Requested-command output is rendered by the inline pane whenever it is
expanded. Keep the backing terminal block hidden in both states so
collapsing the pane does not move the output to the bottom of the
conversation.
- Track user-initiated expansion state to avoid auto-collapse conflicts
- Invert inline action visibility so terminal block hides while inline pane owns the expanded body
- Add scrollable output rendering in requested command expanded view
- Simplify CLI monitor nudge message and extract to reusable method
- Show only latest user query and assistant text in monitor task transcript
- Add handle_ctrl_c_for_conversation to status bar for child agent cancellation
- Update rig_request tests for adjusted monitor nudge wording
Ensure parallel tool results finish before follow-ups, preserve warping
status across exchanges, clean up streams before crosscheck reviews, and
restore terminal focus when conversations complete. Remove temporary
debug
logging.
Add the 'Crosscheck Work' experiment to the Agents settings. When enabled,
a reviewer sub-agent is spawned after the main agent finishes a turn (with
no pending tool calls). The reviewer critiques the output using a dedicated
system prompt focused on correctness, simplicity, and code quality. If the
reviewer does not respond with 'LGTM!', its feedback is injected as a
synthetic user query back to the main agent, which must address it. This
loop continues until the reviewer approves or max iterations is reached.
Components:
- Feature flag: CrosscheckWork (enabled in DOGFOOD_FLAGS)
- Settings: agents.experiments.crosscheck_enabled,
agents.experiments.crosscheck_model_id,
agents.experiments.crosscheck_max_iterations
- Settings UI: new 'Experiments' subpage under Agents
- Crosscheck module: app/src/ai/crosscheck/ with prompt, reviewer model
- Controller integration: hooks into AfterStreamFinished when no actions
are queued, triggers reviewer, handles feedback injection
- Provider support: OpenAI-compatible and Bedrock direct invocation
- Safety: max iteration guard, error handling, reset on new user query
- Sanitize tool_use_id values in OpenAI request conversion to match
Bedrock's required pattern ^[a-zA-Z0-9_-]+$. Fixes 400 errors when
LiteLLM proxies to Bedrock and tool IDs contain invalid characters.
- Parse cache usage stats from LiteLLM/OpenAI responses
(prompt_tokens_details.cached_tokens, cache_read_input_tokens,
cache_creation_input_tokens) and propagate to token usage tracking.
- Hide cache-o-meter in session status bar when provider doesn't report
cache data (LiteLLM/OpenAI), instead of showing misleading 0% stats.
- Update cost estimation to account for cache read/write pricing tiers.
typescript-language-server requires a valid TypeScript installation to
function. Previously, no initializationOptions were sent during the LSP
initialize request, causing the server to fail with:
'Could not find a valid TypeScript installation. Please ensure that
the typescript dependency is installed in the workspace or that a
valid tsserver.path is specified.'
This fix:
- Adds initializationOptions.tsserver.path resolution that searches for
TypeScript in: workspace node_modules, global npm install, and npx cache
- Wires initialization_options into the LSP startup flow via LSPServerType
- Updates the install step to proactively install TypeScript globally if
not found locally
When a skill was invoked on a clean slate (no conversation history),
the request sent to the AI provider contained only a system prompt
with zero user messages, causing Bedrock/LiteLLM to reject it with:
'Invalid Message bedrock requires at least one non-system message'
Root cause: extract_new_input_messages() had no handler for
Type::InvokeSkill, so it fell through to the _ => {} wildcard and
produced zero ConversationMessage results.
Fix adds InvokeSkill handling to three functions:
- extract_new_input_messages(): generates a User message with the
skill name and content wrapped in <skill-instructions> tags
- extract_input_messages(): persists the InvokeSkill as a proper
api::Message in task history for conversation continuity
- extract_user_query_text(): returns '/<skill-name>' for the
UserQuery proto event used in conversation title generation
- Load global rules (AIFact/AIMemory) from local CloudModel and inject
them into the Bedrock/OpenAI system prompt as a '## Global Rules' section
when memory is enabled.
- Fix rule seeding: always re-seed predefined rules when the CloudModel has
none, regardless of the has_seeded_predefined_rules flag (handles case
where flag was set but rules never persisted due to prior missing owner).
