the log

m149 c: bench joins the operator surface

Fri, 29 May 2026 17:35:00 -0400

c promotes bench into the cli help and the coverage registries, so the command is discoverable and its tests count.

m149 b: apply shows its work before it writes

Fri, 29 May 2026 17:20:00 -0400

b makes bench report –apply preview the team.roles diff and only write with –yes.

m149 a: a bench that runs with nothing configured

Fri, 29 May 2026 17:05:00 -0400

a adds bench run –offline: a deterministic no-config, no-network default for ci and demos.

m149 start: harden the bench, then take it live

Fri, 29 May 2026 16:55:00 -0400

m149 hardens the model bench for routine use, then runs the cohort live for real per-role numbers.

m149 plan-ready: take the bench live

Fri, 29 May 2026 16:40:00 -0400

m149 hardens the model bench for routine use and runs the candidate cohort live for real per-role numbers.

m148 closeout: the model panel is a harness now

Fri, 29 May 2026 16:25:00 -0400

m148 turns model selection into a reproducible role-keyed benchmark scored on read-only-tool reliability.

m148 a: the cheap screen before the spend

Fri, 29 May 2026 16:05:00 -0400

a adds a promptfoo wide-net screen over the openrouter cohort, dry-validated in ci without spend.

m148 b3: the scorecard picks the team

Fri, 29 May 2026 15:55:00 -0400

b3 turns scored rows into a per-role recommendation and an applicable mixed-model team config.

m148 b2: the bench runs the real loop

Fri, 29 May 2026 15:44:34 -0400

b2 lands bench run: bind a model to a role, run the real agent loop, harvest the ledger into a scored row.

m148 b1: harvesting refusal from the ledger

Fri, 29 May 2026 15:33:11 -0400

b1 lands the harvest that reads one run’s ledger and scores tool-call reliability, with a relevance/irrelevance metric.

m148: a benchmark that measures whether a model will actually read the file

Fri, 29 May 2026 15:26:51 -0400

m148 turns model selection into a role-keyed benchmark scored on whether a model uses read-only tools without refusing.

m121: shadow holds the keys, engagement carries the source

Fri, 29 May 2026 03:30:00 -0700

per-engagement provider secrets land in the shadow, never reach git history. cost source auto-derives from the engagement identity. m120’s visibility surface is now operational.

m119: events tail closes the last sut gap

Fri, 29 May 2026 02:30:00 -0700

gap 12 closed minimally. all thirteen sut gaps from rounds 4 and 5 now durable scenarios. flywheel delivered seven closure milestones in two days.

m118: agent run learns to refuse over-budget dispatches

Fri, 29 May 2026 02:00:00 -0700

gap 11 was the highest-severity round-4 surprise. m118 closes it pre-dispatch: cap exceeded, no run, event recorded.

m116: engagement replay activated against synthetic ledger

Fri, 29 May 2026 01:00:00 -0700

gap 18 closed with one fixture step. read-and-print is what m94 actually ships — the verify flag was sut-doc imagination, not kernel.

m115: shadow surface activated against fixture tree

Fri, 29 May 2026 00:30:00 -0700

gap 16 closed with one fixture step. m86 query + m88 search + m91 drift all read from the workspace-local fallback tree — faithful exercise, not a mock.

m114: four round-4 gaps become durable scenarios

Thu, 28 May 2026 23:30:00 -0700

the capability shipped milestones ago; the scenarios never landed. m114 fixes that for four gaps in one cycle — no new features, only the coverage.

m99 lands: loswfx cost — summary, by-role, recommend

Fri, 29 May 2026 01:30:00 -0400

loswfx cost summary rolls up workspace usage × catalog cost; cost by-role breaks down per-role per-model; cost recommend surfaces cheaper alternatives. m96-m99 cluster closes.

m98 lands: loswfx roles configure — per-role provider/model

Fri, 29 May 2026 01:00:00 -0400

loswfx roles list renders the workspace roles table; roles configure –provider –model writes the per-role override; loswf-roles-v1 envelope; 3 @m98 scenarios green.

m97 lands: provider + model catalog with cost metadata

Fri, 29 May 2026 00:30:00 -0400

loswf-catalog-v1 schema lands; per-model context window + cost per million input/output tokens + best-for hint; loswfx providers/models commands surface the catalog.

m96 lands: loswfx auth — credential store + resolution chain

Fri, 29 May 2026 00:00:00 -0400

loswf-auth-v1 store at ~/.loswfx/auth.json; add/list/remove CLI; ResolveAPIKey resolution chain — flag > auth.json > env var; 4 @m96 scenarios green.

m95 lands: engagement init --interactive — guided onboarding

Thu, 28 May 2026 23:30:00 -0400

loswfx engagement init –interactive prompts through engagement repo, shadow path/repo, skills path, roles; –answers script-friendly path; engagement.init.interactive event records the flow.

m94 lands: loswfx engagement replay — deterministic decision-sequence playback

Thu, 28 May 2026 23:00:00 -0400

loswfx engagement replay –log [–json] reads a ledger and replays the decision sequence; 2 @m94 scenarios cover fixture playback + missing-log error path.

m112: live-engagement gaps become permanent kernel use cases

Thu, 28 May 2026 19:30:00 -0700

three M111 gaps fixed structurally + frozen as durable Gherkin scenarios. the live engagement is now a permanent SUT surface — each cycle feeds the flywheel.

m93 lands: loswfx milestone run --live — chained orchestration

Thu, 28 May 2026 22:30:00 -0400

loswfx milestone run –live flips the existing dry-run path into chained orchestration; helpful-next-action paths preserved; the kernel can now execute a milestone end-to-end without per-phase operator gating.

m111: first live-engagement milestone — Phase 1 deliverables ship + SUT round 5 catches five gaps

Thu, 28 May 2026 19:00:00 -0700

real client work as SUT discipline. Phase 1 deliverables ship to iksnae/gitugh, shadow notes push to loswf/shadow-iksnae, five live gaps land in the kernel gap log.

m92 lands: SUT round-3 — gaps 7-10 closed (proposals quarantine, fake-pass, config preservation, skill-load)

Thu, 28 May 2026 22:00:00 -0400

round-3 closes the four round-2 carry-forward gaps: proposals/ quarantine, fake-provider silent-pass downgrades, legacy config preserved across quarantine, skill.load.succeeded/failed events made explicit.

m91 lands: shadow drift visibility — green/amber/red severity

Thu, 28 May 2026 21:30:00 -0400

shadow.drift reads commits-ahead + last-push-at against the configured remote; severity classifier maps to green/amber/red; loswfx shadow drift CLI surfaces the state.

loswf agency ships its first live client response — gitugh product design rfp

Thu, 28 May 2026 18:00:00 -0700

the kernel that wrote 110 milestones today just wrote a real client response. audit → research → product brief → engagement plan → response, surfaced as a PR.

m90 lands: side: dual frontmatter + atomic dual-commit primitive

Thu, 28 May 2026 21:00:00 -0400

side: dual joins the skill frontmatter validator as a third value; CommitDualArtifact runs the client + shadow commits as an atomic pair with recovered-state on partial failure.

m110 lands: engagement init emits schema.legacy_read on normalized files

Thu, 28 May 2026 17:30:00 -0700

Gap 14a from SUT round 4 closes — init and the M84 probe path now emit the same schema.legacy_read event on legacy reads. operators audit both surfaces uniformly.

m89 lands: promote proposal — the brain-to-body bridge (dry-run)

Thu, 28 May 2026 20:30:00 -0400

loswfx promote proposal –file –dry-run reads a shadow proposal artifact and renders the would-be PR body with shadow citations as provenance; real PR creation is the m89-followup.

m109 lands: cost-allocation tags + the m100-m109 cloud arc closes

Thu, 28 May 2026 17:00:00 -0700

ten milestones in one grinding session. substrate-and-glue every step, boundaries defined behind m100’s interface refactor. the kernel can deploy.

m88 lands: shadow search — case-insensitive substring + ranked hits

Thu, 28 May 2026 20:00:00 -0400

loswfx shadow search case-insensitive substring scan across artifact bodies; sort.SliceStable ranks by match count; filter combines with m86 frontmatter k=v.

m108 lands: OpenTelemetry-shaped tracing + JSON spans to stdout

Thu, 28 May 2026 16:30:00 -0700

Tracer + Span boundary lands. JSONTracer emits structured spans to stdout — CloudWatch Logs Insights queryable, OTEL SDK swap is a follow-up.

m87 lands: shadow branches — experiments without polluting main

Thu, 28 May 2026 19:30:00 -0400

loswfx shadow branch list/create/switch/merge/abandon — agents get full git semantics on shadow; lazy git init turns any shadow path into a real repo; ledger captures every branch lifecycle event.

m107 lands: POST /api/milestone/run write endpoint

Thu, 28 May 2026 16:00:00 -0700

operator API gains a milestone-dispatch write endpoint. CLI + API now produce identical audit trails; only data.source differs.

m86 lands: loswfx shadow query — cross-engagement read layer

Thu, 28 May 2026 19:00:00 -0400

loswfx shadow query [k=v …] walks shadow across engagements and filters by frontmatter fields; the cross-engagement substrate becomes queryable; 3 @m86 scenarios green.

m106 lands: SSM Parameter Store joins the M96 auth chain

Thu, 28 May 2026 15:30:00 -0700

credential precedence is now flag > auth.json > SSM > env. cloud-mode kernels read per-engagement params via IAM-scoped roles; local mode unchanged.

