dsh-context 0.51.1 → 0.52.1

package/README.md

@@ -59,13 +59,22 @@ Open any session and click the **Context / 上下文** tab:
 
 The headline occupancy and composition read the **same official token-meter projections as the chat composer's context ring** (`contextPressure` / `contextBreakdown`), so the figures always match what the ring tells you.
 
-### 🧱 Current Context — who ate the budget
+### Context Stats
+
+#### Token Stats and Timing Stats
+![Token_Stats_and_Timing_Stats](https://raw.githubusercontent.com/bowenliang123/dsh-context/main/docs/token-stats-and-timing-stats.png)
+
+#### Context Stats
+![Context_Stats](https://raw.githubusercontent.com/bowenliang123/dsh-context/main/docs/context-stats.png)
+
+
+### 🧱 Current Context — what's in the context window now
 
 ![Current Context card](https://raw.githubusercontent.com/bowenliang123/dsh-context/main/docs/current-context.png)
 
 A six-color stacked bar against the model's full window (hatching = free headroom): system prompt, tool schemas, user messages, injected context, assistant replies, tool results — each with its ≈token figure and share. When a conversation starts degrading, this is where you see *which part* is responsible.
 
-### 📈 Context Trend — every request, sized and explained
+### 📈 Context Trend — how the context grew and evolved by turn or steps
 
 ![Context Trend with the step brief](https://raw.githubusercontent.com/bowenliang123/dsh-context/main/docs/context-trend.png)
 
@@ -82,7 +91,7 @@ One stacked bar per model request — finer than per-message — so you watch th
 
 ### 🧭 Context Browser — open the box of any request
 
-Pick **Live (next request)** or any retained step, and browse what that request was assembled from: six collapsible categories expand into one row per element with its token price, and every element expands again into its **actual content** — the system prompt, each tool's JSON schema, message text, reasoning, tool arguments, and tool outputs.
+Pick **Live (next request)** or any retained step, and browse what that request was assembled from: seven collapsible categories expand into one row per element with its token price, and every element expands again into its **actual content** — the system prompt, each tool's JSON schema, message text, reasoning, tool arguments, and tool outputs. Skill content (the available-skills catalog, `/skill` invocations, and `skill`-tool loads) has its own **Skill Injections** category, so a stealthy skill's context footprint can't hide inside the injected-context and tool-result buckets.
 
 - **Who provides each tool** — every tool-schema row carries a best-effort source chip: `tool-*` first-party packages, `dsh-*` capability packages, `mcp:<server>` proxies, or the exact plugin watched live from `tools.register()`. Sort by **size / name**, and filter every category by its own searchable fields: