fengming 0.3.8 → 0.3.9

package/skills/openai-whisper-api/SKILL.md

@@ -1,71 +0,0 @@
----
-name: openai-whisper-api
-description: "OpenAI Audio Transcriptions API via curl; gpt-4o-transcribe, mini, diarize, or whisper-1."
-homepage: https://platform.openai.com/docs/guides/speech-to-text
-metadata:
-  {
-    "fengming":
-      {
-        "emoji": "🌐",
-        "requires": { "bins": ["curl", "node"], "env": ["OPENAI_API_KEY"] },
-        "primaryEnv": "OPENAI_API_KEY",
-        "install":
-          [
-            {
-              "id": "brew",
-              "kind": "brew",
-              "formula": "curl",
-              "bins": ["curl"],
-              "label": "Install curl (brew)",
-            },
-          ],
-      },
-  }
----
-
-# OpenAI transcriptions API
-
-Transcribe audio through `/v1/audio/transcriptions`. Set `OPENAI_BASE_URL` for an OpenAI-compatible proxy or local gateway.
-
-## Quick start
-
-```bash
-{baseDir}/scripts/transcribe.sh /path/to/audio.m4a
-```
-
-Defaults:
-
-- Model: `gpt-4o-transcribe`
-- Output: `<input>.txt`
-
-## Useful flags
-
-```bash
-{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model gpt-4o-transcribe --out /tmp/transcript.txt
-{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model gpt-4o-mini-transcribe
-{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model gpt-4o-transcribe-diarize --json
-{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model whisper-1
-{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --language en
-{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --prompt "Speaker names: Peter, Daniel"
-{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --json --out /tmp/transcript.json
-```
-
-Notes:
-
-- Supported upload formats include `mp3`, `mp4`, `mpeg`, `mpga`, `m4a`, `wav`, `webm`.
-- 25 MB upload limit on the hosted API.
-- Use diarize for speaker labels; script sends `chunking_strategy=auto` and rejects `--prompt`.
-
-## API key
-
-Set `OPENAI_API_KEY`, or configure it in the active FengMing config file (`$FENGMING_CONFIG_PATH`, default `~/.fengming/fengming.json`). Optionally set `OPENAI_BASE_URL`:
-
-```json5
-{
-  skills: {
-    "openai-whisper-api": {
-      apiKey: "OPENAI_KEY_HERE",
-    },
-  },
-}
-```

