@knightcodeai/cli-linux-arm64 0.9.1 → 0.9.3

package/bin/docs/compaction.md

@@ -1,13 +1,13 @@
-# Compaction & Branch Summarization
+# Compaction Reference
 
-LLMs have limited context windows. When conversations grow too long, KnightCode uses compaction to summarize older content while preserving recent work. This page covers both auto-compaction and branch summarization.
+This reference describes automatic compaction, branch summarization, persisted entries, and extension hooks. For the user workflow, see [Sessions and Context](sessions.md#manage-conversation-context).
 
 **Source files** ([knightcode](https://github.com/KnightCodeAI/knightcode)):
-- [`packages/coding-agent/src/core/compaction/compaction.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/coding-agent/src/core/compaction/compaction.ts) - Auto-compaction logic
-- [`packages/coding-agent/src/core/compaction/branch-summarization.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/coding-agent/src/core/compaction/branch-summarization.ts) - Branch summarization
-- [`packages/coding-agent/src/core/compaction/utils.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/coding-agent/src/core/compaction/utils.ts) - Shared utilities (file tracking, serialization)
-- [`packages/coding-agent/src/core/session-manager.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/coding-agent/src/core/session-manager.ts) - Entry types (`CompactionEntry`, `BranchSummaryEntry`)
-- [`packages/coding-agent/src/core/extensions/types.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/coding-agent/src/core/extensions/types.ts) - Extension event types
+- [`packages/cli/src/core/compaction/compaction.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/cli/src/core/compaction/compaction.ts) - Auto-compaction logic
+- [`packages/cli/src/core/compaction/branch-summarization.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/cli/src/core/compaction/branch-summarization.ts) - Branch summarization
+- [`packages/cli/src/core/compaction/utils.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/cli/src/core/compaction/utils.ts) - Shared utilities (file tracking, serialization)
+- [`packages/cli/src/core/session-manager.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/cli/src/core/session-manager.ts) - Entry types (`CompactionEntry`, `BranchSummaryEntry`)
+- [`packages/cli/src/core/extensions/types.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/cli/src/core/extensions/types.ts) - Extension event types
 
 For TypeScript definitions in your project, inspect `node_modules/@knightcodeai/cli/dist/`.
 
@@ -20,7 +20,7 @@ KnightCode has two summarization mechanisms:
 | Compaction | Context exceeds threshold, or `/compact` | Summarize old messages to free up context |
 | Branch summarization | `/tree` navigation | Preserve context when switching branches |
 
-Both use the same structured summary format and track file operations cumulatively. Compaction and branch-summary requests use fresh routing session IDs and, where supported by the provider, disable prompt-cache writes because these one-off prompts are unlikely to be reused.
+Both use closely related structured formats and track file operations cumulatively. Summarization requests disable prompt-cache writes because these one-off prompts are unlikely to be reused.
 
 ## Compaction
 
@@ -34,14 +34,16 @@ contextTokens > contextWindow - reserveTokens
 
 By default, `reserveTokens` is 16384 tokens (configurable in `~/.knightcode/agent/settings.json` or `<project-dir>/.knightcode/settings.json`). This leaves room for the LLM's response.
 
-During a multi-turn agent run, KnightCode checks this threshold after tools finish and their results are appended, before starting the next assistant response. If the threshold is crossed, KnightCode compacts inside the same agent run and resumes with the summary and retained messages. It skips this between-turn check when the completed tool batch terminates the run and no queued message requires another response. KnightCode also checks the threshold before a new user prompt and after a low-level agent run ends.
+During a multi-turn agent run, KnightCode checks the canonical projected context after tools finish and their results are appended, before starting the next assistant response. If the threshold is crossed, KnightCode compacts during `prepareNextTurn`, then performs the existing catch-up steering poll before `turn_start`. It skips this between-turn check when the completed tool batch terminates the run and no queued message requires another response. KnightCode also checks before a new user prompt and performs final-attempt overflow recovery after the low-level run ends.
+
+A provider context-overflow error or an early final `stopReason: "length"` can select one compact-and-retry recovery attempt. Length responses with tool calls retain their synthetic failed tool results and follow the ordinary tool/queue scheduler rather than forcing the run to end.
 
 You can also trigger manually with `/compact [instructions]`, where optional instructions focus the summary.
 