- Rename /context slash command to /copy-context: dumps the full context
window (global rules, progressive summary, message history) to the
clipboard for debugging.
Previously, predefined rules (11 system-defined behavioral rules) were
only seeded when the user navigated to the Rules settings page, and
required a cloud-authenticated owner to create cloud objects.
Since Galaxy operates without Warp cloud auth:
1. personal_drive() now returns a synthetic local owner
('local-galaxy-user') when not authenticated, allowing cloud objects
(rules, etc.) to be created and stored locally in SQLite.
2. seed_predefined_rules_if_needed() runs at app startup (after
CloudModel and UpdateManager are initialized) to seed rules on
first launch without requiring the user to visit settings.
Rules are now visible in Galaxy Drive > Rules on first launch.
The previous implementation only used the standard OpenAI /models
endpoint which often lacks context window and capability metadata,
causing a blind 200K fallback for all models.
Now fetch_openai_models_from_endpoint tries LiteLLM's /model/info
endpoint first, which returns rich metadata:
- max_input_tokens (e.g. 1,000,000 for Sonnet 4.6)
- max_output_tokens (e.g. 128,000 for max models)
- supports_vision
- supports_function_calling
- underlying model path (for provider detection)
Falls back to /models if /model/info is unavailable (e.g. non-LiteLLM
OpenAI-compatible endpoints).
This ensures the model picker and context window configuration reflect
the actual capabilities of the configured models.
Galaxy should never call Warp's cloud API for AI. This is a policy
requirement. All model availability is now determined exclusively by
locally configured providers (Bedrock and/or OpenAI/LiteLLM).
Changes:
- Disable refresh_authed_models, refresh_public_models, refresh_available_models
(now no-ops with debug log)
- Disable on_server_update and update_feature_model_choices
- Disable get_cached_models (no stale server models restored from cache)
- Replace ModelsByFeature::default() with minimal placeholder that gets
stripped by inject_bedrock_models/inject_openai_models
- Make inject_bedrock_models strip Unknown placeholders unconditionally
- Make default_llm_info() return a static fallback instead of panicking
when no models are configured (prevents null reference crashes)
- Add has_any_provider_models() for UI to check provider availability
- Make ProviderConfig::None return a user-friendly error instead of
calling Warp's cloud API (the previous fallback behavior)
Safety: if no providers are enabled, the system gracefully returns an
error message rather than crashing or silently calling Warp's servers.
When LiteLLM routes OpenAI-format requests to AWS Bedrock, the provider
rejects conversations ending with an assistant message with:
'This model does not support assistant message prefill.'
Add ensure_ends_with_user_message() as the final sanitization step in
sanitize_messages_for_openai(). If the conversation ends with an assistant
message, a minimal 'Continue.' user message is appended.
Updated tests to reflect the new behavior and added dedicated tests for
the new function.
Rewrote the skill from a single-feature porting tool into a full upstream
merge workflow that:
- Fetches and merges latest warp/master
- Resolves conflicts preserving Galaxy's AI providers (Bedrock/OpenAI-LiteLLM)
- Strips any Warp API/auth/telemetry additions
- Iteratively repairs the build until cargo build succeeds
- Runs clippy/format/leak checks before committing
- Update version from 1.6.3 to 2.0.0 in app/Cargo.toml and Cargo.lock
- Add install-galaxy.sh upload step to build-and-deploy-hermes script
- Include pending AI provider and agent changes
- Construct ServerTask directly for Bedrock CLI subagents so messages route
correctly without needing a server CreateTask upgrade
- Handle CliAgentUserQuery input type in both request translators, including
running command context and terminal output
- Add force_cancel_all_streaming_exchanges fallback for when Ctrl+C finds no
in-flight streams (stuck subagent / unexpected stream end)
- Cancel active conversation on Ctrl+C in agent view compose state
- Skip agent view entry when agent is tagged-in for a running command
- Set root_task_id on Bedrock requests for proper optimistic task upgrade
- Persist app state on will_terminate to avoid losing sessions
- Trust persisted CWD without is_dir() recheck (fixes network mount restore)
- Log warning instead of silently dropping tabs with unreadable root nodes
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Remove duplicate popup rendering from render_vertical_tabs_panel.