package/skills/openai-whisper-api/scripts/transcribe.sh

@@ -1,154 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-usage() {
-  cat >&2 <<'EOF'
-Usage:
-  transcribe.sh <audio-file> [--model gpt-4o-transcribe] [--out /path/to/out.txt] [--language en] [--prompt "hint"] [--json]
-EOF
-  exit 2
-}
-
-if [[ "${1:-}" == "" || "${1:-}" == "-h" || "${1:-}" == "--help" ]]; then
-  usage
-fi
-
-in="${1:-}"
-shift || true
-
-model="gpt-4o-transcribe"
-out=""
-language=""
-prompt=""
-json_output=0
-
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --model)
-      model="${2:-}"
-      shift 2
-      ;;
-    --out)
-      out="${2:-}"
-      shift 2
-      ;;
-    --language)
-      language="${2:-}"
-      shift 2
-      ;;
-    --prompt)
-      prompt="${2:-}"
-      shift 2
-      ;;
-    --json)
-      json_output=1
-      shift 1
-      ;;
-    *)
-      echo "Unknown arg: $1" >&2
-      usage
-      ;;
-  esac
-done
-
-if [[ ! -f "$in" ]]; then
-  echo "File not found: $in" >&2
-  exit 1
-fi
-
-if [[ "${OPENAI_API_KEY:-}" == "" ]]; then
-  echo "Missing OPENAI_API_KEY" >&2
-  exit 1
-fi
-
-if [[ "$out" == "" ]]; then
-  base="${in%.*}"
-  if [[ "$json_output" == "1" ]]; then
-    out="${base}.json"
-  else
-    out="${base}.txt"
-  fi
-fi
-
-mkdir -p "$(dirname "$out")"
-
-api_base="${OPENAI_BASE_URL:-https://api.openai.com/v1}"
-api_base="${api_base%/}"
-
-request_format="text"
-if [[ "$json_output" == "1" ]]; then
-  request_format="json"
-fi
-
-diarize=0
-case "$model" in
-  gpt-4o-transcribe | gpt-4o-mini-transcribe | gpt-4o-mini-transcribe-*)
-    request_format="json"
-    ;;
-  gpt-4o-transcribe-diarize)
-    diarize=1
-    request_format="diarized_json"
-    ;;
-esac
-
-if [[ "$diarize" == "1" && "$prompt" != "" ]]; then
-  echo "--prompt is not supported with gpt-4o-transcribe-diarize" >&2
-  exit 2
-fi
-
-target="$out"
-tmp=""
-if [[ "$json_output" == "0" && ( "$request_format" == "json" || "$request_format" == "diarized_json" ) ]]; then
-  tmp="$(mktemp)"
-  trap '[[ "$tmp" == "" ]] || rm -f "$tmp"' EXIT
-  target="$tmp"
-fi
-
-curl_args=(
-  -sS "${api_base}/audio/transcriptions"
-  -H "Authorization: Bearer $OPENAI_API_KEY"
-  -H "Accept: application/json"
-  -F "file=@${in}"
-  -F "model=${model}"
-  -F "response_format=${request_format}"
-)
-if [[ "$language" != "" ]]; then
-  curl_args+=(-F "language=${language}")
-fi
-if [[ "$prompt" != "" ]]; then
-  curl_args+=(-F "prompt=${prompt}")
-fi
-if [[ "$diarize" == "1" ]]; then
-  curl_args+=(-F "chunking_strategy=auto")
-fi
-
-curl "${curl_args[@]}" >"$target"
-
-if [[ "$target" != "$out" ]]; then
-  node -e '
-const fs = require("fs");
-const input = process.argv[1];
-const output = process.argv[2];
-const payload = JSON.parse(fs.readFileSync(input, "utf8"));
-if (Array.isArray(payload.segments)) {
-  const lines = payload.segments
-    .map((segment) => {
-      const text = typeof segment?.text === "string" ? segment.text.trim() : "";
-      if (!text) return "";
-      const speaker = typeof segment?.speaker === "string" ? segment.speaker.trim() : "";
-      return speaker ? `${speaker}: ${text}` : text;
-    })
-    .filter(Boolean);
-  if (lines.length > 0) {
-    fs.writeFileSync(output, lines.join("\n"));
-    process.exit(0);
-  }
-}
-if (typeof payload.text !== "string") {
-  throw new Error("Transcription response missing text");
-}
-fs.writeFileSync(output, payload.text);
-' "$target" "$out"
-fi
-
-echo "$out"

