Compare commits

..
7 Commits
Author SHA1 Message Date
Daniel SamsonandClaude Opus 4.6 aa986a470e Remove log viewer app, output goes to agent logs directly
Publish Image / publish (push) Successful in 15s
The startup script already writes to stdout which the Coder agent
captures. No need for a separate HTTP log server or coder_app button.
Logs are visible via the Coder web terminal or agent log viewer.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-12 14:18:00 +01:00
Daniel SamsonandClaude Opus 4.6 520fc8f81e Custom workspace image + fix slash command invocation
Publish Workspace Image / publish (push) Successful in 3m51s
- Add coder/workspace.Dockerfile with Node.js 22, wrangler, claude-code,
  and Playwright deps pre-installed. Eliminates ~3 min of installs on
  every workspace startup.
- Add CI workflow to build and push to registry.samson.media/coder-workspace
- Fix slash command: -p mode doesn't support /commands, so read the .md
  file directly, strip frontmatter, substitute $ARGUMENTS, pass as prompt
- Switch workspace image from codercom/enterprise-base to custom image

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-12 14:15:17 +01:00
Daniel SamsonandClaude Opus 4.6 d46e3ca247 Fix slash command invocation: /analyse not /project:analyse
The project: prefix is not valid Claude Code syntax. Slash commands
in .claude/commands/ are invoked as /$TASK_TYPE directly.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-12 14:09:08 +01:00
Daniel SamsonandClaude Opus 4.6 ec0b012586 Reconcile queue state on startup, remove age-based staleness check
Publish Image / publish (push) Successful in 20s
On boot, query Coder for running workspaces and re-adopt them into the
active queue. This prevents 409 conflicts after restarts and ensures
callbacks still work for in-flight tasks.

On 409: only delete stopped/failed workspaces. Running workspaces are
adopted — never killed based on age.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-12 14:01:56 +01:00
Daniel SamsonandClaude Opus 4.6 36c80458e0 Safe 409 handling: check workspace age/status before deleting
Publish Image / publish (push) Successful in 20s
Instead of blindly deleting on 409 conflict, now checks:
- Stopped/failed → safe to delete and recreate
- Running but >30 min old → stale, delete and recreate
- Running and <30 min old → adopt existing workspace (mid-task)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-12 13:59:59 +01:00
Daniel SamsonandClaude Opus 4.6 06cf4d1b9e Handle stale workspaces: 409 conflict auto-cleanup + verbose logging
Publish Image / publish (push) Successful in 20s
When the orchestrator restarts, it loses in-memory queue state. If a
stale workspace still exists, createWorkspace now auto-deletes it and
retries instead of failing with 409. Also adds --verbose to Claude Code
invocation for better task log debugging.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-12 13:58:08 +01:00
Daniel SamsonandClaude Opus 4.6 4f1d306fdf Fix ImagePullBackOff: use multi-arch base image tag
The tag `ubuntu-arm64` doesn't exist on Docker Hub. Switch to `latest`
which includes arm64 in its multi-arch manifest.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-12 13:44:44 +01:00
6 changed files with 192 additions and 28 deletions
+27
View File
@@ -0,0 +1,27 @@
name: Publish Workspace Image
on:
push:
paths:
- 'coder/workspace.Dockerfile'
branches:
- main
concurrency:
group: publish-workspace
cancel-in-progress: false
jobs:
publish:
runs-on: self-hosted
steps:
- uses: actions/checkout@v4
- name: Log in to registry
run: echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.samson.media -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
- name: Build and push
run: |
IMAGE=registry.samson.media/coder-workspace
docker build -f coder/workspace.Dockerfile -t "$IMAGE:latest" .
docker push "$IMAGE:latest"
+32 -25
View File
@@ -442,6 +442,25 @@ resource "coder_agent" "main" {
web_terminal = true
}
metadata {
display_name = "Task Status"
key = "task_status"
script = <<-EOS
if [ -f ~/task-output.log ]; then
if grep -q "Task completed" ~/task-output.log 2>/dev/null; then
echo "✅ Complete"
else
echo "⏳ Running ($(wc -l < ~/task-output.log) lines)"
fi
elif [ -n "$TASK_TYPE" ]; then
echo "⏳ Starting..."
