Promote QQsci config for QQnote calls

SKILL.md

@@ -47,6 +47,7 @@ positioning, introduction logic, comparison, novelty framing, and citations.
 | [references/literature-routing.md](references/literature-routing.md) | User wants Zotero/Obsidian/DeepSeek note search, strong/weak related-paper screening, keyword extraction, or literature-grounded rewriting |
 | [references/word-citation-comments.md](references/word-citation-comments.md) | User wants citation insertion guidance in Word, reference placement, DOI-only comments, or annotated `.docx` citation suggestions |
 | [references/zotero-obsidian-subskill.md](references/zotero-obsidian-subskill.md) | User asks QQsci to obtain or refresh literature-note inputs through QQnote, including Zotero child-note summaries or paper comparison tables |
+| [references/configuration.md](references/configuration.md) | You need DeepSeek, Zotero, Obsidian, QQnote inheritance, config precedence, secret handling, or wrapper-script usage |
 | [references/journal-positioning.md](references/journal-positioning.md) | Target journal is missing, uncertain, or needs recommendation and writing-position adjustment |
 
 ## Intake
@@ -187,6 +188,11 @@ summaries or paper comparison tables with QQnote, use
 Important defaults:
 
 - QQnote is only the note/table generation tool.
+- QQsci owns the top-level DeepSeek, Zotero, Obsidian, and QQnote routing
+  configuration for manuscript workflows. Open `references/configuration.md`
+  before calling QQnote from QQsci.
+- QQnote must remain independently usable through its own environment variables,
+  vault `.env`, or AwesomeGPT/Zotero preferences when run outside QQsci.
 - QQsci owns keyword extraction, strong/weak related-paper screening, target
   journal positioning, comparative review, submission-package audit, and
   DOI-only Word citation comments.

config/config.template.json

@@ -2,18 +2,28 @@
   "deepseek": {
     "api_key": "",
     "base_url": "https://api.deepseek.com",
-    "model": "deepseek-chat"
+    "model": "deepseek-chat",
+    "env_api_key": "AWESOMEGPT_API_KEY",
+    "env_base_url": "AWESOMEGPT_BASE_URL",
+    "env_model": "AWESOMEGPT_MODEL"
   },
   "zotero": {
     "local_api": "http://127.0.0.1:23119/api/users/0",
     "web_api_key": "",
     "user_id": "",
-    "library_type": "user"
+    "library_type": "user",
+    "env_web_api_key": "ZOTERO_API_KEY",
+    "env_user_id": "ZOTERO_USER_ID"
   },
   "obsidian": {
-    "vault_path": "",
+    "vault_path": "C:\\Users\\qyh15\\Documents\\Obsidian Vault",
     "zotero_integration_note_folder": ""
   },
+  "qqnote": {
+    "skill_path": "C:\\Users\\qyh15\\.codex\\skills\\QQnote-skill",
+    "config_mode": "inherit_from_qqsci_when_called_by_qqsci",
+    "standalone_mode": "use_QQnote_environment_vault_env_or_AwesomeGPT_preferences"
+  },
   "workflow": {
     "manifest_path": "state/qqsci-literature-manifest.jsonl",
     "skip_existing_notes": true,

