@haaaiawd/loom 1.3.1 → 2.0.1

package/design.md

@@ -0,0 +1,201 @@
+# LOOM 2 System Design
+
+Status: implemented core, evaluation pending independent trials.
+
+## Product decision
+
+LOOM is for the Agent, not the human. Its job is to make a normal capable Agent substantially better at
+understanding a personalized project, acquiring the right professional judgment, continuing after context
+loss, and completing real work. The human experience remains natural conversation.
+
+The system therefore optimizes for four observable outcomes:
+
+1. The Agent can explain the intended whole rather than mirror a feature list.
+2. Consequential uncertainty becomes useful conversation instead of silent guessing or a fixed questionnaire.
+3. Consequential product, experience, system, contract, and verification decisions remain navigable as
+   separate documents rather than collapsing into one summary.
+4. Each relevant professional field changes decisions and produces a distinctive project stance without
+   being blended into an invented hybrid capability.
+5. A fresh Agent can resume the current Task from disk without inherited chat memory.
+
+Document production, role performance, stage completion, and graph density are not success metrics.
+
+## Minimal closed loop
+
+```text
+Understand → Clarify → Record → Map professional fields
+     ↑                              ↓
+     └──── update whole ← Design document graph → Work Map
+                            ↑                      ↓
+                            └── Keeper gaps ← fresh Keeper
+                                                   ↓ passed
+                           blocked/reopen ← Active Task → Evidence → next Task
+```
+
+### Understand and clarify
+
+The Agent inspects the workspace when the user's request makes it relevant. It describes the emerging
+result naturally and identifies the current uncertainty frontier. The frontier contains only decisions
+whose answers could materially change outcome, behavior, boundary, system, risk, or completion.
+
+The prompt constrains judgment, not question content. It requires a coherent high-value round, adaptive
+grouping, first-principles re-evaluation, and a convergence condition. It does not mandate headings,
+question counts, or a universal sequence.
+
+Convergence means the Agent can explain the whole result, its boundaries, the professional capability it
+needs, and how completion will be observed. Remaining unknowns must be reversible and local, explicitly
+delegated to the Agent, or explicitly skipped by the human after a concrete warning.
+
+### Record
+
+Markdown stores human-readable project truth. JSON stores machine state that people do not need to edit.
+Important corrections do not leave contradictory truths scattered through the corpus: PROJECT.md maps the
+current whole, `.loom/design/` owns detailed decisions, and DECISIONS.md records consequential supersession
+with rationale and impact.
+
+### Design document graph
+
+`PROJECT.md` is an entry point, not a compression target. Product definition, experience, independent
+systems, contracts, verification, operations, and research receive separate documents when they have their
+own decisions, interfaces, failure modes, or proof. Project size determines document count. This keeps a small
+project small while allowing a large system to become fully legible instead of “minimal” in the anemic sense.
+
+### Acquire capability
+
+Capabilities are project-scoped professional-field dossiers, not reusable expert personas or task methods.
+One dossier maps to one recognizable field. UI/UX design, visual art direction, game design, psychology,
+biology, security, and distributed systems remain separate when they use different evidence or judgments.
+Cross-field synthesis lives in the design document whose decision it changes. A dossier contains:
+
+- the field boundary, the decisions it changes, and the project reality grounding it;
+- specialist principles, evidence, sources, conflicts, and uncertainty;
+- an authored, falsifiable project stance and deliberate refusals;
+- questions whose answers could change the decision;
+- design and implementation consequences;
+- generic failure modes and observable verification signals;
+- opened sources, what each changed, conflicts, and uncertainty when research is used.
+
+Acquisition can happen quietly. The Agent may briefly name the capability it is obtaining, but does not
+turn research logistics into user workflow.
+
+### Work Map and Task
+
+Planning uses progressive resolution. A broad initial Work Map protects whole-project coverage and may be
+very long. Only the active horizon receives detailed actions. The context compiler returns counts and the
+current Task rather than injecting the whole plan.