 ### How It Works
 
-1. **Find cut point**: Walk backwards from newest message, accumulating token estimates until `keepRecentTokens` (default 20k, configurable in `~/.knightcode/agent/settings.json` or `<project-dir>/.knightcode/settings.json`) is reached
-2. **Extract messages**: Collect messages from the previous kept boundary (or session start) up to the cut point
+1. **Find cut point**: Walk backwards through the finalized session projection, accumulating token estimates until `keepRecentTokens` (default 20k, configurable in `~/.knightcode/agent/settings.json` or `<project-dir>/.knightcode/settings.json`) is reached
+2. **Extract messages**: Collect projected messages from the previous kept boundary (or session start) up to the cut point
 3. **Generate summary**: Call LLM to summarize with structured format, passing the previous summary as iterative context when present
 4. **Append entry**: Save `CompactionEntry` with summary and `firstKeptEntryId`
 5. **Rebuilds context**: Session rebuilds the context for the next request, using summary + messages from `firstKeptEntryId` onwards
@@ -78,16 +80,31 @@ What the LLM sees:
     prompt   from cmp          messages from firstKeptEntryId
 ```
 
-On repeated compactions, the summarized span starts at the previous compaction's kept boundary (`firstKeptEntryId`), not at the compaction entry itself, falling back to the entry after the previous compaction if that kept entry cannot be found in the path. This preserves messages that survived the earlier compaction by including them in the next summarization pass as well. KnightCode also recalculates `tokensBefore` from the rebuilt session context before writing the new `CompactionEntry`, so the token count reflects the actual pre-compaction context being replaced.
+On repeated compactions, the summarized span starts at the previous compaction's kept boundary (`firstKeptEntryId`), not at the compaction entry itself, falling back to the entry after the previous compaction if that kept entry cannot be found in the path. A retain-none compaction records its own ID as `firstKeptEntryId`; repeated compaction starts after that entry. This preserves messages that survived the earlier compaction by including them in the next summarization pass as well. KnightCode also recalculates `tokensBefore` from the rebuilt, context-edited session projection before writing the new `CompactionEntry`, so the token count reflects the actual pre-compaction context being replaced. Omitted raw entries remain stored but do not affect cut selection, summaries, checkpoints, or token estimates.
+
+### Overflow and Length Recovery Ordering
+
+Recovery preserves the existing lifecycle and queue order. The completed attempt remains visible to `turn_end` and `agent_end`; post-run recovery then repairs persisted model context before a fresh retry:
+
+```text
+persist final assistant response
+→ extension/public turn_end
+→ extension/public agent_end
+→ append context_edit omissions for the selected attempt
+→ for overflow/length: run session_before_compact and append compaction on success
+→ start the retry as a fresh run
+```
+
+If recovery compaction fails or is cancelled, KnightCode keeps the omission edits, appends no compaction, and schedules no internal retry. Existing queued work remains governed by ordinary steering and follow-up rules. `agent_before_settle` sees the repaired projection after recovery processing. Raw transcript history, exports, billing totals, and history-search extensions can still inspect the omitted attempt.
 
-### Split Turns
+### Split user-message spans
 
-A "turn" starts with a user message and includes all assistant responses and tool calls until the next user message. Normally, compaction cuts at turn boundaries.
+A user-message span starts with a user message and includes all turns until the next user message. Normally, compaction cuts at user-message boundaries.
 
-When a single turn exceeds `keepRecentTokens`, the cut point lands mid-turn at an assistant message. This is a "split turn":
+When one user-message span exceeds `keepRecentTokens`, the cut point lands within that span at an assistant message. This is a split user-message span:
 
