diff --git a/claude-obsidian/README.md b/claude-obsidian/README.md index c7522d6..877937d 100644 --- a/claude-obsidian/README.md +++ b/claude-obsidian/README.md @@ -36,6 +36,8 @@ claude.ai export .zip ────────┼─ condense → redact → sum claude-obsidian-sync sync # what the timer runs claude-obsidian-sync sync --session # one session, now, ignoring the settle window claude-obsidian-sync import-claude-ai ~/Downloads/data-2026-09-13.zip +claude-obsidian-sync sync --prefetch --limit 3 # summarize into the local cache, vault untouched +claude-obsidian-sync usage # calls, billed tokens, spend: last 5h / 24h / 7d ``` Claude reads the vault through the plugin's MCP server: @@ -53,6 +55,22 @@ claude mcp add --scope user --transport http obsidian http://:27123/mcp/ \ subscription has no key of its own, so a background job cannot use its `claude-*` models. - **`--no-session-persistence` is load-bearing.** Without it every summary writes a new transcript into `~/.claude/projects`, and the next run summarizes its own summarizing. +- **Usage is metered and capped.** Every model call is appended to + `~/.local/state/claude-obsidian/usage.jsonl` with *billed* tokens (the CLI's `modelUsage`, not + the visible turn) and `total_cost_usd` — API list-price equivalent, a faithful proxy for how much + was consumed; the plan's own meter is only visible in Claude Code's `/usage`. Before each call + its cost is **estimated** (+20% margin) and the call is refused if it would cross + `BUDGET_USD_PER_RUN` or the rolling `BUDGET_USD_PER_DAY` — so budgets are never overshot. Not + `claude -p --max-budget-usd`: that aborts *after* the tokens are spent and discards the result + (measured: $0.26 for nothing). Every run ends with a one-line usage report. +- **Three cost levers, measured on one session — $0.057 → $0.010, same summary content:** + `alwaysThinkingEnabled=false` (extended thinking was ~85% of output tokens), + `DISABLE_PROMPT_CACHING=1` (the CLI writes each prompt to the 1-hour cache at 2× input price, and + a one-shot call never reads it back), and `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1` (otherwise a + hidden side request re-reads the entire prompt, doubling billed input). A whole ~110-session + backlog is about $2 at list price with all three. +- **Summaries are cached until their note is written**, so a vault outage never pays for the same + summary twice, and `--prefetch` can do the summarizing while the vault is unreachable. - **It shares your plan's usage limits.** A first backfill of ~100 sessions in parallel hit a session limit within minutes — which also limits *interactive* use. So: one job at a time, `MAX_PER_RUN` sessions per run (newest first), and the run **stops at the first usage-limit diff --git a/claude-obsidian/__pycache__/claude-obsidian-synccpython-312.pyc b/claude-obsidian/__pycache__/claude-obsidian-synccpython-312.pyc new file mode 100644 index 0000000..d91fad6 Binary files /dev/null and b/claude-obsidian/__pycache__/claude-obsidian-synccpython-312.pyc differ diff --git a/claude-obsidian/claude-obsidian-sync b/claude-obsidian/claude-obsidian-sync index 5b0041d..7352e2d 100755 --- a/claude-obsidian/claude-obsidian-sync +++ b/claude-obsidian/claude-obsidian-sync @@ -70,6 +70,16 @@ DEFAULTS = { # Cap per run. Summaries draw on the same plan limits as interactive Claude use, so the # timer drips a backlog instead of bursting it (a 107-session burst exhausted a session limit). "MAX_PER_RUN": "10", + # Spend guards, in API list-price USD as