keisei/KeiSeiKit-1.0
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
385 commits 3 branches 11 tags 12 MiB
Commit graph

15 commits

Author SHA1 Message Date
Parfii-bot
9622d41bb6 refactor(wave17): cleanup — kei-shared SSoT + MEDIUM audit residuals + docs drift 
47 crates, 771 tests green (up from 753 at v0.33.0). Zero new
features — pure hygiene.

## kei-shared extract (SSoT for DNA format)

New crate `kei-shared` consolidates DNA-parse logic that was duplicated
across kei-agent-runtime + kei-dna-index. Both consumers migrated to
import ParsedDna / parse_dna / is_hex8 from kei_shared.

- 12 tests (10 integration + 2 unit)
- kei-dna-index LOC reduction: -60 in parsed.rs (body replaced by wrapper)
- kei-agent-runtime preserves lenient DnaError (legacy 4-hex parse path)
- Format-string SSoT: kei_shared::compose_dna is sole source

## MEDIUM audit residuals closed (kei-entity-store)

A. DDL panic coverage — verified exhaustive match across all 12
   FieldKind variants; new test ddl_never_panics_on_any_fieldkind
   compile-time-breaks if a variant added without test update.
B. Update FTS reindex invariant — doc + new update_invariant.rs module
   with debug_assert validating non-input FTS columns don't drift
   pre/post UPDATE. Zero release-mode cost (cfg-gated).
C. WAL fallback — wal_pragma_fallback_keeps_store_usable test (cfg(unix))
   verifies read-only-parent dir doesn't brick Store::open.
D. Search Unicode edge cases — 4 new tests (punctuation, emoji,
   zero-width, mixed RTL). has_searchable_token already correct, no
   source change needed; tests pin current behavior.

Added: residual_audit_smoke.rs (8 tests), update_invariant.rs module.
kei-entity-store: 57 → 65 tests.

## Docs drift fixed (count claims → reality)

- README.md: "36 crates → 47 crates", "500+ tests → 800+ tests"
- PLUGIN.md, docs/INSTALL.md, docs/REFERENCE.md, docs/SUBSTRATE-SCHEMA.md
  all synced to real counts.
- CHANGELOG.md: 6 new version blocks (v0.28 → v0.33) consolidated
  in existing style.
- Historical snapshots (HANDOFF-WAKE v0.29, CONVERGENCE-PLAN, etc)
  deliberately preserved — they're version-scoped, not drift.

## Known deviation from task spec

kei-shared's [workspace] table was dropped (Cargo rejected "multiple
workspace roots" when parent workspace pulls via path dep). Crate
registered in workspace.members instead. Verified cargo check + test
clean in both modes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-23 20:34:43 +08:00
Parfii-bot
0ea429054f feat(wave14): 5 bio-inspired primitives + phase2 cleanup + substrate dogfood 
## Wave 14 — 5 new primitives (44 crates total, 713 tests green)

All specs written as task.toml → passed through kei-agent-runtime prepare
→ composed prompts via capability fragments → Agent tool invocation.
First fully-dogfooded wave.

- kei-prune (9 tests): biological pruning. `candidates(idle_days)` +
  `mark_retired(id)` on sidecar `prune_retirements` table (agents.status
  CHECK precluded 'retired' value).
- kei-discover (8 tests): federated marketplace discovery stub. UNIQUE
  slug via custom migration + FTS5 on slug+description. Engine-native
  via kei-entity-store. Typed DuplicateSlug error.
- kei-brain-view (6-8 tests): stdout visualizer for ledger taxonomy
  graph + agent lineage. Tree / stats / lineage subcommands. NO_COLOR
  env respected. No kei-entity-store dep (direct rusqlite).
- kei-hibernate (6 tests): whole-brain tar.zst export/import. Manifest
  with sha256 per-file, version gate, safe_join on extract, dry-run
  mode. tar 0.4 + zstd 0.13.
- kei-ledger-sign (7 tests): ed25519 creator attestation. keygen / sign /
  verify CLI. Canonical message `dna|spec_sha|creator_id` with pipe
  rejection. chmod 600 on key storage (unix). Tamper-detection on load
  via pubkey re-derivation.