+
+Task is the single execution contract:
+
+```json
+{
+  "id": "TASK-001",
+  "title": "Implement restartable context",
+  "outcome": "A fresh Agent receives only decision-relevant context",
+  "done_when": ["A forced-reset transcript resumes correctly"],
+  "boundaries": ["The human never operates LOOM"],
+  "depends_on": [],
+  "reads": [".loom/PROJECT.md", ".loom/design/context-system.md", ".loom/capabilities/human-agent-interaction.md", "fixtures/reset-case.md"],
+  "touches": ["cli/src/context.js"],
+  "status": "active",
+  "progress": {
+    "completed": [],
+    "current": "Implementing selector",
+    "next": "Run reset transcript"
+  },
+  "evidence": []
+}
+```
+
+There is at most one active Task. Completion requires a concrete evidence mapping for every exact `done_when`
+criterion. A completed Task can be reopened with a reason when later evidence disproves it. The Task plan may change without
+human approval when the change is a reversible implementation refinement inside the agreed whole; outcome,
+authority, risk, or material cost changes return to the conversation.
+
+### One-time Keeper
+
+Keeper is not a recurring role. It is a single isolation test at the transition from shaping to material
+execution. A fresh Agent receives no prior conversation, runs `loom context --keeper`, explains the whole,
+selects a first Task, navigates its design documents and professional capabilities, and identifies concrete evidence. Every attempt binds a unique
+fresh-thread `run_id` to the digest frozen by `project ready`. It may return gaps; summary, evidence and exact gaps
+are injected into the main Agent's next context. Revision must change project truth or Task definitions before a
+new digest and fresh Keeper run are allowed. Once passed, normal Task evidence replaces further Keeper ceremony.
+
+If the host lacks subagents, LOOM supplies a one-sentence prompt for a new window. Explicit skip is possible
+but must preserve a concrete reason and reduced confidence.
+
+## Runtime structure
+
+```text
+cli/bin/loom.js       small command router
+cli/src/store.js      state, design, capability, Task, Keeper, context and eval operations
+cli/src/protocol.js   layered Agent prompts and every human-readable template
+cli/test/run-all.js   end-to-end contract tests
+```
+
+The CLI has six responsibilities:
+
+1. Initialize the minimal project backbone.
+2. Record structured understanding and decision history safely.
+3. Scaffold a scalable design-document graph and separate professional-field dossiers.
+4. Maintain a large Work Map and a single active Task.
+5. Compile only decision-relevant context after reset.
+6. Prepare one-time Keeper and controlled Evil Eval artifacts.
+
+It does not orchestrate models, browse the web, generate project documents, or pretend that a CLI command
+clears model memory. Those capabilities belong to the host Agent and its tools.
+
+## State transition
+
+Project status is a compact orientation signal, not a phase bureaucracy:
+
+```text
+shaping ⇄ question, design-document, and professional-capability loop
+   ↓
+ready_for_keeper ⇄ fresh Keeper needs_revision or blocked → shaping
+   ↓ passed
+build_ready → building ⇄ Task repair or block or reopen → complete
+```
+
+`project ready` checks only structural prerequisites: PROJECT.md is no longer a template, at least one design
+document and a Work Map exist, and no high-impact open question remains. Keeper judges semantic build-readiness. Task start requires Keeper
+pass or an explicit recorded skip. An unchanged revision, duplicate Keeper run, wrong digest, or stale prepared
+state is rejected. Imported Tasks start open, `task start` rejects missing or directory-level context reads,
+generic updates cannot change status, and completion requires criterion-by-criterion evidence.
+
+## Context selection
+
+`loom context` always injects:
+
+- the stable Agent protocol;
+- compact state counts and open uncertainty;
+- PROJECT.md, with decision history identified as on-demand context;
+- the active Task, if one exists;
+- the exact design, capability, source, contract, or fixture files named in that Task's `reads` list.
+
+When a Task is active, context also injects a short execution protocol. It tells a reset Agent to reconcile
+the Task with the current workspace and version-control state, inspect relevant tests before editing, choose
+verification according to risk and the exact `done_when` claims, persist `completed/current/next` at meaningful
+handoff boundaries, and close only with reproducible criterion-level evidence. It deliberately does not require
+a ceremonial unit test for every kind of work or a branch, commit, or pull request for every Task. Those
+delivery mechanisms remain conditional on the human request and repository workflow.
+
+Workspace code paths in `touches` are identified but not automatically copied into context. Full decision
+history is not repeatedly injected because current truth belongs in PROJECT.md and linked design documents.
+`loom context --keeper` includes history, every design document, and every professional capability dossier
+because whole-project coverage and contradiction detection are exactly what the isolated handoff tests.