else
echo "Interactive"
fi
EOS
interval = 10
}
env = {
ANTHROPIC_API_KEY = data.coder_parameter.anthropic_api_key.value
GITHUB_TOKEN = data.coder_external_auth.github.access_token
@@ -459,28 +478,6 @@ resource "coder_agent" "main" {
#!/bin/bash
set -e
# --- Install Node.js 22 ---
if ! command -v node &> /dev/null; then
curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash -
sudo apt-get install -y nodejs
fi
# --- Install global tools ---
if ! command -v wrangler &> /dev/null; then
sudo npm install -g wrangler @anthropic-ai/claude-code
fi
# --- Install Playwright system dependencies ---
if ! dpkg -s libgbm1 &> /dev/null; then
sudo apt-get update
sudo apt-get install -y libnss3 libnspr4 libatk1.0-0 libatk-bridge2.0-0 \
libcups2t64 libdrm2 libxkbcommon0 libxcomposite1 libxdamage1 libxfixes3 \
libxrandr2 libgbm1 libpango-1.0-0 libcairo2 libasound2t64 libatspi2.0-0 \
|| sudo apt-get install -y libnss3 libnspr4 libatk1.0-0 libatk-bridge2.0-0 \
libcups2 libdrm2 libxkbcommon0 libxcomposite1 libxdamage1 libxfixes3 \
libxrandr2 libgbm1 libpango-1.0-0 libcairo2 libasound2 libatspi2.0-0
fi
# --- Configure git ---
git config --global user.name "${data.coder_workspace_owner.me.full_name}"
git config --global user.email "${data.coder_workspace_owner.me.email}"
@@ -525,8 +522,18 @@ resource "coder_agent" "main" {
ARGS="$DEPLOY_ENV"
fi
# Run Claude Code in non-interactive mode
claude --print --dangerously-skip-permissions "/project:$TASK_TYPE $ARGS" 2>&1 | tee ~/task-output.log
# Read the slash command .md file, strip YAML frontmatter, substitute $ARGUMENTS
CMD_FILE=".claude/commands/$TASK_TYPE.md"
if [ ! -f "$CMD_FILE" ]; then
echo "ERROR: Command file not found: $CMD_FILE" | tee ~/task-output.log
exit 1
fi
PROMPT=$(sed '1{/^---$/!q}; 1,/^---$/d' "$CMD_FILE" | sed "s/\\\$ARGUMENTS/$ARGS/g")
# Run Claude Code in non-interactive mode with tool access
claude -p --dangerously-skip-permissions --verbose "$PROMPT" 2>&1 | tee ~/task-output.log
EXIT_CODE=$?
echo "Claude exited with code: $EXIT_CODE" | tee -a ~/task-output.log
echo "Task completed. Output saved to ~/task-output.log"
@@ -620,7 +627,7 @@ resource "kubernetes_deployment_v1" "workspace" {
container {
name = "coder-agent"
image = "codercom/enterprise-base:ubuntu-arm64"
image = "registry.samson.media/coder-workspace:latest"
command = ["sh", "-c", coder_agent.main.init_script]
+23
View File
@@ -0,0 +1,23 @@
FROM codercom/enterprise-base:latest
USER root
# Node.js 22
RUN curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \
&& apt-get install -y nodejs \
&& rm -rf /var/lib/apt/lists/*
# Global npm tools
RUN npm install -g wrangler @anthropic-ai/claude-code
# Playwright system dependencies (both Ubuntu 24.04 and 22.04 package names)
RUN apt-get update && apt-get install -y --no-install-recommends \
libnss3 libnspr4 libatk1.0-0 libatk-bridge2.0-0 \
libdrm2 libxkbcommon0 libxcomposite1 libxdamage1 libxfixes3 \
libxrandr2 libgbm1 libpango-1.0-0 libcairo2 libatspi2.0-0 \
jq netcat-openbsd \
&& (apt-get install -y libcups2t64 libasound2t64 2>/dev/null \
|| apt-get install -y libcups2 libasound2 2>/dev/null) \
&& rm -rf /var/lib/apt/lists/*
USER coder
+5
View File
@@ -84,6 +84,11 @@ if (maintenanceRepos.length > 0) {
// Start
// ---------------------------------------------------------------------------
// Reconcile queue state with Coder before accepting traffic
queue.reconcile().catch((err) =>
console.error("[startup] reconcile failed:", err),
);
serve({ fetch: app.fetch, port: config.port }, (info) => {
console.log(`SDLC Orchestrator listening on :${info.port} (concurrency: ${concurrency})`);
});
+28
View File
@@ -35,6 +35,34 @@ export class TaskQueue {
this.concurrency = concurrency;
}
/**
* Reconcile in-memory state with Coder on startup.
