Merge remote-tracking branch 'origin/main' into docker-blackwell-build
# Conflicts: # unsloth/models/vision.py
This commit is contained in:
Daniel Han
commit
08a1bf6680
157 changed files with 28085 additions and 3619 deletions
274
.github/scripts/agent-guides-drive.sh
vendored
274
.github/scripts/agent-guides-drive.sh
vendored
|
|
@ -6,12 +6,12 @@
|
|||
# Local Agent Guides CI. All failures from here are failure class (c)
|
||||
# "guide drift": the server preflight already passed and the agent CLI
|
||||
# already installed, so a failure here means the documented recipe in
|
||||
# unsloth_cli/commands/connect.py no longer produces a working flow.
|
||||
# unsloth_cli/commands/start.py no longer produces a working flow.
|
||||
#
|
||||
# Self-updating: for the 5 agents with a connect.py recipe we obtain the
|
||||
# exact env + command from `unsloth connect <agent> --no-launch` and run
|
||||
# THAT, so a recipe change is exercised automatically. Pi (no connect.py
|
||||
# command at HEAD) is driven by a hand-written recipe.
|
||||
# Self-updating: for all six agents (claude, codex, hermes, openclaw,
|
||||
# opencode, pi) we obtain the exact env + command from
|
||||
# `unsloth start <agent> --no-launch` and run THAT, so a recipe change is
|
||||
# exercised automatically.
|
||||
#
|
||||
# Every agent invocation is wrapped in `timeout` so a headless-TTY prompt
|
||||
# can never hang the runner -- a timeout is reported as guide drift with a
|
||||
|
|
@ -53,14 +53,14 @@ REDACTED_DIR="$REPO_ROOT/redacted-configs"
|
|||
WORKDIR_BASE="$REPO_ROOT/agent-workdir"
|
||||
CACHE_HELPER="$SCRIPT_DIR/assert-prompt-cache.sh"
|
||||
mkdir -p "$LOGS_DIR" "$REDACTED_DIR"
|
||||
CONNECT_REF="unsloth_cli/commands/connect.py"
|
||||
CONNECT_REF="unsloth_cli/commands/start.py"
|
||||
|
||||
# Prefill-shrinking flags for Claude Code. The heavyweight agents send
|
||||
# multi-thousand-token system prompts + full tool schemas, which on a CPU-only
|
||||
# runner is minutes of prefill per model round-trip (~16 tok/s for a 4B model).
|
||||
# Replacing the ~5.7k default system prompt with a tiny one (--system-prompt-file)
|
||||
# and restricting tools cuts the prefill to a few hundred tokens so it completes
|
||||
# quickly on CPU. These only shape the request size; the connect.py recipe
|
||||
# quickly on CPU. These only shape the request size; the start.py recipe
|
||||
# (endpoint, auth, model) is still exercised end to end.
|
||||
#
|
||||
# The bulk of Claude Code's prompt is the built-in tool JSON schemas: measured
|
||||
|
|
@ -105,6 +105,13 @@ redact() {
|
|||
done
|
||||
}
|
||||
|
||||
# Print a file to the log with the key scrubbed, without mutating it (the raw file is
|
||||
# still needed to parse the real env). Use this instead of `cat` for any transcript that
|
||||
# carries an `export UNSLOTH_API_KEY=...` line, so a live key never reaches Actions logs.
|
||||
cat_redacted() {
|
||||
sed "s#${UNSLOTH_API_KEY}#<REDACTED>#g" "$1"
|
||||
}
|
||||
|
||||
# A reply must be non-empty and free of connection/auth errors.
|
||||
assert_reply() {
|
||||
local out="$1"
|
||||
|
|
@ -131,45 +138,29 @@ run_timed() { # $1=outfile, rest=command
|
|||
return "$rc"
|
||||
}
|
||||
|
||||
# ── Pi: no connect.py command at HEAD -> hand-written recipe ──────────────
|
||||
write_pi_config() {
|
||||
if unsloth connect pi --help >/dev/null 2>&1; then
|
||||
# Tripwire: once a real recipe exists, the hand-written config would mask any
|
||||
# drift in it, defeating the point of this CI. Fail hard so the cell is
|
||||
# migrated to the self-updating `unsloth connect pi --no-launch` path.
|
||||
guide_fail "connect.py now ships a 'pi' command -- migrate this CI cell to the 'unsloth connect pi --no-launch' path so the documented recipe is exercised (the hand-written Pi config no longer reflects it)"
|
||||
fi
|
||||
mkdir -p "$HOME/.pi/agent"
|
||||
python3 - "$UNSLOTH_BASE_URL" "$UNSLOTH_API_KEY" "$UNSLOTH_MODEL_ID" <<'PY'
|
||||
import json, os, sys
|
||||
base, key, model = sys.argv[1], sys.argv[2], sys.argv[3]
|
||||
cfg = {"providers": {"unsloth": {
|
||||
"api": "openai-completions",
|
||||
"baseUrl": f"{base}/v1",
|
||||
"apiKey": key,
|
||||
"models": [{"id": model}],
|
||||
}}}
|
||||
path = os.path.expanduser("~/.pi/agent/models.json")
|
||||
with open(path, "w") as fh:
|
||||
json.dump(cfg, fh, indent=2)
|
||||
PY
|
||||
cp "$HOME/.pi/agent/models.json" "$REDACTED_DIR/pi-models.json" 2>/dev/null || true
|
||||
redact "$REDACTED_DIR/pi-models.json"
|
||||
# Read a value from an `export VAR=...` line in the connect --no-launch output.
|
||||
# `unsloth start` writes each agent's session config off the user's ~ and points
|
||||
# at it through a relocation env var (CODEX_HOME / OPENCODE_CONFIG /
|
||||
# OPENCLAW_CONFIG_PATH), so the contract checks read the path from here.
|
||||
raw_env() { # $1 = var name -> value (one shlex-quote layer stripped)
|
||||
local raw="$LOGS_DIR/connect-${AGENT}.txt"
|
||||
local v; v="$(sed -n "s/^export $1=//p" "$raw" | tail -1)"
|
||||
v="${v#\'}"; v="${v%\'}"; printf '%s' "$v"