+
+## Compatibility decision
+
+LOOM 2 is a major redesign. It does not silently mutate `.loom/v1` projects and does not preserve the old command
+surface. Encountering a legacy layout produces an explicit migration boundary. Git remains the recovery path;
+an automated semantic migration can be designed only after real v1 projects reveal which history is valuable.
+
+## Known boundaries
+
+- External capability acquisition is represented but not automated yet; the host Agent performs research.
+- Markdown is intentionally human-editable. LOOM validates file existence and structured state, not prose truth.
+- Keeper independence depends on the host creating a fresh thread or window.
+- Evil Eval scaffolding controls experiment design but does not itself launch model runs.
+- A one-time Keeper verifies build-readiness, not the eventual quality of every implementation Task.
+
+These are honest capability boundaries, not deferred stages disguised as completion.

package/docs/PROMPT_CATALOG.md

@@ -0,0 +1,106 @@
+# LOOM Prompt and Message Catalog
+
+LOOM's prompts are cognitive interfaces, not a collection of role-playing personas. The exact live
+inventory is emitted by:
+
+```bash
+loom prompts
+```
+
+The command is the auditable source of truth. It returns the complete text, placeholders, and composition
+order as JSON, so documentation cannot quietly describe a different prompt from the one Agents receive.
+
+## Instruction layers
+
+| Layer | Message | Injected when | Purpose |
+|---|---|---|---|
+| Stable core | `layers.stable_core` | Every `loom context` | Durable collaboration judgment: user ownership, evidence classes, question threshold, corrections, reversible delegation |
+| Runtime adaptation | `layers.runtime_protocol` | Every `loom context` | LOOM-specific disk model, document graph, capability boundaries, Work Map, and three production loops |
+| Project state | `layers.project_state` | Every `loom context` | Dynamic status, uncertainty, assumptions, document/capability inventory, Task counts, and Keeper feedback |
+| Execution protocol | `layers.execution_protocol` | Active Task or `--task` | Recovery, workspace inspection, risk-based testing, progress persistence, exact proof, and delivery boundaries |
+| Current task | `layers.current_task` | Active Task or `--task` | Exact Task JSON followed by the exact contents of every path in `reads` |
+
+This separation is deliberate. Project-specific expertise does not inflate the stable prompt; it lives in
+field dossiers. One-off Task instructions do not become global doctrine. Host permissions and tools are not
+claimed by prompt text.
+
+## Workspace and document messages
+
+`workspace_anchor` is the short block added to `AGENTS.md`. It tells an entering or reset Agent to run
+`loom context`, rerun it before editing after an interruption, persist state at meaningful boundaries rather
+than before every tool call, and keep CLI operation invisible to the human.
+
+`templates.project_index` creates `.loom/PROJECT.md` as a concise whole and document map. It explicitly
+prevents a large project's systems from being compressed into one file.
+
+`templates.design_documents` contains all seven live design templates:
+
+1. `product` — outcome, users, problem, product principles, scope, end-to-end behavior, success and failure.
+2. `experience` — journey, information architecture, states, content, visual direction, accessibility, recovery, usability proof.
+3. `system` — responsibilities, boundaries, control flow, data, interfaces, dependencies, failure, implementation, verification.
+4. `contract` — consumers, schemas or commands, invariants, permissions, errors, compatibility, fixtures, contract tests.
+5. `verification` — claims, environments, fixtures, acceptance matrix, commands, negative tests, blind spots.
+6. `operations` — authority, procedures, commands, safety, failure recovery, evidence and audit trail.
+7. `research` — decision, evidence, method, sources, findings, conflicts, consequences and follow-up proof.
+
+These are possible document kinds, not a fixed seven-file checklist. The Agent creates as many actual
+documents as the project's independent decision surfaces require.
+
+`templates.professional_capability` is the only capability template. It enforces one recognizable field per
+file, a project-specific diagnosis and stance, opened evidence, rejected generic defaults, concrete design and
+verification consequences, failure modes, and links to adjacent fields without merging them.
+
+`templates.decision_history` is the preamble for consequential superseding decisions. Current truth stays in
+the project map and linked design documents.
+
+## Keeper message
+
+`keeper` is the exact independent handoff prompt. It binds a unique fresh-Agent `run_id` to a frozen
+`prepared_digest`, asks the Keeper to navigate the whole corpus and attempt the first Task, and defines three
+verdicts:
+
+- `passed`: a fresh Agent can responsibly begin.
+- `needs_revision`: concrete disk-truth gaps can be repaired.