reported by `claude -p` (total_cost_usd). Not the + # plan's own meter -- that is only visible in Claude Code's /usage -- but a faithful proxy + # for how much was consumed. Hitting one stops the run like a usage limit (exit 75). + "BUDGET_USD_PER_RUN": "0.50", + "BUDGET_USD_PER_DAY": "2.00", + # Pre-call estimate prices (USD per million tokens, list). A call is refused BEFORE it runs + # if the estimate would cross a budget. Deliberately NOT `claude -p --max-budget-usd`: that + # aborts after the tokens are spent and throws the result away (measured: $0.26 for nothing). + "LLM_PRICE_IN_PER_M": "1.0", + "LLM_PRICE_OUT_PER_M": "5.0", } @@ -251,6 +261,68 @@ errors and their causes, decisions, open questions. Be specific. Never reproduce CHUNK_CHARS = 300_000 +class Ledger: + """Append-only record of every model call: tokens and list-price cost. Also enforces budgets.""" + + def __init__(self, cfg: dict): + self.path = pathlib.Path(os.path.expanduser(cfg["STATE_FILE"])).parent / "usage.jsonl" + self.run_budget = float(cfg["BUDGET_USD_PER_RUN"]) + self.day_budget = float(cfg["BUDGET_USD_PER_DAY"]) + self.lock = threading.Lock() + self.run_cost = 0.0 + self.run_calls = 0 + self.run_in = self.run_out = 0 + + def entries(self, since: dt.datetime | None = None) -> list[dict]: + if not self.path.exists(): + return [] + out = [] + for line in self.path.read_text().splitlines(): + try: + e = json.loads(line) + except json.JSONDecodeError: + continue + if since is None or dt.datetime.fromisoformat(e["ts"]) >= since: + out.append(e) + return out + + def spent_since(self, hours: float) -> float: + since = dt.datetime.now(dt.timezone.utc) - dt.timedelta(hours=hours) + return sum(e.get("cost_usd") or 0 for e in self.entries(since)) + + def check(self, estimate: float = 0.0) -> None: + """Called BEFORE each model call with that call's estimated cost -- so a budget is never overshot.""" + with self.lock: + if self.run_cost + estimate > self.run_budget: + raise BudgetExhausted(f"run budget ${self.run_budget:.2f}: ${self.run_cost:.3f} spent, " + f"next call est. ${estimate:.3f}") + day = self.spent_since(24) + if day + estimate > self.day_budget: + raise BudgetExhausted(f"24h budget ${self.day_budget:.2f}: ${day:.3f} spent, next call est. ${estimate:.3f}") + + def record(self, label: str, model: str, usage: dict, cost: float | None) -> None: + e = {"ts": dt.datetime.now(dt.timezone.utc).isoformat(timespec="seconds"), "item": label, "model": model, + "input": (usage.get("input_tokens") or 0) + (usage.get("cache_creation_input_tokens") or 0) + + (usage.get("cache_read_input_tokens") or 0), + "output": usage.get("output_tokens") or 0, "cost_usd": cost} + with self.lock: + self.path.parent.mkdir(parents=True, exist_ok=True) + with self.path.open("a") as f: + f.write(json.dumps(e) + "\n") + self.run_calls += 1 + self.run_cost += cost or 0 + self.run_in += e["input"] + self.run_out += e["output"] + + def report(self) -> str: + return (f"usage this run: {self.run_calls} model calls, {self.run_in:,} in / {self.run_out:,} out tokens, " + f"${self.run_cost:.3f} list-price equiv | last 24h ${self.spent_since(24):.3f} of ${self.day_budget:.2f}") + + +class BudgetExhausted(RuntimeError): + """A configured spend budget is reached -- stop the run the same way as a usage limit.""" + + class QuotaExhausted(RuntimeError): """The plan/API usage limit is hit. Every further call would fail the same way -- stop the run.""" @@ -267,7 +339,11 @@ class LLM: openai: any OpenAI-compatible /chat/completions