diff --git a/.dockerignore b/.dockerignore
index feb3681..79817f5 100644
--- a/.dockerignore
+++ b/.dockerignore
@@ -21,4 +21,3 @@ dist
 *.sqlite3
 *.db
 tests
-docs
diff --git a/README.md b/README.md
index b07f1d6..9ee177e 100644
--- a/README.md
+++ b/README.md
@@ -5,6 +5,8 @@ same independently evolvable Agent loop; its scheduler, context policy, memory,
 tools, evidence rules, and child Agents are owned by this repository.
 
 The production instance is available at <https://agent.k1412.top>.
+Architecture, Agent internals, and the experiment board are published at
+<https://agent.k1412.top/doc/>.
 
 ## Architecture
 
@@ -120,9 +122,14 @@ Open WebUI and re-signed for the Workspace Gateway; no internal key is exposed.
 
 ## Documentation
 
+- [Documentation index](docs/README.md)
 - [Architecture and Agent loop](docs/architecture.md)
+- [Agent loop implementation](docs/agent-loop.md)
+- [Experiment system](docs/experiments.md)
+- [Project history and decisions](docs/project-history.md)
 - [Open WebUI integration](docs/openwebui-integration.md)
 - [Infrastructure map](docs/infrastructure.md)
+- [Development and verification](docs/development.md)
 - [Operations runbook](docs/operations.md)
 - [Security model](docs/security.md)
 
diff --git a/docker/web.Dockerfile b/docker/web.Dockerfile
index 9b09cc0..bc35221 100644
--- a/docker/web.Dockerfile
+++ b/docker/web.Dockerfile
@@ -80,6 +80,7 @@ WORKDIR /app/backend
 COPY --from=web-build /src/backend /app/backend
 COPY --from=web-build /src/build /app/build
 COPY --from=web-build /src/CHANGELOG.md /app/CHANGELOG.md
+COPY docs/site /app/build/doc
 
 COPY --from=web-build /src/LICENSE /app/OPEN_WEBUI_LICENSE
 COPY THIRD_PARTY_NOTICES.md /app/THIRD_PARTY_NOTICES.md
diff --git a/docs/README.md b/docs/README.md
new file mode 100644
index 0000000..57c6cb3
--- /dev/null
+++ b/docs/README.md
@@ -0,0 +1,55 @@
+# K1412 Agent documentation
+
+This directory is the canonical technical record for K1412 Agent. The public
+documentation portal at <https://agent.k1412.top/doc/> is a curated rendering
+of the same design. When behavior, infrastructure, or an experiment changes,
+update the relevant Markdown document and the portal snapshot in the same
+commit.
+
+## Start here
+
+| Document | Audience | What it answers |
+| --- | --- | --- |
+| [Architecture](architecture.md) | Everyone | What runs where, and why are the boundaries drawn this way? |
+| [Agent loop](agent-loop.md) | Agent researchers and backend engineers | How do context, tools, scheduling, evidence, memory, and child Agents work? |
+| [Experiment system](experiments.md) | Agent researchers | How do we change the loop without losing comparability or production safety? |
+| [Project history](project-history.md) | Maintainers | Which product and architecture decisions have already been made? |
+| [Open WebUI integration](openwebui-integration.md) | Frontend and platform engineers | What belongs to Open WebUI, and what remains K1412-owned? |
+| [Security model](security.md) | Security and platform engineers | How are users, credentials, workspaces, and Docker separated? |
+| [Infrastructure map](infrastructure.md) | Operators | Which services are shared infrastructure and which are Agent core? |
+| [Development and verification](development.md) | Contributors | How do I run, test, and safely change the system? |
+| [Operations runbook](operations.md) | Operators | How is production built, deployed, verified, backed up, and migrated? |
+
+## Current product contract
+
+- There is one user-facing mode: the K1412 Agent loop. The earlier Chat/Work
+  split was removed deliberately.
+- Open WebUI owns accounts, sessions, approval, conversation storage, and the
+  chat shell. K1412 owns Agent behavior.
+- Four server-defined model choices are exposed: Luna, Terra, Sol, and
+  DeepSeek V4 Pro. Model identity and thinking capability are displayed
+  separately.
+- Every Open WebUI user receives an isolated Docker container, network, and
+  persistent volume on the dedicated physical execution host.
+- Generated files can be browsed and downloaded through the authenticated Web
+  UI. Internal dependency directories are hidden.
+- Provider credentials, internal prompts, Docker access, SSH configuration,
+  and tool-service credentials are never browser-configurable.
+
+## What is experimental
+
+The stable platform boundary is authentication, user/workspace isolation,
+durable storage, and the public OpenAI-compatible Runtime API. The intended
+experimental surface is:
+
+- context selection and compaction;
+- memory retrieval and lifecycle;
+- tool descriptions, normalization, and routing;
+- parallel scheduling and mutation serialization;
+- child-Agent delegation policy;
+- evidence and completion gates;
+- recovery prompts and retry policy;
+- model routing and per-tier budgets.
+
+Every experiment should be versioned in run events and evaluated against a
+fixed task set before production rollout. See [experiments.md](experiments.md).
diff --git a/docs/agent-loop.md b/docs/agent-loop.md
new file mode 100644
index 0000000..ecb2757
--- /dev/null
+++ b/docs/agent-loop.md
@@ -0,0 +1,223 @@
+# Agent loop implementation
+
+## Purpose
+
+The K1412 loop turns a model completion API into an accountable coding Agent.
+Its primary rule is simple: a textual claim is not proof that work happened.
+Files, commands, reports, and tests must be backed by successful tool events
+from the current run.
+
+The current event metadata identifies the implementation as:
+
+- strategy: `agent-loop-v3`;
+- scheduler: `safe-parallel-v1`;
+- context policy: `recent-visible-v1`.
+
+These identifiers are part of the experiment contract, not marketing version
+numbers. Change them when behavior changes in a way that can affect evaluation.
+
+## Run state machine
+
+```mermaid
+stateDiagram-v2
+    [*] --> BuildContext
+    BuildContext --> RequestModel
+    RequestModel --> ValidateCalls: tool calls
+    RequestModel --> CheckCompletion: no tool calls
+    ValidateCalls --> Schedule
+    Schedule --> Execute
+    Execute --> RecordEvidence
+    RecordEvidence --> RequestModel
+    CheckCompletion --> RequestModel: evidence missing and budget remains
+    CheckCompletion --> Completed: evidence sufficient
+    CheckCompletion --> Unverified: evidence missing and retry budget exhausted
+    Completed --> [*]
+    Unverified --> [*]
+```
+
+Every top-level run receives a unique `run_id`. All events include the user,
+chat, monotonic sequence, timestamp, event type, and a sanitized payload.
+
+## Context policy
+
+`ContextPolicy.prepare`:
+
+1. accepts only system, developer, user, and assistant messages;
+2. strips rendered `<details type="tool_calls">` blocks from old assistant
+   messages so UI markup is not fed back as model context;
+3. prepends the K1412 system contract;
+4. appends up to eight durable user memories as context, explicitly not as
+   higher-priority instructions;
+5. walks visible messages newest-first until the model's character budget is
+   reached;
+6. records how many old messages were dropped.
+
+The policy is intentionally simple and inspectable. It does not yet summarize
+old conversation branches, retrieve semantic workspace context, or estimate
+provider-specific tokenization. Those are future experiment candidates.
+
+## Model contract
+
+`ModelSpec` is the server-side source of truth for:
+
+- public and provider model IDs;
+- provider selection;
+- thinking capability and display label;
+- reasoning effort when the provider supports it;
+- maximum output tokens;
+- maximum loop iterations;
+- context character budget.
+
+Luna, Terra, and Sol are separate local models with boolean thinking support;
+they are not three effort settings for one model. DeepSeek V4 Pro uses the
+DeepSeek provider with thinking enabled and `reasoning_effort=max`.
+
+Runtime preserves provider `reasoning_content` across tool turns when required
+for protocol correctness, but does not publish hidden reasoning as user-facing
+content.
+
+## Tool catalog
+
+Workspace tools:
+
+- status, list, read, search, write, and patch files;
+- execute foreground commands;
+- inspect Git status and diff;
+- start, poll, and cancel background processes.
+
+Runtime state tools:
+
+- update a per-chat plan;
+- remember, recall, and forget durable user memory.
+
+Delegation tool:
+
+- start one bounded child Agent with a role, task, and explicit write policy.
+
+Tool schemas use `additionalProperties: false` so malformed model arguments
+fail early. Arguments are normalized before policy checks. Content and patch
+bodies are omitted from public run-event payloads.
+
+## Intent-based tool selection
+
+The root loop does not always send every tool. Lightweight request classifiers
+detect whether the task concerns artifacts, execution, source files, reports,
+comparisons, processes, Git, memory, or delegation. The selected catalog keeps
+the model's tool decision smaller while retaining the core workspace tools.
+
+This is heuristic routing, not authorization. Gateway remains the enforcement
+boundary.
+
+## Scheduler
+
+Each model response can request at most eight tool calls. Calls are parsed in
+their original order and divided into consecutive groups:
+
+- tools marked `parallel_safe` execute concurrently;
+- mutations and other non-parallel tools execute serially;
+- read-only child Agents may run in parallel;
+- a child with write access is serialized;
+- child Agents cannot delegate again.
+
+Gateway also serializes workspace mutations per user. This second lock is
+important because multiple Runtime requests or browser actions can address the
+same workspace.
+
+The scheduler preserves result order even when a parallel group completes out
+of order.
+
+## Defensive normalization and retry guards
+
+The loop repairs a small set of common model formatting mistakes, then applies
+policy:
+
+- reject bare interactive commands such as `python3`, `bash`, or `node`;
+- reject attempts to run documentation/data files as executable source;
+- reject syntactically invalid complete Python files before writing;
+- decode repeated escaped source-layout newlines produced by weak models;
+- skip identical successful writes;
+- block an identical failed write until content changes;
+- block an unchanged failed command until a mutation or materially different
+  diagnostic occurs;
+- deduplicate repeated commands in one batch;
+- cap generation, iteration, and tool-batch sizes.
+
+At the execution layer, Bash runs with `pipefail` and returns the true exit
+code. Foreground tools default to a 900-second ceiling; background processes
+have explicit start/poll/cancel lifecycle.
+
+## Evidence-gated completion
+
+The loop derives required evidence from the user request.
+
+| Request shape | Minimum evidence |
+| --- | --- |
+| Concrete artifact | A successful file mutation and a later successful verification |
+| Execute/test/analyze | At least one successful execution or inspection |
+| Source-code request | A separate executable source file |
+| Report request | A separate report written after execution |
+| Benchmark/comparison report | Exact numeric measurements copied from successful execution output |
+
+Verification includes a later file read, Git diff/status, command execution, or
+background-process poll. A failed command remains unresolved until a later
+execution succeeds.
+
+If a model tries to finish too early, Runtime emits `completion.rejected`,
+returns a focused recovery instruction to the model, and continues. After
+repeated rejected checkpoints or iteration exhaustion, Runtime returns an
+explicit incomplete result instead of laundering an unverified claim into a
+success.
+
+## Delegation
+
+A root Agent can delegate a bounded independent task. The child receives:
+
+- a role and exact task;
+- a reduced iteration budget of at most eight;
+- no delegation tool;
+- read-only tools unless write access was explicitly requested.
+
+Child events share the root run stream with an increased `depth`. The current
+implementation is recursive execution inside one Runtime process, not a
+distributed queue or a persistent autonomous worker.
+
+## Memory and plans
+
+Durable memories are scoped by user ID. Recall is currently recency-first with
+optional case-insensitive substring filtering. Plans are scoped by user and
+chat and allow at most one `in_progress` item.
+
+Memory is useful but intentionally conservative: the system does not
+automatically extract facts from every conversation and does not yet perform
+embedding retrieval, confidence scoring, expiry, or conflict resolution.
+
+## Run event model
+
+Important event types include:
+
+- `run.created`, `context.built`, `run.completed`, `run.failed`,
+  `run.cancelled`;
+- `model.requested`, `model.responded`;
+- `tool.started`, `tool.completed`, `tool.batch_limited`;
+- `completion.rejected`, `completion.unverified`;
+- `agent.spawned`, `agent.completed`.
+
+The event stream powers UI detail blocks today and is the basis for future
+replay, evaluation, cost analysis, and A/B assignment. Events store public
+arguments and concise summaries, not credentials, full write bodies, or hidden
+reasoning.
+
+## Known limitations
+
+- Context compaction drops old messages instead of summarizing them.
+- Memory retrieval is lexical rather than semantic.
+- Tool intent classifiers are regular-expression based.
+- The scheduler parallelizes only consecutive safe calls and has no resource
+  cost model.
+- Child Agents are not durable across Runtime restarts.
+- Experiment assignment and aggregate dashboards are not yet implemented.
+- Provider token accounting is retained when returned but is not yet converted
+  into a unified cost model.
+
+These are deliberate experiment targets, documented in
+[experiments.md](experiments.md).
diff --git a/docs/architecture.md b/docs/architecture.md
index 587e876..0cc284c 100644
--- a/docs/architecture.md
+++ b/docs/architecture.md
@@ -1,74 +1,185 @@
 # Architecture
 
-## Single Agent path
+## Design objective
 
-Open WebUI owns authenticated users, conversation history, and rendering.
-Every normal model request is delegated to the K1412 Runtime. There is no
-second Chat loop and no per-conversation mode state.
+K1412 Agent is a multi-user web coding Agent whose loop can be changed
+independently of its account system and user interface. The architecture keeps
+the high-cost experimental surface small: researchers should be able to change
+context, memory, scheduling, tools, delegation, or completion policy without
+forking authentication, chat history, Docker lifecycle, or the whole frontend.
 
-## Agent loop
+The system deliberately has one Agent path. The earlier idea of a lightweight
+Chat loop beside a custom Work loop was removed because it duplicated product
+behavior, confused model selection, and increased the amount of frontend and
+backend code that had to remain compatible.
 
-The first strategy is intentionally modular:
+## System context
 
-- `ModelProvider` owns provider transport.
-- `ContextPolicy` owns visible-message cleanup and compaction.
-- `ToolRegistry` owns tool schemas and dispatch.
-- `AgentLoop` owns iteration, safe parallel scheduling, and delegation.
-- `RuntimeStore` owns events, plans, and durable Agent memory.
-- `ExecutionProvider` owns local or SSH Docker execution.
+```mermaid
+flowchart LR
+    U["Browser user"] --> P["DNS, TLS and Nginx Proxy Manager"]
+    P --> W["Open WebUI<br/>auth, RBAC, history, UI"]
+    W --> R["Agent Runtime<br/>loop, context, memory, model routing"]
+    R --> M["Model providers<br/>K1412 API or DeepSeek"]
+    R --> G["Workspace Gateway<br/>identity and execution policy"]
+    G -->|Tailscale + SSH Docker| X["Per-user workspace container<br/>home-node-itx"]
+    W --> DB["PostgreSQL<br/>users and chats"]
+    R --> DB
+    W --> Q["Redis<br/>coordination"]
+```
 
-Every run records its model ID, strategy version, scheduler version, context
-policy, model/tool events, failures, and completion. This event stream is the
-foundation for replay, evaluation, and future experiment assignment.
+Only Web is publicly reachable. Runtime, Gateway, PostgreSQL, and Redis live on
+private Compose networks. Workspace containers run on a separate physical
+Docker host, receive no application secrets, and expose no host ports.
 