+- `blocked`: progress needs unavailable authority or external state.
+
+A failed result is injected into the next project-state message. A retry requires changed project truth, a
+new digest, and another fresh Keeper.
+
+## Evil Eval messages
+
+`evaluation.baseline_condition` gives a normal capable Agent the identical brief and ordinary tools without
+LOOM. It does not weaken the baseline or prohibit normal planning.
+
+`evaluation.loom_condition` gives the same brief, model class, tools, workspace facts, and budget, adding only
+LOOM continuity infrastructure and no extra authority.
+
+`evaluation.blind_judge` scores anonymized output on intent fidelity, question value, whole coverage,
+professional depth, buildability, reset continuity, implementation evidence, human burden, and cost. It
+penalizes ceremony and runs an order swap.
+
+## Composition messages
+
+`composition.normal_resume`, `composition.active_task`, and `composition.keeper_handoff` list the exact block
+order. Keeper receives every design and capability document; a normal active Task receives only its declared
+reads. This difference is intentional: Keeper audits whole-project coverage, while delivery protects context
+focus.
+
+The active Task composition adds `execution_protocol` between the recovered project whole and the exact Task.
+It requires inspection of current workspace/version-control reality, risk-appropriate tests, restartable
+progress, and criterion-level proof. It does not force a unit test for non-code claims or a branch/PR for every
+Task; those are selected when the behavior, human request, or repository workflow makes them meaningful.
+
+## CLI operational messages
+
+`loom --help` is the complete command-oriented message surface. JSON command results report state and the next
+host action. Validation errors are contract enforcement rather than cognitive prompts; they reject unsafe
+references, template-only readiness, missing design documents, open high-impact uncertainty, unchanged Keeper
+retries, stale digests, duplicate run identities, Task dependency violations, missing or directory-level Task
+reads, status bypasses, completion without evidence for every done condition, and reasonless reopening of a
+disproven completion.
+
+The short human fallback when the host cannot create a Keeper Agent remains:
+
+```text
+Please open a new window in this project, run loom keeper prompt, and follow it.
+```

package/docs/RELEASE_CHECKLIST.md

@@ -0,0 +1,53 @@
+# LOOM release checklist
+
+This checklist stops a documentation-complete release from becoming a runtime-incomplete release.
+
+## 1. Confirm the release surface
+
+```bash
+node cli/bin/loom.js --version
+node cli/bin/loom.js --help
+node cli/bin/loom.js prompts
+npm test
+npm pack --dry-run
+```
+
+Confirm that the package contains the CLI runtime, English and Chinese READMEs, design, prompt catalog, UX flow, Evil Eval
+protocol, changelog, license, contribution guide, and security policy. Check that it does not contain pilot
+workspaces, eval artifacts, temporary browser profiles, or local project state.
+
+## 2. Confirm metadata and registry state
+
+```bash
+npm whoami
+npm view @haaaiawd/loom version
+git status --short
+git diff --check
+```
+
+The version in `package.json`, `CHANGELOG.md`, and `loom --version` must agree. The new version must not
+already exist in the registry.
+
+## 3. Publish deliberately
+
+```bash
+git tag v2.0.1
+git push origin HEAD
+git push origin v2.0.1
+npm publish --access public
+```
+
+Run these commands only after reviewing the final diff and confirming the authenticated GitHub remote and
+npm identity. Tags and published npm versions are externally visible and should not be used as test steps.
+
+## 4. Verify from the outside
+
+In a clean temporary directory:
+
+```bash
+npm view @haaaiawd/loom version
+npx @haaaiawd/loom@2.0.1 --version
+```
+
+Then open the GitHub README and npm package page to confirm the SVG header, diagrams, links, and changelog
+render correctly. Record any unverified platform boundary instead of silently declaring it passed.

package/docs/UX_FLOW.md

@@ -0,0 +1,171 @@
+# LOOM 2 Complete UX and Loop Specification
+
+## Experience promise
+
+The human experiences one capable Agent who understands, asks, decides, builds, and recovers. They do not experience
+framework stages, role handoffs, status commands, or document maintenance. LOOM is the Agent's backstage continuity
+system.
+
+The system has three nested production loops and one external evaluation loop:
+
+1. Understanding loop — converge on the whole, its design-document graph, and the professional fields it needs.
+2. Readiness loop — let a fresh Keeper expose missing context and feed gaps back into understanding.