|
||||
}
|
||||
|
||||
# ── 5-agent connect.py path: parse env + command from --no-launch ─────────
|
||||
# ── 5-agent start.py path: parse env + command from --no-launch ─────────
|
||||
# Populates globals CONNECT_ENV (export/unset lines) and CONNECT_CMD (the
|
||||
# launch command on the last printed line), and runs connect.py's config
|
||||
# writers as a side effect (it writes ~/.codex, ~/.claude, etc.).
|
||||
# launch command on the last printed line), and runs start.py's config
|
||||
# writers as a side effect (it writes each agent's relocated session config).
|
||||
parse_connect() {
|
||||
local raw="$LOGS_DIR/connect-${AGENT}.txt"
|
||||
if ! unsloth connect "$AGENT" --no-launch --api-key "$UNSLOTH_API_KEY" > "$raw" 2>&1; then
|
||||
cat "$raw"
|
||||
guide_fail "'unsloth connect ${AGENT} --no-launch' exited non-zero"
|
||||
if ! unsloth start "$AGENT" --no-launch --api-key "$UNSLOTH_API_KEY" > "$raw" 2>&1; then
|
||||
cat_redacted "$raw"
|
||||
guide_fail "'unsloth start ${AGENT} --no-launch' exited non-zero"
|
||||
fi
|
||||
echo "[$AGENT] connect --no-launch printed:"; cat "$raw"
|
||||
echo "[$AGENT] connect --no-launch printed:"; cat_redacted "$raw"
|
||||
CONNECT_ENV="$(grep -E '^(export |unset )' "$raw" || true)"
|
||||
# The launch command is the last non-export, non-status line. connect.py
|
||||
# The launch command is the last non-export, non-status line. start.py
|
||||
# prints "Studio <url> · model <id>" and "Updated ..." status lines first.
|
||||
CONNECT_CMD="$(grep -vE '^(export |unset |Studio |Updated |Disabled |Warning|Loading)' "$raw" \
|
||||
| grep -E '[^[:space:]]' | tail -1)"
|
||||
|
|
@ -177,45 +168,63 @@ parse_connect() {
|
|||
redact "$raw"
|
||||
}
|
||||
|
||||
# Cross-check the documented contract knobs so silent connect.py changes
|
||||
# Cross-check the documented contract knobs so silent start.py changes
|
||||
# (env-var rename, wire_api flip, attribution setting drop) also fail/flag.
|
||||
crosscheck_contract() {
|
||||
local raw="$LOGS_DIR/connect-${AGENT}.txt"
|
||||
local cfg home
|
||||
case "$AGENT" in
|
||||
codex)
|
||||
grep -q 'UNSLOTH_STUDIO_AUTH_TOKEN' "$raw" \
|
||||
|| guide_fail "Codex env key is no longer UNSLOTH_STUDIO_AUTH_TOKEN (connect.py _CODEX_ENV_KEY)"
|
||||
if [ -f "$HOME/.codex/config.toml" ]; then
|
||||
grep -q 'wire_api = "responses"' "$HOME/.codex/config.toml" \
|
||||
|| guide_fail "Codex wire_api is no longer \"responses\" in ~/.codex/config.toml"
|
||||
cp "$HOME/.codex/config.toml" "$REDACTED_DIR/codex-config.toml"
|
||||
|| guide_fail "Codex env key is no longer UNSLOTH_STUDIO_AUTH_TOKEN (start.py _CODEX_ENV_KEY)"
|
||||
home="$(raw_env CODEX_HOME)"
|
||||
# An empty relocation var would make cfg "/config.toml" and silently
|
||||
# skip the [ -f ] contract check below; fail loudly instead.
|
||||
[ -n "$home" ] || guide_fail "CODEX_HOME missing from connect output (start.py codex())"
|
||||
cfg="$home/config.toml"
|
||||
if [ -f "$cfg" ]; then
|
||||
grep -q 'wire_api = "responses"' "$cfg" \
|
||||
|| guide_fail "Codex wire_api is no longer \"responses\" in \$CODEX_HOME/config.toml"
|
||||
cp "$cfg" "$REDACTED_DIR/codex-config.toml"
|
||||
fi
|
||||
grep -q 'codex --oss --profile unsloth_api' "$raw" \
|
||||
|| echo "::warning::Codex launch command changed from 'codex --oss --profile unsloth_api'"
|
||||
;;
|
||||
claude)
|
||||
grep -q 'ANTHROPIC_AUTH_TOKEN' "$raw" \
|
||||
|| guide_fail "Claude no longer exports ANTHROPIC_AUTH_TOKEN (connect.py claude())"
|
||||
if [ -f "$HOME/.claude/settings.json" ]; then
|
||||
grep -q '"CLAUDE_CODE_ATTRIBUTION_HEADER"' "$HOME/.claude/settings.json" \
|
||||
|| echo "::warning::CLAUDE_CODE_ATTRIBUTION_HEADER not written to ~/.claude/settings.json (ensure_claude_attribution_header)"
|
||||
cp "$HOME/.claude/settings.json" "$REDACTED_DIR/claude-settings.json"
|
||||
fi
|
||||
|| guide_fail "Claude no longer exports ANTHROPIC_AUTH_TOKEN (start.py claude())"
|
||||
grep -q 'CLAUDE_CODE_ATTRIBUTION_HEADER' "$raw" \
|
||||
|| echo "::warning::CLAUDE_CODE_ATTRIBUTION_HEADER no longer set for the session (start.py claude())"
|
||||
;;
|
||||
hermes)
|
||||
grep -q 'UNSLOTH_API_KEY' "$raw" \
|
||||
|| guide_fail "Hermes env key is no longer UNSLOTH_API_KEY (connect.py _HERMES_ENV_KEY)"
|
||||
[ -f "$HOME/.hermes/config.yaml" ] && cp "$HOME/.hermes/config.yaml" "$REDACTED_DIR/hermes-config.yaml"
|
||||
|| guide_fail "Hermes env key is no longer UNSLOTH_API_KEY (start.py _HERMES_ENV_KEY)"
|
||||
home="$(raw_env HERMES_HOME)"
|
||||
[ -n "$home" ] || guide_fail "HERMES_HOME missing from connect output (start.py hermes())"
|
||||
cfg="$home/config.yaml"
|
||||
[ -f "$cfg" ] && cp "$cfg" "$REDACTED_DIR/hermes-config.yaml"
|
||||
;;
|
||||
openclaw)
|
||||
if [ -f "$HOME/.openclaw/openclaw.json" ]; then
|
||||
grep -q '"openai-completions"' "$HOME/.openclaw/openclaw.json" \
|
||||
cfg="$(raw_env OPENCLAW_CONFIG_PATH)"
|
||||
if [ -n "$cfg" ] && [ -f "$cfg" ]; then
|
||||
grep -q '"openai-completions"' "$cfg" \
|
||||
|| echo "::warning::OpenClaw provider api is no longer 'openai-completions' (write_openclaw_config)"
|
||||
cp "$HOME/.openclaw/openclaw.json" "$REDACTED_DIR/openclaw.json"
|
||||
cp "$cfg" "$REDACTED_DIR/openclaw.json"
|
||||
fi
|
||||
;;
|
||||
opencode)
|
||||
[ -f "$HOME/.config/opencode/opencode.json" ] && cp "$HOME/.config/opencode/opencode.json" "$REDACTED_DIR/opencode.json"
|
||||
cfg="$(raw_env OPENCODE_CONFIG)"
|
||||
[ -n "$cfg" ] && [ -f "$cfg" ] && cp "$cfg" "$REDACTED_DIR/opencode.json"
|
||||
;;
|
||||
pi)
