Share image input across agent vendors

This commit is contained in:
Ian Gulliver
2026-10-21 15:48:21 -07:00
parent 06987c1989
commit 8e865e69b2
6 changed files with 27 additions and 48 deletions
+6
View File
@@ -0,0 +1,6 @@
package agentinput
type Image struct {
MediaType string
Data []byte
}
+7 -6
View File
@@ -13,6 +13,7 @@ import (
"sync"
"time"
"g.fc.run/ai/byre/internal/agentinput"
"g.fc.run/ai/byre/internal/api"
"g.fc.run/ai/byre/internal/claude"
"g.fc.run/ai/byre/internal/clients"
@@ -602,7 +603,7 @@ func (m *Manager) launch(ctx context.Context, sess api.AgentSession, task api.Ta
return m.store.GetSession(ctx, sess.Id)
}
func (m *Manager) deliver(ctx context.Context, sess api.AgentSession, task api.Task, actor, client, text string, imgs []image, compacting bool) error {
func (m *Manager) deliver(ctx context.Context, sess api.AgentSession, task api.Task, actor, client, text string, imgs []agentinput.Image, compacting bool) error {
l, err := m.ensureLive(ctx, sess, task)
if err == nil {
err = m.syncModel(ctx, l, sess.Model)
@@ -642,14 +643,14 @@ func (m *Manager) deliverRecorded(ctx context.Context, sess api.AgentSession, ta
return true, m.deliver(ctx, sess, task, ev.Actor, client, text, imgs, isHandoffPrompt(ev.Actor, text))
}
func (m *Manager) readImages(ctx context.Context, ids []string) ([]image, error) {
imgs := []image{}
func (m *Manager) readImages(ctx context.Context, ids []string) ([]agentinput.Image, error) {
imgs := []agentinput.Image{}
for _, id := range ids {
b, data, err := m.store.ReadBlob(ctx, id)
if err != nil {
return nil, err
}
imgs = append(imgs, image{mediaType: b.ContentType, data: data})
imgs = append(imgs, agentinput.Image{MediaType: b.ContentType, Data: data})
}
return imgs, nil
}
@@ -702,7 +703,7 @@ func (m *Manager) message(ctx context.Context, sess api.AgentSession, task api.T
return m.send(ctx, l, m.agentText(actor, "", text), imgs)
}
func (m *Manager) send(ctx context.Context, l *live, text string, imgs []image) error {
func (m *Manager) send(ctx context.Context, l *live, text string, imgs []agentinput.Image) error {
err := l.sess.send(ctx, text, imgs)
if err != nil {
return err
@@ -710,7 +711,7 @@ func (m *Manager) send(ctx context.Context, l *live, text string, imgs []image)
return m.store.MarkSessionDelivered(ctx, l.id)
}
func (m *Manager) recordMessage(ctx context.Context, sess api.AgentSession, task api.Task, actor, text, sendID, client string, images []string) ([]image, bool, error) {
func (m *Manager) recordMessage(ctx context.Context, sess api.AgentSession, task api.Task, actor, text, sendID, client string, images []string) ([]agentinput.Image, bool, error) {
implementer := sess.Role == api.Implementer
if implementer && isMergeInPrompt(actor, text) {
m.ownMerge(sess.Id, task.Id, task.WorktreePath)
+8 -24
View File
@@ -10,6 +10,7 @@ import (
"strings"
"time"
"g.fc.run/ai/byre/internal/agentinput"
"g.fc.run/ai/byre/internal/antigravity"
"g.fc.run/ai/byre/internal/api"
"g.fc.run/ai/byre/internal/claude"
@@ -17,13 +18,8 @@ import (
"g.fc.run/ai/byre/internal/mcp"
)
type image struct {
mediaType string
data []byte
}
type agentProcess interface {
send(ctx context.Context, text string, images []image) error
send(ctx context.Context, text string, images []agentinput.Image) error
interrupt(ctx context.Context) error
setModel(ctx context.Context, model string) error
kill()
@@ -118,12 +114,8 @@ func (m *Manager) startClaude(ctx context.Context, sess api.AgentSession, l *liv
return claudeProcess{s: s}, nil
}
func (p claudeProcess) send(ctx context.Context, text string, images []image) error {
imgs := []claude.Image{}
for _, img := range images {
imgs = append(imgs, claude.Image{MediaType: img.mediaType, Data: img.data})
}
return p.s.Send(text, imgs...)
func (p claudeProcess) send(ctx context.Context, text string, images []agentinput.Image) error {
return p.s.Send(text, images...)
