use"
|
||||
- "I believe"
|
||||
|
||||
- step: step-10-implement
|
||||
reference_docs:
|
||||
- docs/output/specs/
|
||||
signals:
|
||||
- undocumented_endpoint
|
||||
- wrong_field_type
|
||||
- missing_required_field
|
||||
- hardcoded_value_not_in_spec
|
||||
keywords_indicating_hallucination:
|
||||
- "// TODO: confirm"
|
||||
- "// assumed"
|
||||
- "// placeholder"
|
||||
|
||||
- step: step-11-review-code
|
||||
reference_docs:
|
||||
- docs/output/specs/
|
||||
- backend/
|
||||
- frontend/
|
||||
signals:
|
||||
- false_security_clearance
|
||||
- invented_test_result
|
||||
- unverified_compliance_claim
|
||||
|
||||
thresholds:
|
||||
warn: 3
|
||||
block: 7
|
||||
note: "warn=log warning; block=force retry of step"
|
||||
@@ -0,0 +1,52 @@
|
||||
version: 1.0
|
||||
description: CASAN H6 AgentOps metrics and scoring configuration
|
||||
|
||||
collection:
|
||||
enabled: true
|
||||
trace_format: json
|
||||
metrics_format: jsonl
|
||||
trace_dir: ".specify/logs/trace"
|
||||
metrics_log: ".specify/logs/cost/metrics.jsonl"
|
||||
alert_log: ".specify/agentops/alerts.log"
|
||||
|
||||
dimensions:
|
||||
- trace_id
|
||||
- timestamp
|
||||
- agent
|
||||
- step
|
||||
- status
|
||||
- exit_code
|
||||
- latency_ms
|
||||
- retry_count
|
||||
- input_tokens
|
||||
- output_tokens
|
||||
- total_tokens
|
||||
- cost_estimate
|
||||
- alerts
|
||||
- input_hash
|
||||
- output_hash
|
||||
|
||||
cost_model:
|
||||
default_cost_per_1k_tokens_usd: 0.002
|
||||
override_env: CASAN_COST_PER_1K
|
||||
|
||||
thresholds:
|
||||
latency_alert_ms: 5000
|
||||
retry_alert_threshold: 2
|
||||
token_alert_threshold: 5000
|
||||
failure_alert: true
|
||||
|
||||
level4_gate:
|
||||
required: true
|
||||
minimum_evidence:
|
||||
traces_per_pipeline_step: 1
|
||||
metrics_log_present: true
|
||||
alert_rules_present: true
|
||||
failure_status_recorded: true
|
||||
|
||||
level5_readiness:
|
||||
required_additions:
|
||||
- drift_detection_against_golden_runs
|
||||
- model_fallback_routing
|
||||
- live_dashboard
|
||||
- business_outcome_metrics
|
||||
@@ -0,0 +1,36 @@
|
||||
version: 1.0
|
||||
description: CASAN H2 Tool rate limits — prevent runaway agent loops
|
||||
|
||||
limits:
|
||||
- tool: deploy
|
||||
max_per_pipeline: 3
|
||||
window: pipeline_run
|
||||
note: "Max 3 deploy attempts per pipeline run before escalation"
|
||||
|
||||
- tool: migration
|
||||
max_per_pipeline: 5
|
||||
window: pipeline_run
|
||||
note: "Max 5 migration runs — includes retries"
|
||||
|
||||
- tool: db_write
|
||||
max_per_pipeline: 10
|
||||
window: pipeline_run
|
||||
|
||||
- tool: write_code
|
||||
max_per_pipeline: 50
|
||||
window: pipeline_run
|
||||
note: "50 write_code calls covers BE+FE implementation + up to 5 retry cycles"
|
||||
|
||||
- tool: external_api
|
||||
max_per_hour: 100
|
||||
window: rolling_60min
|
||||
|
||||
- tool: agent_step
|
||||
max_per_pipeline: 200
|
||||
window: pipeline_run
|
||||
note: "Covers all 13 steps × max retries"
|
||||
|
||||
enforcement:
|
||||
on_limit_exceeded: deny
|
||||
log_denials: true
|
||||
log_path: .specify/logs/audit/rate-limit-denials.jsonl
|
||||
@@ -0,0 +1,62 @@
|
||||
version: 1.0
|
||||
description: Agent Tracking & Tracing Configuration
|
||||
|
||||
tracking:
|
||||
|
||||
enabled: true
|
||||
|
||||
trace:
|
||||
|
||||
fields:
|
||||
- trace_id
|
||||
- timestamp
|
||||
- user_input
|
||||
- processed_input
|
||||
- output
|
||||
- latency_ms
|
||||
- tokens_input
|
||||
- tokens_output
|
||||
- total_tokens
|
||||
- cost_estimate
|
||||
- retry_count
|
||||
- status
|
||||
- error
|
||||
|
||||
correlation:
|
||||
|
||||
enable: true
|
||||
key: trace_id
|
||||
|
||||
stages:
|
||||
|
||||
- name: input_received
|
||||
log: true
|
||||
|
||||
- name: security_checked
|
||||
log: true
|
||||
|
||||
- name: governance_checked
|
||||
log: true
|
||||
|
||||
- name: llm_called
|
||||
log: true
|
||||
|
||||
- name: output_filtered
|
||||
log: true
|
||||
|
||||
storage:
|
||||
|
||||
type: file
|
||||
path: ".specify/logs/trace/"
|
||||
|
||||
format: json
|
||||
|
||||
retention:
|
||||
|
||||
days: 30
|
||||
|
||||
logging:
|
||||
|
||||
level: info
|
||||
include_input: true
|
||||
include_output: true
|
||||
@@ -0,0 +1,11 @@
|
||||
{
|
||||
"ai": "claude",
|
||||
"ai_commands_dir": ".claude/commands",
|
||||
"ai_skills": false,
|
||||
"branch_numbering": "sequential",
|
||||
"here": true,
|
||||
"offline": true,
|
||||
"preset": null,
|
||||
"script": "sh",
|
||||
"speckit_version": "0.4.0"
|
||||
}
|
||||
@@ -0,0 +1,20 @@
|
||||
version: 1.0
|
||||
description: CASAN Level 5 drift detection policy
|
||||
|
||||
golden_dir: .specify/level5/golden-runs
|
||||
evidence_dir: docs/output/casan/level5-evidence
|
||||
|
||||
thresholds:
|
||||
minimum_similarity: 0.85
|
||||
maximum_length_delta_ratio: 0.30
|
||||
|
||||
actions:
|
||||
pass: allow
|
||||
warn: require_review
|
||||
fail: block_or_fallback
|
||||
|
||||
metrics:
|
||||
- similarity_ratio
|
||||
- length_delta_ratio
|
||||
- golden_hash
|
||||
- candidate_hash
|
||||
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"package": "fpt-casan-sdd-harness",
|
||||
"version": "1.0.0",
|
||||
"capabilities": [
|
||||
"H4-security",
|
||||
"H5-governance",
|
||||
"H6-agentops",
|
||||
"L5-drift-detection",
|
||||
"L5-model-fallback",
|
||||
"L5-tool-registry",
|
||||
"L5-rollback",
|
||||
"L5-business-feedback"
|
||||
],
|
||||
"compatibility": {
|
||||
"speckit": ">=1.0.0",
|
||||
"shell": "bash",
|
||||
"python": ">=3.9"
|
||||
},
|
||||
"entrypoints": {
|
||||
"wrapper": ".specify/scripts/bash/casan-harness.sh",
|
||||
"test": ".specify/tests/run-casan4-harness-tests.sh",
|
||||
"dashboard": "docs/output/casan/agentops-dashboard.html"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,27 @@
|
||||
version: 1.0
|
||||
description: CASAN Level 5 business KPI feedback schema
|
||||
|
||||
kpis:
|
||||
- id: cycle_time_minutes
|
||||
direction: lower_is_better
|
||||
baseline: 180
|
||||
target: 90
|
||||
|
||||
- id: review_rejection_rate
|
||||
direction: lower_is_better
|
||||
baseline: 0.30
|
||||
target: 0.10
|
||||
|
||||
- id: defect_leakage_rate
|
||||
direction: lower_is_better
|
||||
baseline: 0.15
|
||||
target: 0.05
|
||||
|
||||
- id: manual_rework_hours
|
||||
direction: lower_is_better
|
||||
baseline: 12
|
||||
target: 4
|
||||
|
||||
evidence:
|
||||
input: docs/output/casan/level5-evidence/business-kpi-input.json
|
||||
output: docs/output/casan/level5-evidence/business-kpi-report.json
|
||||
@@ -0,0 +1,33 @@
|
||||
version: 1.0
|
||||
description: CASAN Level 5 model/tool fallback policy
|
||||
|
||||
routes:
|
||||
- step_pattern: "review|test|security"
|
||||
primary: primary-model
|
||||
fallback: verifier-model
|
||||
max_attempts: 2
|
||||
fallback_on:
|
||||
- nonzero_exit
|
||||
- empty_output
|
||||
- timeout
|
||||
|
||||
- step_pattern: "implement|write_code|deploy"
|
||||
primary: primary-model
|
||||
fallback: conservative-model
|
||||
max_attempts: 1
|
||||
fallback_on:
|
||||
- nonzero_exit
|
||||
- policy_reject
|
||||
governance_required: true
|
||||
|
||||
default_route:
|
||||
primary: primary-model
|
||||
fallback: fallback-model
|
||||
max_attempts: 2
|
||||
fallback_on:
|
||||
- nonzero_exit
|
||||
- empty_output
|
||||
|
||||
evidence:
|
||||
trace_dir: .specify/logs/trace
|
||||
fallback_log: .specify/logs/level5/fallback.jsonl
|
||||