 ```
-Split turn (one huge turn exceeds budget):
+Split user-message span (one span exceeds budget):
 
   entry:  0     1     2      3     4      5      6     7      8
         ┌─────┬─────┬─────┬──────┬─────┬──────┬──────┬─────┬──────┐
@@ -100,13 +117,13 @@ Split turn (one huge turn exceeds budget):
                                                       └── kept (7-8)
 
   isSplitTurn = true
-  messagesToSummarize = []  (no complete turns before)
+  messagesToSummarize = []  (no earlier user-message spans)
   turnPrefixMessages = [usr, ass, tool, ass, tool, tool]
 ```
 
-For split turns, KnightCode generates two summaries and merges them:
+For split user-message spans, KnightCode generates two summaries and merges them:
 1. **History summary**: Previous context (if any)
-2. **Turn prefix summary**: The early part of the split turn
+2. **User-message-span prefix summary**: The early part of the split user-message span
 
 ### Cut Point Rules
 
@@ -118,16 +135,18 @@ Valid cut points are:
 
 Never cut at tool results (they must stay with their tool call).
 
+Preparation advances the kept boundary into a context-invisible suffix only when that suffix contains an omitted assistant attempt and no unomitted context-producing entries. Recovery `context_edit` omissions satisfy this rule; intrinsically context-invisible metadata may coexist with them. Metadata alone and newly appended custom messages do not move the cut. A replacement edit affecting the candidate input or summarized prefix also blocks advancement because the omitted assistant answered the pre-edit input; replacements of suffix entries that are ultimately omitted remain safe. This allows an over-budget recovered input to be summarized while retaining the edits that keep the abandoned attempt omitted, without making bookkeeping change whether new model input is preserved verbatim.
+
 ### CompactionEntry Structure
 
-Defined in [`session-manager.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/coding-agent/src/core/session-manager.ts):
+Defined in [`session-manager.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/cli/src/core/session-manager.ts):
 
 ```typescript
 interface CompactionEntry<T = unknown> {
   type: "compaction";
   id: string;
-  parentId: string;
-  timestamp: number;
+  parentId: string | null;
+  timestamp: string;
   summary: string;
   firstKeptEntryId: string;
   tokensBefore: number;
@@ -145,7 +164,7 @@ interface CompactionDetails {
 
 Extensions can store any JSON-serializable data in `details`. The default compaction tracks file operations, but custom extension implementations can use their own structure. Generated and extension-provided summaries store their LLM `usage` when available so session totals include summarization work.
 
-See [`prepareCompaction()`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/coding-agent/src/core/compaction/compaction.ts) and [`compact()`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/coding-agent/src/core/compaction/compaction.ts) for the implementation. For direct programmatic summarization, `generateSummary()` returns the summary text and `generateSummaryWithUsage()` returns `{ text, usage }`.
+See [`prepareCompaction()`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/cli/src/core/compaction/compaction.ts) and [`compact()`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/cli/src/core/compaction/compaction.ts) for the implementation. For direct programmatic summarization, `generateSummary()` returns the summary text and `generateSummaryWithUsage()` returns `{ text, usage }`.
 
 ## Branch Summarization
 
@@ -180,22 +199,20 @@ After navigation with summary:
 
 ### Cumulative File Tracking
 
-Both compaction and branch summarization track files cumulatively. When generating a summary, knightcode extracts file operations from:
-- Tool calls in the messages being summarized
-- Previous compaction or branch summary `details` (if any)
+Default compaction and branch summarization track files cumulatively. Both extract file operations from tool calls in the messages being summarized. Compaction also carries file lists from the previous KnightCode-generated compaction. Branch summarization carries file lists from KnightCode-generated branch summaries in the entries it summarizes.
 
-This means file tracking accumulates across multiple compactions or nested branch summaries, preserving the full history of read and modified files.
+File tracking therefore accumulates across default compactions and nested default branch summaries. KnightCode does not automatically carry file lists from extension-generated summaries whose `fromHook` field is `true`; extensions manage their own `details` format.
 
 ### BranchSummaryEntry Structure
 
-Defined in [`session-manager.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/coding-agent/src/core/session-manager.ts):
+Defined in [`session-manager.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/cli/src/core/session-manager.ts):
 
 ```typescript
 interface BranchSummaryEntry<T = unknown> {
   type: "branch_summary";
   id: string;
-  parentId: string;
-  timestamp: number;
+  parentId: string | null;
+  timestamp: string;
   summary: string;
   fromId: string;      // Entry we navigated from
   usage?: Usage;       // LLM usage that generated the summary
@@ -212,11 +229,13 @@ interface BranchSummaryDetails {
 
 Same as compaction, extensions can store custom data in `details`.
 
-See [`collectEntriesForBranchSummary()`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/coding-agent/src/core/compaction/branch-summarization.ts), [`prepareBranchEntries()`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/coding-agent/src/core/compaction/branch-summarization.ts), and [`generateBranchSummary()`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/coding-agent/src/core/compaction/branch-summarization.ts) for the implementation.
+See [`collectEntriesForBranchSummary()`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/cli/src/core/compaction/branch-summarization.ts), [`prepareBranchEntries()`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/cli/src/core/compaction/branch-summarization.ts), and [`generateBranchSummary()`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/cli/src/core/compaction/branch-summarization.ts) for the implementation.
 
 ## Summary Format
 
-Both compaction and branch summarization use the same structured format:
+Both formats include Goal, Constraints & Preferences, Progress, Key Decisions, and Next Steps. Compaction summaries also include Critical Context. Branch summaries stop after Next Steps. KnightCode appends file lists to either format when relevant.
+
+Compaction summaries use this format:
 