+3. Delivery loop — execute one restartable Task, test, repair or reflow, attach evidence, and continue.
+4. Evil Eval — compare the same Agent with no LOOM against the Agent using LOOM under equal conditions.
+
+## Surfaces and responsibilities
+
+| Surface | Human visible | Responsibility |
+|---|---:|---|
+| Natural conversation | Yes | Desired result, meaningful questions, delegated decisions, risk authority, progress and delivery |
+| Workspace and product artifacts | When useful | The real code, files, commands, reports, or operational result |
+| PROJECT.md, design docs, capability dossiers | Optional | Human-editable whole, detailed system decisions, and separate professional judgments |
+| `loom context` and structured state | No | Agent continuity after compression or a new session |
+| Work Map and active Task | Normally no | Broad coverage, current outcome, boundaries, relevant context, progress and evidence |
+| Keeper prompt and attempts | Only if a new window is required | One readiness handoff, with revision loops before execution |
+| Evil Eval harness | No during normal work | Controlled evidence about whether LOOM itself helps |
+
+## 0. Resume or receive a request
+
+The Agent runs `loom context` when LOOM exists. It then interprets the current request normally. Existing workspace
+inspection is conditional: inspect only when the request depends on the existing project, not because LOOM demands a scan.
+
+Human UX: nothing framework-specific appears.
+
+## 1. Form the emerging whole
+
+The Agent explains what it currently believes the finished result should be. This is conversational, not a mandatory
+template recital. It is most useful initially, after a consequential correction, and before material execution.
+
+The Agent identifies the current uncertainty frontier: decisions whose answers could materially change outcome,
+experience, boundaries, architecture, risk, cost, or proof of completion.
+
+## 2. Ask one dense, adaptive round
+
+The Agent asks all currently visible high-value questions in a coherent round. It may group by a natural decision cluster,
+but it does not follow a fixed domain list or question count.
+
+It does not ask facts reliably discoverable from tools, professional decisions it can responsibly make, speculative future
+details that do not affect the current whole, or framework questions whose only purpose is filling a schema.
+
+| Human response | Agent behavior |
+|---|---|
+| Direct answer | Record confirmed fact and update current truth |
+| Correction | Update PROJECT.md and affected design docs; append a superseding decision with impact |
+| `You decide` | Make the best reversible Agent decision, explain the important tradeoff, and record it |
+| `I don't know` | Research or decide when safe; ask again only if the human owns the missing preference or authority |
+| `Skip questions and continue` | Name the concrete quality or risk loss, record skipped uncertainty, then proceed |
+
+After every answer round, the Agent re-evaluates the whole. If material uncertainty remains, it loops to another adaptive
+round. If only reversible local uncertainty remains, it continues.
+
+## 3. Build project-specific capability
+
+The Agent maps which established professional fields could change questions, design, implementation, risk, or verification.
+It creates one dossier per recognizable field. UI/UX design, visual art direction, game design, psychology, biology, security,
+and other fields remain separate when their evidence or judgments differ. Task techniques such as triage, ranking, parsing,
+or caching are design mechanisms, not replacements for the capability map. Cross-field synthesis belongs in the affected
+design document.
+
+A useful dossier changes action. It contains its field boundary, specialist evidence, a falsifiable project stance,
+deliberate refusals, decision-changing questions, implementation consequences, failure modes, verification signals, sources,
+and tensions. Generic summaries and expert roleplay fail this step.
+
+Research can be quiet. A natural update is enough: `I need to strengthen the privacy, cognitive-load and information-architecture judgment; I will bring the consequences back into the design.`
+
+## 4. Shape the project corpus and Work Map
+
+PROJECT.md is the concise entry point and map. DECISIONS.md holds only consequential supersession. The actual product,
+experience, independent systems, contracts, verification, research, and operations decisions live under `.loom/design/`.
+A document is split when its subject has independent responsibilities, interfaces, failure modes, or proof. Document count
+therefore scales with project complexity: neither a fixed checklist nor an artificial one-file minimum.
+
+The Agent creates a broad initial Work Map early. It may be thousands of lines because it remains on disk. Only the active
+horizon receives detailed actions. Every Task states outcome, done conditions, boundaries, dependencies, relevant reads,
+affected paths, progress, next action, and evidence.
+
+## 5. Transition to readiness
+
+Before engineering or other material execution, the Agent tells the human what is about to happen and which important
+assumptions remain. Ordinary reversible work does not require another approval. Irreversible, high-risk, or materially costly
+action requires explicit authority.