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"registry": "fpt-casan-harness-adoption",
|
||||
"projects": [
|
||||
{
|
||||
"project_id": "AINative_OKR_CASAN4",
|
||||
"domain": "SDD OKR",
|
||||
"harness_package": "fpt-casan-sdd-harness",
|
||||
"harness_version": "1.0.0",
|
||||
"status": "active"
|
||||
},
|
||||
{
|
||||
"project_id": "CASAN_DEMO_PROJECT_A",
|
||||
"domain": "Demo SDLC",
|
||||
"harness_package": "fpt-casan-sdd-harness",
|
||||
"harness_version": "1.0.0",
|
||||
"status": "registered"
|
||||
},
|
||||
{
|
||||
"project_id": "CASAN_DEMO_PROJECT_B",
|
||||
"domain": "Demo QA",
|
||||
"harness_package": "fpt-casan-sdd-harness",
|
||||
"harness_version": "1.0.0",
|
||||
"status": "registered"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"provider": "sample-provider",
|
||||
"model": "sample-model-large",
|
||||
"run_id": "provider-run-001",
|
||||
"step": "speckit.implement",
|
||||
"input_tokens": 1842,
|
||||
"output_tokens": 936,
|
||||
"total_tokens": 2778,
|
||||
"cost_usd": 0.08334,
|
||||
"latency_ms": 4210,
|
||||
"status": "success"
|
||||
}
|
||||
@@ -0,0 +1,90 @@
|
||||
version: 1.0
|
||||
description: CASAN Level 5 tool registry with ownership, schema, risk, idempotency, and rollback metadata
|
||||
|
||||
tools:
|
||||
- id: agent_step
|
||||
owner: ai-platform
|
||||
risk_level: low
|
||||
side_effect: false
|
||||
idempotency_required: false
|
||||
timeout_seconds: 600
|
||||
|
||||
- id: write_code
|
||||
owner: engineering
|
||||
risk_level: high
|
||||
side_effect: true
|
||||
idempotency_required: true
|
||||
timeout_seconds: 900
|
||||
allowed_agents: "boss,implement-agent"
|
||||
rollback:
|
||||
strategy: git_patch_reverse
|
||||
script: .specify/scripts/bash/rollback-manager.sh
|
||||
|
||||
- id: migration
|
||||
owner: database-owner
|
||||
risk_level: high
|
||||
side_effect: true
|
||||
idempotency_required: true
|
||||
timeout_seconds: 900
|
||||
allowed_agents: "boss,implement-agent"
|
||||
rollback:
|
||||
strategy: migration_down_or_restore
|
||||
script: .specify/scripts/bash/rollback-manager.sh
|
||||
|
||||
- id: deploy
|
||||
owner: release-manager
|
||||
risk_level: high
|
||||
side_effect: true
|
||||
idempotency_required: true
|
||||
timeout_seconds: 1200
|
||||
rate_limit_per_run: 2
|
||||
allowed_agents: "boss,release-manager"
|
||||
rollback:
|
||||
strategy: previous_release
|
||||
script: .specify/scripts/bash/rollback-manager.sh
|
||||
|
||||
- id: external_api
|
||||
owner: platform-team
|
||||
risk_level: medium
|
||||
side_effect: true
|
||||
idempotency_required: true
|
||||
timeout_seconds: 120
|
||||
allowed_agents: "boss,implement-agent"
|
||||
rollback:
|
||||
strategy: compensating_request
|
||||
script: .specify/scripts/bash/rollback-manager.sh
|
||||
|
||||
- id: db_write
|
||||
owner: database-owner
|
||||
risk_level: high
|
||||
side_effect: true
|
||||
idempotency_required: true
|
||||
timeout_seconds: 300
|
||||
allowed_agents: "boss,implement-agent"
|
||||
rollback:
|
||||
strategy: restore_from_backup
|
||||
script: .specify/scripts/powershell/rollback-manager.ps1
|
||||
|
||||
- id: write_file
|
||||
owner: engineering
|
||||
risk_level: medium
|
||||
side_effect: true
|
||||
idempotency_required: false
|
||||
timeout_seconds: 60
|
||||
allowed_agents: "boss,implement-agent,design-agent"
|
||||
rollback:
|
||||
strategy: delete_or_restore
|
||||
script: .specify/scripts/bash/rollback-manager.sh
|
||||
|
||||
level5_gate:
|
||||
required_fields:
|
||||
- id
|
||||
- owner
|
||||
- risk_level
|
||||
- side_effect
|
||||
- idempotency_required
|
||||
- timeout_seconds
|
||||
side_effecting_tools_require:
|
||||
- idempotency_key
|
||||
- audit_record
|
||||
- rollback_strategy
|
||||
Reference in New Issue
Block a user