package/skills/oracle/SKILL.md

@@ -1,126 +0,0 @@
----
-name: oracle
-description: "Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine."
-homepage: https://askoracle.dev
-metadata:
-  {
-    "fengming":
-      {
-        "emoji": "🧿",
-        "requires": { "bins": ["oracle"] },
-        "install":
-          [
-            {
-              "id": "node",
-              "kind": "node",
-              "package": "@steipete/oracle",
-              "bins": ["oracle"],
-              "label": "Install oracle (node)",
-            },
-          ],
-      },
-  }
----
-
-# oracle
-
-Oracle bundles a prompt + selected files for one second-model pass. Treat output as advisory; verify against code + tests.
-
-## Main path
-
-Current CLI default model: `gpt-5.5-pro`. Browser engine is useful for long ChatGPT Pro runs; API engine is useful when `OPENAI_API_KEY` or Azure config is ready.
-
-Recommended defaults:
-
-- Preview first: `--dry-run summary --files-report`
-- Browser long run: `--engine browser --model gpt-5.5-pro`
-- API explicit: `--engine api --model gpt-5.5`
-
-## Golden path
-
-1. Pick a tight file set (fewest files that still contain the truth).
-2. Preview payload + token spend (`--dry-run` + `--files-report`).
-3. Use browser mode for long Pro thinking; API mode for explicit API calls.
-4. If the run detaches/timeouts: reattach to the stored session. Do not blindly re-run.
-
-## Commands (preferred)
-
-- Help:
-  - `oracle --help`
-  - If the binary isn't installed: `npx -y @steipete/oracle --help` (avoid `pnpx` here; sqlite bindings).
-
-- Preview (no tokens):
-  - `oracle --dry-run summary -p "<task>" --file "src/**" --file "!**/*.test.*"`
-  - `oracle --dry-run full -p "<task>" --file "src/**"`
-
-- Token sanity:
-  - `oracle --dry-run summary --files-report -p "<task>" --file "src/**"`
-
-- Browser run (main path; long-running is normal):
-  - `oracle --engine browser --model gpt-5.5-pro -p "<task>" --file "src/**"`
-
-- Manual paste fallback:
-  - `oracle --render --copy -p "<task>" --file "src/**"`
-  - Note: `--copy` is a hidden alias for `--copy-markdown`.
-
-## Attaching files (`--file`)
-
-`--file` accepts files, directories, and globs. You can pass it multiple times; entries can be comma-separated.
-
-- Include:
-  - `--file "src/**"`
-  - `--file src/index.ts`
-  - `--file docs --file README.md`
-
-- Exclude:
-  - `--file "src/**" --file "!src/**/*.test.ts" --file "!**/*.snap"`
-
-- Defaults (implementation behavior):
-  - Default-ignored dirs: `node_modules`, `dist`, `coverage`, `.git`, `.turbo`, `.next`, `build`, `tmp` (skipped unless explicitly passed as literal dirs/files).
-  - Honors `.gitignore` when expanding globs.
-  - Does not follow symlinks.
-  - Dotfiles filtered unless opted in via pattern (e.g. `--file ".github/**"`).
-  - Files > 1 MB rejected.
-
-## Engines (API vs browser)
-
-- Auto-pick: `api` when `OPENAI_API_KEY` is set; otherwise `browser`.
-- Browser supports GPT + Gemini only; use `--engine api` for Claude/Grok/Codex or multi-model runs.
-- Browser attachments:
-  - `--browser-attachments auto|never|always` (auto pastes inline up to ~60k chars then uploads).
-- Remote browser host:
-  - Host: `oracle serve --host 0.0.0.0 --port 9473 --token <secret>`
-  - Client: `oracle --engine browser --remote-host <host:port> --remote-token <secret> -p "<task>" --file "src/**"`
-
-## Sessions + slugs
-
-- Stored under `~/.oracle/sessions` (override with `ORACLE_HOME_DIR`).
-- Runs may detach or take a long time (browser + Pro often does). If the CLI times out: do not re-run; reattach.
-  - List: `oracle status --hours 72`
-  - Attach: `oracle session <id> --render`
-- Use `--slug "<3-5 words>"` to keep session IDs readable.
-- Duplicate prompt guard exists; use `--force` only when you truly want a fresh run.
-
-## Prompt template (high signal)
-
-Oracle starts with **zero** project knowledge. Assume the model cannot infer your stack, build tooling, conventions, or "obvious" paths. Include:
-
-- Project briefing (stack + build/test commands + platform constraints).
-- "Where things live" (key directories, entrypoints, config files, boundaries).
-- Exact question + what you tried + the error text (verbatim).
-- Constraints ("don't change X", "must keep public API", etc).
-- Desired output ("return patch plan + tests", "give 3 options with tradeoffs").
-
-## Safety
-
-- Don't attach secrets by default (`.env`, key files, auth tokens). Redact aggressively; share only what's required.
-
-## "Exhaustive prompt" restoration pattern
-
-For long investigations, write a standalone prompt + file set so you can rerun days later:
-
-- 6-30 sentence project briefing + the goal.
-- Repro steps + exact errors + what you tried.
-- Attach all context files needed (entrypoints, configs, key modules, docs).
-
-Oracle runs are one-shot; the model doesn't remember prior runs. "Restoring context" means re-running with the same prompt + `--file …` set (or reattaching a still-running stored session).

