summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2025-08-20chore: bump version to v0.2.0; docs: split config/usage and update in-editor ↵v0.2.0Paul Buetow
chat
2025-08-20chore: bump version to v0.1.1v0.1.1Paul Buetow
2025-08-20lsp: add tiny LRU cache for last 10 completions; ignore trailing whitespace ↵Paul Buetow
in cache key; log cache hits; report busy with isIncomplete to prompt client retry
2025-08-19config: apply HEXAI_* env even without config file; docs: clarify Copilot ↵Paul Buetow
key; prefer HEXAI_COPILOT_API_KEY in builders
2025-08-19config: add HEXAI_* env overrides with precedence; prefer ↵Paul Buetow
HEXAI_OPENAI_API_KEY over OPENAI_API_KEY; update docs
2025-08-19lsp/codeactions: make actions lazy and resolve on selection\n\n- Advertise ↵Paul Buetow
CodeAction resolveProvider and implement codeAction/resolve\n- Return lightweight actions with data; no LLM call during listing\n- On resolve, perform LLM and populate WorkspaceEdit\n- Update tests to cover lazy+resolve flow
2025-08-19logging: highlight LLM no-op skips in yellow\n\n- Add AnsiYellow to logging ↵Paul Buetow
utilities\n- Colorize skip logs (no-trigger, short-prefix, busy) in hexai-lsp logs
2025-08-19lsp: include space in trigger characters and allow space-triggered ↵Paul Buetow
completions\n\n- Defaults now include space (" ") in trigger list\n- Prefix heuristic treats space as structural trigger (no min-prefix required)\n- README and config example updated\n- Tests: add coverage for space trigger
2025-08-19lsp: replace time throttle with in-flight guard; improve short-prefix ↵Paul Buetow
heuristic\n\n- Prevent overlapping LLM requests via llmBusy guard\n- Remove time-based throttle and option plumbing\n- Short-prefix heuristic now skips over trailing whitespace and clamps index\n- Add tests for busy guard and trailing-space allowance
2025-08-19lsp: reduce eager completions and add throttling\n\n- Defaults: remove ';' ↵Paul Buetow
and '?' from trigger characters\n- Add min-typed-prefix heuristic for LLM completions (>=2 chars)\n- Add simple time-based throttle between LLM completions (default 900ms)\n- Tests: verify default triggers and skip logic (throttle + min prefix)\n- Config example: update trigger_characters list
2025-08-19lsp: strip inline spans for completions\n\n- Add stripInlineCodeSpan helper ↵Paul Buetow
to extract first inline backtick span\n- Apply only in completion path after fence stripping\n- Add comprehensive unit tests for inline span handling
2025-08-19chore: commit pending changes in status, LSP, and Ollama modulesPaul Buetow
2025-08-19llm/copilot: add required headers and update default model\n\n- Send ↵Paul Buetow
X-GitHub-Api-Version and User-Agent headers for Copilot requests\n- Default Copilot model to gpt-4o-mini (avoid non-existent 'codex'/'gpt-4.1')\n- README and config.json.example: update Copilot defaults and guidance\n\nNote: Copilot provider expects Copilot-issued auth; for public access use GitHub Models via OpenAI-compatible endpoint.
2025-08-18lsp: strip Markdown code fences from LLM outputs (completions and code actions)Paul Buetow
2025-08-18hexaicli: load config with logger to respect provider\n\nFix CLI requiring ↵Paul Buetow
OPENAI_API_KEY when provider is ollama by actually loading user config.\n\nREADME: update Helix example to use hexai-lsp binary.
2025-08-18lsp: add comprehensive unit tests for findFirstInstructionInLine and strict ↵Paul Buetow
semicolon tag
2025-08-18rename to projectstatusPaul Buetow
2025-08-18refactor(lsp,llm,hexailsp,appconfig): split long funcs; add testsPaul Buetow
- Extract helpers to keep funcs <=50 lines; no behavior changes - Add tests for prompt removal, code actions, and LLM request builders - Table-drive TestInParamList; run gofmt
2025-08-18feat(lsp): add coding_temperature knob and remove hardcoded temps\n\n- Add ↵Paul Buetow
to app config and server options.\n- Use in LSP code actions and completions.\n- Default to provider temperature when not set.\n- Update README and config.json.example.
2025-08-18feat(config): per-provider temperature defaults and docs\n\n- Add , , to ↵Paul Buetow
config with coding-friendly default 0.2.\n- Wire defaults through providers (OpenAI, Copilot, Ollama).\n- Update CLI and LSP runners to pass configured temperatures.\n- Document temperature behavior and examples in README.\n- Update config.json.example to show new keys.
2025-08-17refactor(ordering): place constructors immediately after type definitions as ↵Paul Buetow
first functions
2025-08-17refactor(ordering): types/constants first; exported before private; ensure ↵Paul Buetow
consistent receiver semantics per file
2025-08-17logging: move ChatLogger to value semantics; llm: switch clients to value ↵Paul Buetow
receivers and return values from constructors
2025-08-17refactor as per manual code reviewsPaul Buetow
2025-08-17refactor: Split up Load function in config.goPaul Buetow
The Load function was too long, so it has been split up into smaller functions to improve readability and maintainability.
2025-08-17refactor: Remove unused NoDiskIO flagPaul Buetow
This flag was not used anywhere in the codebase, so it has been removed.
