Commit Graph
12 Commits
Author SHA1 Message Date
can1357 93cc1fed1c merged PR #5417: fix(openai): render native response images
# Conflicts:
#	packages/coding-agent/src/modes/components/chat-transcript-builder.ts
#	packages/coding-agent/test/agent-session-skill-keywords.test.ts
2026-07-16 03:48:21 +02:00
can1357 5ff277349c refactor(coding-agent): consolidated tool surface onto xd:// devices and hub
- Added the `xd://` virtual device protocol (`internal-urls/xd-protocol.ts`, `tools/xdev.ts`): tools declaring `loadMode: "discoverable"` are unmounted from the request tools array and driven via `read xd://` (list/docs+schema) and `write xd://<tool>` (execute), gated by the `tools.xdev` setting (default on) and inlined into the system prompt.
- Merged the `irc`, `job`, and `launch` tools into a single `hub` tool (`tools/hub/`, `async/job-manager.ts`): messaging keeps `send`/`inbox`/`list`, job control maps to `wait`/`cancel`/`jobs`, process supervision keeps `start`/`logs`/`stop`/`restart`/`describe` with `ps`, and the unified `wait` races background jobs against peer messages; SDK `IrcTool`/`JobTool`/`LaunchTool` are replaced by `HubTool`.
- Removed the hidden `resolve` tool in favor of the `xd://resolve`/`xd://reject`/`xd://propose` resolution devices, auto-including `write` whenever a deferrable tool or plan mode is present.
- Removed the BM25 tool-discovery system: the `search_tool_bm25` tool, the `tool-discovery` module, the `tools.discoveryMode`/`mcp.discoveryMode`/`mcp.discoveryDefaultServers`/`tools.essentialOverride` settings, per-tool MCP selection, and the `mcp_tool_selection` message type.
- Unified tool presentation on `ToolLoadMode` (`essential`|`discoverable`), replacing the custom-tool `xdev?: boolean` opt-out; custom, extension, MCP, RPC host, image-generation, and TTS tools now default to `discoverable`, and added a `satisfies` predicate to `SoftToolRequirement`.
- Removed the standalone `ssh` command tool and `ssh/ssh-executor` (the `ssh://` read/write/search protocol stays), and made `--tools` address hidden built-ins.
- Updated collab-web to render `xd://` dispatches and `hub` op families, dropped the `search_tool_bm25`/`ssh`/`report-finding` renderers, refreshed tool docs and prompts, and migrated the affected tests and changelogs.
2026-07-15 15:16:29 +02:00
roboomp b6b947bdbe fix(openai): rendered native response images
- Normalized completed image_generation_call results into assistant image blocks.
- Persisted image bytes through the session blob store and rendered them in live, replay, ACP, proxy, telemetry, and HTML paths.
- Added response normalization, persistence, and TUI rendering regressions.

Fixes #4768
2026-07-14 16:15:53 +00:00
roboomp 949ccaa245 fix(tui): preserved mixed assistant segment order
- Split mixed assistant text into per-tool segments instead of one post-tool tail.
- Insert each segment immediately after its preceding tool component across live and rebuilt transcripts.
- Extended the regression test to cover two tool calls with middle and final assistant text.

Fixes #4871
2026-07-11 06:30:34 +00:00
roboomp 411600aa28 fix(tui): displayed cursor final answers after tools
- Split mixed assistant messages so pre-tool text stays before tool panels while trailing text renders after the tool timeline.
- Applied the split to live streaming, transcript rebuilds, and file-backed transcript rendering.
- Added a focused EventController regression test for text/toolCall/text Cursor-shaped turns.

Fixes #4871
2026-07-11 06:01:53 +00:00
roboomp 177977856a fix(tui): kept token badges for billed empty turns
Replace the visible-anchor suppression with a billed-usage predicate so live and resume paths agree on rendering the badge whenever the turn actually consumed tokens. Only genuinely free turns (no input, output, cache, or premium requests) drop the row, so hidden automated turns keep cost transparency.

Fixes #4532
2026-07-04 16:58:50 +00:00
roboomp c5c95ecd12 fix(tui): suppressed empty assistant token badges
Suppress token-usage rows for assistant turns that have no visible text, tool call, or terminal error anchor. Share the same decision across live rendering and transcript rebuilds so resume matches live output.

Fixes #4532
2026-07-04 16:40:09 +00:00
can1357 71dd8c8e81 refactor(coding-agent/modes): updated abort reason rendering logic
- Refactored abort reason handling to rely on shouldRenderAbortReason instead of isSilentAbort.
- Updated documentation to clarify that both silent and user-interrupt aborts yield no label.
2026-07-04 11:37:54 +02:00
can1357 6e2bba871e feat(agent): implemented automated retry recovery and transcript compaction
- Introduced an automated retry recovery system to track, manage, and persist recovered error states within agent sessions.
- Enabled compact transcript rendering for recovered auto-retry errors by removing heuristic commit machinery.
- Improved raw read tracking and provenance in the ReadTool to support refined file snapshot recording and hashline editing.
- Excluded recovered assistant messages from default model context and updated event controllers to handle retry recovery life cycles.
2026-07-04 11:22:04 +02:00
can1357 e8090bb48a feat: introduced binary file detection to prevent encoding corruption
- Introduced `isProbablyBinary` utility to sniff file headers for NUL bytes or invalid UTF-8 sequences.
- Updated `ReadTool` to use the binary sniffer, preventing mojibake corruption in output when reading non-text files.
- Refined `file-mentions` auto-reads to skip binary files and mark them as `binary` in the message transcript.
- Added comprehensive unit tests for binary detection logic, covering NUL bytes, truncated multibyte characters, and path-based file sniffing.
2026-06-30 02:59:41 +02:00
can1357 c3f7e849e5 refactor: centralized AI error handling into a dedicated module
- Migrated 288 lines of scattered error classification logic from `utils/error-id.ts` into a cohesive `packages/ai/src/error/` module with 13 specialized submodules covering flags, classes, OAuth, providers, rate-limiting, and finalization.
- Replaced 100+ generic `Error` throws across 60+ provider and registry files with semantic `AIError.*` classes (e.g., `AIError.MissingApiKeyError`, `AIError.OAuthError`, `AIError.ProviderResponseError`), improving error diagnostics and retry logic.
- Consolidated error utility imports from `pi-utils` and scattered classification functions into a single `AIError` namespace, reducing coupling and simplifying error handling across all packages.
2026-06-27 10:44:13 +02:00
can1357 93db34b0d5 refactor(coding-agent): consolidated editor state and unify transcript rendering
- Centralized draft state and image management by migrating fields from context to the CustomEditor component.
- Standardized transcript row construction by introducing shared helpers for background jobs, IRC traffic, and file mentions.
- Refactored redundant UI logic and helper functions into reusable utility modules to streamline message submission and component rendering.
- Standardized event handler types by consolidating lifecycle definitions into a shared module while maintaining public API stability.
2026-06-22 06:11:57 +02:00