 ```markdown
 ## Goal
@@ -256,7 +275,7 @@ path/to/changed.ts
 
 ### Message Serialization
 
-Before summarization, messages are serialized to text via [`serializeConversation()`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/coding-agent/src/core/compaction/utils.ts):
+Before summarization, messages are serialized to text via [`serializeConversation()`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/cli/src/core/compaction/utils.ts):
 
 ```
 [User]: What they said
@@ -272,7 +291,7 @@ Tool results are truncated to 2000 characters during serialization. Content beyo
 
 ## Custom Summarization via Extensions
 
-Extensions can intercept and customize both compaction and branch summarization. See [`extensions/types.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/coding-agent/src/core/extensions/types.ts) for event type definitions.
+Extensions can intercept and customize both compaction and branch summarization. See [`extensions/types.ts`](https://github.com/KnightCodeAI/knightcode/blob/main/packages/cli/src/core/extensions/types.ts) for event type definitions.
 
 ### session_before_compact
 
@@ -283,7 +302,7 @@ knightcode.on("session_before_compact", async (event, ctx) => {
   const { preparation, branchEntries, customInstructions, reason, willRetry, signal } = event;
 
   // preparation.messagesToSummarize - messages to summarize
-  // preparation.turnPrefixMessages - split turn prefix (if isSplitTurn)
+  // preparation.turnPrefixMessages - user-message-span prefix (if isSplitTurn)
   // preparation.previousSummary - previous compaction summary
   // preparation.fileOps - extracted file operations
   // preparation.tokensBefore - context tokens before compaction
@@ -357,7 +376,7 @@ knightcode.on("session_compact_failed", async (event, ctx) => {
   const { reason, errorMessage, aborted, willRetry, fromExtension } = event;
   // reason - "manual" (/compact), "threshold", or "overflow"
   // errorMessage - present for non-abort failures
-  // aborted - true for cancelled/aborted compactions
+  // aborted - true for canceled/aborted compactions
   // willRetry - whether the aborted turn would have retried after compaction
   // fromExtension - whether extension-provided compaction content was being used
 });
@@ -441,4 +460,4 @@ Keys are exact, case-sensitive `provider/modelId` values, including any slashes
 
 These resolved values are used for manual compaction, all automatic threshold checks, overflow recovery, and extension-visible `preparation.settings`. Model switches affect subsequent checks and compactions without changing ordinary settings. Compaction already in progress uses the model and settings captured for that operation. Branch summarization settings are unaffected.
 
-Overrides work in both global and project settings. The files merge recursively before lookup, so a global model-specific value beats a project-wide fallback; a project must override that model entry to change it. See [settings.md](settings.md#per-model-compaction-overrides) for details.
+Overrides work in both global and project settings. The files merge recursively before lookup, so a global model-specific value beats a project-wide fallback; a project must override that model entry to change it. See [Settings](settings.md#per-model-compaction-overrides) for details.

package/bin/docs/configuration.md

@@ -0,0 +1,46 @@
+# Configuration
+
+KnightCode supports user-level and project configuration. User-level configuration lives in the agent directory, which defaults to `~/.knightcode/agent`. Project configuration lives in `.knightcode` under the working directory and loads after [project trust](security.md#understand-project-trust) is granted. The only exception is `sessionDir`, which KnightCode reads before resolving trust so it can locate sessions.
+