-Luna, Terra, and Sol are three independent Ollama models. Each advertises
-boolean thinking support, but none advertises adjustable reasoning effort.
-DeepSeek V4 Pro is a fourth model configured with thinking enabled and maximum
-reasoning effort. Provider selection and credentials remain server-side.
-Thinking state is preserved across tool turns when the provider requires the
-assistant's `reasoning_content` to be returned with following tool results.
-The Agent never publishes hidden reasoning as its own user-facing output.
+## Responsibility boundaries
 
-Completion is evidence-gated. Requests for scripts, reports, code, or
-other concrete artifacts are not accepted as complete until a file mutation
-has succeeded and a later read, diff, or command has verified the latest
-mutation. Bare interactive shell commands are rejected. If the iteration
-budget is exhausted without evidence, Runtime returns an explicit incomplete
-checkpoint instead of repeating an unverified model claim.
+| Layer | Owns | Must not own |
+| --- | --- | --- |
+| Open WebUI | Registration, login, sessions, admin approval, RBAC, chat persistence, rendering | Agent scheduling, provider secrets, Docker access |
+| Agent Runtime | Model catalog, context policy, Agent loop, tools, scheduling, delegation, memory, plans, run events, evidence gates | Browser sessions, Docker socket |
+| Workspace Gateway | Signed identity enforcement, workspace path policy, per-user locks, Docker lifecycle, file delivery | Model calls, public authentication UI |
+| Workspace container | User code, dependencies, generated files, command execution | Other users' data, service credentials, Docker socket |
+| PostgreSQL | Open WebUI durable state plus Runtime events, plans, and memories | Execution |
+| Shared infrastructure | TLS, registry, source hosting, private routing, model serving | Agent behavior |
 
-Read-only tools and read-only child Agents may run concurrently. Workspace
-mutations are serialized. A child Agent cannot delegate again, and read-only
-children receive only read-only tools.
+This separation lets the Web UI be upgraded on its own schedule while the
+Agent loop can iterate frequently.
 
-## Execution providers
+## Request lifecycle
 
-`local-docker` connects the Workspace Gateway to the local Docker daemon.
-`ssh-docker` connects the same Docker SDK operations to a remote physical
-machine through SSH. Both create the same workspace image, persistent per-user
-volume, and dedicated per-user bridge network, so moving execution off the web
-host changes configuration rather than Agent behavior.
+### Agent request
 
-For SSH mode, layer `compose.ssh.yaml` over the development Compose file, or
-`deploy/docker-compose.ssh.yml` over the two production Compose files. The
-override removes the local Docker socket and mounts only the selected SSH
-configuration directory read-only.
+```mermaid
+sequenceDiagram
+    participant B as Browser
+    participant W as Open WebUI
+    participant R as Runtime
+    participant M as Model provider
+    participant G as Gateway
+    participant X as User workspace
 
-Only Open WebUI publishes a host port. Runtime, Gateway, Postgres, and Redis
-remain unpublishing services. Runtime and Gateway also join an egress-only
-bridge so the model API and a future SSH Docker host are reachable without
-exposing either service on the host.
+    B->>W: Authenticated chat request
+    W->>R: OpenAI-compatible request + service key + signed user identity
+    R->>R: Verify identity, build context, record run.created
+    loop Until evidence-backed completion or budget exhausted
+        R->>M: Recent context + tools + provider policy
+        M-->>R: Assistant content and/or tool calls
+        R->>R: Normalize, validate, limit, and schedule calls
+        R->>G: Tool request + service key + freshly signed identity
+        G->>G: Verify identity and bind user workspace
+        G->>X: Execute with resource and path constraints
+        X-->>G: Exit code, output, or file result
+        G-->>R: Structured tool result
+        R->>R: Persist events and evaluate completion evidence
+    end
+    R-->>W: SSE answer and completed tool detail blocks
+    W-->>B: Rendered Agent response
+```
 
-## Workspace file path
+The identity sent by Open WebUI is verified once when Runtime accepts the
+request. Runtime then signs the already verified identity again for every
+Gateway call. This prevents a long Agent run from reusing an identity token
+that expired while the model or a tool was working.
+
+### Workspace file request
 
 ```text
 browser with Open WebUI session
   -> /api/v1/k1412/workspace/*
-  -> Open WebUI backend verifies the user
-  -> backend mints a short-lived signed identity JWT
-  -> Workspace Gateway verifies service key + user JWT
-  -> provider selects only that user's hashed container and volume
+  -> Open WebUI verifies the logged-in user
+  -> Web signs a short-lived user identity
+  -> Gateway verifies service key + signed identity
+  -> Gateway selects only the hashed container and volume for that user
+  -> browse, download, or streamed archive response
 ```
 
-The file API exposes read-only browse, file download, and streamed directory
-archive operations. Paths pass through the same `/workspace` normalization as
-Agent tools. The browser never talks to Gateway or Docker directly.
+The browser never receives a Gateway service key and never connects to Docker.
+
+## Runtime internals
+
+Runtime is an OpenAI-compatible provider from Open WebUI's point of view, but
+normal chat completions are implemented by the K1412 loop:
+
+- `ModelProvider` translates the internal model spec to a provider request and
+  normalizes streamed completion responses.
+- `ContextPolicy` removes rendered tool-detail markup, prepends the system
+  contract and durable memories, and keeps the newest visible messages within
+  a per-model character budget.
+- `ToolRegistry` declares tool schemas and routes workspace tools to Gateway or
+  state tools to `RuntimeStore`.
+- `AgentLoop` owns iteration, tool normalization, validation, scheduling,
+  recovery, delegation, and evidence-gated completion.
+- `RuntimeStore` persists run events, per-chat plans, and user memories.
+
+More detail is in [agent-loop.md](agent-loop.md).
+
+## Workspace architecture
+
+`local-docker` and `ssh-docker` implement the same `ExecutionProvider`
+contract. Production uses `ssh-docker`: Gateway talks to Docker on
+`home-node-itx` through a dedicated SSH configuration mounted read-only.
+
+Each immutable Open WebUI user ID maps to a SHA-256-derived workspace ID and
+therefore to exactly one:
+
+- container named `k1412-ws-<workspace-id>`;
+- named volume `k1412-ws-data-<workspace-id>`;
+- bridge network `k1412-ws-net-<workspace-id>`.
+
+Containers run as UID/GID 1000 with a read-only root filesystem, all Linux
+capabilities dropped, `no-new-privileges`, PID/CPU/memory limits, no Docker
+socket, and no published ports. `/workspace` is the only persistent writable
+filesystem. `/tmp` is writable but mounted `noexec`.
+
+Python environments live at `/workspace/.venv`. User-level home and package
+caches live below `/workspace/.agent`. The image puts the virtual environment
+and user binary directories first on `PATH`. Commands run under Bash with
+`pipefail`, so a failed install cannot be hidden by a successful `tail` or
+similar pipeline stage.
+
+When `WORKSPACE_IMAGE` changes to a new immutable tag, Gateway replaces a stale
+container on its next access but reattaches the existing named volume. Image
+upgrades therefore change the execution environment without deleting user
+files.
+
+## Networks and deployment
+
+Production runs as one Unraid Compose Manager project:
+
+- `public`: Web ingress;
+- `internal`: private service-to-service traffic;
+- `egress`: Runtime provider access and Gateway SSH access.
+
+Only Web publishes NAS port `12004`. Nginx Proxy Manager on the VPS terminates
+TLS for `agent.k1412.top` and forwards over Tailscale. Images are built for
+`linux/amd64`, pushed to `docker.k1412.top/wuyang/*` with immutable
+timestamp-and-commit tags, and deployed by updating only the relevant service.
+
+The documentation portal is packaged inside the Web image at `/doc/`. It does
+not add a public service, port, database, or proxy rule.
+
+## Stable and experimental surfaces
+
+Stable platform contracts:
+
+- authenticated Web-to-Runtime request;
+- signed Runtime/Web-to-Gateway identity;
+- `ExecutionProvider` workspace semantics;
+- per-user volume isolation;
+- run-event persistence;
+- public model IDs;
+- workspace file API.
+
+Expected experiment surfaces:
+
+- prompt and context policy;
+- memory selection;
+- tool catalog and intent routing;
+- scheduler and parallelism;
+- delegation;
+- recovery and evidence rules;
+- model budgets and routing.
+
+Version experiment-sensitive behavior in `run.created` so results remain
+comparable after the implementation changes.
diff --git a/docs/development.md b/docs/development.md
new file mode 100644
index 0000000..870745f
--- /dev/null
+++ b/docs/development.md
@@ -0,0 +1,129 @@
+# Development and verification
+
+## Repository layout
+
+```text
+agent_platform/
+  runtime/        Agent API, loop, context, model transport, and tools
+  gateway/        Authenticated workspace and file service
+  auth.py         Internal service and signed identity verification
+  models.py       Public model catalog and server-side budgets
+  store.py        Run events, memories, and plans
+docker/
+  web/            Open WebUI components and reproducible patch set
+  *.Dockerfile    Web, Runtime, Gateway, and Workspace images
+docs/
+  site/           Static source for /doc/
+deploy/           Production Compose files and SSH override
+e2e/              Deterministic full-stack verifier and fake provider
+scripts/          Verification, evaluation, audit, and secret helpers
+tests/            Unit and real Docker integration tests
+```
+
+## Local environment
+
+```bash
+python3 -m venv .venv
+.venv/bin/python -m pip install -e '.[dev]'
+cp .env.example .env
+./scripts/init-secrets.sh
+```
+
+Keep real provider credentials in a protected local environment or deployment
+file. Never add them to Git, Docker build arguments, frontend code, test
+fixtures, or logs.
+
+Build the user workspace, then start the stack:
+
+```bash
+docker compose --profile build-only build workspace-image
+docker compose up --build
+```
+
+Open <http://localhost:3000>. New registrations have the `pending` role until
+approved by the bootstrap administrator.
+
+## Fast feedback
+
+```bash
+.venv/bin/ruff check agent_platform tests e2e
+.venv/bin/ruff format --check agent_platform tests e2e
+.venv/bin/pytest
+```
+
+Unit tests are deterministic and do not require a model provider.
+
+## Real Docker integration
+
+```bash
+docker build -f docker/workspace.Dockerfile \
+  -t k1412-agent-workspace:test .
+RUN_DOCKER_INTEGRATION=1 \
+  .venv/bin/pytest tests/test_docker_workspace.py
+```
+
+The test creates unique containers, networks, and volumes and removes only
+those resources in cleanup.
+
+## Full-stack E2E
+
+```bash
+./scripts/verify-e2e.sh
+```
+
+The script builds a disposable six-service stack, uses a deterministic model
+stub, performs authentication and isolation checks, and removes the stack and
+test volumes on exit.
+
+## Live Agent evaluation
+
+```bash
+set -a
+source /path/to/protected/provider.env
+set +a
+.venv/bin/python scripts/eval-live-work.py --model deepseek-v4-pro
+```
+
+Use `--keep-workspace` only when inspecting a failed case; remove that uniquely
+named evaluation workspace afterward.
+
+## Image audit
+
+```bash
+./scripts/audit-images.sh
+```
+
+The audit requires consistent Python environments and no fixable
+High/Critical vulnerabilities in the finished images. Web also receives a
+Python dependency audit.
+
+## Documentation portal
+
+`docs/site/` is dependency-free static HTML, CSS, JavaScript, and JSON. It is
+copied into `/app/build/doc` by `docker/web.Dockerfile` after Open WebUI's
+frontend build completes.
+
+Validate it locally with:
+
+```bash
+python3 -m http.server 4173 --directory docs/site
+```
+
+The production path is `/doc/`; all internal assets therefore use relative
+URLs. Keep the Markdown documents and portal content aligned in the same
+commit. Add experiment cards through `docs/site/experiments.json`.
+
+## Change checklist
+
+Before pushing:
+
+1. keep unrelated working-tree changes untouched;
+2. update architecture or behavior documentation;
+3. add deterministic tests for policy changes;
+4. run unit and formatting checks;
+5. run Docker integration for workspace/Gateway changes;
+6. run E2E for public model, auth, loop, or file-delivery changes;
+7. audit every rebuilt image;
+8. use immutable production image tags;
+9. verify public health and one representative user flow;
+10. retain the previous image and deployment backup until verification passes.
diff --git a/docs/experiments.md b/docs/experiments.md
new file mode 100644
index 0000000..3b71539
--- /dev/null
+++ b/docs/experiments.md
@@ -0,0 +1,133 @@
+# Agent experiment system
+
+## Goal
+
+The project exists to make Agent-loop iteration cheap, observable, and
+reversible. An experiment should change one behavioral hypothesis while
+holding authentication, workspace isolation, and delivery infrastructure
+constant.
+
+The public portal at <https://agent.k1412.top/doc/#experiments> contains a
+curated experiment board. This Markdown document defines the durable process;
+the portal catalog is a presentation layer.
+
+## Experiment unit
+
+Every experiment should define:
+
+1. **Question** — the behavior we want to improve.
+2. **Hypothesis** — the concrete loop change and expected direction.
+3. **Variant identifier** — a stable string recorded in `run.created`.
+4. **Task set** — fixed prompts, starting workspace fixtures, and model tier.
+5. **Metrics** — success, quality, latency, model/tool usage, and regressions.
+6. **Safety constraints** — behavior that must not worsen.
+7. **Decision rule** — promote, iterate, or reject.
+8. **Artifact** — code commit, configuration, raw event export, and report.
+
+Do not compare variants from different task inputs or silently change the
+model, prompt, context budget, or workspace fixture.
+
+## Recommended metrics
+
+Primary:
+
+- task success under explicit evidence checks;
+- verified-deliverable rate;
+- unresolved tool-failure rate;
+- human or rubric quality score.
+
+Efficiency:
+
+- end-to-end latency;
+- model calls and iterations;
+- prompt/completion tokens when available;
+- tool-call count;
+- duplicated or policy-blocked calls;
+- child-Agent count and concurrency;
+- estimated provider and electricity cost.
+
+Reliability and safety:
+
+- incomplete checkpoints correctly rejected;
+- false-success rate;
+- workspace escape or cross-user access failures;
+- non-zero command exits incorrectly recorded as success;
+- identity/authentication failures;
+- Runtime or workspace restart recovery.
+
+## Evaluation layers
+
+### Unit and policy tests
+
+Fast deterministic tests cover parsing, tool normalization, evidence gates,
+authentication, context selection, event persistence, and provider response
+normalization.
+
+### Real Docker integration
+
+The integration test creates two disposable users and proves:
+
+- separate containers, networks, and volumes;
+- workspace path confinement;
+- file browse/download/archive behavior;
+- read-only root and dropped capabilities;
+- persistent Python virtual environments;
+- foreground and background `pipefail` exit codes.
+
+### Disposable full-stack E2E
+
+The E2E stack uses a deterministic fake model provider and exercises:
+
+- registration and admin approval;
+- the exact four-model public catalog;
+- the custom Agent loop;
+- evidence-backed file generation;
+- file delivery;
+- per-user isolation.
+
+### Live-model evaluation
+
+`scripts/eval-live-work.py` runs a real model against a unique disposable
+workspace and records latency, token usage, events, tool counts, and output
+files. Live evaluations complement deterministic tests; they do not replace
+them.
+
+### Production smoke test
+
+After deployment, use a low-impact authenticated task to confirm public Web,
+Runtime, Gateway, the remote workspace host, and file retrieval. Remove only
+the smoke artifact after verification.
+
+## Current baselines
+
+| ID | Area | Status | Result |
+| --- | --- | --- | --- |
+| `loop-v3-evidence` | Completion policy | Production baseline | Artifacts require mutation followed by verification; reports and benchmarks require stronger evidence. |
+| `safe-parallel-v1` | Scheduler | Production baseline | Consecutive read-only calls and read-only delegates run concurrently; mutations remain serialized. |
+| `recent-visible-v1` | Context | Production baseline | Keep recent visible messages under a per-model character budget and attach up to eight memories. |
+| `workspace-python-v1` | Execution | Validated | Persistent `.venv`, persistent user caches, 900-second tool ceiling, and true pipeline exits. |
+| `fresh-gateway-identity-v1` | Authentication | Validated | Runtime re-signs verified identity for each tool request so long runs survive the original token expiry. |
+
+## Initial backlog
+
+1. Semantic or hybrid memory retrieval with conflict and expiry policy.
+2. Structured old-context summarization with replay comparison.
+3. Dependency-aware tool DAG scheduling rather than consecutive safe groups.
+4. Child-Agent result contracts and budget allocation.
+5. Experiment assignment stored per run and an aggregate comparison API.
+6. Cost accounting across local electricity and paid provider tokens.
+7. Workspace quotas, egress policy, abuse monitoring, and backup drills.
+
+## Adding an experiment
+
+1. Add the hypothesis and metrics to this document or a dedicated
+   `docs/experiments/<id>.md` file.
+2. Add the experiment to `docs/site/experiments.json` for the public board.
+3. Add or update the relevant strategy/scheduler/context identifier in
+   `run.created`.
+4. Add deterministic tests before a live run.
+5. Run the standard verification and capture a report.
+6. Promote with an immutable image tag; retain the previous tag for rollback.
+
+Never put provider keys, private event payloads, user identifiers, prompts from
+real users, or internal credentials in an experiment artifact.
diff --git a/docs/operations.md b/docs/operations.md
index c79d4bc..63e4cf8 100644
--- a/docs/operations.md
+++ b/docs/operations.md
@@ -3,6 +3,7 @@
 ## Production layout
 
