feat: add validation framework with conversation logger and auto-setup

- Add `/validate` skill with `batch_validate.py` for running trace validation
  against the Altimate backend (single trace, date range, or session mode)
- Add `conversation-logger.ts` that fires on session idle and posts each
  conversation turn to `/log-conversation` (opt-out via `ALTIMATE_LOGGER_DISABLED=true`)
- Add `logger_hook.py` — Claude Code Stop hook that reads the session JSONL
  transcript and posts conversation turns in the same payload format
- Auto-install validate skill and logger hook on every `InstanceBootstrap`:
  - Copies `SKILL.md` + `batch_validate.py` → `~/.claude/skills/validate/`
  - Writes `altimate_logger_hook.py` → `~/.claude/hooks/` and merges Stop hook
    into `~/.claude/settings.json` (skipped if `ALTIMATE_LOGGER_DISABLED=true`)
- Add `resolvePrompt` helper in session routes to deterministically route
  `/validate` commands without LLM classification
- Add logging docs at `docs/docs/configure/logging.md`
- Remove `validate install` from `bun run build` — setup is fully automatic

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Author: Bharatram-altimate-ai

.github/workflows/ci.yml

@@ -13,7 +13,7 @@ concurrency:
 jobs:
   typescript:
     name: TypeScript
-    runs-on: ubuntu-latest
+    runs-on: ${{ github.event.pull_request.head.repo.fork && 'ubuntu-latest' || 'arc-runner-altimate-code' }}
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
@@ -44,7 +44,7 @@ jobs:
 
   lint:
     name: Lint
-    runs-on: ubuntu-latest
+    runs-on: ${{ github.event.pull_request.head.repo.fork && 'ubuntu-latest' || 'arc-runner-altimate-code' }}
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
@@ -62,7 +62,7 @@ jobs:
 
   python:
     name: Python ${{ matrix.python-version }}
-    runs-on: ubuntu-latest
+    runs-on: ${{ github.event.pull_request.head.repo.fork && 'ubuntu-latest' || 'arc-runner-altimate-code' }}
     timeout-minutes: 60
     strategy:
       matrix:

.github/workflows/release.yml

@@ -15,7 +15,7 @@ env:
 jobs:
   build:
     name: Build (${{ matrix.os }})
-    runs-on: ubuntu-latest
+    runs-on: arc-runner-altimate-code
     timeout-minutes: 60
     permissions:
       contents: read
@@ -59,7 +59,7 @@ jobs:
   publish-npm:
     name: Publish to npm
     needs: build
-    runs-on: ubuntu-latest
+    runs-on: arc-runner-altimate-code
     timeout-minutes: 60
     permissions:
       contents: read
@@ -125,7 +125,7 @@ jobs:
   # doesn't need CLI binary artifacts. This allows it to run in parallel.
   publish-engine:
     name: Publish engine to PyPI
-    runs-on: ubuntu-latest
+    runs-on: arc-runner-altimate-code
     timeout-minutes: 60
     environment: pypi
     permissions:
@@ -156,7 +156,7 @@ jobs:
   github-release:
     name: Create GitHub Release
     needs: [build, publish-npm]
-    runs-on: ubuntu-latest
+    runs-on: arc-runner-altimate-code
     timeout-minutes: 60
     permissions:
       contents: write

.github/workflows/test.yml

@@ -14,7 +14,7 @@ jobs:
       matrix:
         settings:
           - name: linux
-            host: ubuntu-latest
+            host: arc-runner-altimate-code
           - name: windows
             host: windows-latest
     runs-on: ${{ matrix.settings.host }}
@@ -46,7 +46,7 @@ jobs:
       matrix:
         settings:
           - name: linux
-            host: ubuntu-latest
+            host: arc-runner-altimate-code
             playwright: bunx playwright install --with-deps
           - name: windows
             host: windows-latest
@@ -89,7 +89,7 @@ jobs:
 
   required:
     name: test (linux)
-    runs-on: ubuntu-latest
+    runs-on: arc-runner-altimate-code
     needs:
       - unit
       - e2e

.gitignore

@@ -23,8 +23,37 @@ target
 .scripts
 .direnv/
 
+# Python
+__pycache__/
+*.pyc
+*.pyo
+*.egg-info/
+
+# SQLite databases (feedback store creates these at runtime)
+*.db
+
+# Runtime logs
+*.log
+logs/
+
+# Large intermediate files at repo root (generated during benchmark runs)
+/queries.json
+/queries_1k.json
+/results/
+
+# Local runtime config
+.altimate-code/
+
+# Commit message scratch files
+.github/meta/
+
+# Experiment / simulation artifacts
+/data/
+/experiments/
+/models/
+/simulation/
+
 # Local dev files
 opencode-dev
-logs/
 *.bun-build
 tsconfig.tsbuildinfo

README.md

@@ -157,6 +157,20 @@ Full docs at **[altimate-code.sh](https://altimate-code.sh)**.
 - [Agent Modes](https://altimate-code.sh/data-engineering/agent-modes/)
 - [Configuration](https://altimate-code.sh/configure/model-providers/)
 
+## Data Collection
+
+Altimate Code logs conversation turns (prompt, tool calls, and assistant response) to improve validation quality and agent behavior. Logs are sent to Altimate's backend and are not shared with third parties.
+
+**To opt out:**
+
+```bash
+export ALTIMATE_LOGGER_DISABLED=true
+```
+
+Add it to your shell profile (`~/.zshrc`, `~/.bashrc`) to make it permanent.
+
+See [`docs/docs/configure/logging.md`](docs/docs/configure/logging.md) for details on what is collected.
+
 ## Community & Contributing
 
 - **Issues**: [GitHub Issues](https://github.com/AltimateAI/altimate-code/issues)

bun.lock

@@ -0,0 +1,60 @@
+# Conversation Logging
+
+Altimate Code automatically logs each conversation turn to the Altimate backend. This powers validation, audit, and quality analysis features. Logging is **enabled by default** — no configuration is required to activate it.
+
+## What Is Logged
+
+Each turn (one user prompt + all assistant responses) sends the following to the Altimate backend:
+
+| Field | Description |
+|-------|-------------|
+| `session_id` | The current session identifier |
+| `conversation_id` | The assistant message ID for this turn |
+| `user_id` | Your email or username (from your Altimate account) |
+| `user_prompt` | The text of your message |
+| `parts` | All reasoning, text, and tool call/response parts from the assistant |
+| `final_response` | The last text response from the assistant |
+| `metadata` | Model ID, token counts, and cost for the turn |
+
+Logging fires after the session becomes idle (i.e., after the assistant finishes responding). Up to 500 messages are captured per turn to ensure complete coverage of multi-step agentic sessions.
+
+## Why We Log
+
+Conversation logs are used to:
+
+- **Validate AI responses** — power the `/validate` skill that audits factual claims against source data
+- **Quality analysis** — identify recurring failure patterns across sessions
+- **Audit trails** — provide a record of what the assistant did and why
+
+## Disabling Logging
+
+Logging is on by default. To disable it, set the following environment variable before starting Altimate Code:
+
+```bash
+export ALTIMATE_LOGGER_DISABLED=true
+```
+
+To make this permanent, add it to your shell profile (`~/.zshrc`, `~/.bashrc`, etc.):
+
+```bash
+echo 'export ALTIMATE_LOGGER_DISABLED=true' >> ~/.zshrc
+source ~/.zshrc
+```
+
+To re-enable logging, unset the variable:
+
+```bash
+unset ALTIMATE_LOGGER_DISABLED
+```
+
+Setting `ALTIMATE_LOGGER_DISABLED=false` is equivalent to not setting it — logging will be active.
+
+## Network
+
+Conversation logs are sent to:
+
+| Endpoint | Purpose |
+|----------|---------|
+| `apimi.tryaltimate.com` | Conversation log ingestion |
+
+Requests are fire-and-forget — a failed log request does not affect your session in any way.

docs/docs/configure/logging.md

@@ -71,6 +71,15 @@ const migrations = await Promise.all(
 )
 console.log(`Loaded ${migrations.length} migrations`)
 
+// Load validate skill assets for embedding
+const validateSkillMd = await Bun.file(path.join(dir, "src/skill/validate/SKILL.md")).text()
+const validateBatchPy = await Bun.file(path.join(dir, "src/skill/validate/batch_validate.py")).text()
+console.log("Loaded validate skill assets")
+
+// Load logger hook for embedding
+const loggerHookPy = await Bun.file(path.join(dir, "src/skill/validate/logger_hook.py")).text()
+console.log("Loaded logger hook")
+
 const singleFlag = process.argv.includes("--single")
 const baselineFlag = process.argv.includes("--baseline")
 const skipInstall = process.argv.includes("--skip-install")
@@ -220,6 +229,9 @@ for (const item of targets) {
       OPENCODE_LIBC: item.os === "linux" ? `'${item.abi ?? "glibc"}'` : "undefined",
       OPENCODE_MIGRATIONS: JSON.stringify(migrations),
       OPENCODE_CHANGELOG: JSON.stringify(changelog),
+      ALTIMATE_VALIDATE_SKILL_MD: JSON.stringify(validateSkillMd),
+      ALTIMATE_VALIDATE_BATCH_PY: JSON.stringify(validateBatchPy),
+      ALTIMATE_LOGGER_HOOK_PY: JSON.stringify(loggerHookPy),
       OTUI_TREE_SITTER_WORKER_PATH: bunfsRoot + workerRelativePath,
     },
   })

packages/altimate-code/src/provider/models-snapshot.ts

@@ -106,6 +106,7 @@ import type { EventSource } from "./context/sdk"
 export function tui(input: {
   url: string
   args: Args
+  config: TuiConfig.Info
   directory?: string
   fetch?: typeof fetch
   headers?: RequestInit["headers"]