}
func (p claudeProcess) interrupt(ctx context.Context) error {
@@ -196,12 +188,8 @@ func (m *Manager) startCodex(ctx context.Context, sess api.AgentSession, l *live
return codexProcess{s: s}, nil
}
func (p codexProcess) send(ctx context.Context, text string, images []image) error {
imgs := []codex.Image{}
for _, img := range images {
imgs = append(imgs, codex.Image{MediaType: img.mediaType, Data: img.data})
}
_, err := p.s.Send(ctx, text, imgs...)
func (p codexProcess) send(ctx context.Context, text string, images []agentinput.Image) error {
_, err := p.s.Send(ctx, text, images...)
return err
}
@@ -267,12 +255,8 @@ func (m *Manager) startAntigravity(ctx context.Context, sess api.AgentSession, l
return antigravityProcess{s: s}, nil
}
func (p antigravityProcess) send(ctx context.Context, text string, images []image) error {
imgs := []antigravity.Image{}
for _, img := range images {
imgs = append(imgs, antigravity.Image{MediaType: img.mediaType, Data: img.data})
}
return p.s.Send(text, imgs...)
func (p antigravityProcess) send(ctx context.Context, text string, images []agentinput.Image) error {
return p.s.Send(text, images...)
}
func (p antigravityProcess) interrupt(ctx context.Context) error {
+2 -6
View File
@@ -20,6 +20,7 @@ import (
"syscall"
"time"
"g.fc.run/ai/byre/internal/agentinput"
"g.fc.run/ai/byre/internal/mcp"
"g.fc.run/ai/byre/internal/procgroup"
)
@@ -43,11 +44,6 @@ type Options struct {
OnBadLine func(line []byte, reason string)
}
type Image struct {
MediaType string
Data []byte
}
type Event struct {
Kind string
Raw json.RawMessage
@@ -460,7 +456,7 @@ type block struct {
Text string `json:"text"`
}
func (s *Session) Send(text string, images ...Image) error {
func (s *Session) Send(text string, images ...agentinput.Image) error {
s.mu.Lock()
defer s.mu.Unlock()
+2 -6
View File
@@ -17,6 +17,7 @@ import (
"sync/atomic"
"time"
"g.fc.run/ai/byre/internal/agentinput"
"g.fc.run/ai/byre/internal/mcp"
"g.fc.run/ai/byre/internal/procgroup"
)
@@ -427,12 +428,7 @@ func (s *Session) ID() string {
return s.id
}
type Image struct {
MediaType string
Data []byte
}
func (s *Session) Send(text string, images ...Image) error {
func (s *Session) Send(text string, images ...agentinput.Image) error {
var content any = text
if len(images) > 0 {
blocks := []map[string]any{}
+2 -6
View File
@@ -17,6 +17,7 @@ import (
"sync/atomic"
"time"
"g.fc.run/ai/byre/internal/agentinput"
"g.fc.run/ai/byre/internal/mcp"
"g.fc.run/ai/byre/internal/procgroup"
)
@@ -58,11 +59,6 @@ func (e Event) Decode() (any, error) {
return v, nil
}
type Image struct {
MediaType string
Data []byte
}
type RPCError struct {
Code int64 `json:"code"`
Message string `json:"message"`
@@ -368,7 +364,7 @@ func (s *Session) SetModel(model string) {
s.stateMu.Unlock()
}
func (s *Session) Send(ctx context.Context, text string, images ...Image) (Turn, error) {
func (s *Session) Send(ctx context.Context, text string, images ...agentinput.Image) (Turn, error) {
input := []UserInput{}
for _, img := range images {
input = append(input, UserInput{