The popup was rendered both inside the panel's stack AND at the
workspace level in a Dismiss overlay, causing event dispatch conflicts
due to shared MouseStateHandle instances between the two identical
popup trees.
- Fix start_agent tool mapping: route to Tool::StartAgent instead of
dead-end Tool::Subagent so tool calls become executable actions
- Block start_agent until child finishes: parent waits for child
conversation to complete and receives full output as tool result
- Fix tool result delivery: add StartAgent/StartAgentV2 cases to
extract_tool_result_content so the model actually sees agent output
- Support parallel agent spawning: change StartAgent action phase from
Serial to Parallel, and track multiple pending agents via Vec
- Mark child conversations as Success on EndTurn: emit
ConversationStatus::Success when a child stream ends with no actions
- Skip orchestration SSE in local mode: prevent app freeze from trying
to connect to non-existent server
- Remove send_message_to_agent and suggest_next_prompt from tool list:
these require server infrastructure that doesn't exist in OSS mode
- Add "Waiting for sub-agents..." status message while agents process
- Fix child agent pane close: actually dismiss instead of re-hiding,
track dismissed IDs to prevent re-creation on restart
- Fix cache_miss_tokens calculation and show per-block cache stats
- Add [tool-debug] logging throughout tool invocation pipeline
Bump version to 1.6.0.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two changes addressing agent context visibility and error recovery:
1. Enable DOGFOOD_FLAGS in oss.rs — this activates AgentViewBlockContext,
which auto-attaches user-executed command output (stdout/stderr/exit code)
to the AI conversation context. Previously the LLM was blind to any
commands the user ran via `!` prefix in agent view.
2. Add instant "Fix this error" prompt suggestion when a user-run command
fails (non-zero exit) in agent view. This lets users hand off errors to
the agent with one click instead of manually copy-pasting output.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Move token/cache/cost metrics from the expandable per-block usage button
into a persistent status bar rendered in the agent input area. This gives
always-visible feedback without requiring user interaction.
- Add render_session_status_bar to agent input showing context %, cache
hit rate, and cost
- Persist cache/cost totals in ConversationUsageMetadata for session restore
- Remove render_usage_button, ToggleIsUsageFooterExpanded action, and
UsageFooterToggled event
- Remove "Request tokens: --" debug block footer overlay
- Fix has_footer() to return false so blocks no longer reserve phantom
footer space (root cause of padding/margin issue)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Module is scaffolded but not yet wired into callers — allow dead code
at the module level until integration is complete.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Resolves merge conflicts integrating compact_summary parameter into
build_converse_request alongside the existing CachingConfig approach.
Adds the new prompt_builder module for structured prompt construction.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The apply_file_diffs tool now includes a required "summary" field so the
model provides a brief description of edits. This surfaces as the title
on the diff panel instead of showing only +/- line counts.