+
+`loom project ready` verifies structural readiness and freezes a digest of the project map, design documents, capability dossiers, and Task
+definitions for the next Keeper attempt.
+
+## 6. Keeper readiness loop
+
+A fresh Agent thread runs `loom keeper prompt` and `loom context --keeper`. It receives no prior conversation. Each attempt has
+a unique `run_id`, attempt number, and prepared digest.
+
+Keeper tests whether it can explain the whole, navigate every necessary design system, locate distinct professional capabilities, select the correct first Task, find all context,
+name the first concrete action, and reproduce completion evidence.
+
+### Passed
+
+State becomes `build_ready`. Keeper leaves the normal workflow permanently; Task evidence now carries delivery quality.
+
+### Needs revision or blocked
+
+The result records summary, evidence, and exact gaps. State returns to `shaping`. The next `loom context` injects this feedback
+as the highest-priority uncertainty.
+
+The main Agent decides where the gap belongs, repairs everything it can, asks the human only for decisions they genuinely own,
+changes the relevant disk truth, runs `loom project ready` again, and opens a new Keeper run with a new run_id and digest.
+
+LOOM refuses an unchanged revision, a duplicate run_id, a result for the wrong digest, and a result written before ready.
+
+If the host has no subagents, the human sees one short request: `Please open a new window in this project, run loom keeper prompt, and follow it.`
+
+## 7. Delivery loop
+
+The Agent selects `loom task next`, starts it, and runs `loom context`. Context contains the current whole, current Task, and the
+exact design, capability, source, contract, and fixture files in `reads`—not the full Work Map or history.
+
+- A local failure keeps the Task active. Update progress and evidence, repair, and test again.
+- A missing permission, dependency, or upper-level contradiction uses `task block` with a reason and recovery conditions.
+- After the condition is repaired, use `task reopen`, then start it again. A prior `done` may also be
+  reopened with a concrete reason when its evidence is disproven.
+- `task done` requires a check quoting every exact `done_when` criterion and mapping it to concrete evidence.
+- Generic update cannot modify status, and imported Tasks must begin open.
+
+When a Task is done, the Agent chooses the next dependency-ready Task. When every Task is done, project status becomes complete
+and the Agent delivers the real result, evidence, remaining tradeoffs, and any user-owned follow-up.
+
+## 8. Mid-build change
+
+New user information is first evaluated for impact. A local reversible implementation detail updates the active Task. A change
+to the desired whole updates PROJECT.md and affected design documents, records a superseding decision, revises affected Task definitions, and blocks or reopens
+the active Task as needed. The one-time Keeper does not return after initial build-readiness; implementation evidence and explicit
+human authority govern later changes.
+
+## Recovery matrix
+
+| Failure | Recovery |
+|---|---|
+| Context compressed | `loom context` compiles current truth and active horizon |
+| User contradicts earlier answer | Update PROJECT.md and affected design docs; append superseding decision; revise affected Tasks |
+| Important answer unavailable | Agent decides reversibly or records open or skipped uncertainty |
+| Capability is generic or hybrid | Split into recognizable fields; move synthesis to design docs; add stance, consequences and proof |
+| Keeper cannot start | Feedback returns to shaping; change disk truth; new digest and fresh run |
+| Project changes after ready | Old Keeper result rejected as stale |
+| Same Keeper identity reused | Duplicate run_id rejected |
+| Local implementation test fails | Keep Task active, record observation, repair and repeat |
+| Dependency or authority missing | Block Task with recovery conditions, then reopen |
+| Attempt to mark done without evidence | CLI rejects it |
+| Evidence disproves an earlier done state | Reopen with a reason, then repair, re-verify, or block |
+| Host cannot spawn Keeper | Ask the human to open a new window with one short prompt |
+
+## Flow diagrams
+
+- [Production loops](loom-production-loop.drawio) — editable Draw.io source; [SVG](loom-production-loop.svg).
+- [Evil Eval](loom-eval-loop.drawio) — editable Draw.io source; [SVG](loom-eval-loop.svg).
+
+## Primary evaluation question
+
+The causal baseline is a normal capable Agent with no LOOM—not LOOM v1. Both conditions receive the same raw brief, model,
+tools, workspace, user oracle, budget, and reset schedule. LOOM v1 may be added as a secondary regression condition, but it does
+not answer whether the framework itself creates value over no framework.
