loki-mode 11.72.4 → 11.73.0

package/SKILL.md

@@ -3,7 +3,7 @@ name: loki-mode
 description: Runs an autonomous software factory that knows what it is supposed to deliver and proves it did, with a signed receipt. Use when the user says Loki Mode or asks to build, fix or verify software autonomously.
 ---
 
-# Loki Mode v11.72.4
+# Loki Mode v11.73.0
 
 **Current entry points (Loki 10 engine):** `loki "<task>"`, `loki owner/repo#N` and `loki quick "<task>"` run the Loki 10 engine and end with a signed receipt (`loki verify`). `loki backlog owner/repo --all` runs many issues in parallel. Guide: `docs/v10/GUIDE.md`. The skill instructions below, and `loki start`, describe the previous bash loop. PRD-file starts (`loki start ./prd.md`) and the opencode provider still run on it until FC38-SWEEP ports them; the legacy-engine command and the LOKI_ENGINE switch remain removed. Prefer `loki owner/repo#N` for issues.
 
@@ -476,4 +476,4 @@ Implemented, planned and deprecated items, with the version each landed in: `ski
 
 ---
 
-**v11.72.4 | [Autonomi](https://www.autonomi.dev/) flagship product | core skill**
+**v11.73.0 | [Autonomi](https://www.autonomi.dev/) flagship product | core skill**

package/VERSION

@@ -1 +1 @@
-11.72.4
+11.73.0

package/dashboard/__init__.py

@@ -7,6 +7,6 @@ Modules:
     control: Session control helpers (status, atomic writes, origin check)
 """
 
-__version__ = "11.72.4"
+__version__ = "11.73.0"
 
 __all__ = ["__version__"]

package/docs/CLI-REFERENCE.md

@@ -1,6 +1,6 @@
 # CLI reference
 
-Generated from `loki-ts/src/cli/registry.ts` by `scripts/generate-stale-zero.sh` for v11.72.4. Do not edit by hand.
+Generated from `loki-ts/src/cli/registry.ts` by `scripts/generate-stale-zero.sh` for v11.73.0. Do not edit by hand.
 Hidden and legacy-only commands are omitted; see `docs/v10/CLI-MODERN.md` for the full inventory.
 
 | Command | Description |

package/docs/INSTALLATION.md

@@ -2,7 +2,7 @@
 
 Loki Mode, by [Autonomi](https://www.autonomi.dev/), turns a spec or an issue into a verified pull request with a receipt you can check. This page covers installing it, a first run, and the options around it.
 
-**Version:** v11.72.4
+**Version:** v11.73.0
 
 **Engine note:** `loki start` is the primary command. `loki start`, `loki "<task>"`, `loki owner/repo#N` and `loki quick` all run the Loki 10 engine, whatever the flag order or input form (PRD file, issue ref, task or one-word brief). The previous loop runs only on `--engine legacy`, `LOKI_ENGINE=legacy`, or for one call when a flag Loki 10 cannot honor is present. See the [user guide](v10/GUIDE.md) and the [5-minute quickstart](QUICKSTART.md).
 

package/docs/dev/architecture-reference.md

@@ -84,6 +84,32 @@ Observability: SDK failures emit a structured `capability_degraded` record to
 `.loki/events.jsonl`; `.loki/app-runner/first-preview.json` records
 time-to-first-preview write-once (bash route only).
 