Also propagates is_error from tool result content back to the model so it
can distinguish failed tool calls from successful ones.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New features:
- Inline subagent panels with expand/collapse and click-to-toggle
- /context slash command to inspect bedrock_message_history
- Child-to-parent question routing with auto-answer for subagents
- Subagent token usage and cost merging into parent conversation
- Randomized session-colored user avatar silhouettes
Bug fixes:
- Bedrock: remove orphaned tool_results after compaction
- Bedrock: self-healing exchange lookup for out-of-order streaming
- Bedrock: append continuation prompt when conversation ends with assistant
- Duration sanity check rejects epoch-time artifacts from session restore
- Cache hit rate calculation uses actual total_input_tokens
- Hide "Time to first token" when value is zero
Improvements:
- Demote verbose bedrock-debug logs to debug/trace levels
- Bedrock tool usage counting falls back to action counting
- Remove logout menu item from workspace menu
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Major features:
- Auto-compact: triggers conversation summarization when context window >= 85%,
compacts Bedrock message history to a summary pair, and tracks live context tokens
- Bedrock summarization: plumbs `is_summarization` flag through translator/client/response
pipeline, handles SummarizeConversation input type, and marks `summarized` in metadata
- Session restore: rebuilds bedrock_message_history from persisted task messages via
newly-public `convert_proto_message`, preventing empty history on reconnect
- Subagent orchestration: adds SubagentQuestion/Answer/CompletionSummary event types,
parent-child question routing with depth limits, retry counting, and drain methods
- Summarization UI: inline SummarizationView in AI blocks with progress/finished states
Refactors:
- Rename WarpTheme → GalaxyTheme across ~100 files (rebrand continuation)
- Rename warp_home_config_dir → galaxy_home_config_dir and related path functions
- Predefined rules: replace "System Defined Rule #N" with descriptive names
(e.g. "Correctness Over Speed", "Never Guess") and add lookup helpers
- Usage view: replace cumulative input/output token display with live context tokens,
cache hit rate calculation, and separate cache read/write stats
- Telemetry: remove verbose doc comments, simplify trait definitions
- Facts view: simplify delete permission check (always allow local deletion)
- Remove warp_managed_paths_watcher.rs (dead code)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Major changes:
- **Bedrock translator architecture**: Extract orchestration logic from `impl.rs` into
a dedicated `translator.rs` module. Rename `convert_request.rs` → `request_translator.rs`
and `stream.rs` → `response_translator.rs` for clarity. Remove `tool_docs.rs` (inlined).
Remove `fallback_to_warp` setting and server fallback path — Bedrock is now the sole backend.
- **Unknown tool handling**: The response translator now detects hallucinated/unknown tool
calls from the model and synthesizes error tool_results so the conversation doesn't
deadlock waiting for a result that will never come.
- **Usage display overhaul**: Replace credit-based usage display with detailed token metrics
showing context window %, cache hit rate (read/write/miss), and estimated cost in dollars.
Add `total_input_tokens`, `total_cache_read_tokens`, `total_cache_write_tokens`, and
`cache_miss_tokens` accessors to `AIConversation`.
- **Predefined rules system**: Add `predefined_rules.rs` with 11 system-defined behavioral
rules that are auto-seeded on first launch. Add "Add Predefined Rules" button to the
Rules UI for re-adding them later. Track seeding state via `has_seeded_predefined_rules`
setting.
- **Session restore improvements**: Rename database file from `warp.sqlite` to
`galaxy.sqlite` with automatic migration from both same-directory and state_dir legacy
paths. Improve CWD persistence by falling back to `session_startup_path` for agent-mode
and fresh tabs. Add extensive session-save/restore logging.
- **Shell bootstrap rebrand**: Rename `WARP_INITIAL_WORKING_DIR` environment variable to
`GALAXY_INITIAL_WORKING_DIR` across bash, zsh, and fish bootstrap scripts.
- **Model defaults**: Change default Bedrock model from Opus 4.7 to Opus 4.6.
Add `context_window_for_model()` helper with model-aware context sizes.
Remove `is_bedrock_model()` (no longer needed without server fallback).
- **User query persistence**: The response translator now emits a `UserQuery` proto message
at stream start so the user's prompt persists across sessions for conversation titles.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Show "File changes" label on collapsed code diff views when no title
- Reinforce shell command availability in agent system prompt
- Persist working directory for agent/viewer panes on session save
- Remove unused make_nsstring import
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Previously, Bedrock error snapshots were unconditionally written to disk
on any API or stream failure. Now they are only written when
GALAXY_BEDROCK_DIAGNOSTICS=1 is set, consistent with the rest of the
diagnostic logging.
Bumps version to 1.2.1.