+
+The anonymization harness must preserve runnable relative layout, record a file/digest manifest, and rerun each condition's
+declared tests and smoke command before judging. Packet-construction failures are eval failures, never evidence against a run.

package/docs/brand/loom-mark.svg

@@ -0,0 +1,18 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="256" height="256" viewBox="0 0 256 256" role="img" aria-labelledby="title desc">
+  <title id="title">LOOM mark</title>
+  <desc id="desc">A continuous thread passes through four frames, resumes after a gap, and loops forward.</desc>
+  <rect width="256" height="256" rx="52" fill="#F5F2EA"/>
+  <g fill="none" stroke="#17212B" stroke-width="6">
+    <rect x="38" y="61" width="42" height="88" rx="9"/>
+    <rect x="88" y="61" width="42" height="88" rx="9"/>
+    <rect x="138" y="61" width="42" height="88" rx="9"/>
+    <rect x="188" y="61" width="30" height="88" rx="9"/>
+  </g>
+  <path d="M24 105H50C61 105 61 82 72 82S83 128 94 128s11-46 22-46 11 46 22 46 11-46 22-46 11 46 22 46"
+        fill="none" stroke="#4169E1" stroke-width="10" stroke-linecap="round" stroke-linejoin="round"/>
+  <circle cx="198" cy="128" r="5" fill="#4169E1"/>
+  <circle cx="214" cy="128" r="5" fill="#4169E1" opacity=".55"/>
+  <path d="M226 128c14 0 17 12 17 23 0 23-18 42-42 42H79"
+        fill="none" stroke="#4169E1" stroke-width="10" stroke-linecap="round"/>
+  <path d="M92 180 75 193l17 13" fill="none" stroke="#4169E1" stroke-width="10" stroke-linecap="round" stroke-linejoin="round"/>
+</svg>

package/docs/brand/loom-readme-header.svg

@@ -0,0 +1,34 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="1280" height="360" viewBox="0 0 1280 360" role="img" aria-labelledby="title desc">
+  <title id="title">LOOM — Keep the whole. Continue the work.</title>
+  <desc id="desc">A flat minimal header showing a continuous thread moving through project understanding, expertise, verification, and delivery.</desc>
+  <rect width="1280" height="360" rx="28" fill="#F5F2EA"/>
+  <path d="M0 304H1280" stroke="#D8D3C8"/>
+  <g transform="translate(84 70)">
+    <g fill="none" stroke="#17212B" stroke-width="4">
+      <rect x="0" y="16" width="38" height="76" rx="8"/>
+      <rect x="47" y="16" width="38" height="76" rx="8"/>
+      <rect x="94" y="16" width="38" height="76" rx="8"/>
+      <rect x="141" y="16" width="30" height="76" rx="8"/>
+    </g>
+    <path d="M-14 54H10c10 0 10-20 20-20s10 40 20 40 10-40 20-40 10 40 20 40 10-40 20-40 10 40 20 40"
+          fill="none" stroke="#4169E1" stroke-width="8" stroke-linecap="round" stroke-linejoin="round"/>
+    <circle cx="145" cy="74" r="4" fill="#4169E1"/><circle cx="158" cy="74" r="4" fill="#4169E1" opacity=".5"/>
+    <path d="M171 74c20 0 27 13 27 28 0 23-18 42-42 42H59" fill="none" stroke="#4169E1" stroke-width="8" stroke-linecap="round"/>
+    <path d="M72 132 56 144l16 12" fill="none" stroke="#4169E1" stroke-width="8" stroke-linecap="round" stroke-linejoin="round"/>
+  </g>
+  <g font-family="Inter,Segoe UI,Arial,sans-serif" fill="#17212B">
+    <text x="350" y="142" font-size="94" font-weight="750" letter-spacing="12">LOOM</text>
+    <text x="355" y="190" font-size="24" font-weight="560">Keep the whole. Continue the work.</text>
+    <text x="355" y="228" font-size="17" fill="#58636D">Invisible project understanding and continuity for AI Agents.</text>
+  </g>
