loki-mode 7.45.1 → 7.47.0

package/README.md

@@ -19,14 +19,14 @@ _The free, source-available autonomous coding agent by [Autonomi](https://www.au
 
 ---
 
-> **How it works:** Drop a spec -- a PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. Loki Mode classifies complexity (`run.sh:detect_complexity()`), assembles an agent team from 41 specialized agent roles across 8 domains - prompt-defined specifications the orchestrator adopts per phase, with parallel review (blind council) and optional worktree streams on Claude Code, sequential on other providers - and runs autonomous RARV cycles (Reason - Act - Reflect - Verify, see `run.sh:run_autonomous()`) with 11 quality gates (see `skills/quality-gates.md`). Code is not "done" until it passes automated verification. Output is a Git repo with source, tests, configs, and audit logs.
+> **How it works:** Drop a spec -- a PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. Loki Mode classifies complexity (`run.sh:detect_complexity()`), assembles an agent team from 41 specialized agent roles across 8 domains - prompt-defined specifications the orchestrator adopts per phase, with parallel review (blind council) and optional worktree streams on Claude Code, sequential on other providers - and runs autonomous RARV cycles (Reason - Act - Reflect - Verify, see `run.sh:run_autonomous()`) with 8 quality gates (see `skills/quality-gates.md`). Code is not "done" until it passes automated verification. Output is a Git repo with source, tests, configs, and audit logs.
 
 ---
 
 ## Why Loki Mode?
 
 - **Spec-driven, autonomous, with a built-in trust layer** -- Hand Loki a spec, walk away, come back to working code with tests. The full RARV-C closure loop (Reason - Act - Reflect - Verify - Close) runs until the work is actually done, not just attempted. The verified-completion evidence gate (`skills/quality-gates.md`) refuses any "done" claim on an empty git diff against the run-start commit, and blocks completion when tests run red, so "complete" means proven, not promised.
-- **Production quality built in** -- 11 quality gates (`skills/quality-gates.md`), blind 3-reviewer code review (`run.sh:run_code_review()`), anti-sycophancy checks
+- **Production quality built in** -- 8 quality gates (`skills/quality-gates.md`), blind 3-reviewer code review (`run.sh:run_code_review()`), anti-sycophancy checks
 - **Standalone verification: `loki verify`** -- Run Loki's deterministic gates (build, tests, static analysis, secret scan, dependency audit) against any branch or PR diff, including code written by other agents or humans. CI-ready exit codes (0 VERIFIED, 1 CONCERNS, 2 BLOCKED), machine-readable evidence at `.loki/verify/evidence.json`. Inconclusive evidence is never reported as VERIFIED (v7.27.0).
 - **Living spec and pre-build interrogation** -- `loki spec` locks a spec and detects drift deterministically (`spec.lock`, `drift-report.json`, and a `SPEC_DRIFT` finding in `loki verify` with CI exit codes), so you can tell when the build diverges from what was agreed. `loki grill` runs a Devil's-Advocate interrogation of the spec before you build, surfacing gaps and contradictions early (v7.28.0).
 - **Mid-flight model switching** -- switch the model a live run uses from the dashboard (applies at the next iteration, current run only). A Fable tier lever exists in the CLI, dashboard, and override paths, but Claude Fable 5 is not yet available at the API, so selecting Fable currently collapses to Opus at every dispatch chokepoint and the `loki plan` quote reflects Opus accordingly. For every model lever (session pin, mid-flight override, architect pass) and every `LOKI_MAX_TIER` path, the `loki plan` quote, the dashboard's reported model, and the actual dispatched model agree, with the ceiling enforced (v7.31.0; Fable-to-Opus collapse v7.39.1).
@@ -41,7 +41,7 @@ _The free, source-available autonomous coding agent by [Autonomi](https://www.au
 - **MCP server** -- 34 tools (including ChromaDB code search) plus 3 resources and 2 prompts (`mcp/server.py`, with magic tools registered from `mcp/magic_tools.py` and the managed-memory tool from `mcp/managed_tools.py`). Of the 34, 33 are always available; `loki_memory_redact` is registered but only succeeds when `LOKI_MANAGED_AGENTS=true` and `LOKI_MANAGED_MEMORY=true`. Launch with `loki mcp` (bootstraps the Python MCP SDK on first run).
 - **Full-stack output** -- Source code, tests, Docker Compose stacks (multi-service with healthchecks), CI/CD pipelines, audit logs
 - **Provider-agnostic** -- runs on Claude, Codex, Cline, or Aider with automatic failover (`loki-ts/src/runner/providers.ts`); no vendor lock-in. Gemini CLI deprecated v7.5.18; Antigravity CLI coming soon.
-- **Open source** -- Free for personal, internal, and academic use.
+- **Source-available (BUSL-1.1)** -- Free for personal, internal, and academic use.
 
