feat: forward generation params via MITM + add usageMetadata to Gemini

- Add GenerationParams struct to MitmStore for temperature, top_p,
  top_k, max_output_tokens, stop_sequences, frequency/presence_penalty
- MITM modify_request injects params into request.generationConfig
- All 3 endpoints (Completions, Responses, Gemini) store client params
- Add usageMetadata to Gemini sync responses (promptTokenCount,
  candidatesTokenCount, totalTokenCount, thoughtsTokenCount)
- Add generation param fields to GeminiRequest (temperature, topP, etc.)
- Completions stream_options.include_usage emits final usage chunk
- Completions reasoning_tokens in completion_tokens_details
- Update endpoint gap analysis doc (all high-priority gaps resolved)

KNOWN_ISSUES.md

@@ -72,11 +72,27 @@ heuristic hint is absent, properly correlating usage to cascades.
 
 **Status: SOLVED (2026-02-15)**
 
-The MITM proxy now captures `thinking_text` from `StreamingAccumulator` into
-`MitmStore` as SSE chunks arrive. The Responses API streaming handler reads
-thinking deltas from MitmStore and emits `response.reasoning_summary_text.delta`
-events in real-time. This works for both Google (`thought: true` parts) and
-Anthropic (`thinking_delta`) formats.
+Thinking text now streams progressively as delta events. The implementation:
+
+1. **LS cascade steps** — `plannerResponse.thinking` (field 3) grows progressively
+   as the LS receives data. For Opus 4.6, thinking text builds up word-by-word
+   over ~1-2s. For Gemini Flash, thinking arrives in 1-2 larger chunks.
+2. **Delta tracking** — `last_thinking_len` tracks the previously emitted length.
+   Each poll compares current thinking length and emits only the new characters
+   as `response.reasoning_summary_text.delta` events.
+3. **Lifecycle** — Structure events (`output_item.added`, `summary_part.added`)
+   emit on first thinking appearance. `done` events emit when response text
+   first appears (indicating thinking phase completed).
+
+**Verified with Opus 4.6:** (2026-02-15 13:22 UTC)
+
+```
+delta_len=24  "The user is asking about"
+delta_len=61  " the Collatz conjecture..."
+delta_len=5   " This"
+delta_len=10  " is a pure"
+... (11 progressive deltas over ~850ms)
+```
 
 ---