+## Anthropic SDK upgrade capability matrix (RQ-104, 2026-10-23)
+
+Pins (exact, all sites): `@anthropic-ai/sdk` 0.124.0 -> 1.2.0 (loki-ts/package.json, loki-ts/bun.lock, docker/Dockerfile peer pin); `@anthropic-ai/claude-agent-sdk` 0.3.293 -> 0.3.309 (loki-ts/package.json, package.json, package-lock.json, bun.lock, docker/Dockerfile). `tests/test-sdk-version-sync.sh` asserts both. Sources: sdk CHANGELOG 0.125.0..1.2.0, agent-sdk CHANGELOG 0.3.294..0.3.309.
+
+| Change | Status |
+|---|---|
+| sdk 1.0.0 BREAKING "new API version 2026-10-21" | WIRED at compile level only: loki-ts/src/runner/sdk_invoker.ts:19,311 (messages.create, output_config) compiles unchanged under tsc rc=0 and sdk_invoker tests pass. Live behavior at API version 2026-10-21 is NOT PROVEN (no API key, no paid run) |
+| sdk 0.129.0 `claude-sonnet-5-5`, 0.128.0 `claude-opus-5-5`, 0.132.0 `claude-haiku-5-5` model ids | WIRED: model ids are passed through as strings by sdk_invoker.ts; no allowlist to change |
+| sdk 0.135.0 `speed` param and `usage.speed` | NOT ADOPTED: the cost ledger (util/child_ledger.ts:54) has no fast-mode price table; adopting speed without pricing would misreport cost |
+| sdk 0.134.0 native OpenTelemetry tracing (auto-on with a global tracer provider) | NOT ADOPTED: Loki registers no global tracer provider, so the SDK stays inert; no opt-in needed |
+| sdk 0.126.0 compaction param, 0.127.0 `compactBeforeNextTurn()`, 0.129.0 tool-call-while-streaming, tool runner fixes (0.128.0, 1.2.0) | NOT ADOPTED: sdk_invoker is a one-shot messages.create judge, not a tool runner or multi-turn loop |
+| sdk 0.129.0 cache diagnostics on Message | NOT ADOPTED: Loki already accounts cache tokens from usage (util/child_ledger.ts cache_creation_tokens, cache_read_tokens; cost_breakdown); diagnostics would add a second source of truth |
+| sdk 0.129.0 `between_tools` thinking | NOT ADOPTED: judge path clamps thinking by effort (sdk_invoker.ts clampThinkingForEffort); between_tools is not offered to judges |
+| sdk 0.135.0/0.136.0 streaming fixes (unread stream close, unknown SSE events) | NOT ADOPTED: sdk_invoker does not stream |
+| sdk 0.130.0-1.2.0 Admin API (analytics, spend limits, RBAC, plugins, webhooks, message threads, usage/cost reports), Managed Agents additions | NOT ADOPTED: no Loki feature calls these APIs |
+| agent-sdk 0.3.302 refused structured output now an error with no payload | NOT AFFECTED: quality_gates.ts:1616 reads `e["structured_output"]` and fails closed to null when it is absent or not an object (falls back to parsing `result`); a refusal with no payload therefore yields null, the same outcome as before. Refusals are also handled by sdk_stream_parser.ts refusal frames |
+| agent-sdk 0.3.300 `thinking: disabled` runs adaptive on models that cannot disable | NOT ADOPTED: providers.ts:846 query() options pass no thinking setting |
+| agent-sdk 0.3.302 fork subagents on by default in SDK sessions | NOT ADOPTED: accepted default, effect on Loki runs unmeasured; `CLAUDE_CODE_FORK_SUBAGENT=0` is the opt-out |
+| agent-sdk 0.3.302 omitted `permissionMode` defaults to `default` on third-party providers | N/A: Loki always passes an explicit permissionMode (providers/claude_flags.ts:1052) |
+| agent-sdk 0.3.301 full-disk login refresh error is `invalid_request`, not `authentication_failed` | NOT ADOPTED: sdk_stream_parser.ts:278 keys only on `authentication_failed`; a full-disk refresh failure surfaces as a generic error, accepted until observed |
+| agent-sdk 0.3.300 PreToolUse/PermissionRequest `updatedInput` validated, unknown keys dropped | N/A: runSdkHostGuard (providers.ts:784) returns no updatedInput |
+| agent-sdk 0.3.296 `claude_code_version` in the initialize control response | NOT ADOPTED: SDK_BUNDLED_CLAUDE_CODE (providers.ts:364) is read before any session starts and is guarded by a test against the installed SDK claudeCodeVersion; the initialize value only exists after spawn |
+| agent-sdk 0.3.295 SDK passes option values as `--flag=value` | N/A: Loki consumes the SDK options API, not CLI argv, on the SDK route |
+| agent-sdk 0.3.301 `BUILTIN_TOOL_NAMES`, sdk MCP `permission_policy`; 0.3.304 `suspendSseStream` (browser); 0.3.296 `autoCompactWindow`; 0.3.307 `wakeup_source`; 0.3.305 `startup()` timeout fix | NOT ADOPTED: no existing Loki feature maps to these options |
+| agent-sdk 0.3.309 `extractFromBunfs()` per-user temp dir | NOT ADOPTED: Loki does not run the SDK from a Bun-compiled binary |
+
 ## Phase 1 / RARV-C Closure Env Vars
 
 Default-on in the Bun runner (see `CHANGELOG.md` v7.x entries; documented in `skills/quality-gates.md:88-110`). Set to `0` to disable; set to `1` to force-enable on the bash route.

package/docs/v10/OPERATING-MODEL.md

@@ -3,15 +3,21 @@
 The CEO is Lokesh Mure (Loki), the founder. Everyone else is an agent. The company ships Loki Mode v10 per docs/V10-VISION.md. Order when goals conflict: moat > Seal accuracy > delivered accuracy > cost > speed. Velocity target: 30-60 releases per day.
 