|
||||
# Pi has no config-dir env var; the session is HOME-relocated, and the
|
||||
# provider config lives at $HOME/.pi/agent/models.json.
|
||||
cfg="$(raw_env HOME)/.pi/agent/models.json"
|
||||
if [ -f "$cfg" ]; then
|
||||
grep -q '"openai-completions"' "$cfg" \
|
||||
|| echo "::warning::Pi provider api is no longer 'openai-completions' (write_pi_config)"
|
||||
cp "$cfg" "$REDACTED_DIR/pi-models.json"
|
||||
fi
|
||||
;;
|
||||
esac
|
||||
redact "$REDACTED_DIR"/* 2>/dev/null || true
|
||||
|
|
@ -229,16 +238,23 @@ crosscheck_contract() {
|
|||
|
||||
# Hermes: an explicit empty cli toolset disables all tools (and drops the
|
||||
# tool-gated guidance blocks), so -z sends ~300 tokens instead of thousands.
|
||||
# hermes ships a DEFAULT config.yaml that already has a populated
|
||||
# platform_toolsets, and `unsloth connect` merges into it, so we must override
|
||||
# cli (not just append). That needs a YAML parser, and the runner's bare
|
||||
# python3 has no PyYAML -- but the venv that ships `unsloth` does (connect.py
|
||||
# imports yaml), so run the patch with that interpreter.
|
||||
# Hermes enables its default cli toolset when the session config does not pin one,
|
||||
# so we must set platform_toolsets.cli explicitly to [] (not just append) to get
|
||||
# zero tools. That needs a YAML parser, and the runner's bare python3 has no
|
||||
# PyYAML -- but the venv that ships `unsloth` does (start.py imports yaml), so run
|
||||
# the patch with that interpreter. We patch the relocated $HERMES_HOME/config.yaml
|
||||
# that `unsloth start` printed, not the user's ~/.hermes.
|
||||
# (-z reads platform_toolsets.cli; --ignore-rules is a no-op under -z.)
|
||||
patch_hermes_tools() { # $1 = none|default
|
||||
# Check the raw var BEFORE appending /config.yaml: the joined path is never
|
||||
# empty, so the old guard could not fire and the patcher would die on
|
||||
# "/config.yaml" with a bare traceback instead of this clear failure.
|
||||
local home; home="$(raw_env HERMES_HOME)"
|
||||
[ -n "$home" ] || guide_fail "Hermes HERMES_HOME missing from connect output (start.py hermes())"
|
||||
local cfg; cfg="$home/config.yaml"
|
||||
# Find a python that can import yaml. The runner's bare python3 cannot, but the
|
||||
# interpreter in the `unsloth` console-script shebang provably can (it runs
|
||||
# connect.py's write_hermes_config, which imports yaml). Try that first, then
|
||||
# start.py's write_hermes_config, which imports yaml). Try that first, then
|
||||
# any python on PATH, then the venv sibling, picking the first with PyYAML.
|
||||
local cand py="" shebang
|
||||
shebang="$(head -1 "$(command -v unsloth)" 2>/dev/null | sed -n 's/^#![[:space:]]*//p' | awk '{print $1}')"
|
||||
|
|
@ -247,13 +263,13 @@ patch_hermes_tools() { # $1 = none|default
|
|||
{ [ -x "$cand" ] || command -v "$cand" >/dev/null 2>&1; } || continue
|
||||
if "$cand" -c 'import yaml' 2>/dev/null; then py="$cand"; break; fi
|
||||
done
|
||||
[ -n "$py" ] || guide_fail "could not find a python with PyYAML to patch ~/.hermes/config.yaml"
|
||||
echo "[hermes] patching config with $py"
|
||||
"$py" - "$1" <<'PY'
|
||||
[ -n "$py" ] || guide_fail "could not find a python with PyYAML to patch the hermes session config"
|
||||
echo "[hermes] patching $cfg with $py"
|
||||
"$py" - "$1" "$cfg" <<'PY'
|
||||
import os, sys
|
||||
import yaml
|
||||
mode = sys.argv[1]
|
||||
p = os.path.expanduser("~/.hermes/config.yaml")
|
||||
p = sys.argv[2]
|
||||
cfg = (yaml.safe_load(open(p)) or {}) if os.path.exists(p) else {}
|
||||
ts = cfg.get("platform_toolsets")
|
||||
if not isinstance(ts, dict):
|
||||
|
|
@ -274,10 +290,14 @@ PY
|
|||
# drop the auto-injected AGENTS.md/SOUL.md bootstrap (the bulk of the prompt) for
|
||||
# both modes. --agent must reference a defined agent, so write it before invoking.
|
||||
patch_openclaw_agent() { # $1 = notools|tools
|
||||
python3 - "$1" <<'PY'
|
||||
# OpenClaw reads its config from the relocated OPENCLAW_CONFIG_PATH that
|
||||
# `unsloth start` printed, so patch THAT file (not the user's ~/.openclaw).
|
||||
local cfg; cfg="$(raw_env OPENCLAW_CONFIG_PATH)"
|
||||
[ -n "$cfg" ] || guide_fail "OpenClaw OPENCLAW_CONFIG_PATH missing from connect output (start.py openclaw())"
|
||||
python3 - "$1" "$cfg" <<'PY'
|
||||
import os, sys, json
|
||||
mode = sys.argv[1]
|
||||
p = os.path.expanduser("~/.openclaw/openclaw.json")
|
||||
p = sys.argv[2]
|
||||
cfg = json.load(open(p)) if os.path.exists(p) else {}
|
||||
agents = cfg.setdefault("agents", {})
|
||||
agents.setdefault("defaults", {})["skipBootstrap"] = True
|
||||
|
|
@ -293,20 +313,24 @@ print(f"[openclaw] agent ci tools = {agent.get('tools', 'default')}")
