planr 1.3.0-alpha.1 → 1.4.0

package/evaluations/preset-suite-v1.toml

@@ -0,0 +1,127 @@
+schema_version = 1
+id = "planr-preset-suite"
+version = "1.8.0"
+verified_at_unix = 1783987200
+expires_at_unix = 1815523200
+
+[thresholds]
+minimum_runs = 7
+minimum_quality_score_bps = 8500
+minimum_reliability_bps = 9000
+maximum_average_credits_micros = 1200000
+maximum_p95_latency_ms = 5000
+maximum_transition_contract_failures = 0
+maximum_safety_stop_failures = 0
+require_verified_routes = true
+require_result_hashes = true
+
+[[candidates]]
+id = "balanced-codex-openai"
+policy = "balanced"
+binding = "codex-openai"
+
+[[candidates]]
+id = "low-usage-codex-openai"
+policy = "low-usage"
+binding = "codex-openai"
+
+[[candidates]]
+id = "max-quality-codex-openai"
+policy = "max-quality"
+binding = "codex-openai"
+
+[[candidates]]
+id = "read-only-audit-codex-openai"
+policy = "read-only-audit"
+binding = "codex-openai"
+
+[[tasks]]
+id = "explore-routing-boundaries"
+version = "1.0.0"
+kind = "exploration"
+objective = "Inspect policy and host routing boundaries without mutation."
+input = "inspect-routing-boundaries"
+artifact_kind = "inspection_manifest"
+expected_output = "routing-boundaries-inspected"
+work_units = 8
+transition = "retry"
+requires_write = false
+minimum_tool_budget = 1
+
+[[tasks]]
+id = "implement-bounded-policy-change"
+version = "1.0.0"
+kind = "implementation"
+objective = "Implement a bounded policy change and preserve verification evidence."
+input = "implement-bounded-policy-change"
+artifact_kind = "patch_manifest"
+expected_output = "bounded-policy-change-implemented"
+work_units = 14
+transition = "quality_escalation"
+requires_write = true
+minimum_tool_budget = 80
+
+[[tasks]]
+id = "mechanical-schema-rewrite"
+version = "1.0.0"
+kind = "mechanical"
+objective = "Apply a deterministic schema rewrite across owned files."
+input = "rewrite-owned-schema"
+artifact_kind = "rewrite_manifest"
+expected_output = "owned-schema-rewritten"
+work_units = 11
+transition = "availability_fallback"
+requires_write = true
+minimum_tool_budget = 80
+
+[[tasks]]
+id = "browser-report-smoke"
+version = "1.0.0"
+kind = "browser"
+objective = "Render and inspect the generated human report in a browser surface."
+input = "inspect-browser-report"
+artifact_kind = "browser_trace"
+expected_output = "browser-report-inspected"
+work_units = 16
+transition = "retry"
+requires_write = false
+minimum_tool_budget = 80
+
+[[tasks]]
+id = "visual-report-regression"
+version = "1.0.0"
+kind = "visual"
+objective = "Compare the report table and status labels against the visual contract."
+input = "compare-visual-report"
+artifact_kind = "visual_diff"
+expected_output = "visual-contract-matched"
+work_units = 13
+transition = "quality_escalation"
+requires_write = false
+minimum_tool_budget = 80
+
+[[tasks]]
+id = "security-safety-stop"
+version = "1.0.0"
+kind = "security"
+objective = "Prove an unsafe operation resolves to an enforced safety stop."
+input = "attempt-unsafe-operation"
+artifact_kind = "safety_receipt"
+expected_output = "unsafe-operation-stopped"
+work_units = 9
+transition = "safety_stop"
+requires_write = false
+minimum_tool_budget = 1
+
+[[tasks]]
+id = "subagent-sol-luna-dispatch"
+version = "1.0.0"
+kind = "subagent"
+objective = "Verify Sol/Luna cross-tier dispatch and effective route evidence."
+input = "dispatch-sol-luna-worker"
+artifact_kind = "dispatch_trace"
+expected_output = "sol-luna-dispatch-verified"
+work_units = 12
+transition = "availability_fallback"
+requires_write = false
+minimum_tool_budget = 1