+In interactive mode, use `/settings` to change common preferences. For other options, ask KnightCode to update the configuration or edit the relevant files directly. Run `/reload` after manually changing settings, keybindings, instructions, or resources.
+
+## Agent directory
+
+The agent directory is shown as `<agent-dir>` below. Set its location with the `KNIGHTCODE_CODING_AGENT_DIR` environment variable or the SDK's [`agentDir`](sdk.md) option.
+
+| Path | Responsibility |
+|---|---|
+| `<agent-dir>/settings.json` | User-level [settings](settings.md), including preferences, defaults, resource paths, and KnightCode package declarations. |
+| `<agent-dir>/keybindings.json` | Custom terminal UI and application [keybindings](keybindings.md). |
+| `<agent-dir>/models.json` | [Compatible endpoints, models, and model overrides](models.md#configure-a-compatible-endpoint). |
+| `<agent-dir>/auth.json` | Saved API keys and OAuth credentials. |
+| `<agent-dir>/tools.json` | [Web tool](usage.md#web-tools) and scratchpad settings written by `/tools`, including the Brave Search key. |
+| `<agent-dir>/AGENTS.override.md`, `AGENTS.md`, `AGENTS.MD`, `CLAUDE.md`, or `CLAUDE.MD` | User instructions applied across working directories. |
+| `<agent-dir>/SYSTEM.md` | Replaces KnightCode’s default system prompt. |
+| `<agent-dir>/APPEND_SYSTEM.md` | Adds instructions to KnightCode’s system prompt. |
+| `<agent-dir>/extensions/` | User [extensions](extensions.md). |
+| `<agent-dir>/skills/` | User [skills](skills.md) and supporting files. |
+| `<agent-dir>/prompts/` | User [prompt templates](prompt-templates.md) exposed as slash commands. |
+| `<agent-dir>/themes/` | User [theme](themes.md) files. |
+
+## Project `.knightcode` directory
+
+| Path | Responsibility |
+|---|---|
+| `.knightcode/settings.json` | Project-level [settings](settings.md), resource paths, and KnightCode package declarations. |
+| `.knightcode/SYSTEM.md` | Replaces the system prompt for the project. |
+| `.knightcode/APPEND_SYSTEM.md` | Adds project-specific instructions to the system prompt. |
+| `.knightcode/extensions/` | Project extensions. |
+| `.knightcode/skills/` | Project skills and supporting files. |
+| `.knightcode/prompts/` | Project prompt templates exposed as slash commands. |
+| `.knightcode/themes/` | Project theme files. |
+
+For `SYSTEM.md` and `APPEND_SYSTEM.md`, the trusted project file takes precedence over the corresponding agent-directory file. Files with the same name are not combined.
+
+## Context files
+
+Context files are separate from project `.knightcode` configuration. KnightCode loads them from the agent directory, the working directory, and its parent directories. A context file applies whenever KnightCode runs in its directory or anywhere below it.
+
+An `AGENTS.override.md` replaces `AGENTS.md` or `CLAUDE.md` only in the same directory. It does not suppress context files from the agent directory or other directories.
+
+Context-file discovery does not require project trust.

package/bin/docs/containerization.md

@@ -1,52 +1,38 @@
-# Containerization
+# Run KnightCode in an isolated environment
 
-KnightCode runs with all permissions by default, but in some cases, you will want to have more control over what directories KnightCode can write to and which accesses it has.
+Use an isolated environment to limit the files, credentials, processes, and network services that generated commands can access or affect.
 
-There are two general options. You can either
-1. run the whole `knightcode` process inside an isolated environment, or
-2. run `knightcode` on the host and route tool execution into an isolated environment.
+You can isolate the complete KnightCode process or keep KnightCode on the host and route selected tools into an isolated environment.
 
-## Choose a pattern
+## Choose an isolation method
 