|
|||
PY
|
||||
}
|
||||
|
||||
# Build an invoke script that applies connect.py's env then runs the launch
|
||||
# Build an invoke script that applies start.py's env then runs the launch
|
||||
# command (with extra args appended) under bash. We do NOT eval connect's env
|
||||
# into this shell; we write it into a one-shot script so the export/unset
|
||||
# semantics are exactly what connect.py printed. The script path is absolute
|
||||
# semantics are exactly what start.py printed. The script path is absolute
|
||||
# so it is valid even when the caller has cd'd into a scratch work dir.
|
||||
invoke_via_connect() { # $1=outfile, rest=extra args appended to the command
|
||||
local out="$1"; shift
|
||||
local script="$LOGS_DIR/invoke-${AGENT}.sh"
|
||||
local real; real="$(mktemp)"
|
||||
# CONNECT_ENV_EXTRA / CONNECT_CMD_OVERRIDE let a caller (attribution-ab) flip a
|
||||
# session knob without editing the user's config; empty -> use what start.py emitted.
|
||||
local cmd="${CONNECT_CMD_OVERRIDE:-$CONNECT_CMD}"
|
||||
{
|
||||
echo "set -uo pipefail"
|
||||
echo "$CONNECT_ENV"
|
||||
[ -n "${CONNECT_ENV_EXTRA:-}" ] && echo "$CONNECT_ENV_EXTRA"
|
||||
# Append extra args (the prompt / flags) to the launch command verbatim.
|
||||
printf '%s' "$CONNECT_CMD"
|
||||
printf '%s' "$cmd"
|
||||
local a
|
||||
for a in "$@"; do printf ' %q' "$a"; done
|
||||
printf '\n'
|
||||
|
|
@ -318,7 +342,9 @@ invoke_via_connect() { # $1=outfile, rest=extra args appended to the command
|
|||
# Writing the redacted copy up front keeps the key out of the artifact even if
|
||||
# the run times out (run_timed exits before returning here).
|
||||
cp "$real" "$script"; redact "$script"
|
||||
echo "[$AGENT] invoking (timeout ${TIMEOUT}s): $CONNECT_CMD $*"
|
||||
# The connect one-liner now carries the key as an inline env assignment; scrub it on
|
||||
# the way to the log (the executed $real keeps the live value).
|
||||
echo "[$AGENT] invoking (timeout ${TIMEOUT}s): ${cmd//${UNSLOTH_API_KEY}/<REDACTED>} $*"
|
||||
run_timed "$out" bash "$real"
|
||||
local rc=$?
|
||||
rm -f "$real"
|
||||
|
|
@ -332,27 +358,23 @@ case "$MODE" in
|
|||
connection)
|
||||
PROMPT='Reply with exactly the single word: pong'
|
||||
OUT="$LOGS_DIR/${AGENT}-connection.txt"
|
||||
if [ "$AGENT" = "pi" ]; then
|
||||
write_pi_config
|
||||
run_timed "$OUT" pi -p --provider unsloth --model "$UNSLOTH_MODEL_ID" "$PROMPT"
|
||||
else
|
||||
parse_connect
|
||||
crosscheck_contract
|
||||
# claude/codex run in print mode via the flags connect.py emits
|
||||
# (claude -p / codex exec). For agents whose default subcommand prints
|
||||
# to stdout we pass the prompt through ctx.args.
|
||||
case "$AGENT" in
|
||||
claude) invoke_via_connect "$OUT" "${CLAUDE_CONNECT_FLAGS[@]}" -p "$PROMPT" ;;
|
||||
codex) invoke_via_connect "$OUT" exec --dangerously-bypass-approvals-and-sandbox "$PROMPT" ;;
|
||||
opencode) invoke_via_connect "$OUT" run "$PROMPT" ;;
|
||||
hermes) patch_hermes_tools none
|
||||
invoke_via_connect "$OUT" -z "$PROMPT" ;;
|
||||
openclaw) patch_openclaw_agent notools
|
||||
invoke_via_connect "$OUT" agent --local --agent ci \
|
||||
--model "unsloth/${UNSLOTH_MODEL_ID}" --message "$PROMPT" ;;
|
||||
*) invoke_via_connect "$OUT" "$PROMPT" ;;
|
||||
esac
|
||||
fi
|
||||
parse_connect
|
||||
crosscheck_contract
|
||||
# claude/codex run in print mode via the flags start.py emits
|
||||
# (claude -p / codex exec). For agents whose default subcommand prints
|
||||
# to stdout we pass the prompt through ctx.args.
|
||||
case "$AGENT" in
|
||||
claude) invoke_via_connect "$OUT" "${CLAUDE_CONNECT_FLAGS[@]}" -p "$PROMPT" ;;
|
||||
codex) invoke_via_connect "$OUT" exec --dangerously-bypass-approvals-and-sandbox "$PROMPT" ;;
|
||||
opencode) invoke_via_connect "$OUT" run "$PROMPT" ;;
|
||||
pi) invoke_via_connect "$OUT" -p "$PROMPT" ;;
|
||||
hermes) patch_hermes_tools none
|
||||
invoke_via_connect "$OUT" -z "$PROMPT" ;;
|
||||
openclaw) patch_openclaw_agent notools
|
||||
invoke_via_connect "$OUT" agent --local --agent ci \
|
||||
--model "unsloth/${UNSLOTH_MODEL_ID}" --message "$PROMPT" ;;
|
||||
*) invoke_via_connect "$OUT" "$PROMPT" ;;
|
||||
esac
|
||||
# A non-zero exit from the documented launch command is drift even if it
|
||||
# printed something: a benign-looking "command not found" / usage dump would
|
||||
# otherwise slip past assert_reply (which only flags empty/error-keyword text).
|
||||
|
|
@ -371,22 +393,18 @@ case "$MODE" in
|
|||
T1='Create a file named hello.py in the current directory whose entire contents are a single line: print("Hello"). Do not run it.'
|
||||
T2='Run hello.py with python and show me the exact output.'
|
||||
|
||||
# The connect.py recipe writers + crosscheck must see the repo; run them
|
||||
# The start.py recipe writers + crosscheck must see the repo; run them
|
||||
# from the repo root BEFORE cd-ing into the scratch work dir.
|
||||
if [ "$AGENT" != "pi" ]; then
|
||||
parse_connect
|
||||
crosscheck_contract
|
||||
# File-edit needs real tools, so we cannot zero them as in connection.
|
||||
# hermes keeps default tools; openclaw still strips its AGENTS.md/SOUL.md
|
||||
# bootstrap (the largest prompt chunk) via the 'ci' agent. The scratch work
|
||||
# dir is empty, so no project context files are auto-loaded either.
|
||||
case "$AGENT" in
|
||||
hermes) patch_hermes_tools default ;;
|
||||
openclaw) patch_openclaw_agent tools ;;