 ---
 
@@ -193,7 +193,7 @@ A "spec" is whatever you hand `loki start`. Loki auto-detects the format and nor
 | OpenSpec change directory | `loki start --openspec ./openspec/change-001` | Reads OpenSpec change manifest + delta files. |
 | Auto-detect (no input) | `loki start` | Picks up `./prd.md`, `./spec.{json,yaml,yml}`, or `./SPEC.md` from cwd. |
 
-All formats land in the same RARV pipeline and pass the same 11 quality gates (`skills/quality-gates.md`).
+All formats land in the same RARV pipeline and pass the same 8 quality gates (`skills/quality-gates.md`).
 
 </details>
 
@@ -252,8 +252,8 @@ Every iteration: **Reason** (read state) - **Act** (execute, commit) - **Reflect
 </td>
 <td width="33%" valign="top">
 
-### 11 Quality Gates
-Blind review, anti-sycophancy, severity blocking, mock/mutation detection, backward compatibility (gate 10, v6.67.0), documentation coverage (gate 11, v7.5.0). Code does not ship until all gates pass.
+### 8 Quality Gates
+Static analysis, test suite (pass/fail), blind 3-reviewer code review with severity blocking, anti-sycophancy Devil's Advocate, mock-integrity detection, test-mutation detection, documentation coverage, and Magic Modules debate. Backward-compatibility is a conditional healing-mode auditor (not one of the 8). Code does not ship until all gates pass.
 
 [Quality Gates](skills/quality-gates.md)
 
@@ -303,15 +303,15 @@ The historical feature set (platform pages, Monaco IDE workspace, AI chat panel)
 |---------|:---------:|:--------:|:------:|:-------:|
 | Self-hosted / your keys | Yes | No | No | No |
 | 5 AI provider failover | Yes | No | No | No |
-| 11 quality gates | Yes | No | No | No |
+| 8 quality gates | Yes | No | No | No |
 | Blind code review | Yes | No | No | No |
 | Enterprise auth (SSO/RBAC) | Yes | No | Yes | No |
 | Air-gapped deployment | Yes | No | No | No |
 | Docker + CI/CD generation | Yes | No | Yes | No |
-| Open source | Yes | No | No | No |
-| Free tier | Open source | Yes | Yes | Yes |
+| Source-available (BUSL-1.1) | Yes | No | No | No |
+| Free tier | Source-available | Yes | Yes | Yes |
 
-Loki Mode is the only platform that is fully self-hosted, open source, and includes automated quality verification. Your code, your keys, your infrastructure.
+Loki Mode is the only platform that is fully self-hosted, source-available (BUSL-1.1), and includes automated quality verification. Your code, your keys, your infrastructure.
 
 ---
 
@@ -432,7 +432,7 @@ See [benchmarks/](benchmarks/) for methodology.
 
 ![Loki Mode Presentation](docs/loki-mode-presentation.gif)
 
-*11 slides: Problem, Solution, 41 Agents, RARV Cycle, 9 Quality Gates (HumanEval 98.78%), Multi-Provider, Enterprise Hardening (Live App Preview), Full Lifecycle*
+*11 slides: Problem, Solution, 41 Agents, RARV Cycle, 8 Quality Gates (HumanEval 98.78%), Multi-Provider, Enterprise Hardening (Live App Preview), Full Lifecycle*
 
 **[Download PPTX](docs/loki-mode-presentation.pptx)**
 
@@ -446,7 +446,7 @@ See [benchmarks/](benchmarks/) for methodology.
 |------|-----------|---------------------|
 | **Code Gen** | Full-stack apps from PRDs | Complex domain logic may need human review |
 | **Deploy** | Generates configs, Dockerfiles, CI/CD | Does not deploy -- human runs deploy commands |
-| **Testing** | 11 automated quality gates | Test quality depends on AI assertions |
+| **Testing** | 8 automated quality gates | Test quality depends on AI assertions |
 | **Providers** | 5 providers with auto-failover | Non-Claude providers lack parallel agents |
 | **Dashboard** | Real-time single-machine monitoring | No multi-node clustering |
 
@@ -499,3 +499,7 @@ See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
 **[Autonomi](https://www.autonomi.dev/)** | **[Documentation](wiki/Home.md)** | **[Changelog](CHANGELOG.md)** | **[Comparisons](references/competitive-analysis.md)**
 
 </div>
+
+## Star History
+
+[![Star History Chart](https://api.star-history.com/chart?repos=asklokesh/loki-mode&type=timeline&legend=bottom-right)](https://www.star-history.com/?repos=asklokesh%2Floki-mode&type=timeline&legend=bottom-right)

package/SKILL.md

@@ -1,13 +1,13 @@
 ---
 name: loki-mode
-description: Autonomous spec-driven build system with a built-in trust layer. It does not call work done until it is verified (RARV-C closure loop, 11 quality gates, completion council, verified-completion evidence gate). Triggers on "Loki Mode". Takes a spec (PRD, GitHub issue, OpenAPI doc, etc.) to deployed product with minimal human intervention. Provider-agnostic. Requires --dangerously-skip-permissions flag.
+description: Autonomous spec-driven build system with a built-in trust layer. It does not call work done until it is verified (RARV-C closure loop, 8 quality gates, completion council, verified-completion evidence gate). Triggers on "Loki Mode". Takes a spec (PRD, GitHub issue, OpenAPI doc, etc.) to deployed product with minimal human intervention. Provider-agnostic. Requires --dangerously-skip-permissions flag.
 ---
 
-# Loki Mode v7.45.1
+# Loki Mode v7.47.0
 
 **You are an autonomous agent. You make decisions. You do not ask questions. You do not stop.**
 
-**Spec in, verified product out.** Spec-driven: a "spec" is whatever describes the work -- a Markdown PRD, a GitHub issue, an OpenAPI doc, a Jira ticket (a PRD is one form of spec). The differentiator is the trust layer: Loki does not call work done until it is verified. The RARV-C closure loop, 11 quality gates, the completion council, and the verified-completion evidence gate must all clear before completion is accepted.
+**Spec in, verified product out.** Spec-driven: a "spec" is whatever describes the work -- a Markdown PRD, a GitHub issue, an OpenAPI doc, a Jira ticket (a PRD is one form of spec). The differentiator is the trust layer: Loki does not call work done until it is verified. The RARV-C closure loop, 8 quality gates, the completion council, and the verified-completion evidence gate must all clear before completion is accepted.
 
 **Provider-agnostic (stable since v5.0.0):** runs on Claude/Codex/Cline/Aider with abstract model tiers and degraded mode for non-Claude providers; no vendor lock-in. Gemini deprecated v7.5.18. See `skills/providers.md`. **Current track (v7.7.x):** LSP grounding as first-class agent tool (v7.7.0-v7.7.9; lsp_get_diagnostics actually-returns-diagnostics regression fix v7.7.14), provider_source cli (v7.7.11-v7.7.12 bash/bun parity), Docker/bash-3.2 robustness (v7.7.13), audit chain cross-file verification fix (v7.7.15), Phase 1 RARV-C closure (real provider judges, gate-failure flock, synthetic PRD e2e, status `--json`).
 
@@ -125,7 +125,7 @@ DEPLOYMENT ──[production live, monitoring active]──> GROWTH
 GROWTH ──[continuous improvement loop]──> GROWTH
 ```
 
-**Transition requires:** All phase quality gates passed. No Critical/High/Medium issues.
+**Transition requires:** All phase quality gates passed. No Critical/High issues (Medium/Low advisory).
 
 ---
 
@@ -407,4 +407,4 @@ See `CHANGELOG.md` entries [7.5.7], [7.5.8], [7.5.13] for the per-fix list and r
 
 ---
 
-**v7.45.1 | [Autonomi](https://www.autonomi.dev/) flagship product | ~260 lines core**
+**v7.47.0 | [Autonomi](https://www.autonomi.dev/) flagship product | ~260 lines core**

package/VERSION

@@ -1 +1 @@
-7.45.1
+7.47.0

package/autonomy/CONSTITUTION.md

@@ -155,7 +155,7 @@ SKILL.md (~190 lines)         # Always loaded: RARV cycle, autonomy rules
 skills/
   00-index.md                  # Module routing table
   model-selection.md           # Task tool, parallelization
-  quality-gates.md             # 9-gate system, anti-sycophancy
+  quality-gates.md             # 8-gate system, anti-sycophancy
   testing.md                   # Playwright, E2E, property-based
   production.md                # CI/CD, batch processing
   agents.md                    # 41 agent types, A2A patterns
@@ -196,7 +196,14 @@ Main Worktree (orchestrator)
 
 ---
 
-## Quality Gates (9-Gate System)
+## Quality Gates
+
+Note: the canonical, implemented quality-gate set is the 8-gate system defined in
+`skills/quality-gates.md` (static analysis, test suite pass/fail, blind 3-reviewer
+code review with severity blocking, anti-sycophancy Devil's Advocate, mock
+integrity, test mutation, documentation coverage, Magic Modules debate). The
+list below is an aspirational SDLC taxonomy and may name phases that are not
+deterministic loop gates; treat `skills/quality-gates.md` as the source of truth.
 
 ### Gate 1: Static Analysis
 ```yaml