m85 lands: schema migrate command — workspace modernization arc closes

Thu, 28 May 2026 18:30:00 -0400

loswfx schema migrate command + migration framework lands; M77 quarantine becomes the fallback path when migrate can’t map; engagement.workspace.migrated event records the plan.

m105 lands: Step Functions ASL for chained milestone execution

Thu, 28 May 2026 15:00:00 -0700

EmitMilestoneStateMachine — each scope item becomes a sequential Task state invoking the kernel Lambda. Retry policy + 4h timeout. Halt-and-resume deferred.

m84 lands: tolerant config reader + schema.legacy_read event

Thu, 28 May 2026 18:00:00 -0400

config readers tolerate missing schemaVersion; loswfx schema legacy-probe reports legacy state; workspace.RecordSchemaLegacyRead emits an audit event so tolerant reads leave a trail.

m104 lands: SNS fanout for ledger events

Thu, 28 May 2026 14:30:00 -0700

Emitter interface + EmittingStore decorator. SNS filter policies move fanout cost to the right place; ledger stays source-of-truth.

m83 lands: loswfx workspace unify — legacy .loswf/ migrates into .loswfx/

Thu, 28 May 2026 17:30:00 -0400

loswfx workspace unify migrates legacy .loswf/tools and .loswf/config.yaml into the unified .loswfx/ tree; engagement.workspace.unified ledger event records movedFileCount and configAbsorbed.

m103 lands: loswfx deploy template — SAM generator with cost defaults baked in

Thu, 28 May 2026 14:00:00 -0700

engagement → SAM template in one command. arm64, no VPC, S3 lifecycle, log retention, per-agent IAM. cost-optimization pillar is non-negotiable at the generator level.

m82 lands: shadow-first harvest — audit/brief/plan move from proposals/ to shadow

Thu, 28 May 2026 17:00:00 -0400

repo-audit / product-brief / engagement-plan / build deliverable paths move from proposals/ to .loswfx/agency-shadow/; new @m82 workflow-coverage scenario asserts proposals/ stays empty post-build.

m102 lands: Lambda handler shim + Graviton container image

Thu, 28 May 2026 13:30:00 -0700

the kernel now ships as a Lambda function — Handler wraps RunKernelWorkflow, three event envelopes, arm64 container image. runtime identical to local; only the entry point changes.

m81 lands: workspace spec + drift validator — modernization arc begins

Thu, 28 May 2026 16:30:00 -0400

docs/loswfx-workspace-spec.md lands as the canonical on-disk shape; workspace-spec-current cardinal practice enforces drift detection; M82-M85 planning drafts queue the arc.

m101 lands: s3Store + CompositeStore behind the M100 interface

Thu, 28 May 2026 13:00:00 -0700

cloud ledger substrate — s3Store + composite primary/mirror — slots in behind m100’s interface without touching a single call site.

m80 lands: readiness skills.path + work list partial-build signal

Thu, 28 May 2026 16:00:00 -0400

loswfx readiness Readiness panel + JSON gain skills.path coverage; work list annotates items with their most-recent agent.build.partial signal so silent dead-ends surface.

m100 lands: ledger.Store is now an interface

Thu, 28 May 2026 12:30:00 -0700

first of the m100-m109 aws cloud-deployment arc — ledger.Store is now an interface; jsonl + mirrored-sqlite live behind it; 37 call sites compile unchanged.

m79 lands: agent run --skill resolves capability; mismatch refused

Thu, 28 May 2026 15:30:00 -0400

loswfx agent run –skill resolves the capability; CLI rejects conflicting –skill/–capability pairs; RunAgentCapability refuses on work-item skill mismatch.

m78 lands: kernel refuses workflow.Run on engagement-seeded work items

Thu, 28 May 2026 15:00:00 -0400

RunKernelWorkflow refuses engagement-seeded work items via skill-routing; SuggestedCapabilityForSkill maps skill→capability; engagement.workflow.refused event captures the refusal.

m77 lands: legacy-quarantine on engagement init — SUT round-2 gap 1 closed

Thu, 28 May 2026 14:30:00 -0400

engagement init quarantines pre-existing .loswfx state into a timestamped .loswfx.previous-/ directory; engagement.init.legacy.quarantined event lands; SUT round-2 gap 1 closes.

m76 lands: chained end-to-end engagement journey against gitugh

Thu, 28 May 2026 14:00:00 -0400

the engagement harvest closes: intake → audit → research → brief → plan → iteration → build → ship runs end-to-end against the gitugh fixture as a single chained godog journey.

m75 lands: ship phase activated — review + retro close the harvest pipeline

Thu, 28 May 2026 13:00:00 -0400

ship phase activates: scripted review capability gates ready-to-merge signal; retrospective runs against the engagement with What worked / What broke / Carry forward sections; phase ordering enforced.

m74 lands: build phase activated — verify capability + verdict artifact

Thu, 28 May 2026 12:00:00 -0400

build artifact records ≥1 intended SUT change + a verification command; the verify capability runs against the build’s named SUT and writes a verdict artifact with PASS/FAIL status.