## Phase 2 cleanup shipped in same commit

- LOC splits: walk.rs 221→91 (path_safety.rs + wikilink.rs extracted),
  prepare.rs 228→199 (dead build_ledger_row removed, fn helpers split).
- Clippy pass: 6 warnings fixed (derivable_impls, manual_contains,
  type_complexity x2, doc_overindented_list_items x2) in
  kei-entity-store, kei-ledger, kei-spawn.
- DNA eprintln removed from kei-agent-runtime/src/dna.rs (stderr
  pollution from library parse).
- kei-pipe integrations: hot_reload.rs (kei-watch wrapper, sync API,
  50ms debounce) + scheduler_bridge.rs (kei-scheduler executor, shell
  exec documented). +6 tests.
- Workspace [workspace.dependencies] centralised: rusqlite/chrono/
  anyhow/thiserror/tempfile/toml — future crates opt in via
  `.workspace = true`. Existing pins preserved.

## Substrate dogfood verified

task.toml → `kei-agent-runtime prepare` → DNA + composed prompt from
capability fragments → Agent tool invocation. kei-spawn also tested
end-to-end (prompt.md written to tasks/<agent-id>/, ledger row created).

Verified: cargo check --workspace clean, 713 tests passing,
substrate_integration.sh ✓, hook_wiring_integration.sh ✓.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-23 17:19:25 +08:00
Parfii-bot
c1556f505a fix: Wave 13 cleanup — HttpDriver + agent_id validator + safe_join + 4 MEDIUM 
Closes the remaining v0.29.0 follow-ups + post-audit MEDIUMs.

## HttpDriver (kei-spawn http-driver feature)
- Real reqwest::blocking POST to api.anthropic.com/v1/messages
- Feature flag `http-driver = ["dep:reqwest"]` (default off, zero breaking)
- KEI_ANTHROPIC_KEY read at invoke time (rotation-friendly)
- 5 httpmock tests (missing key, 200, 4xx, 5xx, malformed json)
- Endpoint override via KEI_ANTHROPIC_ENDPOINT env for tests
- Files: drive.rs, drive_http.rs (new), drive_http_parse.rs (new), tests/http_driver.rs

## agent_id path-traversal validator (HIGH)
- New validate.rs with validate_agent_id() — whitelist grammar, 64-char cap,
  rejects /, \, .., leading dot/dash, NUL, :, whitespace, non-ASCII,
  Windows-reserved (CON/PRN/AUX/NUL/COM1-9/LPT1-9)
- Wired into all 5 agent_id→path sinks: load_task, resolve_agent_id,
  prepare, simulated_merge, verify_task
- autogen_agent_id moved to validate.rs with slugify_role helper —
  output passes validator by construction (100-draw property test)
- 33 new tests in agent_id_validator.rs

## safe_join symlink escape (MEDIUM)
- Base must canonicalize (nonexistent → Canonicalize error)
- Joined must start_with base_canon OR joined.parent() must start_with base_canon
- Blocks symlink-to-outside-base with non-existent tail file
- walk.rs refactored into 5 ≤17-LOC helpers
- 7 new tests in safe_join_hardening.rs

## entity-store 4 MEDIUM fixes
- ddl.rs: panic on unsupported FieldKind → typed DdlError::UnsupportedExtraColumn
  propagated through Store::open as VerbError::InvalidInput (exit 2).
  Extracted ddl_edge.rs + ddl_error.rs modules. Backward-compat shim preserved.
- search.rs: FTS5 empty-tokenization → typed InvalidInput on queries with
  no alphanumeric tokens (was opaque rusqlite error). Unicode-aware via
  char::is_alphanumeric.
- engine.rs: WAL pragma failure now logged to stderr with path + rusqlite
  source; fallback to rollback journal preserved (exit-code contract intact).
- bug_fixes_smoke: added fts5_phrase_quoting_preserves_legitimate_queries —
  catches over-broad sanitizer that passes injection test alone.