package/autonomy/completion-council.sh

@@ -1721,6 +1721,111 @@ EVIDENCE_EOF
     return 1
 }
 
+#===============================================================================
+# P2-2 Assumption ledger gate (spec-robustness).
+#
+# Blocks completion while any high-severity assumption is unresolved, where
+# unresolved means: severity=high AND confirmed=false AND acknowledged=false.
+# This is the completion-side teeth for the spec-interrogation feature: when the
+# spec was ambiguous and Loki had to assume something high-impact, "done" cannot
+# be declared until that assumption has at least been acknowledged (auto-ack
+# lifecycle in run.sh, default-on) or human-confirmed
+# (LOKI_ASSUMPTIONS_REQUIRE_CONFIRM=1).
+#
+# By-design timing: in DEFAULT autonomous mode run.sh auto-acknowledges entries
+# every iteration right after injecting them into the build prompt, so by the
+# time the council reaches this gate (>= COUNCIL_MIN_ITERATIONS) they are already
+# acknowledged and the gate passes. That is intentional: a permanent block on
+# "unconfirmed" in a non-TTY run would just die at max-iterations and never reach
+# the proof-of-done. The PERSISTENT block lives in the
+# LOKI_ASSUMPTIONS_REQUIRE_CONFIRM=1 path (auto-ack disabled, only human
+# confirmed=true clears it). In BOTH modes the assumptions are unconditionally
+# SURFACED in proof-of-done (build_completion_summary reads counts ignoring
+# ack/confirm state), so "done" always means "done, plus here is what I assumed."
+#
+# The block COUNT comes from spec_ledger_high_unresolved_count() in
+# autonomy/spec-interrogation.sh. The gate sources that module if it is not
+# already loaded, so it works both inside run.sh (already sourced) and in
+# standalone tests (sources it here). When the module / ledger is absent the
+# count is 0 and the gate passes -- a project with no recorded assumptions is
+# never blocked (no spurious block on clean specs).
+#
+# Mirrors council_evidence_gate: opt-out knob first, defensive COUNCIL_STATE_DIR
+# default, writes .loki/council/assumption-block.json on block (removed on pass).
+#
+# Returns 0 (pass / OK to complete) or 1 (block / CONTINUE).
+#===============================================================================
+council_assumption_ledger_gate() {
+    # Knob first: opt-out is exact-as-today, before any file read or write.
+    [ "${LOKI_ASSUMPTION_GATE:-1}" = "0" ] && return 0
+
+    if [ -z "${COUNCIL_STATE_DIR:-}" ]; then
+        COUNCIL_STATE_DIR="${TARGET_DIR:-.}/.loki/council"
+    fi
+
+    # Source the spec-interrogation module if its counter is not already defined
+    # (standalone tests / completion-promise route). Best-effort.
+    if ! type spec_ledger_high_unresolved_count >/dev/null 2>&1; then
+        local _si_helper
+        _si_helper="$(dirname "${BASH_SOURCE[0]}")/spec-interrogation.sh"
+        if [ -f "$_si_helper" ]; then
+            # shellcheck disable=SC1090
+            . "$_si_helper" 2>/dev/null || true
+        fi
+    fi
+
+    # No module => no ledger => nothing to block on (pass-through).
+    if ! type spec_ledger_high_unresolved_count >/dev/null 2>&1; then
+        if [ -f "$COUNCIL_STATE_DIR/assumption-block.json" ]; then
+            rm -f "$COUNCIL_STATE_DIR/assumption-block.json"
+        fi
+        return 0
+    fi
+
+    local unresolved
+    unresolved="$(spec_ledger_high_unresolved_count 2>/dev/null || echo 0)"
+    # Defensive: coerce to an integer.
+    case "$unresolved" in
+        ''|*[!0-9]*) unresolved=0 ;;
+    esac
+
+    if [ "$unresolved" -eq 0 ]; then
+        # Gate passes: remove any stale block report.
+        if [ -f "$COUNCIL_STATE_DIR/assumption-block.json" ]; then
+            rm -f "$COUNCIL_STATE_DIR/assumption-block.json"
+        fi
+        return 0
+    fi
+
+    log_warn "[Council] Assumption ledger gate BLOCKED: ${unresolved} high-severity spec assumption(s) unresolved (the spec was ambiguous in ${unresolved} high-impact place(s))."
+    log_warn "[Council] Resolve by confirming them in .loki/assumptions/ (set confirmed=true), or opt out with LOKI_ASSUMPTION_GATE=0."
+
+    mkdir -p "$COUNCIL_STATE_DIR" 2>/dev/null || true
+    local ab_file="$COUNCIL_STATE_DIR/assumption-block.json"
+    local ab_tmp="${ab_file}.tmp"
+    local timestamp
+    timestamp=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
+    cat > "$ab_tmp" << ASSUMPTION_EOF
+{
+    "status": "blocked",
+    "blocked": true,
+    "blocked_at": "$timestamp",
+    "iteration": ${ITERATION_COUNT:-0},
+    "reason": "high_severity_assumptions_unresolved",
+    "high_unresolved": $unresolved
+}
+ASSUMPTION_EOF
+    mv "$ab_tmp" "$ab_file" 2>/dev/null || rm -f "$ab_tmp" 2>/dev/null || true
+
+    if type record_trust_event_bash &>/dev/null; then
+        record_trust_event_bash "assumption_block" \
+            "high_unresolved=$unresolved" \
+            >/dev/null 2>&1 || true
+    fi
+
+    return 1
+}
+
 #===============================================================================
 # Council Member Review - Individual member evaluation
 #===============================================================================
@@ -2512,6 +2617,14 @@ council_evaluate() {
         return 1  # CONTINUE - cannot complete without real evidence
     fi
 