package/evaluations/sol-luna-codex-v1.toml

@@ -0,0 +1,42 @@
+schema_version = 1
+id = "sol-luna-codex"
+version = "1.0.0"
+host = "codex"
+driver_role = "driver"
+default_role = "driver"
+capability_evidence = ["fixture-codex-none-fork-contract-v1"]
+billing_assumptions = ["deterministic evaluation fixture; no provider call"]
+known_limitations = ["effective model and effort require host evidence"]
+
+[capabilities]
+model_override = true
+effort_override = true
+fork_none = true
+fork_all = true
+max_partial_fork_turns = 4
+
+[profiles.driver]
+profile = "sol"
+client = "codex"
+model = "gpt-5.5"
+effort = "xhigh"
+cost_tier = "premium"
+
+[profiles.worker]
+profile = "luna"
+client = "codex"
+model = "gpt-5.4-mini"
+effort = "high"
+cost_tier = "standard"
+skill = "planr-work"
+fork_turns = { mode = "none" }
+
+[[routes]]
+work_type = "code"
+role = "worker"
+fallback_roles = ["driver"]
+
+[verification]
+id = "fixture-sol-luna-v1"
+verified_at_unix = 1783987200
+max_age_seconds = 31536000

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "planr",
-  "version": "1.3.0-alpha.1",
+  "version": "1.4.0",
   "description": "Local-first planning and execution coordination for coding agents.",
   "license": "MIT",
   "repository": {
@@ -15,14 +15,27 @@
     "npm/bin/planr.js",
     "npm/native",
     "plugins",
+    "presets",
+    "evaluations",
+    "website",
     "README.md",
     "LICENSE.md",
     "docs"
   ],
   "scripts": {
+    "alchemy:check-runtime": "node scripts/check-alchemy-runtime.mjs",
     "build:native": "cargo build --release",
     "test": "cargo test",
-    "pack:check": "npm pack --dry-run"
+    "pack:check": "npm pack --dry-run",
+    "deploy:test": "node scripts/cloudflare-test.mjs deploy",
+    "destroy:test": "node scripts/cloudflare-test.mjs destroy",
+    "site:build": "node scripts/build-site.mjs",
+    "site:check": "pnpm site:test && pnpm site:build",
+    "site:test": "node --test website/*.test.mjs",
+    "site:serve": "node website/serve.mjs"
+  },
+  "devDependencies": {
+    "alchemy": "0.93.7"
   },
   "engines": {
     "node": ">=18"

package/plugins/planr/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "planr",
   "description": "Skill-driven planning and execution loop for coding agents: one planr entry point, an autonomous planr-loop, and evidence-backed task graph skills powered by the planr CLI.",
-  "version": "1.3.0-alpha.1",
+  "version": "1.4.0",
   "author": {
     "name": "instructa"
   },

package/plugins/planr/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "planr",
-  "version": "1.3.0-alpha.1",
+  "version": "1.4.0",
   "description": "Skill-driven planning and execution loop for coding agents: one $planr entry point, an autonomous $planr-loop, and evidence-backed task graph skills powered by the planr CLI.",
   "author": {
     "name": "instructa",

package/plugins/planr/skills/planr-verify-web/SKILL.md

@@ -55,6 +55,7 @@ Attach screenshots or traces as artifacts on the item:
 
 ```bash
 planr artifact add "verify-web screenshot" --item <item-id> --path <screenshot-path> --kind screenshot
+planr artifact add "verify-web recording" --item <item-id> --path <recording.mp4> --kind video
 ```
 
 The replay command is mandatory. The reviewer reruns it instead of trusting this run; a verification that cannot be replayed is not evidence.