 ## Roles and models (pin every agent's model explicitly, D13)
-- Chief of Staff (the main session, opus): runs the operating rhythm, owns BOARD.md dispatch, keeps every seat busy, escalates only to Loki, never writes product code.
-- CTO (opus, advisor): architecture and quality calls, approves any change to the moat, gates or release policy.
-- Project Managers (opus, advisors): flow, bottlenecks, staffing. Each PM owns one workstream and its board rows.
-- Architects (opus): split every large task into 10-40 independent slices with non-overlapping file sets and Wall checks. They design; they do not implement.
-- Product Owners (sonnet): backlog ranking, slice cards (60 lines max: goal, file set, Wall checks, commands, budget, tier).
+Ten standing seats. Each file holds the seat's mandate, metrics, decision rights, inputs, outputs, escalation rule and the RETRO-2026.md root causes it owns. Each seat writes .loki/company/status/<slug>.json every turn; the cockpit (tools/cockpit/SPEC.md) reads them.
+- chief-of-staff (opus, the main session; .claude/agents/chief-of-staff.md): operating rhythm, BOARD.md dispatch, CEO digest, founder queue, ROI ledger; holds the PM duty; escalates only to Loki; never writes product code. RC6, RC9, RC1.
+- cto (opus; .claude/agents/cto.md): architecture and quality calls; approves any change to the moat, gates or release policy; acts as Architect for large tasks (designs the slices, never implements them); rules review round 3. RC4, RC7, RC3.
+- release-reliability-lead (sonnet, exactly one; .claude/agents/release-reliability-lead.md): the Release Manager, the only role that pushes main, bumps VERSION, tags or publishes; owns channel truth and the post-publish first-run gate. RC5, RC7, RC4.
+- verification-scientist (opus; .claude/agents/verification-scientist.md): claims registry, Seal and verdict accuracy, guard mutation; veto on uncited claims. RC2, RC1, RC3.
+- research-outcomes-scientist (opus; .claude/agents/research-outcomes-scientist.md): nightly Loki versus raw claude -p scoreboard, the only source for outcome claims. RC1, RC9, RC5.
+- research-harness-scientist (opus; .claude/agents/research-harness-scientist.md): ablation, model-tier pinning, SDK freshness, frontier scan. RC9, RC1, RC10.
+- product-growth-lead (sonnet; .claude/agents/product-growth-lead.md): the Product Owner; strategy page, backlog ranking, slice cards (60 lines max), funnel, competitor matrix. RC10, RC4, RC1.
+- developer-experience-lead (sonnet; .claude/agents/developer-experience-lead.md): install, loki start, preview, dashboard, docs from code, platforms. RC5, RC10, RC2.
+- security-lead (sonnet; .claude/agents/security-lead.md): secrets, deny-by-default env, auth boundaries; dispatches the HIGH security reviewers. RC3, RC5, RC8.
+- platform-lead (sonnet; .claude/agents/platform-lead.md): process safety, guards as mechanisms, CI speed, structured stores, the cockpit build. RC8, RC3, RC7.
+Spawned per slice, not standing seats:
+- Software Engineers (sonnet): one slice each, worktree isolation, single writer, red-then-green tests.
 - Tech Leads (sonnet): LOW and MEDIUM reviews, unanimous (D12).
 - Reviewers for HIGH-tier work (opus): moat, verifier, Seal, auth, security. Unanimous; a reproduced blocking finding always blocks (D12).
-- Software Engineers (sonnet): one slice each, worktree isolation, single writer, red-then-green tests.
-- Release Manager (sonnet, exactly one): the only role that pushes main, bumps VERSION, tags or publishes.
 
 ## Leadership lock (one company per repo)
 - The leader holds .loki/v10-leader (PID and start time). A session becomes leader only if that file is missing or its PID is dead (kill -0 fails).
@@ -20,7 +26,7 @@ The CEO is Lokesh Mure (Loki), the founder. Everyone else is an agent. The compa
 ## Nobody sits idle
 - Ready queue >= 30 specced slices (features, enhancements, fixes evenly; D91). Seat cap 20 (D103: founder ruled cost irrelevant on the Max plan; load and memory are the limit).
 - The Chief of Staff keeps 8-16 engineers busy whenever ready slices exist. When anyone finishes, the next slice is assigned in the same turn.
-- The ready queue never drops below 2x the number of engineers; PMs and POs refill it.
+- The ready queue never drops below 2x the number of engineers; the chief-of-staff and the product-growth-lead refill it.
 - Idle seats while work exists, or an empty ready queue, is a P0 violation.
 
 ## Time limits (anything slower gets redesigned, not waited on)