endpoint (LiteLLM, local models). """ - def __init__(self, cfg: dict): + def __init__(self, cfg: dict, ledger: "Ledger | None" = None): + self.ledger = ledger or Ledger(cfg) + self.price_in = float(cfg["LLM_PRICE_IN_PER_M"]) / 1e6 + self.price_out = float(cfg["LLM_PRICE_OUT_PER_M"]) / 1e6 + self.label = threading.local() self.backend = cfg["LLM_BACKEND"] self.model = cfg["LLM_MODEL"] self.resolved = cfg["LLM_MODEL"] @@ -285,16 +361,31 @@ class LLM: else: raise SystemExit(f"unknown LLM_BACKEND {self.backend!r}") + def estimate(self, system: str, user: str, max_tokens: int) -> float: + # ~3 chars/token over-estimates input (measured 3.1 on transcripts); assume the full output; + # +20% margin for anything unmeasured. Errs high on purpose: refusing early beats overshooting. + return 1.2 * ((len(system) + len(user)) / 3.0 * self.price_in + max_tokens * self.price_out) + def chat(self, system: str, user: str, max_tokens: int = 2500) -> str: + self.ledger.check(self.estimate(system, user, max_tokens)) return self._chat_cli(system, user) if self.backend == "claude-cli" else self._chat_openai(system, user, max_tokens) def _chat_cli(self, system: str, user: str) -> str: + # Cost levers, measured on one session: $0.057 -> $0.015 with identical summary content. + # alwaysThinkingEnabled=false -- extended thinking was ~85% of output tokens + # DISABLE_PROMPT_CACHING=1 -- Claude Code writes prompts to the 1h cache at 2x input + # price; a one-shot call never reads it back + # CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 -- otherwise a hidden side request re-reads the + # whole prompt (~20 tokens out, title-generation shaped), + # doubling billed input: 9,638 vs 4,663 visible tokens. cmd = [self.bin, "-p", "--model", self.model, "--no-session-persistence", "--tools", "", - "--strict-mcp-config", "--output-format", "json", "--system-prompt", system] + "--strict-mcp-config", "--output-format", "json", + "--settings", json.dumps({"alwaysThinkingEnabled": False}), "--system-prompt", system] + env = dict(os.environ, DISABLE_PROMPT_CACHING="1", CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC="1") last = "" for attempt in range(5): try: - proc = subprocess.run(cmd, input=user, capture_output=True, text=True, timeout=900, cwd=self.workdir) + proc = subprocess.run(cmd, input=user, capture_output=True, text=True, timeout=900, cwd=self.workdir, env=env) except subprocess.TimeoutExpired: last = "timeout" else: @@ -302,6 +393,14 @@ class LLM: d = json.loads(proc.stdout) except json.JSONDecodeError: d = {"is_error": True, "result": (proc.stdout or proc.stderr)[-300:]} + if d.get("usage") or d.get("total_cost_usd"): # failed calls can still cost + # modelUsage is what was BILLED across every request the CLI made; `usage` is only + # the visible turn and undercounted by half before the nonessential-traffic fix. + mu = list((d.get("modelUsage") or {}).values()) + billed = {"input_tokens": sum((v.get("inputTokens") or 0) + (v.get("cacheReadInputTokens") or 0) + + (v.get("cacheCreationInputTokens") or 0) for v in mu), + "output_tokens": sum(v.get("outputTokens") or 0 for v in mu)} if mu else (d.get("usage") or {}) + self.ledger.record(getattr(self.label, "v", "?"), self.model, billed, d.get("total_cost_usd")) if not d.get("is_error") and d.get("result"): used = list((d.get("modelUsage") or {}).keys()) if used: @@ -324,7 +423,11 @@ class LLM: "Authorization": f"Bearer {self.key}", "Content-Type": "application/json"}) try: with urllib.request.urlopen(req, timeout=600) as