 - Public URL: `https://agent.k1412.top`
+- Public documentation: `https://agent.k1412.top/doc/`
 - NAS project: `/boot/config/plugins/compose.manager/projects/k1412-agent`
 - Public host port: `12004`
 - Execution provider: `ssh-docker`
@@ -47,6 +48,11 @@ Compose file, image, repository, or log.
 The SSH override removes `/var/run/docker.sock` from Gateway and mounts the
 dedicated SSH directory read-only at `/root/.ssh`.
 
+The documentation portal is copied into the existing Web image at
+`/app/build/doc`. It uses the same host port and proxy route as Open WebUI, so
+it does not require another Compose project, NAS port, DNS record, or Nginx
+Proxy Manager host.
+
 The Workspace image keeps the user home, package caches, and Python user base
 under `/workspace/.agent`; the conventional project virtual environment is
 `/workspace/.venv`. Updating `WORKSPACE_IMAGE` to a new immutable tag causes
diff --git a/docs/project-history.md b/docs/project-history.md
new file mode 100644
index 0000000..524cf56
--- /dev/null
+++ b/docs/project-history.md
@@ -0,0 +1,136 @@
+# Project history and decisions
+
+This record summarizes the rebuild that began on 2026-07-26. Git remains the
+source of truth for exact changes; this document captures product intent and
+architecture decisions that are otherwise difficult to reconstruct from
+individual commits.
+
+## 1. Clean-slate web Agent
+
+The existing business/data-specific application was declared a new project
+with no backward-compatibility requirement. Business skills, domain workflows,
+and user-configurable provider settings were removed from scope. The retained
+core requirement was general coding-Agent capability with an independently
+evolvable loop.
+
+Decision:
+
+- build one general multi-user Web Agent;
+- preserve coding, shell, file, Git, process, planning, memory, and delegation
+  capabilities;
+- keep infrastructure and product shell separate from Agent intelligence.
+
+## 2. Open WebUI as product shell
+
+Instead of maintaining a second full account/chat frontend, Open WebUI v0.9.6
+was pinned and lightly patched. It supplies registration, login, RBAC,
+administrator approval, conversation history, and familiar chat interaction.
+
+K1412 kept ownership of the Agent loop, provider routing, memory, tools,
+scheduling, events, and workspace execution. This reduced the cost of Agent
+experiments without making the loop dependent on Open WebUI internals.
+
+## 3. One Agent path, not Chat versus Work
+
+An early design considered a switch between Open WebUI's native Chat loop and
+the K1412 Work loop. The product was simplified to one Agent path because:
+
+- users should not need to understand two orchestration engines;
+- conversation continuation between modes creates ambiguous state;
+- two loops double frontend states and verification behavior;
+- the custom loop is the main research asset.
+
+The remaining interface is an Agent-first chat with server-owned model
+selection.
+
+## 4. Model and thinking semantics
+
+The original “light / medium / high reasoning” labels conflated different
+models with adjustable effort. The UI and backend now distinguish model
+identity from thinking capability:
+
+- Luna, Terra, and Sol are separate local K1412/Ollama models;
+- each exposes thinking as enabled but without adjustable effort levels;
+- DeepSeek V4 Pro is the cloud extreme tier with maximum reasoning effort.
+
+Provider model IDs, URLs, credentials, and tuning remain server-side.
+
+## 5. Multi-user remote workspaces
+
+Each user received a dedicated Docker container, network, and persistent volume
+derived from a hashed immutable user ID. Execution moved from the NAS to the
+physical `home-node-itx` through SSH Docker.
+
+The physical node was prepared with:
+
+- an ext4 500 GB data disk mounted at `/srv/k1412-data`;
+- Docker root under `/srv/k1412-data/docker`;
+- strict SSH host verification;
+- no application/database secrets.
+
+The local and SSH execution providers retain one interface so the host can be
+replaced without changing Agent behavior.
+
+## 6. File delivery and focused UI
+
+The frontend was simplified around the Agent:
+
+- K1412 product title and assets;
+- a compact model selector with separate thinking status;
+- no exposed provider/tool/system-prompt settings;
+- an authenticated workspace file browser;
+- single-file download and streamed directory archive.
+
+Open WebUI attribution and license requirements remain documented.
+
+## 7. Loop hardening through failed-task analysis
+
+Real sorting-script/report tasks exposed model weaknesses and platform bugs.
+The loop was progressively hardened to:
+
+- require actual files rather than textual claims;
+- require executable source separately from reports;
+- run the source before writing a report;
+- require measured benchmark values;
+- reject invalid Python and escaped-layout corruption;
+- recover from failed verification;
+- prevent unchanged retry loops and duplicate batches;
+- preserve failures even when output is piped through another command;
+- bound iteration, tool-batch, model-output, and retry budgets.
+
+These constraints are not assumed permanently optimal. They are the current
+baseline and should be removed or changed only through measured experiments.
+
+## 8. Python environment and long-run reliability
+
+Production debugging found three platform problems:
+
+1. the container root was read-only while `pip` defaulted to `/home/agent`;
+2. `/tmp` was `noexec`;
+3. shell pipelines returned the last command's status, hiding failed installs.
+
+The fix moved home, caches, user packages, and virtual environments to the
+persistent workspace, enabled Bash `pipefail`, extended tool timeouts to 900
+seconds, and taught the Agent the supported `.venv` workflow.
+
+The same investigation found that a five-minute identity token was reused for
+every tool in a long run. Runtime now signs a fresh short-lived identity for
+each Gateway call after the original request identity has been verified.
+
+Production validation created a real `.venv`, installed and imported
+`psutil 7.2.2`, downloaded the generated proof file through the Web API, and
+then removed the temporary proof file.
+
+## 9. Documentation and experiment portal
+
+The repository documentation was reorganized around architecture, Agent
+implementation, security, operations, history, development, and experiments.
+The curated public portal is shipped inside the existing Web image at
+`/doc/`, avoiding a second service or proxy rule.
+
+## Current direction
+
+The platform is now suitable for controlled Agent-loop experimentation. The
+next work should prioritize evaluation data, context/memory experiments,
+scheduler design, delegation contracts, cost accounting, and hardening for
+hostile multi-tenant use rather than adding business-specific workflows.
diff --git a/docs/site/app.js b/docs/site/app.js
new file mode 100644
index 0000000..c39418f
--- /dev/null
+++ b/docs/site/app.js
@@ -0,0 +1,265 @@
+const flows = {
+	agent: {
+		kicker: 'AGENT REQUEST / 7 HOPS',
+		description:
+			'浏览器的已登录请求由 Web 转换成兼容 OpenAI 的流式调用；Runtime 独立完成上下文构建、模型调用、工具循环和证据校验。',
+		nodes: ['browser', 'web', 'runtime', 'provider', 'gateway', 'workspace', 'store']
+	},
+	identity: {
+		kicker: 'IDENTITY / SHORT-LIVED & SERVER-SIDE',
+		description:
+			'Web 先验证登录用户并签发短期身份；Runtime 验证一次后，在每次 Gateway 工具调用前重新签发，避免长任务复用过期令牌。',
+		nodes: ['browser', 'web', 'runtime', 'gateway', 'workspace']
+	},
+	tool: {
+		kicker: 'TOOL EXECUTION / POLICY BEFORE DOCKER',
+		description:
+			'Runtime 校验并调度工具，Gateway 再执行身份、路径和资源策略，最后才通过 SSH Docker 进入该用户唯一的工作区。',
+		nodes: ['runtime', 'gateway', 'workspace', 'store']
+	},
+	file: {
+		kicker: 'FILE DELIVERY / AUTHENTICATED STREAM',
+		description:
+			'用户在工作区抽屉发起浏览或下载；Web 验证会话后请求 Gateway，文件或归档以流式响应返回，浏览器从不接触内部服务密钥。',
+		nodes: ['browser', 'web', 'gateway', 'workspace']
+	}
+};
+
+const stages = {
+	context: {
+		kicker: 'CONTEXT / recent-visible-v1',
+		title: '把有限上下文留给真正影响下一步的内容',
+		description:
+			'移除旧的工具详情渲染，按模型预算保留最新可见消息，再注入最多 8 条持久记忆。上下文策略和 Agent Loop 分别版本化。',
+		points: [
+			'去掉历史消息中的工具 UI 标记',
+			'最近消息优先，按字符预算截断',
+			'记忆只作为补充上下文，不直接取得执行权限'
+		]
+	},
+	model: {
+		kicker: 'MODEL / SERVER-SIDE CATALOG',
+		title: '模型提出下一步，平台控制它能看到和能花费什么',
+		description:
+			'Runtime 根据公开模型 ID 选择固定 provider、上下文预算、输出预算和循环上限。用户不能从前端注入密钥或任意模型参数。',
+		points: ['支持流式内容与工具调用', '模型和推理强度明确标注', 'provider 差异在传输层统一']
+	},
+	validate: {
+		kicker: 'VALIDATE / NORMALIZE BEFORE TRUST',
+		title: '先把模型输出变成可约束的数据，再决定是否执行',
+		description:
+			'工具名称、参数、批次数量和权限都在执行前检查。一次模型响应最多接受 8 个工具调用，未知或畸形调用会成为可见错误。',
+		points: ['JSON 参数规范化', '工具白名单与参数校验', '重复无进展调用守卫']
+	},
+	schedule: {
+		kicker: 'SCHEDULER / safe-parallel-v1',
+		title: '读取可以加速，写入必须保持可预测',
+		description:
+			'连续且标记为 parallel_safe 的工具并发执行；任何文件写入、命令或状态变更都会形成串行边界，结果按请求顺序返回模型。',
+		points: ['只读调用成组并发', '变更操作严格串行', '批次结果仍保持稳定顺序']
+	},
+	execute: {
+		kicker: 'EXECUTE / TOOLS + BOUNDED DELEGATION',
+		title: '所有能力都通过可记录、可验证的工具边界发生',
+		description:
+			'文件、命令、Git、计划和记忆都有结构化工具。Workspace 工具经 Gateway 进入用户容器；只读子任务可以受限委派。',
+		points: ['工作区工具与状态工具分离', '每次调用记录开始和结果事件', '子 Agent 不得再次委派']
+	},
+	evidence: {
+		kicker: 'EVIDENCE / COMPLETION IS A POLICY',
+		title: '“完成”不是一句自然语言，而是一组已经发生的事实',
+		description:
+			'如果任务要求生成文件、修改代码或给出测量报告，循环必须看到相应的写入、验证和精确结果。证据不足时会继续循环或明确失败。',
+		points: ['变更后必须有后续验证', '失败命令必须修复并重跑', '报告必须晚于来源或实验结果']
+	}
+};
+
+const statusLabels = {
+	baseline: '当前基线',
+	validated: '已验证',
+	backlog: '待实验'
+};
+
+let experimentData = [];
+let activeExperimentFilter = 'all';
+
+function activateFlow(flowName) {
+	const flow = flows[flowName];
+	if (!flow) return;
+
+	document.querySelectorAll('.flow-tab').forEach((button) => {
+		const active = button.dataset.flow === flowName;
+		button.classList.toggle('is-active', active);
+		button.setAttribute('aria-selected', String(active));
+	});
+
+	document.querySelectorAll('.system-node').forEach((node) => {
+		node.classList.toggle('is-flow-active', flow.nodes.includes(node.dataset.node));
+	});
+
+	document.querySelector('.system-map')?.classList.add('has-selection');
+	document.querySelector('#flow-kicker').textContent = flow.kicker;
+	document.querySelector('#flow-description').textContent = flow.description;
+}
+
+function activateStage(stageName) {
+	const stage = stages[stageName];
+	if (!stage) return;
+
+	document.querySelectorAll('.loop-stage').forEach((button) => {
+		const active = button.dataset.stage === stageName;
+		button.classList.toggle('is-active', active);
+		button.setAttribute('aria-selected', String(active));
+	});
+
+	document.querySelector('#stage-kicker').textContent = stage.kicker;
+	document.querySelector('#stage-title').textContent = stage.title;
+	document.querySelector('#stage-description').textContent = stage.description;
+
+	const list = document.querySelector('#stage-points');
+	list.replaceChildren(
+		...stage.points.map((point) => {
+			const item = document.createElement('li');
+			item.textContent = point;
+			return item;
+		})
+	);
+}
+
+function experimentCard(experiment) {
+	const article = document.createElement('article');
+	article.className = 'experiment-card';
+
+	const meta = document.createElement('div');
+	meta.className = 'experiment-meta';
+
+	const id = document.createElement('span');
+	id.textContent = experiment.id;
+
+	const badge = document.createElement('span');
+	badge.className = `status-badge status-${experiment.status}`;
+	badge.textContent = statusLabels[experiment.status];
+	meta.append(id, badge);
+
+	const title = document.createElement('h3');
+	title.textContent = experiment.title;
+
+	const summary = document.createElement('p');
+	summary.textContent = experiment.summary;
+
+	const footer = document.createElement('div');
+	footer.className = 'experiment-footer';
+	[experiment.area, experiment.version, ...(experiment.metrics || [])].filter(Boolean).forEach((text) => {
+		const tag = document.createElement('span');
+		tag.textContent = text;
+		footer.append(tag);
+	});
+
+	article.append(meta, title, summary, footer);
+	return article;
+}
+
+function renderExperiments() {
+	const query = document.querySelector('#experiment-search').value.trim().toLocaleLowerCase('zh-CN');
+	const filtered = experimentData.filter((experiment) => {
+		const statusMatches =
+			activeExperimentFilter === 'all' || experiment.status === activeExperimentFilter;
+		const haystack = [
+			experiment.id,
+			experiment.title,
+			experiment.summary,
+			experiment.area,
+			experiment.version,
+			...(experiment.metrics || [])
+		]
+			.join(' ')
+			.toLocaleLowerCase('zh-CN');
+		return statusMatches && (!query || haystack.includes(query));
+	});
+
+	const grid = document.querySelector('#experiment-grid');
+	if (filtered.length === 0) {
+		const empty = document.createElement('article');
+		empty.className = 'experiment-empty';
+		empty.textContent = '没有匹配的实验记录。';
+		grid.replaceChildren(empty);
+	} else {
+		grid.replaceChildren(...filtered.map(experimentCard));
+	}
+
+	document.querySelector('#experiment-count').textContent =
+		`${String(filtered.length).padStart(2, '0')} / ${String(experimentData.length).padStart(2, '0')} RECORDS`;
+}
+
+async function loadExperiments() {
+	const grid = document.querySelector('#experiment-grid');
+	try {
+		const response = await fetch('./experiments.json', { cache: 'no-cache' });
+		if (!response.ok) throw new Error(`HTTP ${response.status}`);
+		experimentData = await response.json();
+		renderExperiments();
+	} catch (error) {
+		const failure = document.createElement('article');
+		failure.className = 'experiment-empty';
+		failure.textContent = '实验台账暂时无法读取，请查看仓库中的 docs/experiments.md。';
+		grid.replaceChildren(failure);
+		document.querySelector('#experiment-count').textContent = 'DATA UNAVAILABLE';
+	}
+}
+
+function setActiveNavigation(sectionId) {
+	document.querySelectorAll('.nav-link').forEach((link) => {
+		link.classList.toggle('is-active', link.getAttribute('href') === `#${sectionId}`);
+	});
+}
+
+document.querySelectorAll('.flow-tab').forEach((button) => {
+	button.addEventListener('click', () => activateFlow(button.dataset.flow));
+});
+
+document.querySelectorAll('.loop-stage').forEach((button) => {
+	button.addEventListener('click', () => activateStage(button.dataset.stage));
+});
+
+document.querySelectorAll('.filter-button').forEach((button) => {
+	button.addEventListener('click', () => {
+		activeExperimentFilter = button.dataset.filter;
+		document
+			.querySelectorAll('.filter-button')
+			.forEach((candidate) => candidate.classList.toggle('is-active', candidate === button));
+		renderExperiments();
+	});
+});
+
+document.querySelector('#experiment-search').addEventListener('input', renderExperiments);
+
+const toggle = document.querySelector('.nav-toggle');
+const sidebar = document.querySelector('.sidebar');
+toggle.addEventListener('click', () => {
+	const isOpen = sidebar.classList.toggle('is-open');
+	toggle.setAttribute('aria-expanded', String(isOpen));
+});
+
+document.querySelectorAll('.nav-link').forEach((link) => {
+	link.addEventListener('click', () => {
+		sidebar.classList.remove('is-open');
+		toggle.setAttribute('aria-expanded', 'false');
+	});
+});
+
+if ('IntersectionObserver' in window) {
+	const observer = new IntersectionObserver(
+		(entries) => {
+			const visible = entries
+				.filter((entry) => entry.isIntersecting)
+				.sort((a, b) => b.intersectionRatio - a.intersectionRatio);
+			if (visible[0]) setActiveNavigation(visible[0].target.id);
+		},
+		{ rootMargin: '-20% 0px -62% 0px', threshold: [0.05, 0.3] }
+	);
+	document.querySelectorAll('main > section[id]').forEach((section) => observer.observe(section));
+}
+
+activateFlow('agent');
+activateStage('context');
+loadExperiments();
diff --git a/docs/site/experiments.json b/docs/site/experiments.json
new file mode 100644
index 0000000..15cc2c3
--- /dev/null
+++ b/docs/site/experiments.json
@@ -0,0 +1,92 @@
+[
+	{
+		"id": "BASE-001",
+		"title": "统一 Agent 路径",
+		"summary": "删除 Chat / Work 双模式，所有对话通过同一套可观测 Agent Loop；减少前端状态和后端分叉。",
+		"area": "product",
+		"status": "validated",
+		"version": "agent-loop-v3",
+		"metrics": ["维护面", "交互一致性"]
+	},
+	{
+		"id": "BASE-002",
+		"title": "安全读取并行，变更串行",
+		"summary": "连续 parallel_safe 调用并发执行，写文件、命令和状态变更维持模型给出的顺序。",
+		"area": "scheduler",
+		"status": "baseline",
+		"version": "safe-parallel-v1",
+		"metrics": ["wall time", "determinism"]
+	},
+	{
+		"id": "BASE-003",
+		"title": "最近可见上下文",
+		"summary": "清除旧工具详情，按模型字符预算保留最近消息，并注入最多 8 条持久记忆。",
+		"area": "context",
+		"status": "baseline",
+		"version": "recent-visible-v1",
+		"metrics": ["token proxy", "task success"]
+	},
+	{
+		"id": "BASE-004",
+		"title": "证据驱动的完成判定",
+		"summary": "文件、代码和报告任务必须出现写入与后续验证；未解决的命令失败会阻止虚假完成。",
+		"area": "reliability",
+		"status": "validated",
+		"version": "evidence-gate-v1",
+		"metrics": ["false completion", "artifact validity"]
+	},
+	{
+		"id": "BASE-005",
+		"title": "持久 Python 工具链",
+		"summary": "用户依赖安装到 /workspace/.venv；镜像升级保留环境，pipefail 防止安装失败被管道尾部掩盖。",
+		"area": "workspace",
+		"status": "validated",
+		"version": "workspace-python-v2",
