chore: sync fantasy fork with upstream v0.40.0 and openai-go with v3.50.0 (#27981)

Our fantasy fork had drifted far behind upstream charmbracelet/fantasy
(base v0.31.0 vs current v0.40.0). This PR updates the pinned forks
after reconciling which fork hacks upstream has fixed and which we still
need, and adapts this repo to the new APIs.

## Fork updates

- `charm.land/fantasy` ->
[coder/fantasy#51](coder/fantasy#51) (merged):
`coder_2_33` synced with upstream v0.40.0, pinned at the merge commit
`bb10946892ef`.
- `github.com/openai/openai-go/v3` ->
[coder/openai-go#10](coder/openai-go#10)
(merged): `coder/pinned` rebased from v3.16.0 onto upstream v3.50.0
(required by upstream fantasy), pinned at the merge commit
`92b5addb22d2`.
- `coder/anthropic-sdk-go` pin unchanged; the fantasy fork now tracks
the same revision this repo ships.

## Hack reconciliation summary

Dropped from our fantasy diff (upstream now has equivalents, often
stricter): truncated-stream fail-closed detection, Anthropic EffortXHigh
/ computer use / thinking effort / thinking display, replay fidelity for
signed reasoning and web_search errors, PDF and text documents with
sanitized filename titles, refusal finish-reason mapping (upstream also
maps Bedrock `content_filtered`/`guardrail_intervened`), gpt-5.5/5.6
Responses routing, the Go 1.25 downgrade, and the openai-go SSE decoder
and appendCompact patches.

Still fork-only and preserved: OpenAI computer use, OpenAI Responses
replay continuity validation, Anthropic pre-4.6 budget-thinking
conversion plus explicit thinking disable for effort none, Anthropic
RefusalMetadata parsing, Bedrock cross-region inference profile region
mirroring, and openai-go deferred body serialization with the
WithJSONSet fix.

Picked up new upstream features: stream transport retry with in-band SSE
error classification, Bedrock expired-credential refresh, per-message
cache markers for OpenAI-compatible models, tool panic recovery, extra
usage fields in provider metadata, and ClientMetadata on tool results.

## Changes in this repo

- `aibridge/intercept/responses`: `ResponseOutputItemUnion.Arguments`
became a union type in openai-go v3.50; read function-call arguments via
`.OfString` (plus test literal updates).
- `coderd/x/chatd/chatdebug`: register the new fantasy `Call.Headers`,
`ObjectCall.Headers`, and `ToolResultPart.ClientMetadata` fields in the
normalization coverage map (all skipped).
- `aibridge/internal/integrationtest`: make the RST test listener drain
the request before resetting the connection. The new SDK's write path
exposed the previous 1-byte-read race as sporadic `use of closed network
connection` failures; the fix holds over 40 consecutive runs.
- `go.mod`: rewrite the fork provenance comments to describe the
post-sync state.

## Validation

- `go build ./...` and `go vet ./...` clean (vet findings identical to
base).
- Fresh (`-count=1`) runs of `./coderd/x/chatd/...`, `./aibridge/...`,
`./coderd/aibridged/...`, `./coderd/database/db2sdk/`: 37 packages pass.
- `TestClientAndConnectionError` stress-tested 40x clean.
- Both fork PRs have green CI.

> Mux acted on Mike's behalf to create this PR.

Author: ibetitsmike

aibridge/intercept/responses/base.go

@@ -264,7 +264,9 @@ func (i *responsesInterceptionBase) recordNonInjectedToolUsage(ctx context.Conte
 		// have no uniform argument representation.
 		switch item.Type {
 		case string(constant.ValueOf[constant.FunctionCall]()):
-			args = i.parseFunctionCallJSONArgs(ctx, item.Arguments)
+			// Arguments is a union since openai-go v3.50; function_call
+			// arguments are always the JSON string variant.
+			args = i.parseFunctionCallJSONArgs(ctx, item.Arguments.OfString)
 		case string(constant.ValueOf[constant.CustomToolCall]()):
 			args = item.Input
 		case string(constant.ValueOf[constant.WebSearchCall]()),