references/configuration.md

@@ -0,0 +1,96 @@
+# QQsci Configuration
+
+Use this file when QQsci needs DeepSeek, Zotero, Obsidian, or QQnote access.
+
+## Ownership model
+
+QQsci is the top-level configuration owner for manuscript work. Store the
+primary DeepSeek, Zotero, Obsidian, and QQnote routing settings in:
+
+```text
+config/config.local.json
+```
+
+Never commit `config/config.local.json`, print secrets, or ask the user to paste
+API keys into chat.
+
+QQnote remains independently usable. When QQnote is run by itself, it may use
+its own environment variables, the vault `.env`, or AwesomeGPT/Zotero
+preferences. When QQnote is called from QQsci, QQsci should inject its own
+configuration into QQnote's expected environment variables.
+
+## Config precedence
+
+For QQsci-controlled manuscript workflows:
+
+1. Existing process environment variables override everything.
+2. QQsci `config/config.local.json`.
+3. QQsci `config/config.template.json` only for defaults, never secrets.
+4. QQnote standalone fallbacks only when QQsci config is absent or the user asks
+   to run QQnote independently.
+
+For QQnote standalone workflows:
+
+1. Existing process environment variables.
+2. Vault `.env`.
+3. AwesomeGPT/Zotero profile preferences.
+4. Any QQnote-specific local config if QQnote later adds one.
+
+## Environment mapping
+
+QQsci config maps to QQnote's existing environment variable interface:
+
+| QQsci config | QQnote env |
+|---|---|
+| `deepseek.api_key` | `AWESOMEGPT_API_KEY` |
+| `deepseek.base_url` | `AWESOMEGPT_BASE_URL` |
+| `deepseek.model` | `AWESOMEGPT_MODEL` |
+| `zotero.web_api_key` | `ZOTERO_API_KEY` |
+| `zotero.user_id` | `ZOTERO_USER_ID` |
+
+The Zotero local API remains:
+
+```text
+http://127.0.0.1:23119/api/users/0
+```
+
+unless the user explicitly changes it.
+
+## Calling QQnote from QQsci
+
+Prefer the wrapper:
+
+```powershell
+py "$env:USERPROFILE\.codex\skills\qqsci\scripts\run_qqnote_with_qqsci_config.py" --script summarize_zotero_table -- --vault "C:\Users\qyh15\Documents\Obsidian Vault" --item-keys "SXAIQUJT X7GJZ627"
+```
+
+The wrapper loads QQsci local config, sets QQnote-compatible environment
+variables for the child process, and does not print secrets.
+
+Use `--script generate_zotero_ai_note` when QQnote should create Zotero child
+notes.
+
+Use `--script summarize_zotero_table` when QQsci needs a compact paper table.
+
+Use `--script audit_zotero_ai_notes` only for QQnote note-state maintenance, not
+for QQsci's manuscript reasoning.
+
+## What belongs in QQsci
+
+QQsci owns:
+
+- manuscript keyword extraction
+- strong/weak related-paper screening
+- target-journal positioning
+- comparative review against strong papers
+- submission-package audit
+- figure, format, spelling, and terminology checks
+- DOI-only Word citation comments
+
+QQnote owns:
+
+- generating Zotero child-note summaries
+- generating paper comparison tables from Zotero items
+- optional QQnote note-state maintenance when explicitly requested
+
+QQnote output is an input to QQsci, not the decision engine.

references/zotero-obsidian-subskill.md

@@ -3,7 +3,8 @@
 Use this file when QQsci needs literature-note inputs from QQnote.
 
 QQnote is only the tool for summarizing papers into Zotero child notes or
-compact Markdown comparison tables. QQsci owns all manuscript-facing reasoning:
+compact Markdown comparison tables. QQsci owns the top-level DeepSeek/Zotero
+configuration for manuscript workflows and all manuscript-facing reasoning:
 keyword extraction, strong/weak related-paper screening, target-journal
 positioning, comparative review, submission-package audit, figure/format
 checks, terminology checks, and DOI-only Word citation comments.
@@ -31,8 +32,8 @@ Do not default to creating standalone Obsidian markdown notes when the user says
 Use the installed `QQnote-skill` scripts only for note/table generation:
 
 ```powershell
-py "$env:USERPROFILE\.codex\skills\QQnote-skill\scripts\generate_zotero_ai_note.py" --vault "C:\Users\qyh15\Documents\Obsidian Vault" --item-key SXAIQUJT --skip-existing
-py "$env:USERPROFILE\.codex\skills\QQnote-skill\scripts\summarize_zotero_table.py" --vault "C:\Users\qyh15\Documents\Obsidian Vault" --item-keys "SXAIQUJT X7GJZ627" --batch-size 3 --out "C:\Users\qyh15\Documents\Obsidian Vault\99 misc\literature-comparison-table.md"
+py "$env:USERPROFILE\.codex\skills\qqsci\scripts\run_qqnote_with_qqsci_config.py" --script generate_zotero_ai_note -- --vault "C:\Users\qyh15\Documents\Obsidian Vault" --item-key SXAIQUJT --skip-existing
+py "$env:USERPROFILE\.codex\skills\qqsci\scripts\run_qqnote_with_qqsci_config.py" --script summarize_zotero_table -- --vault "C:\Users\qyh15\Documents\Obsidian Vault" --item-keys "SXAIQUJT X7GJZ627" --batch-size 3 --out "C:\Users\qyh15\Documents\Obsidian Vault\99 misc\literature-comparison-table.md"
 ```
 