+		"metrics": ["install success", "restart survival"]
+	},
+	{
+		"id": "EXP-006",
+		"title": "基于相关性的记忆召回",
+		"summary": "比较固定最近记忆、关键词召回和向量召回对长期偏好遵循、上下文成本与错误注入的影响。",
+		"area": "memory",
+		"status": "backlog",
+		"version": "proposal",
+		"metrics": ["recall@k", "task success", "context cost"]
+	},
+	{
+		"id": "EXP-007",
+		"title": "依赖感知工具调度",
+		"summary": "从显式工具属性推进到调用间读写集分析，评估是否能扩大安全并行范围。",
+		"area": "scheduler",
+		"status": "backlog",
+		"version": "proposal",
+		"metrics": ["wall time", "race failures", "parallel ratio"]
+	},
+	{
+		"id": "EXP-008",
+		"title": "自适应模型路由",
+		"summary": "以任务复杂度和中途失败信号决定 Luna、Terra、Sol 或 DeepSeek，而不是让一次选择锁定整个任务。",
+		"area": "model-routing",
+		"status": "backlog",
+		"version": "proposal",
+		"metrics": ["task success", "latency", "API cost"]
+	},
+	{
+		"id": "EXP-009",
+		"title": "受限多 Agent 拓扑",
+		"summary": "比较单循环、只读并行委派和角色化子 Agent，在复杂代码任务中的收益与上下文整合成本。",
+		"area": "delegation",
+		"status": "backlog",
+		"version": "proposal",
+		"metrics": ["task success", "wall time", "tool calls"]
+	},
+	{
+		"id": "EXP-010",
+		"title": "上下文压缩与可逆摘要",
+		"summary": "在最近消息预算之外保存结构化任务状态，并允许模型按需取回原始证据，减少长任务遗忘。",
+		"area": "context",
+		"status": "backlog",
+		"version": "proposal",
+		"metrics": ["long-horizon success", "context cost", "retrieval count"]
+	}
+]
diff --git a/docs/site/index.html b/docs/site/index.html
new file mode 100644
index 0000000..882be00
--- /dev/null
+++ b/docs/site/index.html
@@ -0,0 +1,570 @@
+<!doctype html>
+<html lang="zh-CN">
+	<head>
+		<meta charset="utf-8" />
+		<meta name="viewport" content="width=device-width, initial-scale=1" />
+		<meta name="theme-color" content="#f2f0e9" />
+		<title>K1412 Agent · 架构、实现与实验</title>
+		<meta
+			name="description"
+			content="K1412 多用户 Web Agent 的架构设计、Agent Loop 实现、隔离模型和实验记录。"
+		/>
+		<meta property="og:type" content="website" />
+		<meta property="og:site_name" content="K1412 Agent" />
+		<meta property="og:title" content="K1412 Agent · Architecture & Experiments" />
+		<meta
+			property="og:description"
+			content="A multi-user Web Agent built as an evolvable system for context, tools, parallelism, memory and delegation."
+		/>
+		<meta property="og:url" content="https://agent.k1412.top/doc/" />
+		<meta property="og:image" content="https://agent.k1412.top/doc/og.png" />
+		<link rel="icon" href="../static/favicon.svg" type="image/svg+xml" />
+		<link rel="stylesheet" href="./styles.css" />
+		<script>
+			document.documentElement.classList.add('js');
+		</script>
+		<script src="./app.js" defer></script>
+	</head>
+	<body>
+		<a class="skip-link" href="#main-content">跳到正文</a>
+
+		<header class="topbar">
+			<a class="brand" href="#overview" aria-label="K1412 Agent 文档首页">
+				<span class="brand-mark" aria-hidden="true">K</span>
+				<span>
+					<strong>K1412 Agent</strong>
+					<small>Architecture / Lab Notes</small>
+				</span>
+			</a>
+			<div class="topbar-actions">
+				<span class="system-status"><i></i> 当前架构 · 2026.07</span>
+				<a class="button button-quiet hide-mobile" href="https://git.k1412.top/wuyang/zk-data-agent">
+					查看源码
+				</a>
+				<a class="button button-primary" href="/">进入 Agent <span aria-hidden="true">↗</span></a>
+				<button
+					class="nav-toggle"
+					type="button"
+					aria-label="打开文档目录"
+					aria-expanded="false"
+					aria-controls="side-navigation"
+				>
+					<span></span><span></span>
+				</button>
+			</div>
+		</header>
+
+		<div class="page-shell">
+			<aside class="sidebar" id="side-navigation">
+				<nav aria-label="文档目录">
+					<p class="nav-label">系统</p>
+					<a class="nav-link is-active" href="#overview"><span>01</span>概览</a>
+					<a class="nav-link" href="#architecture"><span>02</span>架构边界</a>
+					<a class="nav-link" href="#agent-loop"><span>03</span>Agent Loop</a>
+					<a class="nav-link" href="#workspace"><span>04</span>执行空间</a>
+					<a class="nav-link" href="#models"><span>05</span>模型与强度</a>
+					<p class="nav-label">演进</p>
+					<a class="nav-link" href="#experiments"><span>06</span>实验记录</a>
+					<a class="nav-link" href="#operations"><span>07</span>部署与观测</a>
+					<a class="nav-link" href="#timeline"><span>08</span>项目历程</a>
+					<a class="nav-link" href="#repository"><span>09</span>仓库文档</a>
+				</nav>
+				<div class="sidebar-note">
+					<span>核心原则</span>
+					<p>稳定的平台外壳，快速演进的 Agent 核心。</p>
+				</div>
+			</aside>
+
+			<main id="main-content">
+				<section class="hero section" id="overview">
+					<div class="eyebrow"><span>ONE AGENT PATH</span> / MULTI-USER / SELF-HOSTED</div>
+					<h1>一套可以被持续<br />实验的 Web Agent</h1>
+					<p class="hero-copy">
+						K1412 Agent 把账户、界面和执行隔离做成稳定平台，把上下文、工具调度、并行、多 Agent、
+						记忆和完成判定留在我们自己的 Agent Loop 中。这里既是系统说明，也是后续实验的公开台账。
+					</p>
+					<div class="hero-actions">
+						<a class="button button-dark" href="#architecture">理解架构 <span aria-hidden="true">↓</span></a>
+						<a class="text-link" href="#experiments">查看实验记录 <span aria-hidden="true">→</span></a>
+					</div>
+
+					<div class="metric-strip" aria-label="当前系统摘要">
+						<div>
+							<strong>01</strong>
+							<span>统一 Agent 路径</span>
+							<small>没有 Chat / Work 分叉</small>
+						</div>
+						<div>
+							<strong>04</strong>
+							<span>可选模型</span>
+							<small>模型与推理强度分离</small>
+						</div>
+						<div>
+							<strong>1 : 1</strong>
+							<span>用户执行空间</span>
+							<small>容器、网络与持久卷</small>
+						</div>
+						<div>
+							<strong>SSE</strong>
+							<span>运行事件流</span>
+							<small>模型、工具与完成证据</small>
+						</div>
+					</div>
+				</section>
+
+				<section class="section architecture-section" id="architecture">
+					<div class="section-heading">
+						<div>
+							<span class="section-index">02 / ARCHITECTURE</span>
+							<h2>稳定外壳与<br />实验核心解耦</h2>
+						</div>
+						<p>
+							点击一条链路，观察一次请求如何穿过系统。公开入口只有 Web；模型密钥、Docker
+							权限和用户执行环境始终留在服务端。
+						</p>
+					</div>
+
+					<div class="architecture-lab">
+						<div class="flow-tabs" role="tablist" aria-label="架构链路">
+							<button class="flow-tab is-active" type="button" role="tab" data-flow="agent">
+								Agent 请求
+							</button>
+							<button class="flow-tab" type="button" role="tab" data-flow="identity">身份链路</button>
+							<button class="flow-tab" type="button" role="tab" data-flow="tool">工具执行</button>
+							<button class="flow-tab" type="button" role="tab" data-flow="file">文件交付</button>
+						</div>
+
+						<div class="system-map" aria-label="K1412 Agent 系统架构图">
+							<div class="map-lane map-public">
+								<span class="lane-label">PUBLIC EDGE</span>
+								<article class="system-node" data-node="browser">
+									<small>01 / CLIENT</small>
+									<strong>Browser</strong>
+									<span>登录、会话、文件下载</span>
+								</article>
+								<span class="map-arrow" aria-hidden="true">→</span>
+								<article class="system-node node-web" data-node="web">
+									<small>02 / STABLE SHELL</small>
+									<strong>Open WebUI</strong>
+									<span>Auth · RBAC · History · UI</span>
+								</article>
+							</div>
+
+							<div class="map-lane map-core">
+								<span class="lane-label">PRIVATE APPLICATION NETWORK</span>
+								<article class="system-node node-runtime" data-node="runtime">
+									<small>03 / EXPERIMENT CORE</small>
+									<strong>Agent Runtime</strong>
+									<span>Context · Loop · Tools · Memory</span>
+								</article>
+								<span class="map-arrow" aria-hidden="true">→</span>
+								<article class="system-node" data-node="provider">
+									<small>04 / INFERENCE</small>
+									<strong>Model Provider</strong>
+									<span>K1412 API · DeepSeek</span>
+								</article>
+								<article class="system-node" data-node="gateway">
+									<small>05 / POLICY GATE</small>
+									<strong>Workspace Gateway</strong>
+									<span>Identity · Path · Docker lifecycle</span>
+								</article>
+								<article class="system-node node-store" data-node="store">
+									<small>STATE</small>
+									<strong>PostgreSQL + Redis</strong>
+									<span>Chats · Events · Plans · Memory</span>
+								</article>
+							</div>
+
+							<div class="map-lane map-execution">
+								<span class="lane-label">TAILSCALE / PHYSICAL WORKER</span>
+								<article class="system-node node-workspace" data-node="workspace">
+									<small>06 / USER BOUNDARY</small>
+									<strong>Per-user Workspace</strong>
+									<span>Container · Network · Persistent volume</span>
+								</article>
+							</div>
+						</div>
+
+						<div class="flow-explainer" aria-live="polite">
+							<span id="flow-kicker">AGENT REQUEST / 7 HOPS</span>
+							<p id="flow-description">
+								浏览器的已登录请求由 Web 转换成兼容 OpenAI 的流式调用；Runtime
+								独立完成上下文构建、模型调用、工具循环和证据校验。
+							</p>
+						</div>
+					</div>
+
+					<div class="boundary-grid">
+						<article>
+							<span class="boundary-number">A</span>
+							<h3>Open WebUI</h3>
+							<p>负责用户系统、会话、历史和呈现。它是产品外壳，不决定 Agent 如何思考与执行。</p>
+							<small>STABLE / UPSTREAM-BASED</small>
+						</article>
+						<article>
+							<span class="boundary-number">B</span>
+							<h3>Agent Runtime</h3>
+							<p>负责模型、上下文、工具、并行、委派、记忆和完成判定，是我们主要的实验面。</p>
+							<small>FAST-MOVING / OWNED</small>
+						</article>
+						<article>
+							<span class="boundary-number">C</span>
+							<h3>Gateway + Workspace</h3>
+							<p>把已验证用户绑定到唯一执行空间，控制路径、资源和 Docker 生命周期。</p>
+							<small>SECURITY BOUNDARY</small>
+						</article>
+					</div>
+				</section>
+
+				<section class="section loop-section" id="agent-loop">
+					<div class="section-heading inverse-heading">
+						<div>
+							<span class="section-index">03 / AGENT LOOP</span>
+							<h2>模型不是 Agent，<br />循环才是。</h2>
+						</div>
+						<p>
+							当前基线为 <code>agent-loop-v3</code>。模型每轮可以回答或提出工具调用；Runtime
+							负责校验、调度、恢复，并拒绝没有证据的“已完成”。
+						</p>
+					</div>
+
+					<div class="loop-console">
+						<div class="loop-stages" role="tablist" aria-label="Agent Loop 阶段">
+							<button class="loop-stage is-active" type="button" data-stage="context">
+								<span>01</span><strong>Context</strong><small>裁剪与记忆</small>
+							</button>
+							<button class="loop-stage" type="button" data-stage="model">
+								<span>02</span><strong>Model</strong><small>生成意图</small>
+							</button>
+							<button class="loop-stage" type="button" data-stage="validate">
+								<span>03</span><strong>Validate</strong><small>规范与限制</small>
+							</button>
+							<button class="loop-stage" type="button" data-stage="schedule">
+								<span>04</span><strong>Schedule</strong><small>并行与串行</small>
+							</button>
+							<button class="loop-stage" type="button" data-stage="execute">
+								<span>05</span><strong>Execute</strong><small>工具与委派</small>
+							</button>
+							<button class="loop-stage" type="button" data-stage="evidence">
+								<span>06</span><strong>Evidence</strong><small>验证与完成</small>
+							</button>
+						</div>
+
+						<div class="loop-detail">
+							<div>
+								<span class="detail-label" id="stage-kicker">CONTEXT / recent-visible-v1</span>
+								<h3 id="stage-title">把有限上下文留给真正影响下一步的内容</h3>
+							</div>
+							<p id="stage-description">
+								移除旧的工具详情渲染，按模型预算保留最新可见消息，再注入最多 8
+								条持久记忆。上下文策略和 Agent Loop 分别版本化。
+							</p>
+							<ul id="stage-points">
+								<li>去掉历史消息中的工具 UI 标记</li>
+								<li>最近消息优先，按字符预算截断</li>
+								<li>记忆只作为补充上下文，不直接取得执行权限</li>
+							</ul>
+						</div>
+					</div>
+
+					<div class="loop-principles">
+						<article>
+							<span>PARALLELISM</span>
+							<h3>只并行已知安全的读取</h3>
+							<p>
+								连续的只读、<code>parallel_safe</code> 工具可以并发；写入和状态变更保持顺序，
+								避免输出更快但结果不可复现。
+							</p>
+						</article>
+						<article>
+							<span>RECOVERY</span>
+							<h3>失败不是上下文噪声</h3>
+							<p>命令失败必须被修复并重新运行，重复无进展调用会被守卫阻止，模型不能用文字绕过失败。</p>
+						</article>
+						<article>
+							<span>DELEGATION</span>
+							<h3>委派是受限的工具</h3>
+							<p>只读子任务可并行，子 Agent 不能继续委派。父循环仍然负责整合证据和最终完成判定。</p>
+						</article>
+					</div>
+
+					<div class="evidence-table" aria-label="完成证据规则">
+						<div class="table-row table-head">
+							<span>声称完成的类型</span><span>最低证据</span><span>阻止条件</span>
+						</div>
+						<div class="table-row">
+							<strong>生成文件</strong><span>成功写入 + 随后读取或列出</span><span>只有模型文字</span>
+						</div>
+						<div class="table-row">
+							<strong>修改代码</strong><span>变更操作 + 相关验证</span><span>未解决的失败命令</span>
+						</div>
+						<div class="table-row">
+							<strong>生成报告</strong><span>来源或执行结果 + 报告文件验证</span><span>报告早于实验</span>
+						</div>
+						<div class="table-row">
+							<strong>性能比较</strong><span>可解析的精确数值</span><span>只有定性结论</span>
+						</div>
+					</div>
+				</section>
+
+				<section class="section workspace-section" id="workspace">
+					<div class="section-heading">
+						<div>
+							<span class="section-index">04 / EXECUTION SPACE</span>
+							<h2>每个用户，一套<br />长期存在的工具台</h2>
+						</div>
+						<p>
+							生产执行发生在物理机 <code>home-node-itx</code>。Gateway 通过 Tailscale + SSH
+							管理 Docker；用户得到独立容器、网络和持久卷，而不是宿主机账号。
+						</p>
+					</div>
+
+					<div class="isolation-visual">
+						<div class="identity-card">
+							<small>IMMUTABLE INPUT</small>
+							<strong>Open WebUI user_id</strong>
+							<code>sha256(user_id) → workspace_id</code>
+						</div>
+						<div class="identity-arrow" aria-hidden="true">→</div>
+						<div class="workspace-stack">
+							<div><span>CONTAINER</span><code>k1412-ws-&lt;id&gt;</code></div>
+							<div><span>NETWORK</span><code>k1412-ws-net-&lt;id&gt;</code></div>
+							<div><span>VOLUME</span><code>k1412-ws-data-&lt;id&gt;</code></div>
+						</div>
+					</div>
+
+					<div class="security-grid">
+						<article>
+							<span class="security-icon">01</span>
+							<h3>身份不下放给浏览器</h3>
+							<p>Web 验证登录，Runtime 每次调用 Gateway 前重新签发短期身份。内部服务密钥从不进入前端。</p>
+						</article>
+						<article>
+							<span class="security-icon">02</span>
+							<h3>容器不是主机边界的替代品</h3>
+							<p>只读根目录、丢弃 capabilities、no-new-privileges、资源限制、无宿主端口和 Docker socket。</p>
+						</article>
+						<article>
+							<span class="security-icon">03</span>
+							<h3>依赖和文件都会留下</h3>
+							<p><code>/workspace</code> 由命名卷持久化；Python 位于 <code>.venv</code>，镜像升级不会删除用户数据。</p>
+						</article>
+						<article>
+							<span class="security-icon">04</span>
+							<h3>输出可以直接取回</h3>
+							<p>工作区抽屉支持浏览、下载文件和流式归档。用户无需接触 Gateway、SSH 或容器名称。</p>
+						</article>
+					</div>
+				</section>
+
+				<section class="section models-section" id="models">
+					<div class="section-heading">
+						<div>
+							<span class="section-index">05 / MODEL POLICY</span>
+							<h2>先标清模型，<br />再标真实思考能力</h2>
+						</div>
+						<p>
+							Luna、Terra、Sol 是三个独立模型，不是同一模型的轻、中、高强度。前端只显示后端确认支持的
+							思考语义；provider、循环和上下文预算仍由服务端模型目录固定。
+						</p>
+					</div>
+
+					<div class="model-grid">
+						<article class="model-card">
+							<div><span class="model-dot luna"></span><small>LOCAL MODEL</small></div>
+							<h3>Luna</h3>
+							<p>思考：开启（不分档）</p>
+							<dl><div><dt>循环上限</dt><dd>8</dd></div><div><dt>上下文预算</dt><dd>120k chars</dd></div></dl>
+						</article>
+						<article class="model-card is-default">
+							<div><span class="model-dot terra"></span><small>LOCAL / DEFAULT</small></div>
+							<h3>Terra</h3>
+							<p>思考：开启（不分档）</p>
+							<dl><div><dt>循环上限</dt><dd>16</dd></div><div><dt>上下文预算</dt><dd>240k chars</dd></div></dl>
+						</article>
+						<article class="model-card">
+							<div><span class="model-dot sol"></span><small>LOCAL MODEL</small></div>
+							<h3>Sol</h3>
+							<p>思考：开启（不分档）</p>
+							<dl><div><dt>循环上限</dt><dd>24</dd></div><div><dt>上下文预算</dt><dd>400k chars</dd></div></dl>
+						</article>
+						<article class="model-card model-deepseek">
+							<div><span class="model-dot deepseek"></span><small>CLOUD / MAX EFFORT</small></div>
+							<h3>DeepSeek V4 Pro</h3>
+							<p>思考强度：极高（max）</p>
+							<dl><div><dt>循环上限</dt><dd>32</dd></div><div><dt>上下文预算</dt><dd>800k chars</dd></div></dl>
+						</article>
+					</div>
+
+					<div class="policy-note">
+						<span>命名规则</span>
+						<p>
+							<strong>Luna / Terra / Sol / DeepSeek V4 Pro</strong> 是四个独立模型。前三者目前只暴露
+							“思考开启”的布尔能力，不能严谨地标成轻、中、高；DeepSeek 才明确使用
+							<strong>reasoning_effort=max</strong>，界面标注为“极高”。
+						</p>
+					</div>
+				</section>
+
+				<section class="section experiments-section" id="experiments">
+					<div class="section-heading">
+						<div>
+							<span class="section-index">06 / EXPERIMENT LOG</span>
+							<h2>每次改进都应该<br />留下可比较的记录</h2>
+						</div>
+						<p>
+							实验以问题、基线、变量、数据集、指标和结论为最小单元。页面读取仓库里的
+							<code>experiments.json</code>，与实现一起版本化。
+						</p>
+					</div>
+
+					<div class="experiment-toolbar">
+						<div class="filter-group" role="group" aria-label="实验状态筛选">
+							<button class="filter-button is-active" type="button" data-filter="all">全部</button>
+							<button class="filter-button" type="button" data-filter="baseline">基线</button>
+							<button class="filter-button" type="button" data-filter="validated">已验证</button>
+							<button class="filter-button" type="button" data-filter="backlog">待实验</button>