package/skills/pyproject.toml

@@ -1,10 +0,0 @@
-[tool.ruff]
-target-version = "py310"
-line-length = 100
-
-[tool.ruff.lint]
-select = ["E9", "F63", "F7", "F82", "I"]
-
-[tool.pytest.ini_options]
-testpaths = ["skills"]
-python_files = ["test_*.py"]

package/skills/python-debugpy/SKILL.md

@@ -1,73 +0,0 @@
----
-name: python-debugpy
-description: Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.
-metadata: { "fengming": { "requires": { "bins": ["python3"] } } }
----
-
-# Python Debugpy
-
-Use when Python code needs interactive debugging: hidden locals, confusing state mutation, failing tests, subprocesses, long-running services, or remote/headless attach.
-
-Pick the smallest debugger that reaches the bad frame.
-
-## Choose
-
-- `breakpoint()`: local code, source edits ok, fastest path.
-- `python3 -m pdb`: no source edit, launch from the beginning.
-- `python3 -m pdb -c continue`: stop at an unhandled exception.
-- `debugpy`: remote/headless process, DAP client, already-running PID, or service startup race.
-
-## Commands
-
-```bash
-python3 -m pdb path/to/script.py arg1
-python3 -m pdb -c continue path/to/script.py
-python3 -c "import debugpy" || python3 -m pip install debugpy
-python3 -m debugpy --listen 127.0.0.1:5678 --wait-for-client path/to/script.py
-python3 -m debugpy --listen 127.0.0.1:5678 --wait-for-client -m package.module
-python3 -m debugpy --listen 127.0.0.1:5678 --pid <pid>
-```
-
-For source-edit attach:
-
-```py
-import debugpy
-
-debugpy.listen(("127.0.0.1", 5678))
-debugpy.wait_for_client()
-debugpy.breakpoint()
-```
-
-For post-mortem:
-
-```py
-import pdb, sys
-
-try:
-    run()
-except Exception:
-    pdb.post_mortem(sys.exc_info()[2])
-    raise
-```
-
-## pdb
-
-- Flow: `n`, `s`, `r`, `c`, `q`.
-- Stack/source: `w`, `u`, `d`, `a`, `l`, `ll`.
-- Values: `p expr`, `pp expr`, `display expr`.
-- Breakpoints: `b file.py:42`, `b func`, `b file.py:42, condition`, `cl <num>`.
-- Mutate/evaluate: `!statement`; full REPL: `interact`.
-
-## Rules
-
-- Reproduce with the smallest command/test first.
-- Disable parallel test workers for pdb; interactive stdin usually breaks inside worker pools.
-- Keep `debugpy` in the active env; do not add it as a project dependency unless the project already wants it.
-- Bind debug servers to `127.0.0.1`; do not expose `0.0.0.0` unless isolated or tunnelled.
-- Use unique ports for parallel sessions.
-- Treat `debugpy --pid` as injection; avoid security-sensitive or production targets unless explicitly approved.
-- If PID attach fails on Linux, check ptrace/container privileges before changing the target.
-- Cleanup before commit: `rg -n 'breakpoint\\(|pdb\\.set_trace|debugpy\\.' --type py`.
-- Rerun the normal project test/gate without the debugger.
-- `PYTHONBREAKPOINT=0` disables `breakpoint()`.
-- If a process is stuck after debugger detach, confirm it is not still paused at a breakpoint.

package/skills/sag/SKILL.md

@@ -1,87 +0,0 @@
----
-name: sag
-description: "ElevenLabs text-to-speech with mac-style say UX."
-homepage: https://sag.sh
-metadata:
-  {
-    "fengming":
-      {
-        "emoji": "🔊",
-        "requires": { "bins": ["sag"], "env": ["ELEVENLABS_API_KEY"] },
-        "primaryEnv": "ELEVENLABS_API_KEY",
-        "install":
-          [
-            {
-              "id": "brew",
-              "kind": "brew",
-              "formula": "steipete/tap/sag",
-              "bins": ["sag"],
-              "label": "Install sag (brew)",
-            },
-          ],
-      },
-  }
----
-
-# sag
-
-Use `sag` for ElevenLabs TTS with local playback.
-
-API key (required)
-
-- `ELEVENLABS_API_KEY` (preferred)
-- `SAG_API_KEY` also supported by the CLI
-
-Quick start
-
-- `sag "Hello there"`
-- `sag speak -v "Roger" "Hello"`
-- `sag voices`
-- `sag prompting` (model-specific tips)
-
-Model notes
-
-- Default: `eleven_v3` (expressive)
-- Stable: `eleven_multilingual_v2`
-- Fast: `eleven_flash_v2_5`
-
-Pronunciation + delivery rules
-
-- First fix: respell (e.g. "key-note"), add hyphens, adjust casing.
-- Numbers/units/URLs: `--normalize auto` (or `off` if it harms names).
-- Language bias: `--lang en|de|fr|...` to guide normalization.
-- v3: SSML `<break>` not supported; use `[pause]`, `[short pause]`, `[long pause]`.
-- v2/v2.5: SSML `<break time="1.5s" />` supported; `<phoneme>` not exposed in `sag`.
-
-v3 audio tags (put at the entrance of a line)
-
-- `[whispers]`, `[shouts]`, `[sings]`
-- `[laughs]`, `[starts laughing]`, `[sighs]`, `[exhales]`
-- `[sarcastic]`, `[curious]`, `[excited]`, `[crying]`, `[mischievously]`
-- Example: `sag "[whispers] keep this quiet. [short pause] ok?"`
-
-Voice defaults
-
-- `ELEVENLABS_VOICE_ID` or `SAG_VOICE_ID`
-
-Confirm voice + speaker before long output.
-
-## Chat voice responses
-
-When the user asks for a "voice" reply (e.g., "crazy scientist voice", "explain in voice"), generate audio and send it:
-
-```bash
-# Generate audio file
-sag -v Clawd -o /tmp/voice-reply.mp3 "Your message here"
-
-# Then include in reply:
-# MEDIA:/tmp/voice-reply.mp3
-```
-
-Voice character tips:
-
-- Crazy scientist: Use `[excited]` tags, dramatic pauses `[short pause]`, vary intensity
-- Calm: Use `[whispers]` or slower pacing
-- Dramatic: Use `[sings]` or `[shouts]` sparingly
-
-Default voice for Clawd: `lj2rcrvANS3gaWWnczSX` (or just `-v Clawd`)