 Use `generate_zotero_ai_note.py` when new or selected papers need Zotero child
@@ -47,8 +48,11 @@ logic unless the user explicitly asks for QQnote maintenance.
 ## Safety and config
 
 - Do not ask the user to paste API keys into chat.
-- Follow QQnote's current config rules for DeepSeek/AwesomeGPT and Zotero
-  credentials when generating notes or tables.
+- For QQsci manuscript workflows, load DeepSeek/AwesomeGPT and Zotero
+  credentials from QQsci `config/config.local.json` and inject them into QQnote
+  with `scripts/run_qqnote_with_qqsci_config.py`.
+- QQnote must still be able to run standalone using its own environment
+  variables, vault `.env`, or AwesomeGPT/Zotero preferences.
 - Keep private config ignored and local-only.
 - Do not print secret-bearing config or preference lines.
 - Treat Zotero local API at `127.0.0.1:23119` as read-oriented.

scripts/run_qqnote_with_qqsci_config.py

@@ -0,0 +1,96 @@
+#!/usr/bin/env python3
+"""Run QQnote scripts with QQsci config injected as environment variables."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import os
+import subprocess
+import sys
+from pathlib import Path
+
+
+SCRIPT_MAP = {
+    "generate_zotero_ai_note": "generate_zotero_ai_note.py",
+    "summarize_zotero_table": "summarize_zotero_table.py",
+    "audit_zotero_ai_notes": "audit_zotero_ai_notes.py",
+}
+
+
+def skill_root() -> Path:
+    return Path(__file__).resolve().parents[1]
+
+
+def load_json(path: Path) -> dict:
+    if not path.exists():
+        return {}
+    return json.loads(path.read_text(encoding="utf-8"))
+
+
+def merged_config(root: Path) -> dict:
+    template = load_json(root / "config" / "config.template.json")
+    local = load_json(root / "config" / "config.local.json")
+
+    def merge(base: dict, override: dict) -> dict:
+        out = dict(base)
+        for key, value in override.items():
+            if isinstance(value, dict) and isinstance(out.get(key), dict):
+                out[key] = merge(out[key], value)
+            else:
+                out[key] = value
+        return out
+
+    return merge(template, local)
+
+
+def set_if_present(env: dict[str, str], key: str, value: object) -> None:
+    if key in env and env[key]:
+        return
+    if value is None:
+        return
+    text = str(value)
+    if text:
+        env[key] = text
+
+
+def build_env(config: dict) -> dict[str, str]:
+    env = os.environ.copy()
+    deepseek = config.get("deepseek") or {}
+    zotero = config.get("zotero") or {}
+
+    set_if_present(env, deepseek.get("env_api_key", "AWESOMEGPT_API_KEY"), deepseek.get("api_key"))
+    set_if_present(env, deepseek.get("env_base_url", "AWESOMEGPT_BASE_URL"), deepseek.get("base_url"))
+    set_if_present(env, deepseek.get("env_model", "AWESOMEGPT_MODEL"), deepseek.get("model"))
+    set_if_present(env, zotero.get("env_web_api_key", "ZOTERO_API_KEY"), zotero.get("web_api_key"))
+    set_if_present(env, zotero.get("env_user_id", "ZOTERO_USER_ID"), zotero.get("user_id"))
+    return env
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--script", required=True, choices=sorted(SCRIPT_MAP))
+    parser.add_argument("--qqnote-path", default="")
+    parser.add_argument("qqnote_args", nargs=argparse.REMAINDER)
+    args = parser.parse_args()
+
+    root = skill_root()
+    config = merged_config(root)
+    qqnote = Path(args.qqnote_path or (config.get("qqnote") or {}).get("skill_path") or "")
+    if not qqnote:
+        qqnote = Path.home() / ".codex" / "skills" / "QQnote-skill"
+    script = qqnote / "scripts" / SCRIPT_MAP[args.script]
+    if not script.exists():
+        print(f"QQnote script not found: {script}", file=sys.stderr)
+        return 2
+
+    extra_args = list(args.qqnote_args)
+    if extra_args and extra_args[0] == "--":
+        extra_args = extra_args[1:]
+
+    command = [sys.executable, str(script), *extra_args]
+    return subprocess.call(command, env=build_env(config))
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())