+						</div>
+						<label class="experiment-search">
+							<span class="sr-only">搜索实验</span>
+							<input id="experiment-search" type="search" placeholder="搜索上下文、并行、记忆…" />
+							<span aria-hidden="true">⌕</span>
+						</label>
+					</div>
+
+					<div class="experiment-grid" id="experiment-grid" aria-live="polite">
+						<article class="experiment-loading">正在读取实验台账…</article>
+					</div>
+					<p class="experiment-count" id="experiment-count"></p>
+				</section>
+
+				<section class="section operations-section" id="operations">
+					<div class="section-heading inverse-heading">
+						<div>
+							<span class="section-index">07 / OPERATIONS</span>
+							<h2>一条公开入口，<br />多层私有服务</h2>
+						</div>
+						<p>
+							生产栈运行于 Unraid NAS，公开流量经 VPS 上的 Nginx Proxy Manager 和 Tailscale
+							进入 NAS。文档和聊天由同一个 Web 镜像提供。
+						</p>
+					</div>
+
+					<div class="deployment-path" aria-label="部署链路">
+						<div><small>GIT</small><strong>git.k1412.top</strong></div>
+						<span>→</span>
+						<div><small>OCI</small><strong>docker.k1412.top</strong></div>
+						<span>→</span>
+						<div><small>COMPOSE</small><strong>Unraid NAS :12004</strong></div>
+						<span>→</span>
+						<div><small>PUBLIC</small><strong>agent.k1412.top</strong></div>
+					</div>
+
+					<div class="ops-grid">
+						<article>
+							<span>01 / BUILD</span>
+							<h3>不可变镜像</h3>
+							<p>镜像按 UTC 时间与 Git commit 标记；发布只替换发生变化的服务。</p>
+						</article>
+						<article>
+							<span>02 / VERIFY</span>
+							<h3>分层验证</h3>
+							<p>静态检查、单元测试、真实 Docker、完整 E2E、镜像审计与公开路径冒烟。</p>
+						</article>
+						<article>
+							<span>03 / OBSERVE</span>
+							<h3>事件优先</h3>
+							<p>每轮上下文、模型、工具和完成状态进入运行事件，便于重放与实验比较。</p>
+						</article>
+						<article>
+							<span>04 / ROLLBACK</span>
+							<h3>保留上个版本</h3>
+							<p>配置先备份，旧镜像不覆盖；验证失败时恢复镜像引用即可回退。</p>
+						</article>
+					</div>
+				</section>
+
+				<section class="section timeline-section" id="timeline">
+					<div class="section-heading">
+						<div>
+							<span class="section-index">08 / PROJECT HISTORY</span>
+							<h2>从业务 Agent 到<br />通用实验平台</h2>
+						</div>
+						<p>
+							项目按“干净重建”推进，不保留旧业务 Skill 和旧 API 兼容层。下面记录已经改变系统性质的关键决策。
+						</p>
+					</div>
+
+					<ol class="timeline">
+						<li>
+							<span>01</span>
+							<div><small>FOUNDATION</small><h3>重建为多人 Web Agent</h3><p>Open WebUI 承担账户和聊天外壳，自研 Runtime 承担 Agent 能力。</p></div>
+						</li>
+						<li>
+							<span>02</span>
+							<div><small>PRODUCT</small><h3>收敛为单一 Agent 路径</h3><p>删除 Chat / Work 双模式，降低交互和后端维护成本。</p></div>
+						</li>
+						<li>
+							<span>03</span>
+							<div><small>EXECUTION</small><h3>迁移到远端持久工作区</h3><p>接入 home-node-itx，打通每用户容器、持久卷与文件交付。</p></div>
+						</li>
+						<li>
+							<span>04</span>
+							<div><small>RELIABILITY</small><h3>建立证据驱动的完成策略</h3><p>加入恢复、重试守卫、精确报告证据和结构化事件。</p></div>
+						</li>
+						<li>
+							<span>05</span>
+							<div><small>PLATFORM</small><h3>补齐 Python 环境与长期身份</h3><p>持久化虚拟环境、pipefail、900 秒工具超时和每次调用的新鲜身份令牌。</p></div>
+						</li>
+						<li class="is-current">
+							<span>06</span>
+							<div><small>NOW</small><h3>文档与实验成为产品界面</h3><p>架构、实现、运维和实验台账随代码发布到同域门户。</p></div>
+						</li>
+					</ol>
+				</section>
+
+				<section class="section repository-section" id="repository">
+					<div class="repository-panel">
+						<div>
+							<span class="section-index">09 / REPOSITORY</span>
+							<h2>网页负责建立心智模型，<br />仓库文档负责成为事实来源。</h2>
+							<p>
+								所有设计说明、限制、运维步骤和实验规范都与代码一同提交。门户是摘要，
+								Markdown 文档是评审与变更时的正式依据。
+							</p>
+							<a class="button button-light" href="https://git.k1412.top/wuyang/zk-data-agent">
+								打开 Git 仓库 <span aria-hidden="true">↗</span>
+							</a>
+						</div>
+						<div class="doc-list">
+							<a href="https://git.k1412.top/wuyang/zk-data-agent">
+								<span>README.md</span><small>产品入口与快速开始</small>
+							</a>
+							<a href="https://git.k1412.top/wuyang/zk-data-agent">
+								<span>docs/architecture.md</span><small>系统边界与请求生命周期</small>
+							</a>
+							<a href="https://git.k1412.top/wuyang/zk-data-agent">
+								<span>docs/agent-loop.md</span><small>Loop、调度、证据与委派</small>
+							</a>
+							<a href="https://git.k1412.top/wuyang/zk-data-agent">
+								<span>docs/experiments.md</span><small>实验方法与路线图</small>
+							</a>
+							<a href="https://git.k1412.top/wuyang/zk-data-agent">
+								<span>docs/operations.md</span><small>发布、恢复与故障处理</small>
+							</a>
+							<a href="https://git.k1412.top/wuyang/zk-data-agent">
+								<span>docs/security.md</span><small>威胁边界与安全控制</small>
+							</a>
+						</div>
+					</div>
+				</section>
+			</main>
+		</div>
+
+		<footer>
+			<span>K1412 AGENT / SYSTEM NOTES</span>
+			<p>代码、文档与实验共同演进。</p>
+			<a href="#overview">回到顶部 ↑</a>
+		</footer>
+	</body>
+</html>
diff --git a/docs/site/og.png b/docs/site/og.png
new file mode 100644
index 0000000..1f88c9a
Binary files /dev/null and b/docs/site/og.png differ
diff --git a/docs/site/styles.css b/docs/site/styles.css
new file mode 100644
index 0000000..5d655d3
--- /dev/null
+++ b/docs/site/styles.css
@@ -0,0 +1,1688 @@
+:root {
+	--paper: #f2f0e9;
+	--paper-deep: #e7e3d8;
+	--ink: #151713;
+	--muted: #676a62;
+	--line: rgba(21, 23, 19, 0.16);
+	--green: #b8f23d;
+	--green-dark: #83b611;
+	--blue: #5c77ff;
+	--orange: #ff6c3d;
+	--dark: #141713;
+	--dark-raised: #20241e;
+	--white: #fffefa;
+	--sidebar-width: 224px;
+	--topbar-height: 78px;
+	--radius: 3px;
+	font-family:
+		Inter, ui-sans-serif, -apple-system, BlinkMacSystemFont, "Segoe UI", "PingFang SC",
+		"Hiragino Sans GB", "Microsoft YaHei", sans-serif;
+	color: var(--ink);
+	background: var(--paper);
+	font-synthesis: none;
+}
+
+* {
+	box-sizing: border-box;
+}
+
+html {
+	scroll-behavior: smooth;
+	scroll-padding-top: calc(var(--topbar-height) + 18px);
+}
+
+body {
+	margin: 0;
+	background:
+		linear-gradient(rgba(21, 23, 19, 0.035) 1px, transparent 1px),
+		linear-gradient(90deg, rgba(21, 23, 19, 0.035) 1px, transparent 1px), var(--paper);
+	background-size: 24px 24px;
+	color: var(--ink);
+}
+
+a {
+	color: inherit;
+	text-decoration: none;
+}
+
+button,
+input {
+	font: inherit;
+}
+
+button {
+	color: inherit;
+}
+
+code {
+	padding: 0.12em 0.32em;
+	border: 1px solid var(--line);
+	background: rgba(255, 255, 255, 0.46);
+	font-family: "SFMono-Regular", Consolas, "Liberation Mono", monospace;
+	font-size: 0.88em;
+}
+
+.sr-only {
+	position: absolute;
+	width: 1px;
+	height: 1px;
+	padding: 0;
+	margin: -1px;
+	overflow: hidden;
+	clip: rect(0, 0, 0, 0);
+	white-space: nowrap;
+	border: 0;
+}
+
+.skip-link {
+	position: fixed;
+	z-index: 200;
+	top: 8px;
+	left: 8px;
+	padding: 10px 14px;
+	transform: translateY(-150%);
+	background: var(--green);
+	font-weight: 800;
+}
+
+.skip-link:focus {
+	transform: translateY(0);
+}
+
+.topbar {
+	position: fixed;
+	z-index: 100;
+	top: 0;
+	right: 0;
+	left: 0;
+	height: var(--topbar-height);
+	display: flex;
+	align-items: center;
+	justify-content: space-between;
+	padding: 0 28px;
+	border-bottom: 1px solid var(--line);
+	background: rgba(242, 240, 233, 0.93);
+	backdrop-filter: blur(16px);
+}
+
+.brand {
+	display: inline-flex;
+	align-items: center;
+	gap: 12px;
+}
+
+.brand-mark {
+	display: grid;
+	width: 38px;
+	height: 38px;
+	place-items: center;
+	border: 1px solid var(--ink);
+	background: var(--green);
+	font-size: 20px;
+	font-weight: 900;
+}
+
+.brand strong,
+.brand small {
+	display: block;
+}
+
+.brand strong {
+	font-size: 14px;
+	letter-spacing: -0.01em;
+}
+
+.brand small {
+	margin-top: 2px;
+	color: var(--muted);
+	font-family: "SFMono-Regular", Consolas, monospace;
+	font-size: 9px;
+	letter-spacing: 0.08em;
+}
+
+.topbar-actions {
+	display: flex;
+	align-items: center;
+	gap: 10px;
+}
+
+.system-status {
+	display: inline-flex;
+	align-items: center;
+	gap: 7px;
+	margin-right: 8px;
+	color: var(--muted);
+	font-family: "SFMono-Regular", Consolas, monospace;
+	font-size: 10px;
+	letter-spacing: 0.06em;
+	text-transform: uppercase;
+}
+
+.system-status i {
+	width: 7px;
+	height: 7px;
+	border-radius: 999px;
+	background: var(--green-dark);
+	box-shadow: 0 0 0 4px rgba(131, 182, 17, 0.12);
+}
+
+.button {
+	display: inline-flex;
+	min-height: 40px;
+	align-items: center;
+	justify-content: center;
+	gap: 18px;
+	padding: 0 16px;
+	border: 1px solid var(--ink);
+	border-radius: var(--radius);
+	font-size: 12px;
+	font-weight: 750;
+	transition:
+		transform 160ms ease,
+		box-shadow 160ms ease,
+		background 160ms ease;
+}
+
+.button:hover {
+	transform: translateY(-2px);
+	box-shadow: 3px 3px 0 var(--ink);
+}
+
+.button-primary {
+	background: var(--green);
+}
+
+.button-quiet {
+	border-color: var(--line);
+	background: transparent;
+}
+
+.button-dark {
+	min-height: 48px;
+	padding: 0 20px;
+	background: var(--dark);
+	color: var(--white);
+}
+
+.button-light {
+	margin-top: 28px;
+	background: var(--white);
+	color: var(--ink);
+}
+
+.nav-toggle {
+	display: none;
+	width: 42px;
+	height: 40px;
+	border: 1px solid var(--ink);
+	background: transparent;
+}
+
+.nav-toggle span {
+	display: block;
+	width: 18px;
+	height: 1px;
+	margin: 5px auto;
+	background: currentColor;
+}
+
+.page-shell {
+	display: grid;
+	grid-template-columns: var(--sidebar-width) minmax(0, 1fr);
+	padding-top: var(--topbar-height);
+}
+
+.sidebar {
+	position: sticky;
+	top: var(--topbar-height);
+	height: calc(100vh - var(--topbar-height));
+	display: flex;
+	flex-direction: column;
+	justify-content: space-between;
+	padding: 36px 22px 24px;
+	border-right: 1px solid var(--line);
+	background: rgba(242, 240, 233, 0.75);
+}
+
+.nav-label {
+	margin: 0 0 10px 12px;
+	color: #8a8c84;
+	font-family: "SFMono-Regular", Consolas, monospace;
+	font-size: 9px;
+	letter-spacing: 0.16em;
+	text-transform: uppercase;
+}
+
+.nav-label:not(:first-child) {
+	margin-top: 30px;
+}
+
+.nav-link {
+	position: relative;
+	display: flex;
+	align-items: center;
+	gap: 11px;
+	padding: 8px 11px;
+	border-radius: var(--radius);
+	color: #565950;
+	font-size: 12px;
+	font-weight: 650;
+	transition:
+		background 140ms ease,
+		color 140ms ease;
+}
+
+.nav-link span {
+	color: #999b94;
+	font-family: "SFMono-Regular", Consolas, monospace;
+	font-size: 9px;
+}
+
+.nav-link:hover,
+.nav-link.is-active {
+	background: var(--ink);
+	color: var(--white);
+}
+
+.nav-link.is-active span {
+	color: var(--green);
+}
+
+.sidebar-note {
+	padding: 15px;
+	border: 1px solid var(--line);
+	border-left: 3px solid var(--green-dark);
+	background: rgba(255, 255, 255, 0.36);
+}
+
+.sidebar-note span {
+	color: var(--green-dark);
+	font-family: "SFMono-Regular", Consolas, monospace;
+	font-size: 9px;
+	letter-spacing: 0.12em;
+}
+
+.sidebar-note p {
+	margin: 8px 0 0;
+	font-size: 12px;
+	line-height: 1.55;
+}
+
+main {
+	min-width: 0;
+}
+
+.section {
+	position: relative;
+	padding: 100px clamp(40px, 7vw, 110px);
+	border-bottom: 1px solid var(--line);
+}
+
+.section-heading {
+	display: grid;
+	grid-template-columns: minmax(420px, 1.15fr) minmax(280px, 0.85fr);
+	gap: 70px;
+	align-items: end;
+	margin-bottom: 60px;
+}
+
+.section-heading h2 {
+	max-width: 780px;
+	margin: 15px 0 0;
+	font-size: clamp(43px, 5.4vw, 76px);
+	font-weight: 720;
+	letter-spacing: -0.06em;
+	line-height: 0.98;
+}
+
+.section-heading > p {
+	max-width: 520px;
+	margin: 0;
+	color: var(--muted);
+	font-size: 14px;
+	line-height: 1.8;
+}
+
+.section-index,
+.eyebrow {
+	color: var(--green-dark);
+	font-family: "SFMono-Regular", Consolas, monospace;
+	font-size: 10px;
+	font-weight: 700;
+	letter-spacing: 0.14em;
+	text-transform: uppercase;
+}
+
+.hero {
+	min-height: calc(100vh - var(--topbar-height));
+	display: flex;
+	flex-direction: column;
+	justify-content: center;
+	overflow: hidden;
+	padding-top: 115px;
+	padding-bottom: 58px;
+}
+
+.hero::after {
+	position: absolute;
+	z-index: -1;
+	top: 70px;
+	right: -120px;
+	width: min(36vw, 500px);
+	aspect-ratio: 1;
+	border: 1px solid rgba(21, 23, 19, 0.1);
+	border-radius: 50%;
+	box-shadow:
+		0 0 0 80px rgba(184, 242, 61, 0.07),
+		0 0 0 160px rgba(92, 119, 255, 0.035);
+	content: "";
+}
+
+.eyebrow span {
+	padding: 5px 8px;
+	background: var(--green);
+	color: var(--ink);
+}
+
+.hero h1 {
+	max-width: 1040px;
+	margin: 26px 0 28px;
+	font-size: clamp(64px, 8.3vw, 124px);
+	font-weight: 720;
+	letter-spacing: -0.075em;
+	line-height: 0.86;
+}
+
+.hero-copy {
+	max-width: 740px;
+	margin: 0;
+	color: #4e5149;
+	font-size: clamp(16px, 1.45vw, 20px);
+	line-height: 1.75;
+}
+
+.hero-actions {
+	display: flex;
+	align-items: center;
+	gap: 28px;
+	margin-top: 36px;
+}
+
+.text-link {
+	display: inline-flex;
+	gap: 12px;
+	align-items: center;
+	padding: 7px 0;
+	border-bottom: 1px solid var(--ink);
+	font-size: 13px;
+	font-weight: 750;
+}
+
+.metric-strip {
+	display: grid;
+	grid-template-columns: repeat(4, minmax(0, 1fr));
+	margin-top: auto;
+	padding-top: 70px;
+}
+
+.metric-strip > div {
+	min-height: 112px;
+	padding: 18px 20px;
+	border-top: 1px solid var(--ink);
+	border-right: 1px solid var(--line);
+}
+
+.metric-strip > div:first-child {
+	padding-left: 0;
+}
+
+.metric-strip strong,
+.metric-strip span,
+.metric-strip small {
+	display: block;
+}
+
+.metric-strip strong {
+	margin-bottom: 17px;
+	font-family: "SFMono-Regular", Consolas, monospace;
+	font-size: 20px;
+	letter-spacing: -0.04em;
+}
+
+.metric-strip span {
+	font-size: 13px;
+	font-weight: 760;
+}
+
+.metric-strip small {
+	margin-top: 5px;
+	color: var(--muted);
+	font-size: 10px;
+}
+
+.architecture-lab {
+	border: 1px solid var(--line);
+	background: #e9e6dd;
+	box-shadow: 8px 8px 0 rgba(21, 23, 19, 0.06);
+}
+
+.flow-tabs {
+	display: flex;
+	border-bottom: 1px solid var(--line);
+	background: rgba(255, 255, 255, 0.38);
+}
+
+.flow-tab {
+	padding: 15px 22px;
+	border: 0;
+	border-right: 1px solid var(--line);
+	background: transparent;
+	color: var(--muted);
+	font-size: 11px;
+	font-weight: 750;
+	cursor: pointer;
+}
+
+.flow-tab:hover,
+.flow-tab.is-active {
+	background: var(--ink);
+	color: var(--white);
+}
+
+.system-map {
+	display: grid;
+	grid-template-columns: 0.8fr 1.35fr 0.85fr;
+	min-height: 500px;
+	padding: 32px;
+	gap: 14px;
+}
+
+.map-lane {
+	position: relative;
+	display: flex;
+	gap: 12px;
+	flex-direction: column;
+	justify-content: center;
+	padding: 44px 16px 20px;
+	border: 1px dashed rgba(21, 23, 19, 0.2);
+	background: rgba(255, 255, 255, 0.35);
+}
+
+.lane-label {
+	position: absolute;
+	top: 14px;
+	left: 16px;
+	color: #8b8d86;
+	font-family: "SFMono-Regular", Consolas, monospace;
+	font-size: 8px;
+	letter-spacing: 0.12em;
+}
+
+.map-arrow {
+	align-self: center;
+	color: #8c8e87;
+	font-family: monospace;
+}
+
+.system-node {
+	position: relative;
+	z-index: 1;
+	padding: 16px;
+	border: 1px solid rgba(21, 23, 19, 0.28);
+	background: var(--paper);
+	transition:
+		border-color 180ms ease,
+		box-shadow 180ms ease,
+		transform 180ms ease,
+		opacity 180ms ease;
+}
+
+.system-node small,
+.system-node strong,
+.system-node span {
+	display: block;
+}
+
+.system-node small {
+	margin-bottom: 14px;
+	color: #898b83;
+	font-family: "SFMono-Regular", Consolas, monospace;
+	font-size: 8px;
+	letter-spacing: 0.08em;
+}
+
+.system-node strong {
+	font-size: 16px;
+}
+
+.system-node span {
+	margin-top: 5px;
+	color: var(--muted);
+	font-size: 9px;
+	line-height: 1.45;
+}
+
+.node-runtime {
+	border-color: var(--green-dark);
+	background: #e4f9b7;
+}
+
+.node-web {
+	background: #dfe4ff;
+}
+
+.node-workspace {
+	background: #ffe1d8;
+}
+
+.node-store {
+	margin-top: 14px;
+}
+
+.system-map.has-selection .system-node:not(.is-flow-active) {
+	opacity: 0.3;
+}
+
+.system-node.is-flow-active {
+	z-index: 2;
+	border-color: var(--ink);
+	box-shadow: 4px 4px 0 var(--ink);
+	transform: translate(-2px, -2px);
+}
+
+.flow-explainer {
+	display: grid;
+	grid-template-columns: 210px 1fr;
+	gap: 22px;
+	padding: 22px 28px;
+	border-top: 1px solid var(--line);
+	background: var(--ink);
+	color: var(--white);
+}
+
+.flow-explainer span {
+	color: var(--green);
+	font-family: "SFMono-Regular", Consolas, monospace;
+	font-size: 9px;
+	letter-spacing: 0.1em;
+}
+
+.flow-explainer p {
+	max-width: 780px;
+	margin: 0;
+	color: #d6d7d1;
+	font-size: 12px;
+	line-height: 1.7;
+}
+
+.boundary-grid {
+	display: grid;
+	grid-template-columns: repeat(3, 1fr);
+	margin-top: 34px;
+}
+
+.boundary-grid article {
+	position: relative;
+	min-height: 245px;
+	padding: 32px;
+	border-top: 1px solid var(--ink);
+	border-right: 1px solid var(--line);
+	background: rgba(255, 255, 255, 0.3);
+}
+
+.boundary-number {
+	display: grid;
+	width: 28px;
+	height: 28px;
+	place-items: center;
+	border: 1px solid var(--ink);
+	font-family: monospace;
+	font-size: 10px;
+}
+
+.boundary-grid h3 {
+	margin: 35px 0 12px;
+	font-size: 20px;
+}
+
+.boundary-grid p {
+	margin: 0;
+	color: var(--muted);
+	font-size: 12px;
+	line-height: 1.7;
+}
+
+.boundary-grid small {
+	position: absolute;
+	bottom: 24px;
+	color: var(--green-dark);
+	font-family: monospace;
+	font-size: 8px;
+	letter-spacing: 0.1em;
+}
+
+.loop-section,
+.operations-section {