-| Pattern | What is isolated | Best for | Notes |
-| --- | --- | --- | --- |
-| Gondolin extension | Built-in tools and `!` commands | Local micro-VM isolation while keeping auth on host | See [`examples/extensions/gondolin/`](../examples/extensions/gondolin/). |
-| Plain Docker | Whole `knightcode` process in a local container | Simple local isolation | Provider API keys enter the container. |
-| OpenShell | Whole `knightcode` process in a policy-controlled sandbox | Local or remote managed sandbox | Requires an OpenShell gateway |
+| Method | Where KnightCode runs | What is isolated | Credential handling | Best for |
+|---|---|---|---|---|
+| Plain Docker | Container | KnightCode, built-in tools, `!` commands, and extensions | Credentials passed into the container | A straightforward local container boundary |
+| OpenShell | Local or remote sandbox | KnightCode, built-in tools, `!` commands, and extensions | Policy-controlled credentials and inference routing | Filesystem, process, network, and credential policies |
+| Gondolin extension | Host | Built-in tools and `!` commands | Stored KnightCode credentials remain on the host, but commands inherit host environment variables | A local micro-VM for tool execution while retaining the host interface |
 
-Extensions run wherever the `knightcode` process runs. If you run host `knightcode` with a tool-routing extension, other custom extension tools still run on the host unless they also delegate their operations.
+The method changes where extensions run. When the complete KnightCode process runs inside an isolated environment, its extensions run there too. When host KnightCode delegates built-in tools through Gondolin, other extension tools still run on the host unless they also delegate their work.
 
-## Gondolin
+## Decide what KnightCode can access
 
-[Gondolin](https://github.com/KnightCodeAI/gondolin) is a local Linux micro-VM.
-Use the [example extension](../examples/extensions/gondolin) when you want `knightcode` on the host but all built-in tools routed into the VM.
+An isolated process can still affect resources you expose to it:
 
-Setup:
+- A read-write host mount lets KnightCode modify those host files.
+- Mounting `~/.knightcode/agent` exposes your KnightCode credentials, settings, extensions, and sessions.
+- Environment variables passed into a container are available to processes inside it.
+- Network access may allow code or tool output to leave the environment.
+- Tool-only isolation does not constrain the host KnightCode process or extension tools that do not use the isolated backend.
 
-```bash
-cp -R packages/coding-agent/examples/extensions/gondolin ~/.knightcode/agent/extensions/gondolin
-cd ~/.knightcode/agent/extensions/gondolin
-npm install --ignore-scripts
-```
-
-Run from the project you want mounted:
-
-```bash
-cd /path/to/project
-knightcode -e ~/.knightcode/agent/extensions/gondolin
-```
-
-The extension mounts the host cwd at `/workspace` in the VM and overrides `read`, `write`, `edit`, `bash`, `grep`, `find`, and `ls`.
-User `!` commands are routed into the VM, as well.
-File changes under `/workspace` write through to the host.
+Expose only the working folder, credentials, and network destinations needed for the task. Use read-only mounts or copy files into and out of the environment when you do not want writes to affect the host.
 
-Requirements: Node.js >= 23.6.0 for `@KnightCodeAI/gondolin`, plus QEMU (requires installation through your package manager).
+## Run KnightCode in plain Docker
 
-## Plain Docker
+Plain Docker provides the simplest whole-process container boundary.
 
-Run the whole `knightcode` process in Docker when you want the simplest local container boundary.
+### Build the image
 
-`Dockerfile.knightcode`:
+Create `Dockerfile.knightcode`:
 