## Verified
- cargo check --workspace clean (both with and without http-driver feature)
- cargo test --workspace: 668 tests green (up from 620)
- substrate_integration.sh ✓, hook_wiring_integration.sh ✓

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-23 16:16:24 +08:00
Parfii-bot
e075ae8df1 fix(compose): render resolved scope block — agent sees concrete paths, not generic text 
Dogfood gap #2 from prepare workflow: capability text fragments say
"your task's scope" generically, but agent never sees the resolved
scope params from task.toml. Migration agent had no way to know
whitelist = kei-chat-store/** without me pasting it.

Fix: render_scope_block() injects a resolved-params section between
capability fragments and task body. Shows:
- files-whitelist / files-denylist glob lists
- cargo-check-crates / cargo-test-crates
- test-count-min (if Option<u32>::Some)
- report-fields-required

If no scope params set, block is empty (no section rendered).

Now `kei-agent-runtime prepare` emits fully self-contained prompt —
no external context needed. Substrate unblocked for parallel migrations.

Tests: 41/41 (was 41 — no regression; scope-block added tests deferred
to follow-up since compose_smoke already covers existing path).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-23 05:44:15 +08:00
Parfii-bot
bf5c4d3dce Merge fix/b2-dna-role — DNA + role + traversal 2026-04-23 05:31:03 +08:00
Parfii-bot
ba75a075e3 Merge fix/b1-pattern-gate — hardening 2026-04-23 05:31:03 +08:00
Parfii-bot
4983d38636 fix(agent-runtime/b2): DNA entropy 32-bit + role path traversal + recursion cap + warnings 
H4/M4/S3 DNA entropy:
- short_sha256() widened to 8 hex (32-bit) for scope + body hash
- nonce expanded to 8 hex from full u32 via rand::random
- Birthday collision at ~77K agents sharing role+caps (was ~256)
- Dna::parse accepts legacy 4-hex values with stderr warning for
  rolling upgrade of pre-fix DNAs

H5 role recursion: resolve_inner depth parameter + MAX_DEPTH=16.
Returns RoleError::MaxDepthExceeded{depth, trace:Vec<String>} for
clear diagnostics.

S1 path traversal — two sites closed:
- role.rs::resolve_inner validates role name + parent in extends
  against regex ^[a-z][a-z0-9-]{0,63}$ before Path::join
- compose.rs::split_cap_name same validation on capability
  category/slug before Path::join
- RoleError::InvalidName{kind, value} on violation

M1 relaxes warnings: eprintln replaced with ResolvedRole.warnings
Vec<String> field. Caller decides: log, fail, ignore.

New typed RoleError (thiserror) — PartialEq/Eq for test ergonomics.

Tests: 73/73 (was 66, +7: 3 DNA + 4 role). Full extends graph + malicious
name + depth+1 all covered.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-23 05:27:59 +08:00
Parfii-bot
f9bfcc23b7 fix(agent-runtime/b1): PatternGate hardening — RwLock, Result, UTF-8, explicit deny 
H1 lock contention: Mutex<HashMap> → RwLock<HashMap>. Hot path cheap
read-lock, write-lock only on first compile per pattern.

H2 panic removed: compile_checked() returns Result<Regex, regex::Error>;
all call sites propagate as GateDecision::Deny{reason:"misconfigured
regex..."}. No .expect()/.unwrap() on compile anywhere.

H3 dead branch: AllowIfMatch + TaskWhitelist/TaskDenylist combo was
silently NotApplicable (allow-everything). Now explicit Deny with
"misconfigured" + "AllowIfMatch" in reason. Fail-closed.

