Commit Graph
24 Commits
Author SHA1 Message Date
rkw6086 5737f8342c Preserve completed command assessments 2026-08-13 16:41:19 -05:00
rkw6086 b3f3a72435 Fix provider tool history handling 2026-08-12 14:19:51 -05:00
rkw6086 88ad290c7e e2e testing 2026-08-10 07:22:56 -05:00
rkw6086 603437a24e Keep long-running monitors polling after prose turns 2026-08-06 23:50:51 -05:00
rkw6086 b0ad07f6f2 Add unified models UI and Rig Bedrock runtime 2026-08-04 17:25:19 -05:00
rkw6086 91d8bd0381 Migrate Rig tool flow to domain runtime 2026-08-04 14:14:51 -05:00
rkw6086 dbfa8bcd48 Complete agent monitoring and Galaxy Control integration
- expose command-monitor conversations and preserve visible agent transcripts
- add bounded polling and a dedicated shell interrupt tool
- improve direct-provider images, skills, tool history, and usage handling
- package and brand Galaxy Control across releases, installers, persistence, and docs
2026-07-29 15:04:58 -05:00
rkw6086 a078287f4b Fix Local Agent Execution And Auth Checks
- Gate server requests on available credentials
- Run local child agents directly without a parent run ID
- Include command IDs in Bedrock context and recognize transfer tools
2026-07-28 10:43:59 -05:00
Ryan Ward 856a6cd6f3 Remove Warp cloud features and OpenTelemetry
Settings cleanup:
- Remove billing_and_usage, main_page, referrals_page, show_blocks_view,
  environments_page, handoff_environment_creation_modal,
  custom_inference_modal, remove_custom_endpoint_confirmation_dialog,
  transfer_ownership_confirmation_modal, delete_environment_confirmation_dialog
- Remove SettingsSection variants: Account, BillingAndUsage, Referrals,
  SharedBlocks, CloudEnvironments, OzCloudAPIKeys
- Remove SettingsPageViewHandle variants: Main, BillingAndUsage, Referrals,
  CloudEnvironments, OzCloudAPIKeys, SharedBlocks
- Add Platform variant for PlatformPageView
- Gut custom inference endpoint UI from ai_page.rs
- Gut transfer ownership modal from teams_page.rs
- Stub environment_management_pane as dead code
- Remove create_discount_badge usage
- Remove handle_experiment_change call

OpenTelemetry removal:
- Remove opentelemetry, opentelemetry-http, opentelemetry-otlp,
  opentelemetry_sdk, tracing-opentelemetry dependencies
- Replace tracing module with no-op stub
- Delete native.rs and cloud_agent_auth.rs

Bug fixes (prior work):
- Fix apply_diffs() to use markdown_unescaped(ctx)
- Fix notebook executor AIDocumentId handling
- Fix margin/corner-radius consistency in requested_command.rs
- Add document tool handlers to extract_tool_result_content()
- Fix deprecated from_byte_stream in MCP SSE transport
- Fix Cargo.toml profile package spec
- Upgrade rust-toolchain to 1.94.1
2026-07-23 11:14:49 -05:00
Ryan Ward 0db915712f fix: handle InvokeSkill in request_translator to prevent empty message error
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
2026-07-16 12:59:51 -05:00
Ryan Ward 3d2d90fd4e feat: inject global rules into AI system prompt and fix Rules UI seeding
- 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.
2026-07-16 12:25:56 -05:00
Ryan Ward 40bd86f662 Adding logging when we crash in bedrock, adding open AI request translator changes and AI page settings cleanup 2026-07-08 15:19:51 -05:00
rkw6086 3769646ca6 Fix cursor focus and selection in input box, add AWS env var warning box, and remove AWS Bedrock login banner 2026-07-02 14:54:15 -05:00
Ryan Ward 4770ac06b5 first pass of merging in warp (doesn't build) 2026-07-01 16:08:58 -05:00
Ryan Ward 2f64909469 Update AI agent, settings, and terminal modules
- Update AI agent conversation, task, and prompt builder
- Add notebooks execution module for blocklist actions
- Update Bedrock and OpenAI response translators
- Refactor settings modules across multiple subsystems
- Update terminal settings and window settings
- Update drive settings and search command settings
2026-07-01 14:30:04 -05:00
Ryan WardandClaude Opus 4.6 57c843d1de Fix CLI subagent task routing, Ctrl+C cancellation, and session restore reliability
- 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>
2026-06-25 08:43:10 -05:00
Ryan Ward 5ea378a38d Add OpenAI/LiteLLM provider support with settings UI
- Add openai/ provider module with translator, client, convert, request/response translators
- Add shared provider/ types (ConversationMessage, MessageRole, ProviderConfig enum)
- Wire OpenAI-compatible provider dispatch alongside Bedrock in response_stream.rs
- Add ai.openai.* settings (enabled, base_url, api_key, model, models)
- Add OpenAI/LiteLLM settings page with model fetch, picker, and config UI
- Extend model menu items and llms.rs to surface LiteLLM models
- Update WARP.md with OpenAI provider architecture docs
2026-06-17 14:14:40 -05:00
Ryan WardandClaude Opus 4.6 59cfd0e2f5 Bump version to 1.6.3
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-06-12 14:17:06 -05:00
Ryan WardandClaude Opus 4.6 840bc4d244 Bump version to 1.6.1
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-06-04 09:57:18 -05:00
Ryan WardandClaude Opus 4.6 a309006458 Implement local sub-agent execution for OSS/Bedrock mode
- 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>
2026-06-03 13:29:09 -05:00
Ryan WardandClaude Opus 4.6 8e2fce08aa Add summary/title to apply_file_diffs tool and propagate is_error on tool results
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>
2026-05-27 11:29:50 -05:00
Ryan WardandClaude Opus 4.6 f278e53b7e v1.5.0: Inline subagent panels, Bedrock compaction fixes, context window debug view
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>
2026-05-21 14:30:04 -05:00
Ryan WardandClaude Opus 4.6 6f54e2cb30 v1.4.0: Auto-compact streaming, Bedrock summarization support, subagent orchestration, and Galaxy rebrand continuation
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>
2026-05-21 11:59:37 -05:00
Ryan WardandClaude Opus 4.6 eaa2ddc75e v1.3.0: Bedrock translator refactor, usage metrics, session restore fixes, and predefined rules
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>
2026-05-20 15:15:28 -05:00