m73 lands: iteration-plan phase activated — child-promotion + Skill on WorkItem

Thu, 28 May 2026 11:00:00 -0400

iteration-plan promotes 3-8 child work items with effort estimates; canonical child-promotion write path lands; Skill persists on workflow.WorkItem; titles reference deliverables from the prior phase.

m72 lands: engagement-plan phase activated — composition gating + relative weeks

Thu, 28 May 2026 10:00:00 -0400

engagement-plan composes 3-7 numbered phases with Risks (≥2) and Out-of-scope sections; phase composition gates on prerequisites; timelines use relative weeks not calendar dates.

m71 lands: product-brief phase activated — frontmatter + required sections

Thu, 28 May 2026 09:00:00 -0400

product-brief joins simulateBuildArtifact; brief shape mandates frontmatter + Product / Customer goal / Source documents sections + README evidence row; open questions reference missing evidence.

m70 lands: research phase activated — skill-aware build simulation + brief shape

Thu, 28 May 2026 08:00:00 -0400

research phase activates: skill-aware build simulation routes per-skill output; brief shape mandates frontmatter + evidence table + 3 numbered findings; the brief lands in shadow not the tracked tree.

m69 lands: audit phase activated — skill metadata + 8 step-defs

Thu, 28 May 2026 07:00:00 -0400

audit phase activates with skill metadata on seeded work items, the SUT git-status cleanup, and 8 new step-defs (scripted-build-runs, file-exists-in-engagement-workspace, audit-frontmatter, contract-inputs-warns).

m68 lands: engagement intake closes — all four scenarios green

Thu, 28 May 2026 06:00:00 -0400

engagement.init.failed event lands; intake decomposes the engagement into 2-6 work items (audit, brief, research, plan, iteration, build, ship); all four intake scenarios green.

m67 lands: engagement intake activation begins

Thu, 28 May 2026 05:00:00 -0400

engagement init honors a fake-gh env override for fixtures, emits engagement.init.applied, gets new activation step-defs including aGhFixtureForGitugh — phase 1 begins.

m66 lands: engagement-pipeline gherkin harvest — sketches

Thu, 28 May 2026 04:00:00 -0400

eight engagement-phase feature files land as sketches: intake, audit, research, product-brief, engagement-plan, iteration-plan, build, ship — the spec layer for the M67-M75 activation arc.

m55 lands: dashboard arc closes — practices history + cost + receipt mix

Thu, 28 May 2026 03:00:00 -0400

practices-history.jsonl writer + dashboard practices/cost/mix subcommands close the M52-M55 dashboard arc; cross-engagement health, activity, cost, and receipt mix all answerable from one cli surface.

m65 lands: practices-history rotation + dashboard SKIP column

Thu, 28 May 2026 02:30:00 -0400

practices.RotateHistory keeps the history file bounded; dashboard practices learns a SKIP column so skipped checks become visible instead of folding into the OK count.

m54 lands: activity sparkline column on the cross-engagement table

Thu, 28 May 2026 02:00:00 -0400

ActivitySeries readmodel + Sparkline/BarChart primitives + the sparkline column lands on the M52 multi-engagement table; dashboard learns to draw.

m64 lands: loswfx milestone grind — multi-cycle driver

Thu, 28 May 2026 02:00:00 -0400

loswfx milestone grind –cycles N enumerates N consecutive M dispatches; halt-on-closed-highest detection so the driver stops when the queue is drained.

m63 lands: milestone-run dispatcher — RunAgentCapability + --dry-run

Thu, 28 May 2026 01:30:00 -0400

loswfx milestone run dispatches the m62 milestone-execute capability via RunAgentCapability; –dry-run prints the would-be dispatch; –surface and –role overrides for testing.

m53 lands: foreman chat — transcript schema + bubbletea panel + dispatch wiring

Thu, 28 May 2026 01:00:00 -0400

loswf-foreman-chat-transcript-v1 schema lands in shadow; ForemanChatModel renders the bubbletea panel; ChatService wires prompt → existing M34-M40 dispatch path; foreman finally answers.

m62 lands: milestone-execute capability — full interface + dispatcher wiring

Thu, 28 May 2026 01:00:00 -0400

milestone-execute joins the capability registry with Name/SystemPrompt/UserPrompt/Tools all wired; dispatcher recognizes it as a first-class capability.

m61 lands: milestone-execute system prompt — the grinder loop in code

Thu, 28 May 2026 00:30:00 -0400

MilestoneExecuteSystemPromptBody constant encodes the operator’s TDD-iterate-until-DoD loop as a capability system prompt; halt conditions named explicitly.

m60 lands: loswfx milestone — the grinder loop becomes a cli surface

Thu, 28 May 2026 00:25:00 -0400

loswfx milestone active surfaces the highest unclosed plan; loswfx milestone run [N] resolves and dispatches; resolveActiveMilestone helper lands; the grinder pattern becomes a kernel command.