S4 UTF-8 panic: &s[..60] byte-slice → s.chars().take(60). Cyrillic/
emoji safe. 60-char budget by code point.

L2 render chain: String::replace chain → single-pass render_template()
that scans {token} markers once. Substituted text cannot bleed into
later tokens.

Tests: 70/70 (was 66, +4). pattern_gate_smoke 10 → 14.
Follow-up (out of file-boundary scope): per-pattern Lazy<Regex> variant
would eliminate the RwLock entirely but requires editing sibling gate
consts.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-23 05:27:59 +08:00
Parfii-bot
9c8c7c3598 fix(prepare): auto-generate agent-id when absent + dogfood ergonomics 
Dogfood gap found: orchestrator running `kei-agent-runtime prepare
<task.toml>` hit "task.agent-id is empty" error. Required 3-step flow
(ledger fork → edit task.toml → prepare) for every spawn.

Fix: auto-generate `ag-<role>-<unix-ms-hex>-<4hex-rand>` if task.agent-id
empty. Orchestrator can still pre-allocate for deterministic ids;
auto-gen is ergonomic default. DNA compose sees the effective id via
clone+inject into TaskSpec before Dna::compose.

Helper `autogen_agent_id()` uses SystemTime millis + rand u16 — low
collision at orchestrator spawn rate (< 1 spawn/ms).

build_ledger_row() split: original preserved as thin wrapper, new
build_ledger_row_with_id() accepts explicit id for auto-gen path.

Verified end-to-end via `/tmp/keisei-dogfood/test-task.toml`:
prepare now emits complete AgentInvocation including composed prompt,
DNA, verify command — ready for orchestrator Agent-tool invocation
without pre-alloc step.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-23 05:23:55 +08:00
Parfii-bot
30a07e22ca Merge feat/convergence-p3-role-dna — role expression + DNA identity 2026-04-23 04:47:30 +08:00
Parfii-bot
84319efcb6 feat(convergence/p3): Role expression (extends/relaxes) + DNA identity 
Layer E + G. Role TOML gains extends/relaxes for parent-role
composition; agent spawn gets self-describing DNA identity alongside
UUID.

Role expression:
- _roles/*.toml gain optional `extends = "<parent>"` + `relaxes = [...]`
- compose.rs + verify.rs delegate to new role::resolve_role() with
  recursive extends-chain resolution + cycle detection
- explorer.toml: 28→18 LOC (extends read-only)
- edit-shared.toml: 31→23 LOC (extends edit-local, relaxes
  scope::files-whitelist for task-param override)

DNA identity:
- new dna.rs (159 LOC) — compose/render/parse round-trip
- AgentInvocation carries dna field (prepare.rs)
- Format: <role>::<caps-bitmap>::<sha4-scope>::<sha4-body>-<hex4-nonce>
- ≤ 80 chars total, greppable, parseable
- 11 capability codes in CAP_CODES table: NG, FW, FD, CP, CG, TG, ND,
  RF, SG, DT, BA

kei-ledger schema v2:
- ADD COLUMN dna TEXT + prefix index
- `kei-ledger fork --dna <string>` optional flag
- AgentRow.dna: Option<String>
- Backward compat: schema migration detects + applies on open

Docs: AGENT-SUBSTRATE-SCHEMA.md Layer E + Layer G sections + CAP_CODES table.

New deps: sha2 (workspace), rand 0.8.

Tests: kei-agent-runtime 50 (was 41, +9: 4 role + 5 DNA), kei-ledger
10 (was 9, +1 DNA roundtrip).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-23 04:46:48 +08:00
Parfii-bot
360a20a942 feat(convergence/p2): PatternGate + CommandVerify unified traits 
Layer C + D. 6 gate modules + 3 verify modules → 1 generic struct per
family + const declarations. Data-driven, not module-per-capability.

