feat(agent-core): record llm request trace in wire.jsonl (#1448)

* feat(agent-core): record llm request trace in wire.jsonl

Add three observability record types so every request sent to the model
can be reconstructed from the wire log at the logical-request level:

- llm.tools_snapshot: content-addressed snapshot of the top-level tools
  table as sent (post deferred-strip), written once per unique table
- llm.request: one record per outbound request (retries, strict resends,
  and compaction rounds included) carrying the effective request params
  and hash links to the system prompt and tools snapshot
- mcp.tools_discovered: the server's verbatim tools/list result plus the
  agent's gating (allow-list, collisions), deduplicated by content hash

Observability records never feed state rebuild; replay only restores the
write-dedup cursors. The records/types.ts contract now documents the two
record classes explicitly (persisted is not the same as replayed).

Recording happens at the single Agent.generate choke point. The
LLMRequestLogFields side channel gains kind/projection/maxTokens/
droppedCount, chatWithRetry preserves caller-set fields, and compaction
tags its requests. The vis wire view renders the new record kinds.

* fix(agent-core): record the provider-clamped completion cap in the request trace

The llm.request trace recorded the client-requested budget cap, but
chat-completions providers tighten the actual wire value inside
withMaxCompletionTokens (remaining-context sizing, transport ceilings,
model-default resolution) — with the default budget the clamp is active
on nearly every non-empty-context request, so the recorded value did not
match what was sent.

Providers now expose the effective cap they computed as a readonly
maxCompletionTokens field on the clone, and the recorder reads it from
the effective provider at the Agent.generate choke point. This replaces
the side-channel recomputation, which is removed along with the
appliedCompletionBudgetCap helper.

* fix(agent-core): park pre-replay MCP discovery records and hash the collision outcome

Two wire-hygiene fixes for the mcp.tools_discovered trace:

Parking: the real Session ordering connects MCP servers concurrently with
agent construction, so ToolManager can observe a connected server before
agent.resume() has replayed the wire. Recording at that point bypassed
the restored dedup cursor (duplicating a 1-50KB record on every resume)
and appended a stray metadata record ahead of replay. AgentRecords now
exposes a one-shot opened latch — set when replay completes (after the
migration rewrite flushes) or when the first live record is logged — and
ToolManager parks discoveries until then, re-running the dedup check at
drain time. A frozen range-limited replay never opens; those agents are
transient previews.

Collision hashing: the dedup hash now covers the collision outcome, not
just the raw list and allow-list. Collisions depend on which other
servers hold a sanitized qualified name at registration time, so a
server can re-register with identical tools but a flipped outcome; that
gating change must produce a new record instead of being suppressed.

* fix(agent-core): skip the request trace for pre-flight-aborted calls

Mirror kosong generate()'s pre-flight abort check at the Agent.generate
choke point: a call whose signal is already aborted never reaches the
wire (generate throws before dispatching), so it must not leave an
llm.request/llm.tools_snapshot trace or a diagnostic log line claiming a
request was sent. Recording stays before dispatch for every call that
passes the gate, preserving the crash-safety of the trace.

* chore(agent-core): remove a leftover adaptive-thinking override hook

The adaptiveThinkingOverride option was a temporary local hook explicitly
marked for removal before commit. Nothing passes it, so resolution falls
back to the alias-level adaptiveThinking value in all cases; drop the
option and the dead indirection.

* fix(kosong): derive the exposed completion cap from generation kwargs

maxCompletionTokens was a field stored only by withMaxCompletionTokens,
so caps that reach the wire through other paths were invisible to the
request trace: with completion budgeting disabled via env, Anthropic
still sends the constructor-resolved max_tokens (required by the
Messages API), and constructor-level kwargs like OpenAILegacyOptions
maxTokens were likewise unreported.

Replace the stored field with a getter derived from each provider's
generation kwargs — the single source the request body reads — covering
constructor defaults, direct withGenerationKwargs configuration, and
budget application in one place. Kimi mirrors its request-time legacy
max_tokens alias normalization; openai-legacy reuses the same
normalizeGenerationKwargs the request path uses.

* feat(agent-core): add thinkingKeep passthrough for Kimi providers and update tests

.changeset/wire-request-trace.md

@@ -0,0 +1,7 @@
+---
+"@moonshot-ai/agent-core": minor
+"@moonshot-ai/kimi-code": minor
+"@moonshot-ai/kosong": minor
+---
+
+Record a request trace in each agent's `wire.jsonl`: content-addressed snapshots of the tool schemas sent to the model, one record per model request (including retries, strict resends, and compaction rounds) with the effective request parameters, and the raw MCP tool listing per server, so sessions carry enough data to reconstruct every model request for debugging. Chat providers now expose the effective completion-token cap they send on the wire, so the trace records the provider-clamped value rather than the requested budget.