 ```dockerfile
 FROM node:24-bookworm-slim
@@ -60,11 +46,17 @@ WORKDIR /workspace
 ENTRYPOINT ["knightcode"]
 ```
 
-Build and run:
+Build it from the directory containing the file:
 
 ```bash
 docker build -t knightcode-sandbox -f Dockerfile.knightcode .
+```
+
+### Start KnightCode
+
+From the working folder you want KnightCode to access, run:
 
+```bash
 docker run --rm -it \
   -e ANTHROPIC_API_KEY \
   -v "$PWD:/workspace" \
@@ -72,40 +64,80 @@ docker run --rm -it \
   knightcode-sandbox
 ```
 
-The `-v "$PWD:/workspace"` mounts your current directory into the container at /workspace such that reads and writes in `/workspace` inside Docker directly affect your host files, like in the Gondolin example.
+Replace `ANTHROPIC_API_KEY` with the credential required by your provider. The named `knightcode-agent-home` volume keeps container-local settings, credentials, and sessions between runs.
+
+Do not mount the host's `~/.knightcode/agent` unless the container should have access to your host KnightCode configuration and credentials.
+
+### Verify the workspace
+
+Inside KnightCode, run:
+
+```text
+!pwd
+```
+
+The command should report `/workspace`. Changes under `/workspace` write through to the mounted host folder. Remove the bind mount or use a read-only mount when that is not acceptable.
 
-Use a named volume for `/root/.knightcode/agent` if you want container-local settings and sessions. Mounting your host `~/.knightcode/agent` exposes host auth and session files to the container.
+## Run KnightCode with OpenShell
 
-## OpenShell
+[NVIDIA OpenShell](https://docs.nvidia.com/openshell/about/overview) provides local or remote sandboxes with filesystem, process, network, credential, and inference policies.
 
-Use [NVIDIA OpenShell](https://docs.nvidia.com/openshell/about/overview) when you want a policy-controlled sandbox with filesystem, process, network, credential, and inference controls.
-OpenShell can run sandboxes through a local gateway backed by Docker, Podman, or a VM runtime, or through a remote Kubernetes gateway.
+### Select a gateway
 
-Every sandbox requires an active gateway.
-Register and select one before creating a sandbox:
+Every sandbox requires an active gateway:
 
 ```bash
 openshell gateway add <gateway-url> --name <name>
 openshell gateway select <name>
 ```
 
-Launch `knightcode` inside an OpenShell sandbox:
+### Create the sandbox
 
 ```bash
 openshell sandbox create --name knightcode-sandbox --from knightcode -- knightcode
 ```
 
-In this pattern, the whole `knightcode` process runs inside the sandbox.
-Built-in tools, `!` commands, and extension tools execute inside the OpenShell boundary.
+KnightCode, its built-in tools, `!` commands, and extension tools run inside the OpenShell boundary.
 
-If the gateway is remote, project files are not bind-mounted from the host, meaning writes in the sandbox are not reflected on your machine.
-Clone the repository inside the sandbox or use OpenShell file transfer commands:
+### Transfer files to a remote sandbox
+
+A remote gateway does not bind-mount your host working folder. Clone the repository inside the sandbox or transfer files explicitly:
+
+```bash
+openshell sandbox upload knightcode-sandbox ./working-folder /workspace
+openshell sandbox download knightcode-sandbox /workspace/working-folder ./working-folder-out
+```
+
+OpenShell inference routing can keep raw model credentials outside the sandbox. When configured, point KnightCode at the corresponding OpenAI-compatible or Anthropic-compatible endpoint exposed by the gateway.
+
+## Route tools through Gondolin
+
+[Gondolin](https://github.com/KnightCodeAI/gondolin) is a local Linux micro-VM. Its example extension keeps the KnightCode process and file-based provider credentials on the host while routing the built-in tools and user `!` commands into the VM.
+
+Commands inside the VM inherit the host process environment. Provider keys supplied through environment variables can therefore be visible inside the VM. Do not use this pattern as a credential boundary unless you remove sensitive variables or change the extension's environment handling.
+
+Gondolin requires Node.js 23.6 or newer and QEMU installed through your operating-system package manager.
+
+### Install the extension
+
+From a KnightCode source checkout:
+
+```bash
+mkdir -p ~/.knightcode/agent/extensions
+cp -R packages/cli/examples/extensions/gondolin ~/.knightcode/agent/extensions/gondolin
+cd ~/.knightcode/agent/extensions/gondolin
+npm install --ignore-scripts
+```
+
+### Start KnightCode
+
+Run KnightCode from the working folder you want mounted:
 
 ```bash
-openshell sandbox upload knightcode-sandbox ./repo /workspace
-openshell sandbox download knightcode-sandbox /workspace/repo ./repo-out
+cd /path/to/working-folder
+knightcode -e ~/.knightcode/agent/extensions/gondolin
 ```
 
-OpenShell providers can keep raw model API keys outside the sandbox.
-When inference routing is configured, code inside the sandbox can call `https://inference.local`, and the gateway injects the configured provider credentials upstream.
-Configure KnightCode to use the corresponding OpenAI-compatible or Anthropic-compatible endpoint if you want model traffic to use this route.
+The extension mounts the host working folder at `/workspace` in the VM and overrides `read`, `write`, `edit`, `bash`, `grep`, `find`, and `ls`. File changes under `/workspace` write through to the host.
+
+Other extension tools still run on the host unless they explicitly delegate their operations. Review the [Gondolin example](../examples/extensions/gondolin/) before adding tools that could bypass the VM boundary.