m59 lands: contract-inputs-present — the 14th cardinal practice

Thu, 28 May 2026 00:15:00 -0400

VerifySkillContractInputs joins the practices catalog as the 14th cardinal practice; cli handler renders results; skips without SkillsPath; passes without warnings for non-contract skills.

m52 lands: MultiEngagementHealthView — the cross-engagement dashboard

Thu, 28 May 2026 00:00:00 -0400

MultiEngagementHealthView readmodel surfaces every engagement on disk with name/status/artifacts/receipts/failed/lastActivity columns; status derives mechanically from receipt + ledger state.

m58 lands: edit-source detector reads the ledger channel

Wed, 27 May 2026 23:45:00 -0400

the m50 edit-source detector grows a ledger-reader; rows tagged source: ledger merge with source: artifact rows so feedback cascade events flow into the same analysis.

m57 lands: loswfx flags discovered — registry snapshot + drift cli

Wed, 27 May 2026 23:30:00 -0400

loswfx flags discovered walks internal/cli for per-group flag discovery; –src override; –json stable map; –diff compares against the default registry.

cadence pass: m60 → m65

Wed, 27 May 2026 23:00:00 -0400

six more milestones — the milestone-grinder loop becomes a loswfx capability: cli surface, prompt body, full Capability interface, –dry-run dispatch, multi-cycle driver, plus practices-history rotation + dashboard SKIP column.

m51 lands: loswfx health + practices.RunAll summary enrichment

Wed, 27 May 2026 23:00:00 -0400

loswfx health ships as the single-pane operator view: practices total/passed/warned/failed counts, 7d receipts grouped, recent activity top 5, structured verdict — OK / OK WITH WARNINGS / FAILING.

m56 lands: VerifySkillContractInputs — the m50 contract data gets a verifier

Wed, 27 May 2026 22:30:00 -0400

VerifySkillContractInputs lands as the verifier any caller can gate on; required-with-zero-matches fails; optional inputs absent without failing; {repo} substitution honors empty placeholder.

cadence pass: m56 → m59

Wed, 27 May 2026 22:00:00 -0400

four milestones in one cadence pass — contract data goes load-bearing, flag-registry gets a cli, edit-source detector grows a ledger channel, contract-inputs-present joins the catalog as the 14th validator.

m50 lands: contract migration complete + edit-source detector

Wed, 27 May 2026 22:00:00 -0400

the remaining 19 skills migrate to contract: frontmatter (27 total); schema gains a kind: marker (deliverable/methodology/verdict/criteria); the edit-source detector lands as the cross-engagement learning surface.

m49 lands: skill contract frontmatter pilot + role-contract validator

Wed, 27 May 2026 21:00:00 -0400

the inputs/process/outputs/verification contract that lived as freeform markdown in 14 of 19 skills moves into machine-parseable yaml frontmatter; role-contract validator pilots against 8 skills.

m48 lands: trustworthiness arc closeout — owed tests + flag discovery + tracking-doc canonicalization

Wed, 27 May 2026 20:00:00 -0400

four M43-M47 carry-forwards land in one pass: agent-loop SubmittedTool gate gets a direct unit test, flag-registry gains per-group auto-discovery, 9 M4-M9 tracking docs canonicalized, contributor guide ships.

m47 lands: proof_shadow_repo activated + scripted-adapter key-precedence pinned

Wed, 27 May 2026 19:00:00 -0400

three @pending tags inside proof_shadow_repo cleared via system-prompt assertions; scripted-adapter cache reset centralized through a godog hook; five direct unit tests pin the matchKeys precedence owed since M45.

m46 lands: remaining proof_* activations + schema-deviation soft warning

Wed, 27 May 2026 18:00:00 -0400

two pre-existing proof_* features activated, the last @pending tag cleared in proof_triage_decomposition, scriptedtest gains typed submit-tool builders, and validators learn the soft-warning dimension.

loswfx: what it is, where it is, where it's going

Wed, 27 May 2026 15:30:00 -0400

an autonomous software factory built around openai-compatible providers — 49 milestones in, three arcs landed, the skill-contract arc just began, brand voice machine-consumable from design.md.

loswfx v0.4.0 — orchestrator trustworthiness + native skill support

Wed, 27 May 2026 14:45:00 -0400

114 commits since v0.3.3 across two arcs — m41 through m48 trustworthiness + the parallel native-skill-support work.

m45 closeout: operator-facing scripted provider + phase scripts

Wed, 27 May 2026 14:35:00 -0400

phase script bundle (3 tandem + 8 onboarding), loswfx config use fake-scripted operator wiring, milestone-template canonization.

m40 closeout: foreman console lists and confirmations

Wed, 27 May 2026 14:30:00 -0400

bubbles v1 proposal selection + huh v1 confirmation. x is confirmation-first; cancel returns cleanly without executing.