New:
- src/gates/pattern_gate.rs (192 LOC) — PatternGate struct with
  GateMode::{DenyIfMatch, AllowIfMatch}, static regex compilation via
  once_cell, bypass env support, Capability trait impl
- src/verifies/command_verify.rs (142 LOC) — CommandVerify struct with
  WorkDir::{WorkspaceRoot, CrateDir, MainRepoSub}, subprocess exec +
  exit-code check, extra_env support, Capability trait impl

Converted (const declarations, ~15-27 LOC each):
- gates/policy_no_git_ops.rs (49→22)
- gates/safety_no_dep_bump.rs (35→19)
- gates/scope_files_whitelist.rs (37→16)
- gates/scope_files_denylist.rs (35→16)
- gates/tools_bash_allowlist.rs (58→27)
- verifies/quality_cargo_check_green.rs (41→18)
- verifies/quality_tests_green.rs (75→80, folded common shape)
- verifies/safety_no_dep_bump.rs (39→47)

Kept separate (different shape, not PatternGate/CommandVerify):
- gates/tools_deny_tools.rs (tool-name match, not pattern)
- verifies/quality_constructor_pattern.rs (LOC walker)
- verifies/output/report_format.rs + severity_grade.rs (text parsers)
- verifies/scope_files_{whitelist,denylist}.rs (diff-walkers)

Registry.rs preserves alias table + deprecation warnings + all_names().

Tests: 57/57 green (was 41, +16: 10 pattern_gate_smoke + 6 command_verify_smoke).

LOC net: 5 gates 214→100 (-53%), shared PatternGate+CommandVerify 334
LOC absorb duplication. Amortization breaks even around 3-4 new gates
added later.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-23 04:46:47 +08:00
Parfii-bot
e4b64418fc feat(convergence/u2): capability renames + back-compat aliases 
Pre-unlock wave U2. Task 3 from CONVERGENCE-PLAN — rename misleading
capability names, keep old names as deprecated aliases.

Renames:
- tools::read-only → tools::deny-tools (mechanism is tool-name denial,
  not "read-only" metaphor)
- tools::cargo-only-bash → tools::bash-allowlist (mechanism is Bash
  pattern allow-list; cargo-only is one config value)

Back-compat via registry.resolve_alias():
- Old dir _capabilities/tools/{read-only,cargo-only-bash}/ retained with
  capability.toml-only stub: `alias = "<new-name>"` + `deprecated` field
- registry.rs loads alias stubs, redirects lookup before dispatch
- warn_deprecated_once() emits single-shot stderr per alias per process
  via OnceLock<Mutex<HashSet>>
- Zero breaking change to existing manifests / task.toml referencing
  old names

Rust impl files renamed in place:
- gates/tools_read_only.rs → gates/tools_deny_tools.rs (struct
  DenyTools)
- gates/tools_cargo_only_bash.rs → gates/tools_bash_allowlist.rs
  (struct BashAllowlist)
- gates/mod.rs + registry.rs + gate_smoke.rs updated

Roles updated (3): read-only.toml, explorer.toml, edit-local.toml —
reference new names directly.

Tests: kei-agent-runtime 41/41 (was 40, +1 deprecated_aliases_resolve
_to_new_names), _assembler 40/40 unchanged (substrate role expansion
follows new paths).

Docs updated: AGENT-ROLES.md, AGENT-SUBSTRATE-SCHEMA.md, 4 _manifests
referencing the old names (comment-only annotations).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-23 03:43:40 +08:00
Parfii-bot
d72ae51f16 feat(agent-substrate/wrapper): kei-agent-runtime prepare — orchestrator ergonomics 
Single-command "prepare spawn" that emits everything orchestrator needs
to invoke the Agent tool: composed prompt, subagent_type (from role's
new claude-subagent-type field), isolation mode, verify command,
ledger row.