2025-08-17review changesPaul Buetow
2025-08-17feat: Support XDG config homePaul Buetow
This change implements support for the XDG Base Directory Specification for the configuration file. The configuration file is now read from `$XDG_CONFIG_HOME/hexai/config.json` if the `XDG_CONFIG_HOME` environment variable is set. If it is not set, it falls back to the previous location, `$HOME/.config/hexai/config.json`. This change also includes: - A fix for a bug in the test suite where a test was failing due to an environment variable being set. - Updates to the documentation to reflect the new configuration file location. - A version bump to 0.1.0.
2025-08-17cli+lsp: refactor main packages into internal runners; add testsPaul Buetow
- Move CLI logic to internal/hexaicli with Run/RunWithClient - Move LSP logic to internal/hexailsp with Run/RunWithFactory - Extract helpers; keep behavior identical for both binaries - Add unit tests for hexaicli (input parsing, messages, streaming) and hexailsp (factory wiring, client creation, logging settings) - Add top-of-file summaries and 'Not yet reviewed by a human' comments to all Go files - Update README with internal package docs
2025-08-17chore(release): bump version to 0.1.0v0.1.0Paul Buetow
2025-08-17cli: stream responses in hexai when supported (OpenAI, Ollama)Paul Buetow
- Add llm.Streamer optional interface - Implement ChatStream for OpenAI (SSE) and Ollama (JSON stream) - CLI uses streaming; LSP unchanged (non-streaming) - README: document streaming behavior for CLI
2025-08-17update readmePaul Buetow
2025-08-17docs(cli): document hexai CLI usage and behaviorsPaul Buetow
- Inputs from stdin/arg, concatenation rules - Stderr styling, immediate provider/model, final stats line - Default concise style; 'explain' keyword for verbose answers - Examples and exit codes
2025-08-17cli: add leading newline before stats on stderr for hexai outputPaul Buetow
2025-08-17cli: add hexai command-line tool and split LSP to hexai-lspPaul Buetow
- New cmd/hexai CLI: reads stdin/arg, prints LLM output to stdout - Prints provider/model immediately to stderr; summary at end - Refactor config loader to internal/appconfig - Update Taskfile to build/install/run both binaries - Update README with new CLI and LSP names
2025-08-17rename CLI binary to hexai-lspPaul Buetow
- Default log path: /tmp/hexai-lsp.log - Taskfile: build/copy/run hexai-lsp binary
2025-08-17llm: add GitHub Copilot providerPaul Buetow
- Implement copilot client reading COPILOT_API_KEY - Wire copilot_base_url and copilot_model config - Update README and config example; defaults to gpt-4.1 - Keep OpenAI default at gpt-4.1 for consistency
2025-08-17docs: remove CHANGELOG.mdPaul Buetow
2025-08-17docs: add CHANGELOG entry for 0.0.3Paul Buetow
2025-08-17chore: bump version to 0.0.3v0.0.3Paul Buetow
2025-08-17lsp/config: include ';' and '?' in default trigger charactersPaul Buetow
- Default trigger set when unset now [., :, /, _, ;, ?] - Update README and example config accordingly
2025-08-17lsp/config: make completion trigger characters configurablePaul Buetow
- Add trigger_characters to JSON config and ServerOptions - Store on server and advertise in initialize - Update README and example config - Preserve previous defaults when unset
2025-08-16lsp: refactor NewServer to use options structPaul Buetow
- Introduce ServerOptions to reduce constructor parameter count - Update main.go call site; preserve defaults and behavior - Build and run tests
2025-08-16lsp: add 'Resolve diagnostics' code action scoped to selectionPaul Buetow
- Parse diagnostics from CodeAction context; filter to overlap with selection - Build LLM prompt from selection-only diagnostics; replace only selected range - Keep existing 'Rewrite selection' action; return both when applicable - Add Diagnostic and CodeActionContext types; make CodeActionParams.Context raw JSON - Add helpers for range overlap; unit tests for filtering/overlap - Update README to document resolve-diagnostics action
2025-08-16fix(lsp): avoid duplicate assignment prefix in completionsPaul Buetow
- Prompt: instruct model to only continue from cursor; do not repeat LHS already typed.\n- Add stripDuplicateAssignmentPrefix to drop duplicated 'name :=' or 'name =' when model repeats it.\n- Tests: cover := and = cases.\n- .gitignore: ignore built binary and go caches.
2025-08-16feat(lsp): code action to rewrite selection with instruction detectionPaul Buetow
- Adds textDocument/codeAction handler that rewrites the selected range.\n- Instruction preference: strict ;text; marker first, then //, #, -- line comments, then single-line block comments (/* */ and <!-- -->). Earliest in the selection wins.\n- Removes the matched instruction from the selection before sending to LLM.\n- README: document code action workflow and instruction formats.
2025-08-16refactor(config): drop env-based config (except OPENAI_API_KEY)Paul Buetow
- Switch to config-file-only; only OPENAI_API_KEY read from env.\n- llm: replace env autodetect with Config + NewFromConfig; add newOpenAI/newOllama.\n- lsp: NewServer now accepts injected llm.Client.\n- cli: remove env overrides; extend appConfig with provider-specific fields; build client from config + OPENAI_API_KEY.\n- docs: update README (config-only, defaults to OpenAI, minimal example); simplify flags table.\n- add config.json.example.\n- prompts: enforce ;text; (no spaces) and add ;;text; to remove entire line; tests added.
2025-08-16feat(logging): add LLM stats (averages and per-minute)v0.0.2Paul Buetow
2025-08-16feat(logging): add LLM stats averages and per-minute metricsPaul Buetow
2025-08-16feat(cli): simplify flags to -log and -version; add JSON config with env ↵Paul Buetow
precedence; update README
generated by cgit v1.2.3 (git 2.25.1) at 2026-06-10 05:52:11 +0000