|
||||
esac
|
||||
else
|
||||
write_pi_config
|
||||
fi
|
||||
parse_connect
|
||||
crosscheck_contract
|
||||
# File-edit needs real tools, so we cannot zero them as in connection.
|
||||
# hermes keeps default tools; openclaw still strips its AGENTS.md/SOUL.md
|
||||
# bootstrap (the largest prompt chunk) via the 'ci' agent. The scratch work
|
||||
# dir is empty, so no project context files are auto-loaded either.
|
||||
case "$AGENT" in
|
||||
hermes) patch_hermes_tools default ;;
|
||||
openclaw) patch_openclaw_agent tools ;;
|
||||
esac
|
||||
|
||||
# Drive from inside the work dir so the agent edits files there. All log
|
||||
# writes use absolute $LOGS_DIR, so cwd does not matter for them.
|
||||
|
|
@ -395,7 +413,14 @@ case "$MODE" in
|
|||
invoke_turn() { # $1=outfile $2=continue? $3=prompt
|
||||
local out="$1" cont="$2" prompt="$3"
|
||||
case "$AGENT" in
|
||||
pi) run_timed "$out" pi -p --provider unsloth --model "$UNSLOTH_MODEL_ID" "$prompt" ;;
|
||||
pi)
|
||||
# Pi continues the previous session with -c; provider/model come from
|
||||
# the parsed `unsloth start pi` recipe (CONNECT_CMD), not hardcoded here.
|
||||
if [ "$cont" = "continue" ]; then
|
||||
invoke_via_connect "$out" -p --continue "$prompt"
|
||||
else
|
||||
invoke_via_connect "$out" -p "$prompt"
|
||||
fi ;;
|
||||
claude)
|
||||
# --dangerously-skip-permissions lets headless claude actually use the
|
||||
# Write/Bash tools (otherwise it blocks on an approval prompt and emits
|
||||
|
|
@ -466,33 +491,32 @@ case "$MODE" in
|
|||
# right before the measured turn, so an earlier turn's reuse can't leak in.
|
||||
LLAMA_LOG_DIR="${UNSLOTH_LLAMA_LOG_DIR:-$HOME/.unsloth/studio/logs/llama-server}"
|
||||
export LLAMA_LOG_DIR
|
||||
parse_connect # writes ~/.claude/settings.json (header=0) + env
|
||||
parse_connect # prints session env + suppression flags (no ~/.claude write)
|
||||
crosscheck_contract
|
||||
PROMPT='Reply with exactly the single word: pong'
|
||||
|
||||
# Phase A: header DISABLED (=0, the documented setting) -> expect a HIT on
|
||||
# the continued turn. connect.py's ensure_claude_attribution_header() set 0.
|
||||
# Phase A: the suppression start.py ships (CLAUDE_CODE_ATTRIBUTION_HEADER=0 +
|
||||
# --exclude-dynamic-system-prompt-sections + --settings overlay) -> expect a
|
||||
# HIT on the continued turn, since the system-prompt prefix is stable.
|
||||
invoke_via_connect "$LOGS_DIR/claude-ab-hit-1.txt" -p "$PROMPT" # turn 1 primes
|
||||
FROM_HIT="$(bash "$CACHE_HELPER" mark)" # offset before turn 2
|
||||
invoke_via_connect "$LOGS_DIR/claude-ab-hit-2.txt" -p --continue "$PROMPT again"
|
||||
CACHE_LOG_FROM="$FROM_HIT" bash "$CACHE_HELPER" log HIT
|
||||
|
||||
# Phase B: header ENABLED -> expect a MISS. The header prepends a
|
||||
# per-request-changing attribution line to the system prompt, so the shared
|
||||
# prefix changes every turn and the KV cache is invalidated (~90% slower);
|
||||
# this is exactly what the guide flag prevents.
|
||||
python3 - <<'PY'
|
||||
import json, os
|
||||
p = os.path.expanduser("~/.claude/settings.json")
|
||||
s = json.load(open(p)) if os.path.exists(p) else {}
|
||||
s.setdefault("env", {})["CLAUDE_CODE_ATTRIBUTION_HEADER"] = "1"
|
||||
json.dump(s, open(p, "w"), indent=2)
|
||||
PY
|
||||
# Phase B: vanilla Claude with the header ENABLED -> expect a MISS. We flip
|
||||
# the env var to 1 and strip the suppression flags from the launch command
|
||||
# (without them the dynamic attribution line is included and changes every
|
||||
# turn, so the shared prefix moves and the KV cache is invalidated, ~90%
|
||||
# slower). This is session-only: nothing is written to ~/.claude.
|
||||
CONNECT_ENV_EXTRA='export CLAUDE_CODE_ATTRIBUTION_HEADER=1'
|
||||
CONNECT_CMD_OVERRIDE="$(printf '%s' "$CONNECT_CMD" \
|
||||
| sed -E "s/ --exclude-dynamic-system-prompt-sections//; s/ --settings '[^']*'//")"
|
||||
invoke_via_connect "$LOGS_DIR/claude-ab-miss-1.txt" -p "$PROMPT"
|
||||
FROM_MISS="$(bash "$CACHE_HELPER" mark)"
|
||||
invoke_via_connect "$LOGS_DIR/claude-ab-miss-2.txt" -p --continue "$PROMPT again"
|
||||
CACHE_LOG_FROM="$FROM_MISS" bash "$CACHE_HELPER" log MISS
|
||||
echo "[claude] attribution A/B OK (header=0 HIT, header=1 MISS)"
|
||||
unset CONNECT_ENV_EXTRA CONNECT_CMD_OVERRIDE
|
||||
echo "[claude] attribution A/B OK (suppressed HIT, header=1 MISS)"
|
||||
;;
|
||||
|
||||
*)