+    # P2-2: assumption ledger gate - block completion while high-severity spec
+    # assumptions are unresolved (the spec was ambiguous in a high-impact place
+    # and Loki had to assume something that has not been acknowledged/confirmed).
+    if ! council_assumption_ledger_gate; then
+        log_info "[Council] Completion blocked by assumption ledger gate"
+        return 1  # CONTINUE - cannot complete with unresolved high-sev assumptions
+    fi
+
     # Compute threshold using the same ceiling(2/3) formula as council_vote and council_aggregate_votes
     local _eval_threshold=$(( (COUNCIL_SIZE * 2 + 2) / 3 ))
 

package/autonomy/lib/sentrux-gate.sh

@@ -2,7 +2,7 @@
 # Loki Mode -- sentrux architectural-drift helper (v7.5.14).
 #
 # Why this exists:
-#   Loki's existing 11 quality gates and 3-reviewer council catch correctness
+#   Loki's existing 8 quality gates and 3-reviewer council catch correctness
 #   and behavioral regressions, but no current gate emits a deterministic,
 #   per-iteration architecture-drift signal. sentrux (https://github.com/sentrux/sentrux)
 #   is a Rust CLI that scores codebase structure (modularity, acyclicity,

package/autonomy/loki

@@ -16135,7 +16135,7 @@ print()
                 echo -e "${RED}Test coverage gate FAILED${NC}"
                 return 1
             else
-                echo -e "${GREEN}Tests passed (min coverage: ${min_coverage}%)${NC}"
+                echo -e "${GREEN}Tests passed (min coverage TARGET, not measured: ${min_coverage}%)${NC}"
                 return 0
             fi
             ;;
@@ -27527,7 +27527,7 @@ if test_results:
     test_lines.append(f"Passed: {test_results.get('pass', 'unknown')}")
     test_lines.append(f"Timestamp: {test_results.get('timestamp', 'unknown')}")
     if test_results.get("min_coverage"):
-        test_lines.append(f"Min coverage target: {test_results['min_coverage']}%")
+        test_lines.append(f"Min coverage TARGET (not measured): {test_results['min_coverage']}%")
 else:
     test_lines.append("No test result data recorded")
 sections.append(("Tests", test_lines))