diff options
| -rw-r--r-- | .gitignore | 3 | ||||
| -rw-r--r-- | CLAUDE.md | 10 | ||||
| -rw-r--r-- | README.md | 12 | ||||
| -rwxr-xr-x | runpod-session.sh | 44 |
4 files changed, 62 insertions, 7 deletions
diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..5ad1d5c --- /dev/null +++ b/.gitignore @@ -0,0 +1,3 @@ +*.bak +state.json +config @@ -4,7 +4,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co ## What this is -Single bash script (`runpod-session.sh`) that manages RunPod GPU pod lifecycle for running Ollama models, then patches `~/.config/opencode/opencode.jsonc` so opencode points at the live pod. +Single bash script (`runpod-session.sh`) that manages RunPod GPU pod lifecycle for running Ollama models, then patches `~/.config/opencode/opencode.jsonc`, `transart.py`, and `my-publisher/config.toml` so all tools point at the live pod. ## Running / testing @@ -31,14 +31,16 @@ All logic is in `main()` which runs these steps in order: 2. **Pod creation** — if none found: picks cheapest secure-cloud GPU under `MAX_PRICE_PER_HR`, creates pod with `ollama/ollama:latest` image, network volume mounted at `/workspace` 3. **Wait for Ollama** — polls `https://<pod-id>-11434.proxy.runpod.net/api/tags` until `.models` appears 4. **Patch opencode.json** — updates `baseURL`, active `model`, and merges `WARMUP_MODELS` into provider models block using jq `*` merge (existing config wins on conflicts) -5. **Warmup** — POST to `/api/generate` with a dummy prompt to load model into VRAM at `WARMUP_NUM_CTX` context length -6. **Save state** — writes `~/.config/runpod-session/state.json` with pod_id, url, model, timestamp +5. **Patch external configs** — `patch_external_configs()` rewrites `OLLAMA_HOST` in `transart.py` and `ollama_host` in `my-publisher/config.toml` using `sed`; paths set via `TRANSART_SCRIPT` / `PUBLISHER_CONFIG` in config; skipped if empty or file missing +6. **Warmup** — POST to `/api/generate` with a dummy prompt to load model into VRAM at `WARMUP_NUM_CTX` context length +7. **Save state** — writes `~/.config/runpod-session/state.json` with pod_id, url, model, timestamp ## Key design constraints - All RunPod calls go through `gql()` — single curl wrapper that exits on API errors - Pod is identified by name matching `test("ollama"; "i")` — not by ID — so the name `ollama-session` set at creation must not change - `patch_opencode_config()` writes a `.bak` before touching opencode.jsonc; jq `*` merge means existing per-model settings survive +- `patch_external_configs()` uses `sed -i` on the bare pod URL (no `/v1`); writes `.bak` before each file; skips silently when var is empty, warns when path set but missing - `OLLAMA_MODELS_PATH` env var on the pod is not set by the script — must be set in config if models live outside default location on the network volume - GPU selection only queries `secureCloud == true` pods; community cloud is excluded @@ -49,3 +51,5 @@ All logic is in `main()` which runs these steps in order: | `~/.config/runpod-session/config` | Sourced as bash; holds API key, defaults | | `~/.config/runpod-session/state.json` | Last session record (pod_id, url, model, timestamp) | | `~/.config/opencode/opencode.jsonc` | Patched in-place; `.bak` written before changes | +| `$TRANSART_SCRIPT` | `OLLAMA_HOST` rewritten on each session start; `.bak` written first | +| `$PUBLISHER_CONFIG` | `ollama_host` rewritten on each session start; `.bak` written first | @@ -56,6 +56,10 @@ CONTAINER_DISK_GB=15 GPU_COUNT=1 STARTUP_TIMEOUT=240 # seconds to wait for Ollama to become reachable WARMUP_NUM_CTX=32768 # context size used when pre-loading models into VRAM + +# External tool configs to patch with the live pod URL (leave empty to skip) +TRANSART_SCRIPT="" # e.g. /home/user/bin/transart.py +PUBLISHER_CONFIG="" # e.g. /home/user/.config/my-publisher/config.toml ``` ## Usage @@ -109,12 +113,14 @@ runpod-session.sh --new --gpu-type "RTX 4090" --max-price 1.80 4. **Startup wait** — polls `https://<pod-id>-11434.proxy.runpod.net/api/tags` every 5 seconds until Ollama responds (up to `STARTUP_TIMEOUT` seconds). -5. **opencode.jsonc patch** — updates three fields in your opencode config: +5. **Config patching** — updates your opencode config and any external tools configured via `TRANSART_SCRIPT` / `PUBLISHER_CONFIG`: - `provider.runpod.options.baseURL` → the live pod URL - `model` → `runpod/<DEFAULT_MODEL>` - `provider.runpod.models` → merges all `WARMUP_MODELS` in (existing per-model settings are preserved via jq recursive merge) + - `OLLAMA_HOST` in `transart.py` → bare pod URL (no `/v1`) + - `ollama_host` in `my-publisher/config.toml` → bare pod URL (no `/v1`) - A `.bak` copy is written before any changes. + A `.bak` copy is written before each file is modified. Entries left empty in config are skipped. 