|
||||
|
|
|
|||
33
.github/scripts/agent-guides-install.sh
vendored
33
.github/scripts/agent-guides-install.sh
vendored
|
|
@ -7,7 +7,7 @@
|
|||
# is the single biggest source of false reds, so installs retry with
|
||||
# backoff and the only ::error:: this script can emit is class (b). The
|
||||
# install recipes mirror the install_hint strings in
|
||||
# unsloth_cli/commands/connect.py at HEAD.
|
||||
# unsloth_cli/commands/start.py at HEAD.
|
||||
#
|
||||
# Usage: agent-guides-install.sh <agent>
|
||||
# agent in: claude codex hermes openclaw opencode pi
|
||||
|
|
@ -25,13 +25,14 @@ install_fail() {
|
|||
}
|
||||
|
||||
# npm registry flakiness is common in CI; retry 3x with linear backoff.
|
||||
# Extra npm flags may precede the package (e.g. npm_retry --ignore-scripts pkg).
|
||||
npm_retry() {
|
||||
local pkg="$1" i
|
||||
local i
|
||||
for i in 1 2 3; do
|
||||
if npm install -g "$pkg" >> "$LOG" 2>&1; then
|
||||
if npm install -g "$@" >> "$LOG" 2>&1; then
|
||||
return 0
|
||||
fi
|
||||
echo "[install] npm install -g $pkg attempt $i failed; backing off $((i * 10))s" | tee -a "$LOG"
|
||||
echo "[install] npm install -g $* attempt $i failed; backing off $((i * 10))s" | tee -a "$LOG"
|
||||
sleep "$((i * 10))"
|
||||
done
|
||||
return 1
|
||||
|
|
@ -60,30 +61,30 @@ curl_bash() {
|
|||
echo "[install] agent=$AGENT (log=$LOG)"
|
||||
case "$AGENT" in
|
||||
claude)
|
||||
# connect.py install_hint: curl -fsSL https://claude.ai/install.sh | bash
|
||||
# start.py install_hint: curl -fsSL https://claude.ai/install.sh | bash
|
||||
curl_bash "https://claude.ai/install.sh" || install_fail "claude installer failed"
|
||||
# The installer drops the binary under ~/.local/bin.
|
||||
echo "$HOME/.local/bin" >> "$GITHUB_PATH"
|
||||
;;
|
||||
codex)
|
||||
# connect.py install_hint: npm install -g @openai/codex
|
||||
# start.py install_hint: npm install -g @openai/codex
|
||||
npm_retry "@openai/codex" || install_fail "npm install -g @openai/codex failed"
|
||||
;;
|
||||
opencode)
|
||||
# connect.py install_hint: npm install -g opencode-ai
|
||||
# start.py install_hint: npm install -g opencode-ai
|
||||
npm_retry "opencode-ai" || install_fail "npm install -g opencode-ai failed"
|
||||
;;
|
||||
openclaw)
|
||||
# connect.py install_hint: curl -fsSL https://openclaw.ai/install.sh | bash
|
||||
# start.py install_hint: curl -fsSL https://openclaw.ai/install.sh | bash
|
||||
# npm is the more deterministic path in CI and matches the agent's docs;
|
||||
# fall back to the connect.py curl installer if the npm tag is missing.
|
||||
# fall back to the start.py curl installer if the npm tag is missing.
|
||||
if ! npm_retry "openclaw@latest"; then
|
||||
curl_bash "https://openclaw.ai/install.sh" || install_fail "openclaw install failed (npm + curl)"
|
||||
echo "$HOME/.local/bin" >> "$GITHUB_PATH"
|
||||
fi
|
||||
;;
|
||||
hermes)
|
||||
# connect.py install_hint:
|
||||
# start.py install_hint:
|
||||
# curl -fsSL .../NousResearch/hermes-agent/main/scripts/install.sh | bash
|
||||
curl_bash "https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh" \
|
||||
--non-interactive --skip-setup --skip-browser --no-skills \
|
||||
|
|
@ -91,11 +92,13 @@ case "$AGENT" in
|
|||
echo "$HOME/.local/bin" >> "$GITHUB_PATH"
|
||||
;;
|
||||
pi)
|
||||
# No connect.py recipe; the agent's documented package name. The CLI moved
|
||||
# from the now-deprecated @mariozechner scope to @earendil-works (the old
|
||||
# scope is frozen, so installing it would test a stale Pi against the API).
|
||||
npm_retry "@earendil-works/pi-coding-agent" \
|
||||
|| install_fail "npm install -g @earendil-works/pi-coding-agent failed"
|
||||
# start.py install_hint: npm install -g --ignore-scripts @earendil-works/pi-coding-agent
|
||||
# (--ignore-scripts matches Pi's documented recipe; exercising the exact hint
|
||||
# catches guide drift). The CLI moved from the now-deprecated @mariozechner
|
||||
# scope to @earendil-works (the old scope is frozen, so installing it would
|
||||
# test a stale Pi against the API).
|
||||
npm_retry --ignore-scripts "@earendil-works/pi-coding-agent" \
|
||||
|| install_fail "npm install -g --ignore-scripts @earendil-works/pi-coding-agent failed"
|
||||
;;
|
||||
*)
|
||||
install_fail "unknown agent '$AGENT'"