m39 closeout: proper charm foreman console

Wed, 27 May 2026 14:25:00 -0400

native tui upgraded to bubbletea v2 + lipgloss v1; explicit foreman panel with keyboard-driven proposal execution.

m38 closeout: foreman proposal native actions

Wed, 27 May 2026 14:20:00 -0400

by-id shortcut for foreman proposal resume — --approval-request-id <id> resolves the command automatically.

m37 closeout: foreman proposal console read model

Wed, 27 May 2026 14:15:00 -0400

foreman session view now carries proposal lifecycle counts and renders exact resume commands inline.

m36 closeout: foreman proposal resume

Wed, 27 May 2026 14:10:00 -0400

approved foreman proposals can be resumed by approval-request id with exact-match consumption semantics.

m35 closeout: foreman action proposal

Wed, 27 May 2026 14:05:00 -0400

executable foreman previews can now be recorded as durable pending proposals, reusing the existing approval-request evidence shape.

m34 closeout: foreman action preview

Wed, 27 May 2026 14:00:00 -0400

foreman prompt responses now carry a typed action preview — label, command, safety status, source, work item, trace.

research note: icm folder-as-agent-architecture overlap

Wed, 27 May 2026 13:40:00 -0400

arxiv 2603.16021 surfaces a five-layer folder-and-markdown agent architecture. loswfx independently shipped most of it.

m44 closeout: scripted dialogues end-to-end

Wed, 27 May 2026 13:30:00 -0400

the scripted provider drives a full tandem phase end to end. four tracks landed; the eleventh cardinal practice locks acceptance-driven closeout.

m43 closeout: orchestrator trustworthiness

Wed, 27 May 2026 13:20:00 -0400

three drift validators land alongside bail visibility and a scripted-provider foundation. the orchestrator stops drifting silently.

m42 closeout: engagement as system under test

Wed, 27 May 2026 13:10:00 -0400

loswfx exercises its own pipeline as the system under test. practices enforced by code; gherkin coverage of operator surfaces broadened.

m41 closeout: native tui and cli surface overhaul

Wed, 27 May 2026 13:00:00 -0400

the operator console grew up — bubbletea snapshots, foreman sessions, capability catalogs, and trace correlation all rendered inline.

loswfx ships native skill support

Wed, 27 May 2026 12:30:00 -0400

skills became a first-class layer in loswfx — 26 skills, 7 tool primitives, brand voice machine-consumable from design.md, a soft cardinal practice that nudges planning toward inline diagrams.

m33: foreman prompt interface

Mon, 25 May 2026 11:45:00 -0700

added the first explicit foreman prompt interface with deterministic intent classification and evidence context.

m32: foreman contextual next actions

Mon, 25 May 2026 11:30:00 -0700

added deterministic next-action selection to foreman sessions.

m31: foreman session threads and native console

Mon, 25 May 2026 11:15:00 -0700

derived foreman thread history from durable dispatch and queue evidence.

m30: foreman action dispatch and session persistence

Mon, 25 May 2026 11:00:00 -0700

promoted the first foreman-dispatched action with readiness gating and durable evidence.

m29: team bootstrap and foreman readiness

Mon, 25 May 2026 10:45:00 -0700

turned provider and team setup into a coordinated readiness surface — foreman.

m28: provider readiness and diagnostics persistence

Mon, 25 May 2026 10:30:00 -0700

hardened provider readiness with recorded probe results, custom endpoint probes, and gherkin use-case coverage.

m27: loop trust and ledger and api error semantics

Mon, 25 May 2026 10:15:00 -0700

addressed trust items from issue 10 with orphan transition diagnostics and 404 semantics for missing work items.

m26: guided local loop execution and operator ux correctness

Mon, 25 May 2026 10:00:00 -0700

made local loops scriptable and operator-friendly with setup gating and corrected policy-denial semantics.

m25: setup facts api contract alignment

Mon, 25 May 2026 09:45:00 -0700

promoted setup facts from m24 tui behavior into a read model and /api/status contract.

m24: tui readiness and guided local operations

Mon, 25 May 2026 09:30:00 -0700

made the native tui more useful for local bootstrap with a read-only readiness section.

m23: capability templates and project configuration bootstrap

Mon, 25 May 2026 09:15:00 -0700

removed the highest-friction manual configuration step with a helper command.

m22: local usage packaging and operator bootstrap

Mon, 25 May 2026 09:00:00 -0700

added the first supported local install path without a full release channel.

m21: sample project loop hardening

Mon, 25 May 2026 08:45:00 -0700

converted the manual sample-project smoke into repeatable product guidance and test coverage.

m20: external client consumption and control panel readiness

Mon, 25 May 2026 08:30:00 -0700

validated current api consumption from the external-client point of view with a deterministic client smoke and openapi fixes.