package/skills/session-logs/SKILL.md

@@ -1,151 +0,0 @@
----
-name: session-logs
-description: "Search and analyze your own session logs (older/parent conversations) using jq."
-metadata:
-  {
-    "fengming":
-      {
-        "emoji": "📜",
-        "requires": { "bins": ["jq", "rg"] },
-        "install":
-          [
-            {
-              "id": "brew-jq",
-              "kind": "brew",
-              "formula": "jq",
-              "bins": ["jq"],
-              "label": "Install jq (brew)",
-            },
-            {
-              "id": "brew-rg",
-              "kind": "brew",
-              "formula": "ripgrep",
-              "bins": ["rg"],
-              "label": "Install ripgrep (brew)",
-            },
-          ],
-      },
-  }
----
-
-# session-logs
-
-Search your complete conversation history stored in session JSONL files. Use this when a user references older/parent conversations or asks what was said before.
-
-## Trigger
-
-Use this skill when the user asks about prior chats, parent conversations, or historical context that isn't in memory files.
-
-## Location
-
-Session logs live under the active state directory:
-`$FENGMING_STATE_DIR/agents/<agentId>/sessions/` (default: `~/.fengming/agents/<agentId>/sessions/`).
-Use the `agent=<id>` value from the system prompt Runtime line.
-
-- **`sessions.json`** - Index mapping session keys to session IDs
-- **`<session-id>.jsonl`** - Full conversation transcript per session
-
-## Structure
-
-Each `.jsonl` file contains messages with:
-
-- `type`: "session" (metadata) or "message"
-- `timestamp`: ISO timestamp
-- `message.role`: "user", "assistant", or "toolResult"
-- `message.content[]`: Text, thinking, or tool calls (filter `type=="text"` for human-readable content)
-- `message.usage.cost.total`: Cost per response
-
-## Common Queries
-
-### List all sessions by date and size
-
-```bash
-AGENT_ID="<agentId>"
-SESSION_DIR="${FENGMING_STATE_DIR:-$HOME/.fengming}/agents/$AGENT_ID/sessions"
-for f in "$SESSION_DIR"/*.jsonl; do
-  date=$(head -1 "$f" | jq -r '.timestamp' | cut -dT -f1)
-  size=$(ls -lh "$f" | awk '{print $5}')
-  echo "$date $size $(basename $f)"
-done | sort -r
-```
-
-### Find sessions from a specific day
-
-```bash
-AGENT_ID="<agentId>"
-SESSION_DIR="${FENGMING_STATE_DIR:-$HOME/.fengming}/agents/$AGENT_ID/sessions"
-for f in "$SESSION_DIR"/*.jsonl; do
-  head -1 "$f" | jq -r '.timestamp' | grep -q "2026-01-06" && echo "$f"
-done
-```
-
-### Extract user messages from a session
-
-```bash
-jq -r 'select(.message.role == "user") | .message.content[]? | select(.type == "text") | .text' <session>.jsonl
-```
-
-### Search for keyword in assistant responses
-
-```bash
-jq -r 'select(.message.role == "assistant") | .message.content[]? | select(.type == "text") | .text' <session>.jsonl | rg -i "keyword"
-```
-
-### Get total cost for a session
-
-```bash
-jq -s '[.[] | .message.usage.cost.total // 0] | add' <session>.jsonl
-```
-
-### Daily cost summary
-
-```bash
-AGENT_ID="<agentId>"
-SESSION_DIR="${FENGMING_STATE_DIR:-$HOME/.fengming}/agents/$AGENT_ID/sessions"
-for f in "$SESSION_DIR"/*.jsonl; do
-  date=$(head -1 "$f" | jq -r '.timestamp' | cut -dT -f1)
-  cost=$(jq -s '[.[] | .message.usage.cost.total // 0] | add' "$f")
-  echo "$date $cost"
-done | awk '{a[$1]+=$2} END {for(d in a) print d, "$"a[d]}' | sort -r
-```
-
-### Count messages and tokens in a session
-
-```bash
-jq -s '{
-  messages: length,
-  user: [.[] | select(.message.role == "user")] | length,
-  assistant: [.[] | select(.message.role == "assistant")] | length,
-  first: .[0].timestamp,
-  last: .[-1].timestamp
-}' <session>.jsonl
-```
-
-### Tool usage breakdown
-
-```bash
-jq -r '.message.content[]? | select(.type == "toolCall") | .name' <session>.jsonl | sort | uniq -c | sort -rn
-```
-
-### Search across ALL sessions for a phrase
-
-```bash
-AGENT_ID="<agentId>"
-SESSION_DIR="${FENGMING_STATE_DIR:-$HOME/.fengming}/agents/$AGENT_ID/sessions"
-rg -l "phrase" "$SESSION_DIR"/*.jsonl
-```
-
-## Tips
-
-- Sessions are append-only JSONL (one JSON object per line)
-- Large sessions can be several MB - use `head`/`tail` for sampling
-- The `sessions.json` index maps chat providers (discord, whatsapp, etc.) to session IDs
-- Deleted sessions have `.deleted.<timestamp>` suffix
-
-## Fast text-only hint (low noise)
-
-```bash
-AGENT_ID="<agentId>"
-SESSION_DIR="${FENGMING_STATE_DIR:-$HOME/.fengming}/agents/$AGENT_ID/sessions"
-jq -r 'select(.type=="message") | .message.content[]? | select(.type=="text") | .text' "$SESSION_DIR"/<id>.jsonl | rg 'keyword'
-```