+  <g transform="translate(82 311)" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="13" font-weight="650" letter-spacing="1.1" fill="#17212B">
+    <circle cx="4" cy="-1" r="4" fill="#4169E1"/><text x="18" y="4">UNDERSTAND</text>
+    <path d="M126-1h42" stroke="#9AD8C2" stroke-width="3"/>
+    <circle cx="181" cy="-1" r="4" fill="#9AD8C2"/><text x="195" y="4">REMEMBER</text>
+    <path d="M306-1h42" stroke="#E88773" stroke-width="3"/>
+    <circle cx="361" cy="-1" r="4" fill="#E88773"/><text x="375" y="4">VERIFY</text>
+    <path d="M452-1h42" stroke="#4169E1" stroke-width="3"/>
+    <circle cx="507" cy="-1" r="4" fill="#4169E1"/><text x="521" y="4">CONTINUE</text>
+  </g>
+  <text x="1198" y="322" text-anchor="end" font-family="ui-monospace,SFMono-Regular,Consolas,monospace" font-size="13" fill="#58636D">npm i -g @haaaiawd/loom</text>
+</svg>

package/docs/brand/loom-readme-header.zh-CN.svg

@@ -0,0 +1,29 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="1280" height="360" viewBox="0 0 1280 360" role="img" aria-labelledby="title desc">
+  <title id="title">LOOM — 记住全貌，继续工作。</title>
+  <desc id="desc">一根连续的线穿过项目理解、专业能力、独立验证和交付，并在中断后继续向前。</desc>
+  <rect width="1280" height="360" rx="28" fill="#F5F2EA"/>
+  <path d="M0 304H1280" stroke="#D8D3C8"/>
+  <g transform="translate(84 70)">
+    <g fill="none" stroke="#17212B" stroke-width="4">
+      <rect x="0" y="16" width="38" height="76" rx="8"/><rect x="47" y="16" width="38" height="76" rx="8"/><rect x="94" y="16" width="38" height="76" rx="8"/><rect x="141" y="16" width="30" height="76" rx="8"/>
+    </g>
+    <path d="M-14 54H10c10 0 10-20 20-20s10 40 20 40 10-40 20-40 10 40 20 40 10-40 20-40 10 40 20 40" fill="none" stroke="#4169E1" stroke-width="8" stroke-linecap="round" stroke-linejoin="round"/>
+    <circle cx="145" cy="74" r="4" fill="#4169E1"/><circle cx="158" cy="74" r="4" fill="#4169E1" opacity=".5"/>
+    <path d="M171 74c20 0 27 13 27 28 0 23-18 42-42 42H59" fill="none" stroke="#4169E1" stroke-width="8" stroke-linecap="round"/>
+    <path d="M72 132 56 144l16 12" fill="none" stroke="#4169E1" stroke-width="8" stroke-linecap="round" stroke-linejoin="round"/>
+  </g>
+  <g font-family="Inter,Segoe UI,Arial,sans-serif" fill="#17212B">
+    <text x="350" y="142" font-size="94" font-weight="750" letter-spacing="12">LOOM</text>
+  </g>
+  <g font-family="Noto Sans SC,Microsoft YaHei,PingFang SC,Segoe UI,Arial,sans-serif" fill="#17212B">
+    <text x="355" y="190" font-size="24" font-weight="650">记住全貌，继续工作。</text>
+    <text x="355" y="228" font-size="17" fill="#58636D">为 AI Agent 提供无形的项目理解与连续性基础设施。</text>
+  </g>
+  <g transform="translate(82 311)" font-family="Noto Sans SC,Microsoft YaHei,PingFang SC,Segoe UI,Arial,sans-serif" font-size="13" font-weight="700" letter-spacing="1.6" fill="#17212B">
+    <circle cx="4" cy="-1" r="4" fill="#4169E1"/><text x="18" y="4">理解</text><path d="M70-1h42" stroke="#9AD8C2" stroke-width="3"/>
+    <circle cx="125" cy="-1" r="4" fill="#9AD8C2"/><text x="139" y="4">记住</text><path d="M191-1h42" stroke="#E88773" stroke-width="3"/>
+    <circle cx="246" cy="-1" r="4" fill="#E88773"/><text x="260" y="4">验证</text><path d="M312-1h42" stroke="#4169E1" stroke-width="3"/>
+    <circle cx="367" cy="-1" r="4" fill="#4169E1"/><text x="381" y="4">继续</text>
+  </g>
+  <text x="1198" y="322" text-anchor="end" font-family="ui-monospace,SFMono-Regular,Consolas,monospace" font-size="13" fill="#58636D">npm i -g @haaaiawd/loom</text>
+</svg>