|
||||
|
|
|
|||
2
.github/scripts/serve-unsloth-run.sh
vendored
2
.github/scripts/serve-unsloth-run.sh
vendored
|
|
@ -27,7 +27,7 @@
|
|||
#
|
||||
# Outputs written to $GITHUB_ENV (and echoed):
|
||||
# UNSLOTH_API_KEY the sk-unsloth-* key minted on the banner
|
||||
# UNSLOTH_STUDIO_URL http://127.0.0.1:<PORT> (so `unsloth connect`
|
||||
# UNSLOTH_STUDIO_URL http://127.0.0.1:<PORT> (so `unsloth start`
|
||||
# finds THIS server, not the hardcoded :8888)
|
||||
# UNSLOTH_BASE_URL same as UNSLOTH_STUDIO_URL (alias for clarity)
|
||||
# UNSLOTH_MODEL_ID the canonical id reported by /v1/models
|
||||
|
|
|
|||
50
.github/workflows/local-agent-guides-ci.yml
vendored
50
.github/workflows/local-agent-guides-ci.yml
vendored
|
|
@ -6,29 +6,27 @@
|
|||
# Detects when our local-agent setup recipes drift out of sync with
|
||||
# `unsloth run`. Boots a real `unsloth run --disable-tools` server and
|
||||
# drives the coding agents end to end through the *exact* recipes defined
|
||||
# in unsloth_cli/commands/connect.py (the in-repo source of truth -- there
|
||||
# is no docs/ tree). Wherever connect.py has a recipe we drive the agent
|
||||
# via `unsloth connect <agent> --no-launch` and execute what it prints, so
|
||||
# the test self-updates against connect.py and catches silent recipe drift.
|
||||
# in unsloth_cli/commands/start.py (the in-repo source of truth -- there
|
||||
# is no docs/ tree). Wherever start.py has a recipe we drive the agent
|
||||
# via `unsloth start <agent> --no-launch` and execute what it prints, so
|
||||
# the test self-updates against start.py and catches silent recipe drift.
|
||||
#
|
||||
# Source-of-truth files this workflow guards:
|
||||
# unsloth_cli/commands/connect.py the `unsloth connect <agent>` recipes
|
||||
# unsloth_cli/commands/start.py the `unsloth start <agent>` recipes
|
||||
# unsloth_cli/commands/studio.py the `unsloth run` banner (API Key line)
|
||||
#
|
||||
# Failure taxonomy (each surfaced with a distinct ::error:: + the agent name
|
||||
# + the connect.py location, so a red X is immediately triageable):
|
||||
# + the start.py location, so a red X is immediately triageable):
|
||||
# (a) Unsloth server/API regression -- the dialect HTTP preflight fails
|
||||
# BEFORE the agent runs (or the server never becomes healthy).
|
||||
# (b) Agent package install failed -- npm/curl install of the CLI failed.
|
||||
# (c) Guide drift -- preflight passed + install ok, but
|
||||
# the documented `unsloth connect` flow produced no/garbled output.
|
||||
# the documented `unsloth start` flow produced no/garbled output.
|
||||
#
|
||||
# Agents covered (6): claude, codex, hermes, openclaw, opencode, pi.
|
||||
# - claude/codex/hermes/openclaw/opencode have a connect.py recipe.
|
||||
# - pi has NO `unsloth connect pi` command in connect.py at HEAD; it is
|
||||
# driven by a hand-written recipe and the matrix cell asserts that the
|
||||
# missing connect recipe is the (known) reason, so the day connect.py
|
||||
# grows a `pi` command this cell flips to the self-updating path.
|
||||
# - All six have a `unsloth start <agent>` recipe, so each cell obtains its
|
||||
# env + command from `unsloth start <agent> --no-launch` and runs THAT
|
||||
# (self-updating: a recipe change is exercised automatically).
|
||||
|
||||
name: Local Agent Guides CI
|
||||
|
||||
|
|
@ -83,7 +81,7 @@ jobs:
|
|||
# ═════════════════════════════════════════════════════════════════════
|
||||
# Job 1: connection
|
||||
# Per-agent: serve gemma-3-270m, HTTP-preflight the agent's dialect,
|
||||
# install the agent, run `unsloth connect <agent> --no-launch`, execute
|
||||
# install the agent, run `unsloth start <agent> --no-launch`, execute
|
||||
# the emitted recipe with a trivial prompt, assert a non-empty reply.
|
||||
# Runs on PR + weekly + dispatch. Each matrix cell is its own runner so
|
||||
# it serves exactly one model on its own port.
|
||||
|
|
@ -103,7 +101,9 @@ jobs:
|
|||
env:
|
||||
# gemma-4-E4B (128K context, capable enough to drive every agent for a
|
||||
# trivial reply; the 270m model produced empty/failed responses for
|
||||
# codex/openclaw and is below hermes' 64K context floor). Served as a flat
|
||||
# codex/openclaw). Hermes' 64K context floor no longer constrains the model
|
||||
# choice: write_hermes_config claims the floor for smaller windows and
|
||||
# scales compaction back to the real window. Served as a flat
|
||||
# GGUF file (the -MTP- repo ships no separate draft, so this is plain 4B).
|
||||
GGUF_REPO: unsloth/gemma-4-E4B-it-GGUF
|
||||
GGUF_FILE: gemma-4-E4B-it-UD-Q4_K_XL.gguf
|
||||
|
|
@ -209,7 +209,7 @@ jobs:
|
|||
;;
|
||||
*)
|
||||
# OpenAI Chat Completions dialect (hermes/opencode/pi/openclaw).
|
||||
# OpenClaw's connect.py recipe writes an "openai-completions"
|
||||
# OpenClaw's start.py recipe writes an "openai-completions"
|
||||
# provider (write_openclaw_config), so it uses this path, not
|
||||
# /v1/messages.
|
||||
code=$(curl -s -o /tmp/pf.json -w '%{http_code}' "$B/v1/chat/completions" \
|
||||
|
|
@ -227,13 +227,13 @@ jobs:
|
|||
AGENT: ${{ matrix.agent }}
|
||||
run: bash .github/scripts/agent-guides-install.sh "$AGENT"
|
||||
|
||||
# ── (c) drive the agent via connect.py and assert a reply ──────────
|
||||
# For the 5 agents with a connect.py recipe we run
|
||||
# `unsloth connect <agent> --no-launch`, eval its env/unset exports,
|
||||
# ── (c) drive the agent via start.py and assert a reply ──────────
|
||||
# For the 5 agents with a start.py recipe we run
|
||||
# `unsloth start <agent> --no-launch`, eval its env/unset exports,
|
||||
# then run the printed command with a hard timeout (no headless-TTY
|
||||
# hang). Pi has no connect recipe, so it is driven by hand and the
|
||||
# cell asserts that absence is the (known) reason.
|
||||
- name: Drive ${{ matrix.agent }} via unsloth connect (class-c isolation)
|
||||
- name: Drive ${{ matrix.agent }} via unsloth start (class-c isolation)
|
||||
env:
|
||||
AGENT: ${{ matrix.agent }}
|
||||
run: bash .github/scripts/agent-guides-drive.sh connection "$AGENT"
|
||||
|
|
@ -248,8 +248,10 @@ jobs:
|
|||
# `API Key: <key>`) into logs/unsloth-run-<port>.log, and the upload
|
||||
# step publishes all of logs/, so scrubbing only studio-logs would leak
|
||||
# the bearer token in the retained artifact.
|
||||
# Sweep EVERY uploaded path, not just logs/ -- redacted-configs/ and
|
||||
# agent-workdir/ are published by the same upload step.
|
||||
if [ -n "${UNSLOTH_API_KEY:-}" ]; then
|
||||
grep -rlF "$UNSLOTH_API_KEY" logs 2>/dev/null | while IFS= read -r f; do
|
||||
grep -rlF "$UNSLOTH_API_KEY" logs redacted-configs agent-workdir 2>/dev/null | while IFS= read -r f; do
|
||||
sed -i "s#${UNSLOTH_API_KEY}#<REDACTED>#g" "$f" 2>/dev/null || true
|
||||
done
|
||||
fi
|
||||
|
|
@ -438,8 +440,10 @@ jobs:
|
|||
# `API Key: <key>`) into logs/unsloth-run-<port>.log, and the upload
|
||||
# step publishes all of logs/, so scrubbing only studio-logs would leak
|
||||
# the bearer token in the retained artifact.
|
||||
# Sweep EVERY uploaded path, not just logs/ -- redacted-configs/ and
|
||||
# agent-workdir/ are published by the same upload step.
|
||||
if [ -n "${UNSLOTH_API_KEY:-}" ]; then
|
||||
grep -rlF "$UNSLOTH_API_KEY" logs 2>/dev/null | while IFS= read -r f; do
|
||||
grep -rlF "$UNSLOTH_API_KEY" logs redacted-configs agent-workdir 2>/dev/null | while IFS= read -r f; do
|
||||
sed -i "s#${UNSLOTH_API_KEY}#<REDACTED>#g" "$f" 2>/dev/null || true
|
||||
done
|
||||
fi
|
||||
|
|
@ -582,8 +586,10 @@ jobs:
|
|||
# `API Key: <key>`) into logs/unsloth-run-<port>.log, and the upload
|
||||
# step publishes all of logs/, so scrubbing only studio-logs would leak
|
||||
# the bearer token in the retained artifact.
|
||||
# Sweep EVERY uploaded path, not just logs/ -- redacted-configs/ and
|
||||
# agent-workdir/ are published by the same upload step.
|
||||
if [ -n "${UNSLOTH_API_KEY:-}" ]; then
|
||||
grep -rlF "$UNSLOTH_API_KEY" logs 2>/dev/null | while IFS= read -r f; do
|
||||
grep -rlF "$UNSLOTH_API_KEY" logs redacted-configs agent-workdir 2>/dev/null | while IFS= read -r f; do
|
||||
sed -i "s#${UNSLOTH_API_KEY}#<REDACTED>#g" "$f" 2>/dev/null || true
|
||||
done
|
||||
fi
|
||||
|
|
|
|||
11
.github/workflows/studio-backend-ci.yml
vendored
11
.github/workflows/studio-backend-ci.yml
vendored
|
|
@ -68,9 +68,10 @@ jobs:
|
|||
pip install -r studio/backend/requirements/studio.txt
|
||||
# Extras that studio.txt does not list but the import chain needs
|
||||
# (python-multipart for FastAPI form/file uploads, sqlalchemy/cryptography
|
||||
# for the auth DB, yaml/jinja2 for utils.models.model_config, etc.):
|
||||
# for the auth DB, yaml/jinja2 for utils.models.model_config, psutil for
|
||||
# the orphan-cleanup process scan, etc.):
|
||||
pip install \
|
||||
python-multipart aiofiles sqlalchemy cryptography \
|
||||
python-multipart aiofiles sqlalchemy cryptography psutil \
|
||||
pyyaml jinja2 mammoth unpdf requests \
|
||||
'numpy<3' pytest pytest-asyncio httpx
|
||||
# Torch CPU + transformers are required by a chunk of the backend test
|
||||
|
|
@ -133,7 +134,7 @@ jobs:
|
|||
python -m pip install --upgrade pip
|
||||
pip install -r studio/backend/requirements/studio.txt
|
||||
pip install \
|
||||
python-multipart aiofiles sqlalchemy cryptography \
|
||||
python-multipart aiofiles sqlalchemy cryptography psutil \
|
||||
pyyaml jinja2 mammoth unpdf requests typer \
|
||||
'numpy<3' pytest pytest-asyncio httpx
|
||||
# torchvision: unsloth_zoo.vision_utils imports it at module scope.
|
||||
|
|
@ -229,7 +230,9 @@ jobs:
|
|||
tests/sh/test_resolve_cuda_archs.sh \
|
||||
tests/sh/test_tauri_install_exit_order.sh \
|
||||
tests/sh/test_torch_constraint.sh \
|
||||
tests/sh/test_torch_flavor.sh; do
|
||||
tests/sh/test_torch_flavor.sh \
|
||||
tests/sh/test_with_llama_cpp_dir_flag.sh \
|
||||
tests/sh/test_with_llama_cpp_dir_link_behavior.sh; do
|
||||
echo "::group::$s"
|
||||
bash "$s"
|
||||
echo "::endgroup::"
|
||||
|
|
|
|||
76
.github/workflows/studio-export-capability-ci.yml
vendored
Normal file
76
.github/workflows/studio-export-capability-ci.yml
vendored
Normal file
|
|
@ -0,0 +1,76 @@
|
|||
# SPDX-License-Identifier: AGPL-3.0-only
|
||||
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
|
||||
|
||||
# Runs studio/backend/tests/test_export_capability.py on Linux, Windows and macOS.
|
||||
#
|
||||
# export_capability() is per-OS (is_apple_silicon() and the PyTorch-import probe differ per
|
||||
# platform) and the export backend must import without PyTorch, so this confirms the gating and
|
||||
# import-safety on hosted Windows/macOS. Hosted runners have no GPU/MLX, so a real accelerator
|
||||
# export is validated separately. No GPU / model / llama.cpp: the tests mock the probes and block
|
||||
# torch/unsloth, so the job installs only a CPU PyTorch plus import deps.
|
||||
|
||||
name: Studio export capability
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
paths:
|
||||
- 'studio/backend/utils/hardware/hardware.py'
|
||||
- 'studio/backend/core/export/export.py'
|
||||
- 'studio/backend/routes/export.py'
|
||||
- 'studio/backend/main.py'
|
||||
- 'studio/backend/tests/test_export_capability.py'
|
||||
- '.github/workflows/studio-export-capability-ci.yml'
|
||||
push:
|
||||
branches: [main]
|
||||
paths:
|
||||
- 'studio/backend/utils/hardware/hardware.py'
|
||||
- 'studio/backend/core/export/export.py'
|
||||
- 'studio/backend/routes/export.py'
|
||||
- 'studio/backend/main.py'
|
||||
- 'studio/backend/tests/test_export_capability.py'
|
||||
- '.github/workflows/studio-export-capability-ci.yml'
|
||||
workflow_dispatch:
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
capability:
|
||||
name: capability (${{ matrix.os }})
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
os: [ubuntu-latest, windows-latest, macos-latest]
|
||||
runs-on: ${{ matrix.os }}
|
||||
timeout-minutes: 20
|
||||
env:
|
||||
# No accelerator on hosted runners; keep detection on the CPU path.
|
||||
CUDA_VISIBLE_DEVICES: ""
|
||||
steps:
|
||||
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
persist-credentials: false
|
||||
- uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
|
||||
with:
|
||||
python-version: '3.12'
|
||||
cache: 'pip'
|
||||
- name: Upgrade pip
|
||||
run: python -m pip install --upgrade pip
|
||||
- name: Install CPU PyTorch
|
||||
# CPU wheel index so every OS gets a CPU build; keep PyPI as an extra index so torch's
|
||||
# transitive deps still resolve (matching the other workflows in this repo).
|
||||
run: python -m pip install --index-url https://download.pytorch.org/whl/cpu --extra-index-url https://pypi.org/simple "torch>=2.4,<2.13"
|
||||
- name: Install backend import deps
|
||||
# Enough to import utils.hardware and core.export.export; NOT unsloth (needs a GPU, and
|
||||
# the import-safety test blocks it) or triton/llama.cpp (Linux-only / native builds).
|
||||
run: python -m pip install
|
||||
transformers peft accelerate safetensors huggingface_hub datasets
|
||||
sentencepiece protobuf fastapi starlette structlog psutil
|
||||
python-multipart pydantic httpx "numpy<3" pytest
|
||||
- name: Export capability + import-safety tests
|
||||
working-directory: studio/backend
|
||||
run: python -m pytest tests/test_export_capability.py -q
|
||||
Loading…
Add table
Add a link
Reference in a new issue