- Rename WarpDockTilePlugin to GalaxyDockTilePlugin
- Fix runtime icon switching to load from compiled-in assets
- Add NSDockTilePlugIn key to embedded Info.plist
- Replace all channel icons with padded Galaxy variants
- Update build.rs references for renamed plugin
- No longer requires post-bundle steps for icon switching
- Bump version to 1.2.0
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Rename all UI-facing "Warp" references to "Galaxy"
- Rename "Warpify" to "Wormhole" throughout the UI
- Replace app icons with 5 new Galaxy-branded variants
- Update About page to show selected app icon dynamically
- Rephrase Privacy page for Bedrock context
- Remove "Fallback to Warp server" toggle from Bedrock settings
- Widen model selector dropdowns in profile editor (480px)
- Update TERM_PROGRAM to "GalaxyTerminal"
- Bump version to 1.1.0
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- F2 keybinding triggers prepareRename at cursor
- Shows inline text input pre-filled with current symbol name
- Enter confirms and applies workspace edits across all occurrences
- Escape cancels the rename
- Full flow: prepareRename → input → rename → apply edits
- AGENTS.md: document inline token/cache/cost stats feature idea
- AGENTS.md: document rename implementation for reference
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- SignatureHelpState: None → Loading → Showing
- Triggers on '(' and ',' characters, dismisses on ')'
- Renders tooltip above cursor with active parameter highlighted
- Active parameter shown in warning color (bold yellow/orange)
- Includes documentation display when available from LSP
- Dismissed on Escape along with other LSP overlays
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- CodeActionsState machine: Idle → Requesting → Available (with menu)
- 200ms debounced fetch on cursor/selection change
- Cmd+. opens the code actions menu
- Menu renders as positioned overlay with action titles and kind labels
- apply_workspace_edit helper applies LSP WorkspaceEdits to the editor
- Wired into SelectionEnd event for automatic background fetching
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Tab/Enter confirms the selected completion item
- Up/Down arrows navigate the completion menu
- Escape dismisses the menu (via existing dismiss_lsp_overlays)
- Editor intercepts keys via completion_intercept_keys flag when menu is showing
- Add AGENTS.md with LLM-powered predictive autocomplete idea
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Bedrock was calling suggest_next_prompt tool which created a SuggestPrompt
action that waited forever on a oneshot channel for UI interaction that
never fires in the Bedrock path, keeping the conversation permanently
InProgress. Fixed by filtering the tool from the Bedrock tool list and
skipping it at the stream level when the LLM calls it from context history.
Also includes: Bedrock cache token tracking, cost estimation, LSP
improvements, conversation usage view updates, and external config support.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When 'Show Memory Stats' debug mode is enabled, the block footer
now displays 'Request tokens: N' (or 'Request tokens: --') instead
of the old grid/flat storage size breakdown.
- Add last_block_token_usage_by_model to AIConversation, tracking
token usage accumulated since the most recent user-initiated request
- Add last_block_total_tokens() accessor summing across all models
- BlockListElement reads this value per block and renders it in the
debug footer text element
- Remove warp-channel-config dependency; all bin targets hardcode ChannelConfig inline
- Rename bin targets: galaxy-oss, galaxy-local, galaxy-stable, galaxy-dev, galaxy-preview
- Rename config dir from .galaxy-ai to .galaxy
- Add Galaxy app icon (512x512 rounded PNG + SVG logo)
- Replace settings gear icon with Stars (sparkle) icon
- Remove lightbulb/resource center button from header toolbar
- Add Galaxy logo SVG to Settings > About page
- Rename Galaxify -> Galaxyize across all UI strings
- Remove Create Team / Join Team sections from Galaxy Drive
- Fix missing => in OpenRichInput match arms
- Clean up unused imports and warnings
- Update Cargo.toml bundle metadata with Samsung branding
- Re-enable code review, project explorer, global search in settings
- bedrock_enabled default: false -> true (was never routing to Bedrock)
- Remove is_bedrock_model check from bedrock_config_if_applicable (model_id
could be 'auto' from server-populated prefs, causing Bedrock to be skipped)
- Default to claude-sonnet-4 when model_id is empty or 'auto'
- fallback_to_warp default: true -> false (no server exists)
- Smoke test: exit immediately on no-text with diagnostic info instead of
polling forever
- Rewrite extract_system_prompt to dynamically include CWD, OS, shell, git,
project rules, and tool usage guidance from request context
- Fix extract_tool_result_content and format_tool_call_result to properly
handle Grep, FileGlobV2, and ApplyFileDiffs results (were returning empty
'Tool completed successfully' strings - model never saw file lists)
- Rename all 'Galaxy AI' references to just 'Galaxy' (menu, window title,
bundle names, plist, welcome text, about)
- Update smoke test with file visibility test prompt
- Suppress dead_code warnings on unused smoke test functions
Ryan Ward