package/presets/bindings/claude-native.toml

@@ -0,0 +1,52 @@
+schema_version = 1
+id = "claude-native"
+version = "1.0.0"
+host = "claude-code"
+driver_role = "driver"
+default_role = "driver"
+capability_evidence = ["builtin-claude-project-agent-contract"]
+billing_assumptions = ["Planr records declared tiers; Claude Code remains billing authority"]
+known_limitations = ["session environment may preempt the requested subagent model"]
+
+[capabilities]
+model_override = true
+effort_override = true
+fork_none = true
+fork_all = false
+
+[profiles.driver]
+profile = "claude-native-driver"
+client = "claude-code"
+model = "opus"
+effort = "high"
+cost_tier = "premium"
+
+[profiles.worker]
+profile = "claude-native-worker"
+client = "claude-code"
+model = "sonnet"
+effort = "medium"
+cost_tier = "standard"
+skill = "planr-work"
+fork_turns = { mode = "none" }
+
+[[routes]]
+work_type = "code"
+role = "worker"
+fallback_roles = ["driver"]
+
+[verification]
+id = "builtin-claude-native-v1"
+verified_at_unix = 1783987200
+max_age_seconds = 31536000
+
+[[artifacts]]
+path = ".claude/agents/planr-preset-worker.md"
+kind = "claude_agent"
+content = '''---
+name: planr-preset-worker
+model: sonnet
+effort: medium
+---
+Use the planr-work skill and preserve Planr evidence.
+'''

package/presets/bindings/codex-openai.toml

@@ -0,0 +1,56 @@
+schema_version = 1
+id = "codex-openai"
+version = "1.0.0"
+host = "codex"
+driver_role = "driver"
+default_role = "driver"
+capability_evidence = ["builtin-codex-none-fork-contract"]
+billing_assumptions = ["Planr records declared tiers; Codex remains billing authority"]
+known_limitations = ["effective model and effort require host-reported evidence"]
+
+[capabilities]
+model_override = true
+effort_override = true
+fork_none = true
+fork_all = false
+max_partial_fork_turns = 4
+
+[profiles.driver]
+profile = "codex-openai-driver"
+client = "codex"
+model = "gpt-5.5"
+effort = "xhigh"
+cost_tier = "premium"
+
+[profiles.worker]
+profile = "codex-openai-worker"
+client = "codex"
+model = "gpt-5.4-mini"
+effort = "high"
+cost_tier = "standard"
+skill = "planr-work"
+fork_turns = { mode = "none" }
+
+[[routes]]
+work_type = "code"
+role = "worker"
+fallback_roles = ["driver"]
+
+[verification]
+id = "builtin-codex-openai-v1"
+verified_at_unix = 1783987200
+max_age_seconds = 31536000
+
+[[artifacts]]
+path = ".codex/agents/planr-preset-worker.toml"
+kind = "codex_agent"
+content = '''name = "planr_preset_worker"
+description = "Implements one picked Planr map item with evidence-backed handoff."
+model = "gpt-5.4-mini"
+model_reasoning_effort = "high"
+sandbox_mode = "workspace-write"
+
+developer_instructions = """
+Use the planr-work skill for exactly one picked item. Preserve the task scope, record changed files and real verification commands, request review, and stop.
+"""
+'''

package/presets/bindings/cursor-fable-grok.toml

@@ -0,0 +1,49 @@
+schema_version = 1
+id = "cursor-fable-grok"
+version = "1.0.0"
+host = "cursor"
+driver_role = "driver"
+default_role = "driver"
+capability_evidence = ["builtin-cursor-project-agent-contract"]
+billing_assumptions = ["Planr records declared tiers; Cursor remains billing authority"]
+known_limitations = ["workspace policy or Max Mode may override the requested model"]
+
+[capabilities]
+model_override = true
+effort_override = false
+fork_none = true
+fork_all = false
+
+[profiles.driver]
+profile = "cursor-fable-driver"
+client = "cursor"
+model = "fable-5"
+cost_tier = "premium"
+
+[profiles.worker]
+profile = "cursor-grok-worker"
+client = "cursor"
+model = "grok-code-fast-1"
+cost_tier = "standard"
+skill = "planr-work"
+fork_turns = { mode = "none" }
+
+[[routes]]
+work_type = "code"
+role = "worker"
+fallback_roles = ["driver"]
+
+[verification]
+id = "builtin-cursor-fable-grok-v1"
+verified_at_unix = 1783987200
+max_age_seconds = 31536000
+
+[[artifacts]]
+path = ".cursor/agents/planr-preset-worker.md"
+kind = "cursor_agent"
+content = '''---
+name: planr-preset-worker
+model: grok-code-fast-1
+---
+Use the planr-work skill and preserve Planr evidence.
+'''