+	background:
+		linear-gradient(rgba(255, 255, 255, 0.035) 1px, transparent 1px),
+		linear-gradient(90deg, rgba(255, 255, 255, 0.035) 1px, transparent 1px), var(--dark);
+	background-size: 24px 24px;
+	color: var(--white);
+}
+
+.inverse-heading > p {
+	color: #afb2aa;
+}
+
+.inverse-heading code {
+	border-color: rgba(255, 255, 255, 0.16);
+	background: rgba(255, 255, 255, 0.08);
+}
+
+.loop-console {
+	border: 1px solid rgba(255, 255, 255, 0.16);
+	background: #1b1e1a;
+}
+
+.loop-stages {
+	display: grid;
+	grid-template-columns: repeat(6, 1fr);
+	border-bottom: 1px solid rgba(255, 255, 255, 0.14);
+}
+
+.loop-stage {
+	min-width: 0;
+	padding: 22px 16px;
+	border: 0;
+	border-right: 1px solid rgba(255, 255, 255, 0.1);
+	background: transparent;
+	color: #8e9289;
+	text-align: left;
+	cursor: pointer;
+}
+
+.loop-stage span,
+.loop-stage strong,
+.loop-stage small {
+	display: block;
+}
+
+.loop-stage span {
+	margin-bottom: 24px;
+	font-family: monospace;
+	font-size: 9px;
+}
+
+.loop-stage strong {
+	color: #c9cbc5;
+	font-size: 12px;
+}
+
+.loop-stage small {
+	margin-top: 5px;
+	font-size: 9px;
+}
+
+.loop-stage:hover,
+.loop-stage.is-active {
+	background: var(--green);
+	color: #587d08;
+}
+
+.loop-stage.is-active strong,
+.loop-stage:hover strong {
+	color: var(--ink);
+}
+
+.loop-detail {
+	display: grid;
+	grid-template-columns: 1.1fr 1fr 0.85fr;
+	gap: 55px;
+	min-height: 240px;
+	padding: 42px;
+	align-items: start;
+}
+
+.detail-label {
+	color: var(--green);
+	font-family: monospace;
+	font-size: 9px;
+	letter-spacing: 0.1em;
+}
+
+.loop-detail h3 {
+	margin: 16px 0 0;
+	font-size: clamp(25px, 2.5vw, 38px);
+	font-weight: 660;
+	letter-spacing: -0.035em;
+	line-height: 1.16;
+}
+
+.loop-detail > p {
+	margin: 24px 0 0;
+	color: #b1b4ad;
+	font-size: 12px;
+	line-height: 1.75;
+}
+
+.loop-detail ul {
+	margin: 24px 0 0;
+	padding: 0;
+	list-style: none;
+}
+
+.loop-detail li {
+	position: relative;
+	padding: 9px 0 9px 17px;
+	border-bottom: 1px solid rgba(255, 255, 255, 0.1);
+	color: #d7d9d3;
+	font-size: 10px;
+	line-height: 1.55;
+}
+
+.loop-detail li::before {
+	position: absolute;
+	top: 14px;
+	left: 0;
+	width: 5px;
+	height: 5px;
+	background: var(--green);
+	content: "";
+}
+
+.loop-principles {
+	display: grid;
+	grid-template-columns: repeat(3, 1fr);
+	margin-top: 28px;
+}
+
+.loop-principles article {
+	min-height: 230px;
+	padding: 29px;
+	border: 1px solid rgba(255, 255, 255, 0.14);
+	border-right: 0;
+}
+
+.loop-principles article:last-child {
+	border-right: 1px solid rgba(255, 255, 255, 0.14);
+}
+
+.loop-principles span,
+.ops-grid span {
+	color: var(--green);
+	font-family: monospace;
+	font-size: 9px;
+	letter-spacing: 0.1em;
+}
+
+.loop-principles h3,
+.ops-grid h3 {
+	margin: 44px 0 12px;
+	font-size: 19px;
+}
+
+.loop-principles p,
+.ops-grid p {
+	margin: 0;
+	color: #aeb1a9;
+	font-size: 11px;
+	line-height: 1.7;
+}
+
+.loop-principles code {
+	border-color: rgba(255, 255, 255, 0.17);
+	background: transparent;
+}
+
+.evidence-table {
+	margin-top: 46px;
+	border-top: 1px solid rgba(255, 255, 255, 0.34);
+}
+
+.table-row {
+	display: grid;
+	grid-template-columns: 0.7fr 1.25fr 1fr;
+	padding: 16px 10px;
+	border-bottom: 1px solid rgba(255, 255, 255, 0.1);
+	color: #aeb1a9;
+	font-size: 11px;
+}
+
+.table-row strong {
+	color: var(--white);
+	font-size: 11px;
+}
+
+.table-head {
+	color: var(--green);
+	font-family: monospace;
+	font-size: 9px;
+	letter-spacing: 0.07em;
+}
+
+.isolation-visual {
+	display: grid;
+	grid-template-columns: minmax(230px, 0.8fr) auto minmax(330px, 1.2fr);
+	gap: 30px;
+	align-items: center;
+	max-width: 1000px;
+	margin: 0 auto 52px;
+}
+
+.identity-card,
+.workspace-stack {
+	border: 1px solid var(--ink);
+	box-shadow: 6px 6px 0 rgba(21, 23, 19, 0.1);
+}
+
+.identity-card {
+	padding: 30px;
+	background: var(--green);
+}
+
+.identity-card small,
+.identity-card strong,
+.identity-card code {
+	display: block;
+}
+
+.identity-card small {
+	font-family: monospace;
+	font-size: 8px;
+	letter-spacing: 0.1em;
+}
+
+.identity-card strong {
+	margin: 27px 0 12px;
+	font-size: 20px;
+}
+
+.identity-card code {
+	border-color: rgba(21, 23, 19, 0.4);
+	background: transparent;
+	font-size: 10px;
+}
+
+.identity-arrow {
+	font-size: 24px;
+}
+
+.workspace-stack {
+	padding: 12px;
+	background: var(--ink);
+	color: var(--white);
+}
+
+.workspace-stack > div {
+	display: grid;
+	grid-template-columns: 100px 1fr;
+	gap: 12px;
+	padding: 15px;
+	border-bottom: 1px solid rgba(255, 255, 255, 0.12);
+}
+
+.workspace-stack > div:last-child {
+	border-bottom: 0;
+}
+
+.workspace-stack span {
+	color: var(--green);
+	font-family: monospace;
+	font-size: 8px;
+	letter-spacing: 0.1em;
+}
+
+.workspace-stack code {
+	border: 0;
+	background: transparent;
+	color: #cfd1ca;
+	font-size: 10px;
+}
+
+.security-grid {
+	display: grid;
+	grid-template-columns: repeat(4, 1fr);
+}
+
+.security-grid article {
+	min-height: 250px;
+	padding: 24px;
+	border-top: 1px solid var(--ink);
+	border-right: 1px solid var(--line);
+}
+
+.security-icon {
+	display: inline-block;
+	padding: 4px 6px;
+	background: var(--ink);
+	color: var(--green);
+	font-family: monospace;
+	font-size: 9px;
+}
+
+.security-grid h3 {
+	margin: 46px 0 12px;
+	font-size: 17px;
+	line-height: 1.3;
+}
+
+.security-grid p {
+	margin: 0;
+	color: var(--muted);
+	font-size: 11px;
+	line-height: 1.7;
+}
+
+.models-section {
+	background: #e8e5dc;
+}
+
+.model-grid {
+	display: grid;
+	grid-template-columns: repeat(4, 1fr);
+	gap: 12px;
+}
+
+.model-card {
+	min-height: 310px;
+	padding: 25px;
+	border: 1px solid var(--line);
+	background: rgba(255, 255, 255, 0.55);
+}
+
+.model-card.is-default {
+	border-color: var(--ink);
+	box-shadow: 5px 5px 0 var(--ink);
+	transform: translateY(-5px);
+}
+
+.model-card > div:first-child {
+	display: flex;
+	align-items: center;
+	justify-content: space-between;
+}
+
+.model-card small {
+	font-family: monospace;
+	font-size: 8px;
+	letter-spacing: 0.08em;
+}
+
+.model-dot {
+	width: 10px;
+	height: 10px;
+	border: 1px solid var(--ink);
+	border-radius: 50%;
+}
+
+.model-dot.luna {
+	background: #c8c8c8;
+}
+
+.model-dot.terra {
+	background: var(--green);
+}
+
+.model-dot.sol {
+	background: var(--orange);
+}
+
+.model-dot.deepseek {
+	background: var(--blue);
+}
+
+.model-card h3 {
+	margin: 55px 0 7px;
+	font-size: 30px;
+	letter-spacing: -0.04em;
+}
+
+.model-card p {
+	margin: 0;
+	color: var(--muted);
+	font-size: 11px;
+}
+
+.model-card dl {
+	margin: 55px 0 0;
+}
+
+.model-card dl div {
+	display: flex;
+	justify-content: space-between;
+	padding: 9px 0;
+	border-top: 1px solid var(--line);
+}
+
+.model-card dt,
+.model-card dd {
+	margin: 0;
+	font-size: 9px;
+}
+
+.model-card dt {
+	color: var(--muted);
+}
+
+.model-card dd {
+	font-family: monospace;
+}
+
+.model-deepseek {
+	background: #e4e8ff;
+}
+
+.policy-note {
+	display: grid;
+	grid-template-columns: 130px 1fr;
+	gap: 40px;
+	margin-top: 40px;
+	padding: 24px 0;
+	border-top: 1px solid var(--ink);
+	border-bottom: 1px solid var(--ink);
+}
+
+.policy-note span {
+	font-family: monospace;
+	font-size: 9px;
+	font-weight: 700;
+	letter-spacing: 0.1em;
+}
+
+.policy-note p {
+	max-width: 800px;
+	margin: 0;
+	color: var(--muted);
+	font-size: 12px;
+	line-height: 1.7;
+}
+
+.experiment-toolbar {
+	display: flex;
+	align-items: center;
+	justify-content: space-between;
+	gap: 24px;
+	margin-bottom: 30px;
+	padding-bottom: 20px;
+	border-bottom: 1px solid var(--ink);
+}
+
+.filter-group {
+	display: flex;
+	gap: 6px;
+}
+
+.filter-button {
+	padding: 9px 14px;
+	border: 1px solid var(--line);
+	background: transparent;
+	font-size: 10px;
+	font-weight: 700;
+	cursor: pointer;
+}
+
+.filter-button:hover,
+.filter-button.is-active {
+	border-color: var(--ink);
+	background: var(--ink);
+	color: var(--white);
+}
+
+.experiment-search {
+	position: relative;
+}
+
+.experiment-search input {
+	width: min(300px, 34vw);
+	padding: 10px 34px 10px 12px;
+	border: 1px solid var(--line);
+	border-radius: 0;
+	outline: none;
+	background: rgba(255, 255, 255, 0.45);
+	font-size: 11px;
+}
+
+.experiment-search input:focus {
+	border-color: var(--ink);
+	box-shadow: 2px 2px 0 var(--ink);
+}
+
+.experiment-search > span:last-child {
+	position: absolute;
+	top: 7px;
+	right: 12px;
+	font-size: 17px;
+}
+
+.experiment-grid {
+	display: grid;
+	grid-template-columns: repeat(2, minmax(0, 1fr));
+	gap: 14px;
+}
+
+.experiment-card {
+	display: grid;
+	grid-template-rows: auto auto 1fr auto;
+	min-height: 295px;
+	padding: 25px;
+	border: 1px solid var(--line);
+	background: rgba(255, 255, 255, 0.48);
+	transition:
+		transform 160ms ease,
+		box-shadow 160ms ease;
+}
+
+.experiment-card:hover {
+	transform: translate(-3px, -3px);
+	box-shadow: 5px 5px 0 var(--ink);
+}
+
+.experiment-meta {
+	display: flex;
+	align-items: center;
+	justify-content: space-between;
+	font-family: monospace;
+	font-size: 8px;
+	letter-spacing: 0.07em;
+}
+
+.status-badge {
+	padding: 5px 7px;
+	border: 1px solid var(--ink);
+}
+
+.status-baseline {
+	background: #dddcd5;
+}
+
+.status-validated {
+	background: var(--green);
+}
+
+.status-backlog {
+	background: #e3e7ff;
+}
+
+.experiment-card h3 {
+	max-width: 530px;
+	margin: 37px 0 11px;
+	font-size: 22px;
+	letter-spacing: -0.03em;
+	line-height: 1.2;
+}
+
+.experiment-card > p {
+	margin: 0;
+	color: var(--muted);
+	font-size: 11px;
+	line-height: 1.7;
+}
+
+.experiment-footer {
+	display: flex;
+	flex-wrap: wrap;
+	gap: 7px;
+	align-items: end;
+	margin-top: 28px;
+}
+
+.experiment-footer span {
+	padding: 5px 7px;
+	border: 1px solid var(--line);
+	color: var(--muted);
+	font-family: monospace;
+	font-size: 8px;
+}
+
+.experiment-loading,
+.experiment-empty {
+	grid-column: 1 / -1;
+	padding: 50px;
+	border: 1px dashed var(--line);
+	color: var(--muted);
+	text-align: center;
+	font-size: 12px;
+}
+
+.experiment-count {
+	margin: 18px 0 0;
+	color: var(--muted);
+	font-family: monospace;
+	font-size: 9px;
+	text-align: right;
+}
+
+.deployment-path {
+	display: grid;
+	grid-template-columns: repeat(7, auto);
+	align-items: center;
+	justify-content: space-between;
+	padding: 26px;
+	border: 1px solid rgba(255, 255, 255, 0.16);
+	background: var(--dark-raised);
+}
+
+.deployment-path div small,
+.deployment-path div strong {
+	display: block;
+}
+
+.deployment-path div small {
+	color: var(--green);
+	font-family: monospace;
+	font-size: 8px;
+	letter-spacing: 0.1em;
+}
+
+.deployment-path div strong {
+	margin-top: 9px;
+	font-family: monospace;
+	font-size: 11px;
+}
+
+.deployment-path > span {
+	color: #686d63;
+}
+
+.ops-grid {
+	display: grid;
+	grid-template-columns: repeat(4, 1fr);
+	margin-top: 28px;
+}
+
+.ops-grid article {
+	min-height: 220px;
+	padding: 26px;
+	border-top: 1px solid rgba(255, 255, 255, 0.24);
+	border-right: 1px solid rgba(255, 255, 255, 0.12);
+}
+
+.timeline {
+	margin: 0;
+	padding: 0;
+	border-top: 1px solid var(--ink);
+	list-style: none;
+}
+
+.timeline li {
+	display: grid;
+	grid-template-columns: 90px 1fr;
+	min-height: 145px;
+	padding: 28px 0;
+	border-bottom: 1px solid var(--line);
+}
+
+.timeline li > span {
+	width: 32px;
+	height: 32px;
+	display: grid;
+	place-items: center;
+	border: 1px solid var(--ink);
+	font-family: monospace;
+	font-size: 9px;
+}
+
+.timeline li.is-current > span {
+	background: var(--green);
+	box-shadow: 3px 3px 0 var(--ink);
+}
+
+.timeline div {
+	display: grid;
+	grid-template-columns: 130px 0.8fr 1fr;
+	gap: 35px;
+	align-items: start;
+}
+
+.timeline small {
+	color: var(--green-dark);
+	font-family: monospace;
+	font-size: 8px;
+	letter-spacing: 0.1em;
+}
+
+.timeline h3 {
+	margin: 0;
+	font-size: 18px;
+}
+
+.timeline p {
+	max-width: 540px;
+	margin: 0;
+	color: var(--muted);
+	font-size: 11px;
+	line-height: 1.7;
+}
+
+.repository-section {
+	padding: 70px clamp(40px, 7vw, 110px);
+	background: var(--green);
+}
+
+.repository-panel {
+	display: grid;
+	grid-template-columns: 1fr 0.85fr;
+	gap: 80px;
+	padding: 60px;
+	background: var(--ink);
+	color: var(--white);
+}
+
+.repository-panel h2 {
+	margin: 20px 0 22px;
+	font-size: clamp(34px, 4.4vw, 62px);
+	font-weight: 680;
+	letter-spacing: -0.055em;
+	line-height: 1.02;
+}
+
+.repository-panel > div:first-child > p {
+	max-width: 610px;
+	margin: 0;
+	color: #b5b8b0;
+	font-size: 12px;
+	line-height: 1.75;
+}
+
+.doc-list {
+	border-top: 1px solid rgba(255, 255, 255, 0.32);
+}
+
+.doc-list a {
+	position: relative;
+	display: grid;
+	grid-template-columns: 1fr 1fr;
+	gap: 20px;
+	padding: 17px 0;
+	border-bottom: 1px solid rgba(255, 255, 255, 0.13);
+	transition: padding 150ms ease;
+}
+
+.doc-list a::after {
+	position: absolute;
+	right: 0;
+	color: var(--green);
+	content: "↗";
+}
+
+.doc-list a:hover {
+	padding-left: 8px;
+}
+
+.doc-list span {
+	font-family: monospace;
+	font-size: 10px;
+}
+
+.doc-list small {
+	padding-right: 20px;
+	color: #8f9389;
+	font-size: 9px;
+}
+
+footer {
+	display: grid;
+	grid-template-columns: 1fr 1fr auto;
+	gap: 30px;
+	padding: 34px 36px;
+	background: var(--ink);
+	color: var(--white);
+}
+
+footer span,
+footer a {
+	font-family: monospace;
+	font-size: 9px;
+	letter-spacing: 0.09em;
+}
+
+footer p {
+	margin: 0;
+	color: #8f928a;
+	font-size: 10px;
+}
+
+footer a {
+	color: var(--green);
+}
+
+@media (max-width: 1120px) {
+	:root {
+		--sidebar-width: 194px;
+	}
+
+	.section {
+		padding-right: 48px;
+		padding-left: 48px;
+	}
+
+	.system-map {
+		grid-template-columns: 1fr;
+	}
+
+	.map-lane {
+		display: grid;
+		grid-template-columns: repeat(2, 1fr);
+		padding-top: 52px;
+	}
+
+	.map-arrow {
+		display: none;
+	}
+
+	.loop-stages {
+		grid-template-columns: repeat(3, 1fr);
+	}
+
+	.loop-detail {
+		grid-template-columns: 1fr 1fr;
+	}
+
+	.loop-detail ul {
+		grid-column: 1 / -1;
+		display: grid;
+		grid-template-columns: repeat(3, 1fr);
+		gap: 12px;
+	}
+
+	.security-grid,
+	.ops-grid,
+	.model-grid {
+		grid-template-columns: repeat(2, 1fr);
+	}
+
+	.deployment-path {
+		grid-template-columns: 1fr;
+		gap: 12px;
+	}
+
+	.deployment-path > span {
+		transform: rotate(90deg);
+		justify-self: start;
+	}
+}
+
+@media (max-width: 820px) {
+	:root {
+		--topbar-height: 66px;
+	}
+
+	.topbar {
+		padding: 0 14px;
+	}
+
+	.system-status,
+	.hide-mobile {
+		display: none;
+	}
+
+	.button-primary {
+		min-height: 38px;
+		padding: 0 12px;
+	}
+
+	.nav-toggle {
+		display: block;
+	}
+
+	.page-shell {
+		display: block;
+	}
+
+	.sidebar {
+		position: fixed;
+		z-index: 90;
+		top: var(--topbar-height);
+		right: 0;
+		left: 0;
+		height: calc(100vh - var(--topbar-height));
+		transform: translateX(-105%);
+		padding: 25px;
+		background: var(--paper);
+		transition: transform 220ms ease;
+	}
+
+	.sidebar.is-open {
+		transform: translateX(0);
+	}
+
+	.sidebar-note {
+		max-width: 280px;
+	}
+
+	.section {
+		padding: 72px 23px;
+	}
+
+	.section-heading {
+		grid-template-columns: 1fr;
+		gap: 28px;
+		margin-bottom: 42px;
+	}
+
+	.section-heading h2 {
+		font-size: clamp(40px, 12vw, 64px);
+	}
+
+	.hero {
+		min-height: calc(100svh - var(--topbar-height));
+		padding-top: 86px;
+	}
+
+	.hero h1 {
+		font-size: clamp(58px, 17vw, 92px);
+	}
+
+	.metric-strip {
+		grid-template-columns: repeat(2, 1fr);
+		padding-top: 60px;
+	}
+
+	.metric-strip > div:nth-child(3) {
+		padding-left: 0;
+	}
+
+	.flow-tabs {
+		display: grid;
+		grid-template-columns: repeat(2, 1fr);
+	}
+
+	.system-map {
+		padding: 14px;
+	}
+
+	.map-lane {
+		grid-template-columns: 1fr;
+	}
+
+	.flow-explainer {
+		grid-template-columns: 1fr;
+	}
+
+	.boundary-grid,
+	.loop-principles,
+	.experiment-grid {
+		grid-template-columns: 1fr;
+	}
+
+	.loop-stages {
+		grid-template-columns: repeat(2, 1fr);
+	}
+
+	.loop-detail {
+		grid-template-columns: 1fr;
+		padding: 28px;
+	}
+
+	.loop-detail ul {
+		grid-column: auto;
+		grid-template-columns: 1fr;
+	}
+
+	.isolation-visual {
+		grid-template-columns: 1fr;
+	}
+
+	.identity-arrow {
+		transform: rotate(90deg);
+		text-align: center;
+	}
+
+	.model-grid,
+	.security-grid,
+	.ops-grid {
+		grid-template-columns: 1fr;
+	}
+
+	.model-card.is-default {
+		transform: none;
+	}
+
+	.experiment-toolbar {
+		align-items: stretch;
+		flex-direction: column;
+	}
+
+	.filter-group {
+		overflow-x: auto;
+	}
+
+	.experiment-search input {
+		width: 100%;
+	}
+
+	.timeline li {
+		grid-template-columns: 48px 1fr;
+	}
+
+	.timeline div {
+		grid-template-columns: 1fr;
+		gap: 10px;
+	}
+
+	.repository-section {
+		padding: 20px;
+	}
+
+	.repository-panel {
+		grid-template-columns: 1fr;
+		gap: 54px;
+		padding: 35px 25px;
+	}
+
+	.doc-list a {
+		grid-template-columns: 1fr;
+		gap: 6px;
+	}
+
+	footer {
+		grid-template-columns: 1fr;
+	}
+}
+
+@media (prefers-reduced-motion: reduce) {
+	* {
+		scroll-behavior: auto !important;
+		transition-duration: 0.01ms !important;
+	}
+}
diff --git a/e2e/verify_stack.py b/e2e/verify_stack.py
index 4325b00..db6e2a5 100644
--- a/e2e/verify_stack.py
+++ b/e2e/verify_stack.py
@@ -149,6 +149,27 @@ def main() -> None:
         health.raise_for_status()
         assert health.json().get("status") is True
 