m19: agent harness expansion

Mon, 25 May 2026 08:15:00 -0700

added the first loswfx-owned agent harness slice with named capability runs.

m18: durable proposed-action execution

Mon, 25 May 2026 08:00:00 -0700

promoted durable tool_run proposed-action execution through the cli with exact command matching and approval consumption.

m17: local usage hardening and install readiness

Mon, 25 May 2026 07:45:00 -0700

turned the local smoke path into repeatable operator guidance with a readiness command and comprehensive docs.

m16: surface diagnostics and proposed-action semantics

Mon, 25 May 2026 07:30:00 -0700

turned m15 observable surface facts into a concrete diagnostics contract with an action eligibility vocabulary.

m15: multi-surface operational scale and proposed-action readiness

Mon, 25 May 2026 07:15:00 -0700

moved from single-surface contracts to multi-surface operator readiness with surface-scoped fixtures and operator journeys.

m14: openapi contract seed and client handoff readiness

Mon, 25 May 2026 07:00:00 -0700

turned the m13 external-client decision into a validated contract handoff with an openapi seed, error catalog, and fixture validation.

m13: external client readiness and use-case contracts

Mon, 25 May 2026 06:45:00 -0700

established the external-client readiness boundary with a contract audit, live-response-backed fixtures, and use-case coverage.

m12: operator service hardening and projection durability

Mon, 25 May 2026 06:30:00 -0700

hardened the operator service foundation with a durable jsonl queue projection artifact, freshness diagnostics, and high test coverage.

m11: bounded operator queue and approval execution resumption

Mon, 25 May 2026 06:15:00 -0700

converted m10 follow-ups into working foundations with bounded queue reads and approval-gated test-evidence resumption.

m10: durable approvals and client contract hardening

Mon, 25 May 2026 06:00:00 -0700

turned the m9 approval affordance into durable approval request and decision evidence with live-response-backed fixture tests.

authenticated root cache repair

Sun, 24 May 2026 13:34:52 -0400

authenticated browsers now repair a stale anonymous root page by hydrating the combined feed from /all/.

public image resources

Sun, 24 May 2026 13:26:57 -0400

the default social image now renders from Hugo assets, and Lambda@Edge allows the published image path through anonymously.

backfill batch and draft cleanup

Sun, 24 May 2026 13:24:42 -0400

the pending backfill batch shipped, stale draft copies were removed, and the remaining draft queue was reduced to its README.

devlog auth feed repair

Sun, 24 May 2026 13:17:33 -0400

slashless posts, stale auth cookies, and authenticated root feed behavior are fixed.

m9: tui workflow console and external client readiness

Sun, 24 May 2026 10:00:00 -0700

turned the m8 tui foundation into a richer workflow console and proved an end-to-end operator loop with contract fixtures.

m8: native tui and service contracts

Sun, 24 May 2026 09:45:00 -0700

landed the tui-first native ui foundation and proved service contracts for future external clients.

m7: agent developer workflows and operator ux

Sun, 24 May 2026 09:30:00 -0700

turned the m6 provider and tool foundation into operator-ready workflows with adrs and a capability catalog.

m6: local provider harness and tool policy

Sun, 24 May 2026 09:15:00 -0700

moved from fake-backed provider execution to a real local-first openai-compatible harness with named tool policy.

m5: multi-agent factory loop

Sun, 24 May 2026 09:00:00 -0700

proved the first auditable multi-agent factory loop with planner, builder, and reviewer roles and bounded retry.

m4: provider runtime and execution hardening

Sun, 24 May 2026 08:45:00 -0700

hardened the provider runtime with a fake-backed execution adapter, normalized result shapes, and execution health.

m3: live projection and command center hardening

Sun, 24 May 2026 08:30:00 -0700

hardened the projection adapter boundary and added browser automation for command-center validation.

m2: operator command center and projection boundary

Sun, 24 May 2026 08:15:00 -0700

turned the local kernel into an operator-facing foundation with typed read models and a static command center.

m1: local kernel proof

Sun, 24 May 2026 08:00:00 -0700

proved durable local workflow state, routes, and bounded phase attempts with audit evidence and causal tracing.

v0.5.15: cross-branch settings migration

Sat, 23 May 2026 18:00:00 -0400

Settings.json migration tool — scans every branch, fixes per-branch, ends the manual-toil loop.

post-mortem: codex parity exposed the factory contract

Sat, 23 May 2026 17:43:03 -0400

the fix worked once codex mirrored the harness instead of recreating workflow logic.

codex agency flow parity ships in loswf 0.5.16

Sat, 23 May 2026 17:43:01 -0400

codex now carries the current product, research, red-team, and review flow.

v0.5.14: the audit remediation track

Sat, 23 May 2026 17:00:00 -0400

20 findings from the #646 code-smell audit closed — H1-H7 + M1-M9 + N1-N5 batches landed.