6. **Model warmup** — sends a short generation request to load the model into VRAM at `WARMUP_NUM_CTX` context length, so the first real request isn't slow. @@ -146,6 +152,8 @@ Your `~/.config/opencode/opencode.jsonc` needs a `runpod` provider block before | `~/.config/runpod-session/state.json` | Last session record | | `~/.config/opencode/opencode.jsonc` | Patched on each session start | | `~/.config/opencode/opencode.jsonc.bak` | Backup written before each patch | +| `$TRANSART_SCRIPT` | `OLLAMA_HOST` updated if set in config | +| `$PUBLISHER_CONFIG` | `ollama_host` updated if set in config | ## Cost notes diff --git a/runpod-session.sh b/runpod-session.sh index c81e8dd..faf0098 100755 --- a/runpod-session.sh +++ b/runpod-session.sh @@ -29,7 +29,7 @@ RUNPOD_API="https://api.runpod.io/graphql" # ─── Defaults (overridden by config file) ───────────────────────────────────── OLLAMA_IMAGE="ollama/ollama:latest" -NETWORK_VOLUME_NAME="danixland-storage" +NETWORK_VOLUME_NAME="my-storage" OPENCODE_PROVIDER="runpod" DEFAULT_MODEL="qwen3-coder:latest" WARMUP_MODELS="qwen3-coder:latest translategemma:27b" @@ -40,6 +40,8 @@ GPU_COUNT=1 POLL_INTERVAL=5 STARTUP_TIMEOUT=240 WARMUP_NUM_CTX=32768 +TRANSART_SCRIPT="" +PUBLISHER_CONFIG="" # ─── Colors ─────────────────────────────────────────────────────────────────── RED='\033[0;31m'; YELLOW='\033[1;33m'; GREEN='\033[0;32m' @@ -66,7 +68,7 @@ if [[ ! -f "$SESSION_CONFIG" ]]; then RUNPOD_API_KEY="" # Network volume name as shown in RunPod dashboard -NETWORK_VOLUME_NAME="danixland-storage" +NETWORK_VOLUME_NAME="my-storage" # Must match the key in your opencode.json "provider" block OPENCODE_PROVIDER="runpod" @@ -87,6 +89,10 @@ CONTAINER_DISK_GB=15 GPU_COUNT=1 STARTUP_TIMEOUT=240 # seconds before giving up waiting for Ollama WARMUP_NUM_CTX=32768 # num_ctx used when warming up models into VRAM + +# External tool configs to patch with the live pod URL (leave empty to skip) +TRANSART_SCRIPT="" # e.g. /home/user/bin/transart.py +PUBLISHER_CONFIG="" # e.g. /home/user/.config/my-publisher/config.toml CONF echo "" echo -e "${YELLOW}Edit ${BOLD}$SESSION_CONFIG${RESET}${YELLOW}, set RUNPOD_API_KEY, then re-run.${RESET}" @@ -445,6 +451,36 @@ patch_opencode_config() { log " model = ${OPENCODE_PROVIDER}/${DEFAULT_MODEL}" } +# ─── Patch external tool configs ───────────────────────────────────────────── +# +# Updates the Ollama host URL in: +# transart.py — replaces OLLAMA_HOST = "..." (bare URL, no /v1) +# config.toml — replaces ollama_host = "..." (bare URL, no /v1) +# +patch_external_configs() { + local bare_url="$1" # https://<pod-id>-11434.proxy.runpod.net (no /v1) + + if [[ -n "${TRANSART_SCRIPT:-}" ]]; then + if [[ ! -f "$TRANSART_SCRIPT" ]]; then + warn "TRANSART_SCRIPT not found: $TRANSART_SCRIPT — skipping" + else + cp "$TRANSART_SCRIPT" "${TRANSART_SCRIPT}.bak" + sed -i "s|^OLLAMA_HOST = \".*\"|OLLAMA_HOST = \"${bare_url}\"|" "$TRANSART_SCRIPT" + ok "transart.py patched: OLLAMA_HOST = $bare_url" + fi + fi + + if [[ -n "${PUBLISHER_CONFIG:-}" ]]; then + if [[ ! -f "$PUBLISHER_CONFIG" ]]; then + warn "PUBLISHER_CONFIG not found: $PUBLISHER_CONFIG — skipping" + else + cp "$PUBLISHER_CONFIG" "${PUBLISHER_CONFIG}.bak" + sed -i "s|^ollama_host = \".*\"|ollama_host = \"${bare_url}\"|" "$PUBLISHER_CONFIG" + ok "my-publisher config patched: ollama_host = $bare_url" + fi + fi +} + # ─── Warm up one model ──────────────────────────────────────────────────────── warmup_model() { local pod_id="$1" model="$2" @@ -582,6 +618,10 @@ main() { # ── 5. Patch opencode.json ──────────────────────────────────────────────── patch_opencode_config "$ollama_url" + # ── 5b. Patch external tool configs (transart, my-publisher) ───────────── + local bare_url="https://${pod_id}-11434.proxy.runpod.net" + patch_external_configs "$bare_url" + # ── 6. Warmup ───────────────────────────────────────────────────────────── if [[ $OPT_ALL_MODELS -eq 1 ]]; then for m in $WARMUP_MODELS; do |