+        docs_entry = client.get("/doc", follow_redirects=False)
+        assert docs_entry.status_code in {307, 308}
+        assert docs_entry.headers["location"].endswith("/doc/")
+        docs = client.get("/doc/")
+        docs.raise_for_status()
+        assert "K1412 Agent · 架构、实现与实验" in docs.text
+        assert docs.headers["content-type"].startswith("text/html")
+        docs_style = client.get("/doc/styles.css")
+        docs_style.raise_for_status()
+        assert "--green: #b8f23d" in docs_style.text
+        docs_script = client.get("/doc/app.js")
+        docs_script.raise_for_status()
+        assert "safe-parallel-v1" in docs_script.text
+        docs_experiments = client.get("/doc/experiments.json")
+        docs_experiments.raise_for_status()
+        assert {item["status"] for item in docs_experiments.json()} == {
+            "baseline",
+            "validated",
+            "backlog",
+        }
+
         admin = _signin(client, ADMIN_EMAIL, ADMIN_PASSWORD)
         admin_token = admin["token"]
 
@@ -276,8 +297,8 @@ def main() -> None:
             assert legacy.status_code == 404, legacy.text
 
     print(
-        "E2E passed: auth approval, four Agent models, custom loop evidence, file downloads, "
-        "and per-user workspace isolation."
+        "E2E passed: public documentation, auth approval, four Agent models, custom loop "
+        "evidence, file downloads, and per-user workspace isolation."
     )
 