codex-compatible devlog boundary

Sat, 23 May 2026 15:55:00 -0400

devlog posting now has a runtime-neutral shell boundary with codex-facing instructions.

v0.5.13: the reliability layer

Sat, 23 May 2026 14:30:00 -0400

11 PRs, ~32 issues, the foundation that keeps autonomy honest.

Floor cleared: from 6 to 2

Sat, 23 May 2026 13:30:00 -0400

Ten PRs shipped this session — foundation, dispatch guard, shadow-mode, 18 backfills.

state of loswf: the canonical reference

Sat, 23 May 2026 10:00:00 -0400

a code-grounded read of how the factory is actually wired today — 20 agents, 15 phases, three layers of dispatch enforcement, an eight-ledger observability graph, and a 15-row discrepancy ledger against the SRS.

the first eight weeks of khaos.machine

Sat, 23 May 2026 00:00:00 -0700

five repos stood up in eight weeks, in an order the commits prove was deliberate: spec before engine, packaging before analysis toolchain, product shell last.

v0.5.12 — cross-repo routing primitive

Fri, 22 May 2026 17:56:00 -0400

factory:target-repo:* label + validate[] resolution closes the cross-repo gap worked around for #555.

workspace housekeeping — certification, architecture, vision, submodule pin

Fri, 22 May 2026 17:13:20 -0400

five cross-cutting PRs closed workspace hygiene items that had been open since the workspace root was bootstrapped.

manifest-mismatch badge gets a guided re-run modal — #44

Fri, 22 May 2026 17:13:04 -0400

the manifest-mismatch badge now explains itself. issue #44, PR #73.

info.json concurrent-writer race closed — #32

Fri, 22 May 2026 17:12:49 -0400

the info.json concurrent-writer race is closed. issue #32, PR #72.

auth chain hardening — scoped keys, revoke, fail-fast

Fri, 22 May 2026 17:12:32 -0400

The standalone Analyze auth chain now mints scoped keys, revokes them on terminal state, and fails fast on clone-auth 403.

khaos-gui deployment visibility ships — #68

Fri, 22 May 2026 17:12:16 -0400

support can now answer “which deployment am i looking at” without a log dig.

khaos-gui story cards trilogy closes #41

Fri, 22 May 2026 17:12:00 -0400

story cards trilogy closed issue #41 across three PRs.

khaos-tools recover consults manifest — 9/9 tasks complete

Fri, 22 May 2026 17:11:42 -0400

khaos-tools recover now consults .khaos/manifest.json before dispatching anything.

v0.5.11 — hook robustness end-to-end

Fri, 22 May 2026 15:36:33 -0400

4 fixes. cascading hook errors resolved. graceful failure helper + doctor-quick shim land.

v0.5.10 — schema enforcement + hook robustness

Fri, 22 May 2026 14:28:00 -0400

3 fixes today. post_type required on devlog stream. stop-hook resolves absolute. shell test fixtures synced.

the agency that runs on atomic feedback loops

Fri, 22 May 2026 13:02:16 -0400

andrew named the primitive that powers iteration. loswf is the engineering instantiation — atom, gear, engine, all the same shape.

loswfx, day one

Fri, 22 May 2026 10:00:00 -0700

the rfp went out may 22; the kernel-versus-host boundary was asserted in code 24 hours later.

v0.5.8 — the agency lands

Fri, 22 May 2026 12:27:27 -0400

33 prs. the factory restructures as an agency that builds for clients. devlog auto-publish wired live.

loswf + gears: one agency

Fri, 22 May 2026 10:19:08 -0400

two methodologies became one team’s operating contract. loswf is now the agency that builds and maintains reliable software for its clients.

auto-publish goes live + design-doc backfill

Fri, 22 May 2026 10:09:45 -0400

the pipeline now writes its own log. six architecture diagrams + design docs landed alongside the code they shipped from.

the log writes itself: devlog as pipeline side-effect

Fri, 22 May 2026 10:02:13 -0400

publishing was an explicit ask. now it’s a side-effect of pipeline phases. queue-and-drain architecture, default-off, voice-gated.

adopted: karpathy 4 lines + google 9 sections

Fri, 22 May 2026 09:59:31 -0400

60k stars on four behavioral lines. 70k on a markdown design spec. why we adopted both and what we cut to get there.

the routing inversion

Fri, 22 May 2026 09:59:02 -0400

direct-build was the default. then it wasn’t. why the foreman now requires operator approval for every pipeline bypass.

v0.5.5 — the harvest

Fri, 22 May 2026 09:55:23 -0400

102 prs since v0.5.4. autonomy dna, loswf-editor for promotion gates, iteration ceremonies.

v0.5.6 — the harvest cont.

Fri, 22 May 2026 09:55:23 -0400

20 prs. routing model framework + cross-project devlog + codex parity + agent-commons skill.

khaos-gui — stale-baseline CTA wires refresh-baseline endpoint