* Re-adopts any running workspaces so callbacks and dedup work correctly.
*/
async reconcile(): Promise<void> {
const workspaces = await this.coder.listWorkspaces();
const runningStatuses = ["starting", "running", "started"];
for (const ws of workspaces) {
if (!runningStatuses.includes(ws.latestBuildStatus)) continue;
// Only adopt workspaces that match our naming pattern: {taskType}-{repo}-{issue}
const parts = ws.name.match(/^(.+?)-(.+?)-(\d+)$/);
if (!parts) continue;
this.active.set(ws.name, {
workspaceId: ws.id,
workspaceName: ws.name,
startedAt: new Date(), // approximate — we don't know the real start time
});
console.log(`[queue] reconciled: adopted workspace "${ws.name}" (status: ${ws.latestBuildStatus})`);
}
if (this.active.size > 0) {
console.log(`[queue] reconcile complete: ${this.active.size} active workspace(s) adopted`);
}
}
/** Build a dedup key for a task. */
static key(task: TaskRequest): string {
return `${task.taskType}-${task.giteaRepo}-${task.issueNumber}`;
+77 -3
View File
@@ -50,6 +50,32 @@ export class CoderClient {
},
);
// Handle 409 conflict — workspace with this name already exists.
// This can happen if the orchestrator restarted and lost in-memory state.
if (res.status === 409) {
const existing = await this.findWorkspaceByName(name);
if (!existing) {
throw new Error(`Coder 409 but workspace "${name}" not found — possible race condition`);
}
const stoppedStatuses = ["stopped", "failed", "canceled", "deleted"];
if (stoppedStatuses.includes(existing.latestBuildStatus)) {
// Workspace is done — safe to replace
console.log(
`[coder] workspace "${name}" exists but ${existing.latestBuildStatus} — deleting and retrying`,
);
await this.deleteWorkspace(existing.id);
await new Promise((resolve) => setTimeout(resolve, 5000));
return this.createWorkspace(task);
}
// Workspace is still running — adopt it, don't kill it
console.log(
`[coder] workspace "${name}" is still ${existing.latestBuildStatus} — adopting existing workspace`,
);
return { id: existing.id, name: existing.name };
}
if (!res.ok) {
const text = await res.text();
throw new Error(`Coder API error ${res.status}: ${text}`);
@@ -95,7 +121,42 @@ export class CoderClient {
}
}
async findWorkspaceByName(name: string): Promise<{ id: string } | null> {
/**
* List all workspaces owned by the authenticated user.
* Used at startup to reconcile in-memory state with Coder.
*/
async listWorkspaces(): Promise<
Array<{ id: string; name: string; latestBuildStatus: string }>
> {
const res = await fetch(
`${this.baseUrl}/api/v2/workspaces?q=owner:me`,
{
headers: { "Coder-Session-Token": this.token },
},
);
if (!res.ok) return [];
const data = (await res.json()) as {
workspaces: Array<{
id: string;
name: string;
latest_build: { status: string };
}>;
};
return (data.workspaces ?? []).map((w) => ({
id: w.id,
name: w.name,
latestBuildStatus: w.latest_build?.status ?? "unknown",
}));
}
async findWorkspaceByName(name: string): Promise<{
id: string;
name: string;
createdAt: string;
latestBuildStatus: string;
} | null> {
const res = await fetch(
`${this.baseUrl}/api/v2/workspaces?q=name:${encodeURIComponent(name)}`,
{
@@ -107,8 +168,21 @@ export class CoderClient {
if (!res.ok) return null;
const data = (await res.json()) as { workspaces: Array<{ id: string; name: string }> };
const data = (await res.json()) as {
workspaces: Array<{
id: string;
name: string;
created_at: string;
latest_build: { status: string };
}>;
};
const match = data.workspaces?.find((w) => w.name === name);
return match ? { id: match.id } : null;
if (!match) return null;
return {
id: match.id,
name: match.name,
createdAt: match.created_at,
latestBuildStatus: match.latest_build?.status ?? "unknown",
};
}
}