 
diff --git a/tests/test_docs_site.py b/tests/test_docs_site.py
new file mode 100644
index 0000000..294a65e
--- /dev/null
+++ b/tests/test_docs_site.py
@@ -0,0 +1,90 @@
+from __future__ import annotations
+
+import json
+from html.parser import HTMLParser
+from pathlib import Path
+from urllib.parse import urlparse
+
+SITE_ROOT = Path(__file__).parents[1] / "docs" / "site"
+ALLOWED_STATUSES = {"baseline", "validated", "backlog"}
+
+
+class SiteParser(HTMLParser):
+    def __init__(self) -> None:
+        super().__init__()
+        self.ids: set[str] = set()
+        self.references: list[str] = []
+
+    def handle_starttag(self, tag: str, attrs: list[tuple[str, str | None]]) -> None:
+        values = dict(attrs)
+        if values.get("id"):
+            self.ids.add(values["id"])
+        attribute = "href" if tag in {"a", "link"} else "src" if tag in {"script", "img"} else None
+        if attribute and values.get(attribute):
+            self.references.append(values[attribute])
+
+
+def _parser() -> SiteParser:
+    parser = SiteParser()
+    parser.feed((SITE_ROOT / "index.html").read_text())
+    return parser
+
+
+def test_docs_site_required_files_are_present() -> None:
+    for relative_path in ("index.html", "styles.css", "app.js", "experiments.json", "og.png"):
+        path = SITE_ROOT / relative_path
+        assert path.is_file(), relative_path
+        assert path.stat().st_size > 0, relative_path
+    assert (SITE_ROOT / "og.png").read_bytes().startswith(b"\x89PNG\r\n\x1a\n")
+
+
+def test_docs_site_local_links_and_anchors_resolve() -> None:
+    parser = _parser()
+    for reference in parser.references:
+        if reference.startswith("#"):
+            assert reference[1:] in parser.ids, reference
+            continue
+
+        parsed = urlparse(reference)
+        if parsed.scheme or parsed.netloc or reference.startswith("/"):
+            continue
+        if reference == "../static/favicon.svg":
+            continue
+
+        local_path = (SITE_ROOT / parsed.path).resolve()
+        assert local_path.is_relative_to(SITE_ROOT.resolve()), reference
+        assert local_path.is_file(), reference
+
+
+def test_docs_site_navigation_targets_every_top_level_section() -> None:
+    parser = _parser()
+    html = (SITE_ROOT / "index.html").read_text()
+    expected_sections = {
+        "overview",
+        "architecture",
+        "agent-loop",
+        "workspace",
+        "models",
+        "experiments",
+        "operations",
+        "timeline",
+        "repository",
+    }
+    assert expected_sections <= parser.ids
+    for section_id in expected_sections:
+        assert f'href="#{section_id}"' in html
+
+
+def test_experiment_ledger_has_unique_stable_records() -> None:
+    experiments = json.loads((SITE_ROOT / "experiments.json").read_text())
+    assert len(experiments) >= 5
+
+    ids = [item["id"] for item in experiments]
+    assert len(ids) == len(set(ids))
+    for item in experiments:
+        assert item["status"] in ALLOWED_STATUSES
+        assert item["title"].strip()
+        assert item["summary"].strip()
+        assert item["area"].strip()
+        assert item["version"].strip()
+        assert isinstance(item["metrics"], list)