denpex-mcp 0.2.16 → 0.2.18

package/README.md

@@ -1,12 +1,12 @@
 # Denpex MCP server
 
-Diagnose GPU/ML training failures — CUDA OOM, NCCL timeouts, Xid faults, NaN loss,
-checkpoint corruption — **without leaving your AI tool**. Ask Claude Desktop, Cursor,
+Diagnose GPU/ML training failures. CUDA OOM, NCCL timeouts, Xid faults, NaN loss,
+checkpoint corruption, **without leaving your AI tool**. Ask Claude Desktop, Cursor,
 or Claude Code to *"diagnose the crash in `./logs/train.err`"* and Denpex reads the log
 straight off disk and hands back the root cause and the fix.
 
 - 🩺 **Root cause + escalating fix** (primary → fallback → emergency), verification command, and prevention.
-- 🧭 **Find the culprit rank** in a distributed/NCCL hang, and route GPU Xid faults to the right node action — offline, instantly.
+- 🧭 **Find the culprit rank** in a distributed/NCCL hang, and route GPU Xid faults to the right node action, offline, instantly.
 - 📚 **Bundled failure encyclopedia** (500+ documented classes) searchable by error code or symptom.
 - 🔒 **Zero-egress mode** (`DENPEX_LOCAL=1`): diagnose entirely on-host, nothing leaves the machine. Plus client-side PII scrubbing even in cloud mode.
 
@@ -18,10 +18,12 @@ straight off disk and hands back the root cause and the fix.
 
 Sign in at **[denpex.com/dashboard](https://denpex.com/dashboard) → API Keys** and create a key (`dpx_…`).
 The key unlocks authenticated cloud diagnosis, your diagnosis history, quota, and fleet
-incidents. *Without a key, `diagnose_crash` uses the same canonical anonymous engine as
-the homepage's three free diagnoses. Anonymous clarifications reuse the server-issued,
-log-bound refinement token automatically (or accept it explicitly after an MCP restart),
-so answering Denpex does not spend another diagnosis and cannot be forged with a public
+incidents. *Without a key, the first `diagnose_crash` cloud run is frictionless and uses
+the same canonical anonymous engine as the homepage. Later new anonymous diagnoses need
+the browser check at [denpex.com](https://denpex.com/#instant-diagnosis), which MCP cannot
+complete, or an API key. Anonymous clarifications reuse the server-issued, log-bound
+refinement token automatically (or accept it explicitly after an MCP restart), so
+answering Denpex does not spend another diagnosis and cannot be forged with a public
 boolean header. Set `DENPEX_LOCAL=1` explicitly for zero-egress;
 `lookup_failure` and `analyze_cascade` remain available from the bundled offline data.*
 
@@ -75,7 +77,7 @@ claude mcp add denpex -e DENPEX_API_KEY=dpx_your_key_here -- npx -y denpex-mcp
 
 ### 3. Use it
 
-> "My training job crashed — diagnose the log at `./logs/rank0.err`."
+> "My training job crashed, diagnose the log at `./logs/rank0.err`."
 > "What does Xid 79 mean?"
 > "This 64-GPU run is hung. Which rank failed first?"  *(→ `analyze_cascade`)*
 
@@ -85,7 +87,7 @@ Or pick the **`diagnose-training-crash`** prompt your client surfaces.
 
 ## Offline / air-gapped mode
 
-Diagnose entirely on-host — no network, no logs leaving the cluster. Ideal for VPCs,
+Diagnose entirely on-host, no network, no logs leaving the cluster. Ideal for VPCs,
 secure data centers, and privacy-sensitive labs. Add `DENPEX_LOCAL=1`:
 
 ```json
@@ -115,20 +117,20 @@ are unavailable offline.
 | `recent_diagnoses` | Recall your recent diagnoses and their fixes. | API key |
 | `ask_followup` | Conversational follow-up on a diagnosis. | Team plan / trial |
 | `check_versions` | Flag known-bad CUDA/PyTorch/NCCL/driver combos. | Team plan / trial |
-| `compare_runs` | "It worked yesterday" — isolate what changed between a good run and a bad one. | Team plan / trial |
+| `compare_runs` | "It worked yesterday", isolate what changed between a good run and a bad one. | Team plan / trial |
 | `diff_environments` | Diff torch/CUDA/NCCL/driver versions and env vars between two runs. | Team plan / trial |
 | `validate_checkpoint` | Find the newest checkpoint that is actually safe to resume from. | Team plan / trial |
-| `preflight_check` | "Is this cluster safe to launch on?" — blockers before you burn GPU-hours. | Scale plan |
+| `preflight_check` | "Is this cluster safe to launch on?", blockers before you burn GPU-hours. | Scale plan |
 | `node_health` | Score every monitored node, worst first. | Scale plan |
 | `predict_failures` | Nodes trending toward a failure that has not happened yet. | Scale plan |
 | `list_incidents` | Incidents Denpex's monitor caught & escalated on your fleet. | Scale plan |
 
-Gated tools degrade gracefully — they tell you exactly which plan unlocks them and which
+Gated tools degrade gracefully, they tell you exactly which plan unlocks them and which
 tools work on your current plan. The failure encyclopedia is also exposed as resources at
 `denpex://failures/{slug}`.
 
 **Structured output.** Every tool above returns `structuredContent` alongside its
-markdown, validated against a declared output schema — so an agent branches on
+markdown, validated against a declared output schema, so an agent branches on
 `confidenceBand === "low"` or iterates `rankedHypotheses` instead of regexing prose.
 Two fields deserve attention when you write the agent loop:
 
@@ -145,7 +147,7 @@ Two fields deserve attention when you write the agent loop:
 
 | Variable | Default | Purpose |
 |----------|---------|---------|
-| `DENPEX_API_KEY` | — | Your `dpx_…` key. Enables cloud tools. |
+| `DENPEX_API_KEY` |, | Your `dpx_…` key. Enables cloud tools. |
 | `DENPEX_API_URL` | `https://api.denpex.com` | Override the API base (self-host / staging). |
 | `DENPEX_LOCAL` | `0` | `1` → diagnose entirely on-host (zero egress). |
 | `DENPEX_PRIVACY` | `off` | `mask` / `strict` → scrub PII from logs **before** they leave the machine. |
@@ -163,4 +165,4 @@ npm run inspector  # interactive protocol inspector (MCP Inspector)
 
 The offline corpus (`src/data/denpex_patterns.json`) and canonical engine
 (`src/offline/canonical-engine.mjs`) are generated from the repo's single source of truth
-during `npm run build` — never hand-edit either artifact.
+during `npm run build`, never hand-edit either artifact.