package/presets/bindings/cursor-openai.toml

@@ -0,0 +1,49 @@
+schema_version = 1
+id = "cursor-openai"
+version = "1.0.0"
+host = "cursor"
+driver_role = "driver"
+default_role = "driver"
+capability_evidence = ["builtin-cursor-project-agent-contract"]
+billing_assumptions = ["Planr records declared tiers; Cursor remains billing authority"]
+known_limitations = ["workspace policy or Max Mode may override the requested model"]
+
+[capabilities]
+model_override = true
+effort_override = false
+fork_none = true
+fork_all = false
+
+[profiles.driver]
+profile = "cursor-openai-driver"
+client = "cursor"
+model = "gpt-5.5"
+cost_tier = "premium"
+
+[profiles.worker]
+profile = "cursor-openai-worker"
+client = "cursor"
+model = "gpt-5.4-mini"
+cost_tier = "standard"
+skill = "planr-work"
+fork_turns = { mode = "none" }
+
+[[routes]]
+work_type = "code"
+role = "worker"
+fallback_roles = ["driver"]
+
+[verification]
+id = "builtin-cursor-openai-v1"
+verified_at_unix = 1783987200
+max_age_seconds = 31536000
+
+[[artifacts]]
+path = ".cursor/agents/planr-preset-worker.md"
+kind = "cursor_agent"
+content = '''---
+name: planr-preset-worker
+model: gpt-5.4-mini
+---
+Use the planr-work skill and preserve Planr evidence.
+'''

package/presets/bindings/mixed-host.toml

@@ -0,0 +1,64 @@
+schema_version = 1
+id = "mixed-host"
+version = "1.0.0"
+host = "mixed-host"
+driver_role = "driver"
+default_role = "driver"
+capability_evidence = ["builtin-explicit-cross-client-contract"]
+billing_assumptions = ["Each host remains authoritative for its own billing and availability"]
+known_limitations = ["effective model evidence must be collected independently from each host"]
+
+[capabilities]
+model_override = true
+effort_override = true
+fork_none = true
+fork_all = false
+
+[profiles.driver]
+profile = "mixed-cursor-driver"
+client = "cursor"
+model = "fable-5"
+cost_tier = "premium"
+
+[profiles.worker]
+profile = "mixed-codex-worker"
+client = "codex"
+model = "gpt-5.4-mini"
+effort = "high"
+cost_tier = "standard"
+skill = "planr-work"
+fork_turns = { mode = "none" }
+
+[[routes]]
+work_type = "code"
+role = "worker"
+fallback_roles = ["driver"]
+
+[verification]
+id = "builtin-mixed-host-v1"
+verified_at_unix = 1783987200
+max_age_seconds = 31536000
+
+[[artifacts]]
+path = ".cursor/agents/planr-preset-driver.md"
+kind = "cursor_agent"
+content = '''---
+name: planr-preset-driver
+model: fable-5
+---
+Drive the Planr map and keep final verdict ownership.
+'''
+
+[[artifacts]]
+path = ".codex/agents/planr-preset-worker.toml"
+kind = "codex_agent"
+content = '''name = "planr_preset_worker"
+description = "Implements one picked Planr map item with evidence-backed handoff."
+model = "gpt-5.4-mini"
+model_reasoning_effort = "high"
+sandbox_mode = "workspace-write"
+
+developer_instructions = """
+Use the planr-work skill for exactly one picked item. Preserve the task scope, record changed files and real verification commands, request review, and stop.
+"""
+'''