aibridge/intercept/responses/base_internal_test.go

@@ -114,7 +114,7 @@ func TestRecordToolUsage(t *testing.T) {
 						Type:      "function_call",
 						CallID:    "call_abc",
 						Name:      "get_weather",
-						Arguments: "",
+						Arguments: oairesponses.ResponseOutputItemUnionArguments{OfString: ""},
 					},
 				},
 			},
@@ -138,13 +138,13 @@ func TestRecordToolUsage(t *testing.T) {
 						Type:      "function_call",
 						CallID:    "call_1",
 						Name:      "get_weather",
-						Arguments: `{"location": "NYC"}`,
+						Arguments: oairesponses.ResponseOutputItemUnionArguments{OfString: `{"location": "NYC"}`},
 					},
 					{
 						Type:      "function_call",
 						CallID:    "call_2",
 						Name:      "bad_json_args",
-						Arguments: `{"bad": args`,
+						Arguments: oairesponses.ResponseOutputItemUnionArguments{OfString: `{"bad": args`},
 					},
 					{
 						Type: "message",
@@ -161,7 +161,7 @@ func TestRecordToolUsage(t *testing.T) {
 						Type:      "function_call",
 						CallID:    "call_4",
 						Name:      "calculate",
-						Arguments: `{"a": 1, "b": 2}`,
+						Arguments: oairesponses.ResponseOutputItemUnionArguments{OfString: `{"a": 1, "b": 2}`},
 					},
 				},
 			},
@@ -211,7 +211,7 @@ func TestRecordToolUsage(t *testing.T) {
 						ID:        "fc_item_1",
 						CallID:    "call_both",
 						Name:      "get_weather",
-						Arguments: `{"location": "NYC"}`,
+						Arguments: oairesponses.ResponseOutputItemUnionArguments{OfString: `{"location": "NYC"}`},
 					},
 				},
 			},

aibridge/internal/integrationtest/responses_internal_test.go

@@ -1,6 +1,7 @@
 package integrationtest
 
 import (
+	"bufio"
 	"context"
 	"encoding/json"
 	"fmt"
@@ -1158,10 +1159,12 @@ func startRejectingListener(t *testing.T) (addr string) {
 				return
 			}
 
-			// Read at least 1 byte so the client has started writing
-			// before we RST, ensuring a consistent "connection reset by peer".
-			buf := make([]byte, 1)
-			_, _ = c.Read(buf)
+			// Drain the request before the RST so the client observes a
+			// read-side reset rather than a racy body-write failure.
+			if req, err := http.ReadRequest(bufio.NewReader(c)); err == nil {
+				_, _ = io.Copy(io.Discard, req.Body)
+				_ = req.Body.Close()
+			}
 			if tc, ok := c.(*net.TCPConn); ok {
 				_ = tc.SetLinger(0)
 			}

coderd/x/chatd/chatdebug/model_coverage_internal_test.go

@@ -58,6 +58,7 @@ func TestNormalizationFieldCoverage(t *testing.T) {
 				"Tools":            "normalized",
 				"ToolChoice":       "normalized",
 				"UserAgent":        "skipped: internal transport header, not useful for debug panel",
+				"Headers":          "skipped: transport headers, may carry credentials",
 				"ProviderOptions":  "skipped: opaque provider data, only count preserved",
 			},
 		},
@@ -76,6 +77,7 @@ func TestNormalizationFieldCoverage(t *testing.T) {
 				"PresencePenalty":   "normalized",
 				"FrequencyPenalty":  "normalized",
 				"UserAgent":         "skipped: internal transport header, not useful for debug panel",
+				"Headers":           "skipped: transport headers, may carry credentials",
 				"ProviderOptions":   "skipped: opaque provider data, only count preserved",
 				"RepairText":        "skipped: function value, not serializable",
 			},
@@ -196,6 +198,7 @@ func TestNormalizationFieldCoverage(t *testing.T) {
 				"Output":           "normalized: text extracted via normalizeToolResultOutput",
 				"ProviderExecuted": "skipped: provider vs client distinction not needed for debug panel",
 				"ProviderOptions":  "skipped: opaque provider-specific options",
+				"ClientMetadata":   "skipped: client execution metadata not needed for debug panel",
 			},
 		},