mirror of
https://github.com/instructkr/claw-code.git
synced 2026-04-17 21:55:11 +08:00
87b982ece5
Added criterion benchmarks and optimized flatten_tool_result_content: - Added criterion dev-dependency and request_building benchmark suite - Optimized flatten_tool_result_content to pre-allocate capacity and avoid intermediate Vec construction (was collecting to Vec then joining) - Made key functions public for benchmarking: translate_message, build_chat_completion_request, flatten_tool_result_content, is_reasoning_model, model_rejects_is_error_field Benchmark results: - flatten_tool_result_content/single_text: ~17ns - translate_message/text_only: ~200ns - build_chat_completion_request/10 messages: ~16.4µs - is_reasoning_model detection: ~26-42ns All 119 unit tests and 29 integration tests pass. cargo clippy passes Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
166 lines
8.8 KiB
JSON
166 lines
8.8 KiB
JSON
{
|
|
"version": "1.0",
|
|
"description": "Clawable Coding Harness - Clear roadmap stories and commit each",
|
|
"stories": [
|
|
{
|
|
"id": "US-001",
|
|
"title": "Phase 1.6 - startup-no-evidence evidence bundle + classifier",
|
|
"description": "When startup times out, emit typed worker.startup_no_evidence event with evidence bundle including last known worker lifecycle state, pane command, prompt-send timestamp, prompt-acceptance state, trust-prompt detection result, and transport/MCP health summary. Classifier should down-rank into specific failure classes.",
|
|
"acceptanceCriteria": [
|
|
"worker.startup_no_evidence event emitted on startup timeout with evidence bundle",
|
|
"Evidence bundle includes: last lifecycle state, pane command, prompt-send timestamp, prompt-acceptance state, trust-prompt detection, transport/MCP health",
|
|
"Classifier attempts to categorize into: trust_required, prompt_misdelivery, prompt_acceptance_timeout, transport_dead, worker_crashed, or unknown",
|
|
"Tests verify evidence bundle structure and classifier behavior"
|
|
],
|
|
"passes": true,
|
|
"priority": "P0"
|
|
},
|
|
{
|
|
"id": "US-002",
|
|
"title": "Phase 2 - Canonical lane event schema (4.x series)",
|
|
"description": "Define typed events for lane lifecycle: lane.started, lane.ready, lane.prompt_misdelivery, lane.blocked, lane.red, lane.green, lane.commit.created, lane.pr.opened, lane.merge.ready, lane.finished, lane.failed, branch.stale_against_main. Also implement event ordering, reconciliation, provenance, deduplication, and projection contracts.",
|
|
"acceptanceCriteria": [
|
|
"LaneEvent enum with all required variants defined",
|
|
"Event ordering with monotonic sequence metadata attached",
|
|
"Event provenance labels (live_lane, test, healthcheck, replay, transport)",
|
|
"Session identity completeness at creation (title, workspace, purpose)",
|
|
"Duplicate terminal-event suppression with fingerprinting",
|
|
"Lane ownership/scope binding in events",
|
|
"Nudge acknowledgment with dedupe contract",
|
|
"clawhip consumes typed lane events instead of pane scraping"
|
|
],
|
|
"passes": true,
|
|
"priority": "P0"
|
|
},
|
|
{
|
|
"id": "US-003",
|
|
"title": "Phase 3 - Stale-branch detection before broad verification",
|
|
"description": "Before broad test runs, compare current branch to main and detect if known fixes are missing. Emit branch.stale_against_main event and suggest/auto-run rebase/merge-forward.",
|
|
"acceptanceCriteria": [
|
|
"Branch freshness comparison against main implemented",
|
|
"branch.stale_against_main event emitted when behind",
|
|
"Auto-rebase/merge-forward policy integration",
|
|
"Avoid misclassifying stale-branch failures as new regressions"
|
|
],
|
|
"passes": true,
|
|
"priority": "P1"
|
|
},
|
|
{
|
|
"id": "US-004",
|
|
"title": "Phase 3 - Recovery recipes with ledger",
|
|
"description": "Encode automatic recoveries for common failures (trust prompt, prompt misdelivery, stale branch, compile red, MCP startup). Expose recovery attempt ledger with recipe id, attempt count, state, timestamps, failure summary.",
|
|
"acceptanceCriteria": [
|
|
"Recovery recipes defined for: trust_prompt_unresolved, prompt_delivered_to_shell, stale_branch, compile_red_after_refactor, MCP_handshake_failure, partial_plugin_startup",
|
|
"Recovery attempt ledger with: recipe id, attempt count, state, timestamps, failure summary, escalation reason",
|
|
"One automatic recovery attempt before escalation",
|
|
"Ledger emitted as structured event data"
|
|
],
|
|
"passes": true,
|
|
"priority": "P1"
|
|
},
|
|
{
|
|
"id": "US-005",
|
|
"title": "Phase 4 - Typed task packet format",
|
|
"description": "Define structured task packet with fields: objective, scope, repo/worktree, branch policy, acceptance tests, commit policy, reporting contract, escalation policy.",
|
|
"acceptanceCriteria": [
|
|
"TaskPacket struct with all required fields",
|
|
"TaskScope resolution (workspace/module/single-file/custom)",
|
|
"Validation and serialization support",
|
|
"Integration into tools/src/lib.rs"
|
|
],
|
|
"passes": true,
|
|
"priority": "P1"
|
|
},
|
|
{
|
|
"id": "US-006",
|
|
"title": "Phase 4 - Policy engine for autonomous coding",
|
|
"description": "Encode automation rules: if green + scoped diff + review passed -> merge to dev; if stale branch -> merge-forward before broad tests; if startup blocked -> recover once, then escalate; if lane completed -> emit closeout and cleanup session.",
|
|
"acceptanceCriteria": [
|
|
"Policy rules engine implemented",
|
|
"Rules: green + scoped diff + review -> merge",
|
|
"Rules: stale branch -> merge-forward before tests",
|
|
"Rules: startup blocked -> recover once, then escalate",
|
|
"Rules: lane completed -> closeout and cleanup"
|
|
],
|
|
"passes": true,
|
|
"priority": "P2"
|
|
},
|
|
{
|
|
"id": "US-007",
|
|
"title": "Phase 5 - Plugin/MCP lifecycle maturity",
|
|
"description": "First-class plugin/MCP lifecycle contract: config validation, startup healthcheck, discovery result, degraded-mode behavior, shutdown/cleanup. Close gaps in end-to-end lifecycle.",
|
|
"acceptanceCriteria": [
|
|
"Plugin/MCP config validation contract",
|
|
"Startup healthcheck with structured results",
|
|
"Discovery result reporting",
|
|
"Degraded-mode behavior documented and implemented",
|
|
"Shutdown/cleanup contract",
|
|
"Partial startup and per-server failures reported structurally"
|
|
],
|
|
"passes": true,
|
|
"priority": "P2"
|
|
},
|
|
{
|
|
"id": "US-008",
|
|
"title": "Fix kimi-k2.5 model API compatibility",
|
|
"description": "The kimi-k2.5 model (and other kimi models) reject API requests containing the is_error field in tool result messages. The OpenAI-compatible provider currently always includes is_error for all models. Need to make this field conditional based on model support.",
|
|
"acceptanceCriteria": [
|
|
"translate_message function accepts model parameter",
|
|
"is_error field excluded for kimi models (kimi-k2.5, kimi-k1.5, etc.)",
|
|
"is_error field included for models that support it (openai, grok, xai, etc.)",
|
|
"build_chat_completion_request passes model to translate_message",
|
|
"Tests verify is_error presence/absence based on model",
|
|
"cargo test passes",
|
|
"cargo clippy passes",
|
|
"cargo fmt passes"
|
|
],
|
|
"passes": true,
|
|
"priority": "P0"
|
|
},
|
|
{
|
|
"id": "US-009",
|
|
"title": "Add unit tests for kimi model compatibility fix",
|
|
"description": "During dogfooding we discovered the existing test coverage for model-specific is_error handling is insufficient. Need to add dedicated tests for model_rejects_is_error_field function and translate_message behavior with different models.",
|
|
"acceptanceCriteria": [
|
|
"Test model_rejects_is_error_field identifies kimi-k2.5, kimi-k1.5, dashscope/kimi-k2.5",
|
|
"Test translate_message includes is_error for gpt-4, grok-3, claude models",
|
|
"Test translate_message excludes is_error for kimi models",
|
|
"Test build_chat_completion_request produces correct payload for kimi vs non-kimi",
|
|
"All new tests pass",
|
|
"cargo test --package api passes"
|
|
],
|
|
"passes": true,
|
|
"priority": "P1"
|
|
},
|
|
{
|
|
"id": "US-010",
|
|
"title": "Add model compatibility documentation",
|
|
"description": "Document which models require special handling (is_error exclusion, reasoning model tuning param stripping, etc.) in a MODEL_COMPATIBILITY.md file for operators and contributors.",
|
|
"acceptanceCriteria": [
|
|
"MODEL_COMPATIBILITY.md created in docs/ or repo root",
|
|
"Document kimi models is_error exclusion",
|
|
"Document reasoning models (o1, o3, grok-3-mini) tuning param stripping",
|
|
"Document gpt-5 max_completion_tokens requirement",
|
|
"Document qwen model routing through dashscope",
|
|
"Cross-reference with existing code comments"
|
|
],
|
|
"passes": true,
|
|
"priority": "P2"
|
|
},
|
|
{
|
|
"id": "US-011",
|
|
"title": "Performance optimization: reduce API request serialization overhead",
|
|
"description": "The translate_message function creates intermediate JSON Value objects that could be optimized. Profile and optimize the hot path for API request building, especially for conversations with many tool results.",
|
|
"acceptanceCriteria": [
|
|
"Profile current request building with criterion or similar",
|
|
"Identify bottlenecks in translate_message and build_chat_completion_request",
|
|
"Implement optimizations (Vec pre-allocation, reduced cloning, etc.)",
|
|
"Benchmark before/after showing improvement",
|
|
"No functional changes or API breakage"
|
|
],
|
|
"passes": true,
|
|
"priority": "P2"
|
|
}
|
|
]
|
|
}
|