r: - return json.load(r)["choices"][0]["message"]["content"] + d = json.load(r) + u = d.get("usage") or {} + self.ledger.record(getattr(self.label, "v", "?"), self.model, + {"input_tokens": u.get("prompt_tokens"), "output_tokens": u.get("completion_tokens")}, None) + return d["choices"][0]["message"]["content"] except urllib.error.HTTPError as e: detail = e.read()[:300].decode(errors="replace") if _QUOTA.search(detail): @@ -466,14 +569,26 @@ def top_level_sessions(cfg: dict) -> list[pathlib.Path]: def process(cfg, llm, vault, state, key, meta, source, kind, fingerprint, src_file, dry_run) -> str: - s = llm.summarize(meta) + # Cache the summary until the note is written, so a vault failure never pays for it twice. + cache = pathlib.Path(os.path.expanduser(cfg["STATE_FILE"])).parent / "cache" / \ + f"{hashlib.sha1(key.encode()).hexdigest()[:16]}-{hashlib.sha1(fingerprint.encode()).hexdigest()[:8]}.json" + llm.label.v = key + if cache.exists(): + s = json.loads(cache.read_text()) + else: + s = llm.summarize(meta) + cache.parent.mkdir(parents=True, exist_ok=True) + cache.write_text(json.dumps(s)) prev = state.data.get(key, {}) path = prev.get("note") or note_path(cfg, kind, meta, s["title"]) # stable across re-syncs body = render(meta, s, source, llm.resolved, src_file) + if dry_run == "prefetch": + return f"summary cached ({path})" if dry_run: print(f"\n===== {path} =====\n{body}") return path vault.put(path, body) + cache.unlink(missing_ok=True) state.record(key, {"note": path, "title": s["title"], "fingerprint": fingerprint, "source": source, "started": meta.get("first"), "project": pathlib.Path(meta["cwd"]).name if meta.get("cwd") else None}) @@ -494,7 +609,7 @@ def run_jobs(cfg, work, fn) -> tuple[int, int, str | None]: raise cf.CancelledError() try: return fn(*w) - except QuotaExhausted: + except (QuotaExhausted, BudgetExhausted): stop.set() raise @@ -508,7 +623,7 @@ def run_jobs(cfg, work, fn) -> tuple[int, int, str | None]: print(f"skip {label} (no conversation content)", flush=True) else: print(f"ok {label} -> {result}", flush=True); ok += 1 - except QuotaExhausted as e: + except (QuotaExhausted, BudgetExhausted) as e: if quota is None: quota = str(e) for f in futs: # don't launch the rest @@ -520,15 +635,31 @@ def run_jobs(cfg, work, fn) -> tuple[int, int, str | None]: return ok, failed, quota -def finish(ok: int, failed: int, quota: str | None, dry_run: bool, remaining: int) -> None: - verb = "rendered (dry run, nothing written)" if dry_run else "written" +def finish(ok: int, failed: int, quota: str | None, dry_run, remaining: int, ledger: "Ledger | None" = None) -> None: + verb = {"prefetch": "summarized into cache (vault untouched)"}.get(dry_run) or \ + ("rendered (dry run, nothing written)" if dry_run else "written") print(f"done: {ok} {verb}, {failed} failed, {remaining} still queued") + if ledger: + print(ledger.report()) if quota: - print(f"stopped: usage limit reached -- {quota}", file=sys.stderr) + print(f"stopped: {quota}", file=sys.stderr) sys.exit(EX_TEMPFAIL) sys.exit(1 if failed else 0) +def cmd_usage(cfg, args) -> None: + led = Ledger(cfg) + rows = led.entries() + if not rows: + print("no model calls recorded yet"); return + for label, hours in (("last 5h", 5), ("last 24h", 24), ("last 7d", 168)): + since = dt.datetime.now(dt.timezone.utc) - dt.timedelta(hours=hours) + es = [e for e in rows if dt.datetime.fromisoformat(e["ts"]) >= since] + print(f"{label:>9}: {len(es):4d} calls {sum(e['input'] for e in es):>10,} in " + f"{sum(e['output'] for e in es):>8,} out ${sum(e.get('cost_usd') or 0 for e in es):.3f}") + print(f"budgets: ${led.run_budget:.2f}/run, ${led.day_budget:.2f}/24h (list-price equiv; plan meter: /usage in Claude Code)") + + def cmd_stats(cfg, args) -> None: total = 0 rows = [] @@ -566,23 +697,25 @@ def cmd_sync(cfg, args) -> None: print(f"{total} session(s) pending, summarizing {len(work)} this run", flush=True) if not work: return - llm, vault = LLM(cfg), (None if args.dry_run else Vault(cfg)) + prefetch = getattr(args, "prefetch", False) + llm, vault = LLM(cfg), (None if args.dry_run or prefetch else Vault(cfg)) if vault: vault.ping() + mode = "prefetch" if prefetch else args.dry_run def one(p, fp, key): meta = parse_claude_code(p) if not meta["transcript"].strip(): - if not args.dry_run: + if not args.dry_run and not prefetch: state.record(key, {"note": None, "fingerprint": fp, "source": "claude-code"}) return SKIPPED src = str(p).replace(str(HOME), "~") - return process(cfg, llm, vault, state, key, meta, "claude-code", "Code", fp, src, args.dry_run) + return process(cfg, llm, vault, state, key, meta, "claude-code", "Code", fp, src, mode) ok, failed, quota = run_jobs(cfg, [(w[0].name, *w) for w in work], lambda _l, p, fp, key: one(p, fp, key)) if vault and ok: write_index(cfg, vault, state) - finish(ok, failed, quota, args.dry_run, total - ok) + finish(ok, failed, quota, mode, total - ok, llm.ledger) def cmd_import(cfg, args) -> None: @@ -607,16 +740,19 @@ def cmd_import(cfg, args) -> None: fp, None, args.dry_run)) if vault and ok: write_index(cfg, vault, state) - finish(ok, failed, quota, args.dry_run, total - ok) + finish(ok, failed, quota, args.dry_run, total - ok, llm.ledger) def main() -> None: ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter) sub = ap.add_subparsers(dest="cmd", required=True) + sub.add_parser("usage", help="model calls, tokens and spend from the local ledger") s = sub.add_parser("stats", help="condensed sizes, no network") s.add_argument("--top", type=int, default=15) s = sub.add_parser("sync", help="summarize Claude Code sessions") s.add_argument("--dry-run", action="store_true", help="print notes instead of writing them") + s.add_argument("--prefetch", action="store_true", + help="summarize into the local cache without touching the vault; a later sync writes them at no extra cost") s.add_argument("--force", action="store_true", help="ignore state and the settle window") s.add_argument("--session", help="only this session id") s.add_argument("--limit", type=int, help="max sessions this run (default MAX_PER_RUN)") @@ -628,7 +764,7 @@ def main() -> None: s.add_argument("--limit", type=int, help="max conversations this run (default MAX_PER_RUN)") args = ap.parse_args() cfg = load_config() - {"stats": cmd_stats, "sync": cmd_sync, "import-claude-ai": cmd_import}[args.cmd](cfg, args) + {"stats": cmd_stats, "usage": cmd_usage, "sync": cmd_sync, "import-claude-ai": cmd_import}[args.cmd](cfg, args) if __name__ == "__main__": diff --git a/claude-obsidian/config.env.example b/claude-obsidian/config.env.example index 7531d71..e7dcce5 100644 --- a/claude-obsidian/config.env.example +++ b/claude-obsidian/config.env.example @@ -21,3 +21,5 @@ VAULT_FOLDER=Claude SETTLE_MINUTES=30 # leave sessions alone until they have been idle this long JOBS=1 MAX_PER_RUN=10 # summaries share your plan's usage limits; the timer drips a backlog +BUDGET_USD_PER_RUN=0.50 # list-price USD, refused pre-flight; see `claude-obsidian-sync usage` +BUDGET_USD_PER_DAY=2.00