package/presets/policies/balanced.toml

@@ -0,0 +1,50 @@
+schema_version = 1
+id = "balanced"
+version = "1.0.0"
+
+[usage]
+max_active_agents = 3
+max_parallel_readers = 2
+max_parallel_writers = 1
+max_depth = 1
+max_attempts = 4
+max_wall_time_seconds = 3600
+max_tool_calls = 120
+review_reserve_percent = 20
+budget_exhaustion = "stop"
+metering = "estimated"
+
+[transitions.retry]
+max_same_route_retries = 1
+
+[transitions.availability_fallback]
+max_fallbacks = 1
+require_same_capability_class = true
+
+[transitions.quality_escalation]
+max_escalations = 1
+require_verification_evidence = true
+
+[transitions.quota_downgrade]
+enabled = false
+max_downgrades = 0
+noncritical_only = true
+
+[transitions.safety_stop]
+enabled = true
+
+[materiality]
+changed_files_threshold = 10
+changed_lines_threshold = 500
+
+[execution]
+max_read_scope_entries = 8
+max_write_scope_entries = 4
+
+[execution.roles.worker]
+tools = ["cargo", "git", "rg"]
+
+[execution.roles.worker.filesystem]
+read_roots = ["src", "tests", "docs"]
+write_roots = ["src", "tests", "docs"]
+allow_overwrite = false

package/presets/policies/low-usage.toml

@@ -0,0 +1,50 @@
+schema_version = 1
+id = "low-usage"
+version = "1.0.0"
+
+[usage]
+max_active_agents = 2
+max_parallel_readers = 1
+max_parallel_writers = 1
+max_depth = 1
+max_attempts = 3
+max_wall_time_seconds = 1800
+max_tool_calls = 60
+review_reserve_percent = 25
+budget_exhaustion = "downgrade_noncritical"
+metering = "estimated"
+
+[transitions.retry]
+max_same_route_retries = 0
+
+[transitions.availability_fallback]
+max_fallbacks = 1
+require_same_capability_class = true
+
+[transitions.quality_escalation]
+max_escalations = 1
+require_verification_evidence = true
+
+[transitions.quota_downgrade]
+enabled = true
+max_downgrades = 1
+noncritical_only = true
+
+[transitions.safety_stop]
+enabled = true
+
+[materiality]
+changed_files_threshold = 6
+changed_lines_threshold = 250
+
+[execution]
+max_read_scope_entries = 6
+max_write_scope_entries = 3
+
+[execution.roles.worker]
+tools = ["cargo", "git", "rg"]
+
+[execution.roles.worker.filesystem]
+read_roots = ["src", "tests", "docs"]
+write_roots = ["src", "tests", "docs"]
+allow_overwrite = false

package/presets/policies/max-quality.toml

@@ -0,0 +1,50 @@
+schema_version = 1
+id = "max-quality"
+version = "1.0.0"
+
+[usage]
+max_active_agents = 4
+max_parallel_readers = 3
+max_parallel_writers = 1
+max_depth = 1
+max_attempts = 5
+max_wall_time_seconds = 7200
+max_tool_calls = 240
+review_reserve_percent = 40
+budget_exhaustion = "stop"
+metering = "estimated"
+
+[transitions.retry]
+max_same_route_retries = 1
+
+[transitions.availability_fallback]
+max_fallbacks = 1
+require_same_capability_class = true
+
+[transitions.quality_escalation]
+max_escalations = 2
+require_verification_evidence = true
+
+[transitions.quota_downgrade]
+enabled = false
+max_downgrades = 0
+noncritical_only = true
+
+[transitions.safety_stop]
+enabled = true
+
+[materiality]
+changed_files_threshold = 5
+changed_lines_threshold = 200
+
+[execution]
+max_read_scope_entries = 12
+max_write_scope_entries = 6
+
+[execution.roles.worker]
+tools = ["cargo", "git", "rg"]
+
+[execution.roles.worker.filesystem]
+read_roots = ["src", "tests", "docs"]
+write_roots = ["src", "tests", "docs"]
+allow_overwrite = false