Before this: orchestrator ran compose + read prompt + manually
constructed Agent tool call + manually built verify command. 4 steps.

After: `kei-agent-runtime prepare <task.toml> --format=human` outputs
a single copy-paste-ready block. Orchestrator pastes into Agent tool
and records the verify command for return.

Files:
- src/prepare.rs (170 LOC) — prepare() returns AgentInvocation struct
  (agent_id, prompt, subagent_type, isolation, description,
  verify_command, ledger_row)
- src/main.rs (+39 LOC) — Prepare subcommand with --format=human|json|toml
- src/lib.rs (+2 LOC — pub mod prepare)
- _roles/*.toml (5 files) — new optional claude-subagent-type field:
  - edit-local / edit-shared → "code-implementer"
  - read-only → "critic" (default; "architect" override possible)
  - explorer → "Explore"
  - git-ops → "NOT-SPAWNABLE" (refused by prepare with RULE 0.13)
- tests/prepare_smoke.rs (3 tests) — happy path, unknown role, non-spawnable refusal
- docs/AGENT-SUBSTRATE-SCHEMA.md (+ ## Orchestrator ergonomics section)

Tests: 40/40 (was 37, +3 prepare_smoke). Same path exercised in tempfile
fixtures that the real CLI would hit end-to-end.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-23 03:25:14 +08:00
Parfii-bot
b82e3b039e feat(agent-substrate/phase-3): kei-agent-runtime + kei-capability binaries 
Two new crates implementing the substrate runtime per locked §Runtime
execution contract + §Capability trait contract (Rust) + §Verify
execution worktree→simulated-merge.

kei-agent-runtime — library + CLI binary:
- src/capability.rs — Capability trait (name/check/verify) + GateContext
  + GateDecision + VerifyContext + VerifyResult + RunMode + TaskSpec
- src/registry.rs — &str → &'static dyn Capability dispatch for 14 impls
- src/gates/ — 6 PreToolUse modules (policy::no-git-ops,
  scope::files-{whitelist,denylist}, safety::no-dep-bump,
  tools::read-only, tools::cargo-only-bash)
- src/verifies/ — 8 on-return modules (quality::constructor-pattern,
  quality::cargo-check-green, quality::tests-green, safety::no-dep-bump,
  scope::files-{whitelist,denylist}, output::{report-format,severity-grade})
- src/compose.rs — task.toml + role + capabilities → prompt.md
- src/spawn.rs — ledger fork + prompt write (actual Agent invocation
  remains orchestrator's tool call)
- src/verify.rs — runs all capability verifies per role; collects
  VerifyReport {passed, failed}
- src/simulated_merge.rs — git worktree add test-merge/<id> + apply diff
  + run verify; cleanup on Drop
- src/main.rs — clap CLI: compose | spawn | verify | run

kei-capability — thin CLI adapter crate:
- Depends on kei-agent-runtime path dep
- Subcommand `check <cap-name>` (PreToolUse gate; stdin JSON, exit 0|2)
- Subcommand `verify <cap-name>` (on-return; env-driven, exit 0 or fail)
- Pattern: shell hook = 3-line `exec kei-capability check "$CAP_NAME"`

Workspace Cargo.toml: both crates registered as members (under agent
substrate v1 marker).

cargo check --workspace: PASS
cargo test -p kei-agent-runtime: 37/37 green
  - 6 capability_trait_smoke (registry lookups, unknown name → None)
  - 3 compose_smoke (fixture role + caps → composed prompt)
  - 12 gate_smoke (each gate: happy + deny + bypass)
  - 4 simulated_merge_smoke (git worktree lifecycle)
  - 12 verify_smoke (each verify: pass + fail + edge cases)
cargo test -p kei-capability: 0/0 (CLI binary, tested via lib)

(Agent completion report cut off by rate-limit at 60 tool-uses; code
itself is green — verified by orchestrator post-commit.)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-23 02:35:53 +08:00