sigit-code 1.6.5__tar.gz → 1.6.7__tar.gz

{sigit_code-1.6.5 → sigit_code-1.6.7}/.agents/AGENTS.md

@@ -159,6 +159,12 @@ feeds results back. Neither the loop nor ACP/TUI surfaces depend on a concrete b
   never touched, and an opening tag only counts at the start of a line, since prose writes
   placeholders like `<repo_url>` the same way. It has to run after the inline-call scanner,
   because `<tool_call>` matches its underscore rule.
+  `src/repetition.rs` guards the same stream against a reply that degenerates into a loop over a
+  tiny vocabulary (issue #123): a window of 200 words with at most 40 distinct ones, fenced code
+  excepted, makes `consume_stream` stop reading, truncate the text to where the loop began (so
+  history never holds the junk), tell the user, and finish with `FinishReason::Repetition`
+  (`EndTurn` in ACP). `complete` then retries once with `REPETITION_RETRY`, like the malformed
+  tool call retry. Only the streaming path is guarded; `consume_json` and `LocalBackend` are not.
   Image attachments: ACP fixes `promptCapabilities.image` for the whole connection, while the
   model can change on any turn, so the capability is always advertised and the decision is made
   per prompt. `InferenceBackend::accepts_images` answers for the active model (on-device: no;
@@ -304,7 +310,11 @@ feeds results back. Neither the loop nor ACP/TUI surfaces depend on a concrete b
   conversation); lifecycle and config handlers hold it throughout, and `handle_prompt` holds it
   through a `WorkspaceHold` that it releases while waiting on an HTTP endpoint or a permission
   answer and retakes (reinstalling its session via `resume_workspace`) before any tool runs. An
-  on-device turn never releases it. Take the session lock first, never the other way round. Tool
+  on-device turn never releases it. Take the session lock first, never the other way round. A turn registers its `PromptCancellation` at
+  the top of `handle_prompt`, before it waits on either lock, and a `PromptRegistration`
+  guard clears it on every return, so a `session/cancel` that arrives while the turn
+  is still queued, switching threads, loading a model or running a slash command ends
+  it as `cancelled`. The checks sit after each of those waits. Tool
   execution, subagents included, still runs one session at a time.
 - **`src/instructions.rs`** — project instruction files, the always-on counterpart to skills.
   Reads `AGENTS.md` (the cross-tool [agents.md](https://agents.md) standard) and `CLAUDE.md`,

{sigit_code-1.6.5 → sigit_code-1.6.7}/AGENTS.md

@@ -159,6 +159,12 @@ feeds results back. Neither the loop nor ACP/TUI surfaces depend on a concrete b
   never touched, and an opening tag only counts at the start of a line, since prose writes
   placeholders like `<repo_url>` the same way. It has to run after the inline-call scanner,
   because `<tool_call>` matches its underscore rule.
+  `src/repetition.rs` guards the same stream against a reply that degenerates into a loop over a
+  tiny vocabulary (issue #123): a window of 200 words with at most 40 distinct ones, fenced code
+  excepted, makes `consume_stream` stop reading, truncate the text to where the loop began (so
+  history never holds the junk), tell the user, and finish with `FinishReason::Repetition`
+  (`EndTurn` in ACP). `complete` then retries once with `REPETITION_RETRY`, like the malformed
+  tool call retry. Only the streaming path is guarded; `consume_json` and `LocalBackend` are not.
   Image attachments: ACP fixes `promptCapabilities.image` for the whole connection, while the
   model can change on any turn, so the capability is always advertised and the decision is made
   per prompt. `InferenceBackend::accepts_images` answers for the active model (on-device: no;
@@ -304,7 +310,11 @@ feeds results back. Neither the loop nor ACP/TUI surfaces depend on a concrete b
   conversation); lifecycle and config handlers hold it throughout, and `handle_prompt` holds it
   through a `WorkspaceHold` that it releases while waiting on an HTTP endpoint or a permission
   answer and retakes (reinstalling its session via `resume_workspace`) before any tool runs. An
-  on-device turn never releases it. Take the session lock first, never the other way round. Tool
+  on-device turn never releases it. Take the session lock first, never the other way round. A turn registers its `PromptCancellation` at
+  the top of `handle_prompt`, before it waits on either lock, and a `PromptRegistration`
+  guard clears it on every return, so a `session/cancel` that arrives while the turn
+  is still queued, switching threads, loading a model or running a slash command ends
+  it as `cancelled`. The checks sit after each of those waits. Tool
   execution, subagents included, still runs one session at a time.
 - **`src/instructions.rs`** — project instruction files, the always-on counterpart to skills.
   Reads `AGENTS.md` (the cross-tool [agents.md](https://agents.md) standard) and `CLAUDE.md`,

{sigit_code-1.6.5 → sigit_code-1.6.7}/CHANGELOG.md

@@ -1,5 +1,54 @@
 # Changelog
 
+## 1.6.7
+
+### Fixed
+
+- **A cancel that arrives before the turn starts is no longer lost.** A prompt
+  now registers for `session/cancel` as soon as it begins, not once it reaches
+  inference. A cancel that lands while the turn is queued on the workspace,
+  switching threads, loading a model, or running a slash command ends it with
+  `cancelled` instead of `end_turn`.
+- **A prompt that is only audio is answered.** A clip with no text or image used
+  to end the turn at once with nothing sent to the model, even though the agent
+  advertises audio.
+
+## 1.6.6
+
+### Added
+
+- **A tool call carries its programmatic tool name.** The `tool_call` an editor
+  gets for a running tool now includes `name` (`read_file`, `run_command`,
+  `mcp__…`) next to the human title, sent on the first report of the call only
+  as the protocol asks. A client can tell a command from a file edit without
+  parsing the title, and a replayed thread from `session/load` carries the same
+  name (#196).
+
+### Changed
+
+- **MCP runs on `rmcp`, the official Rust SDK, through `ed-mcp`.** siGit Code's
+  own JSON-RPC client for stdio and Streamable HTTP servers (about 600 lines)
+  is gone; `ed-mcp` is the layer every Onde agent shares. `mcp.toml`, the
+  baked-in `sigit` and `smbcloud` servers, tool names and `/mcp` are unchanged.
+  An HTTP server that stops answering is now reconnected and the call retried
+  once for any failure but a timeout, not only on a 404.
+
+### Fixed
+
+- **A reply that degenerates into a repetition loop is cut off.** After a tool
+  call, a model could fall into thousands of words from a tiny vocabulary
+  (`find: list: check: get: …`) with no tool call and no end, and the junk went
+  into history for the next turn. siGit Code now watches a streamed reply for a
+  window of 200 words with very few distinct ones (code blocks excepted), stops
+  reading, keeps only the text before the loop, tells you it stopped, and asks
+  the model once to make its call or answer briefly (#123).
+- **A linked selection written as `L10-L20` or `L10` reads just those lines.**
+  siGit Code read the line range of a `resource_link` only as `L10:20` or
+  `L10-20`, so `L10-L20` (the GitHub style) and a single line `L10` sent the
+  whole file instead of the selection. It now reads the same forms Zed's own
+  mention parser does, and a range that starts at line 0 or runs backwards
+  counts as no range.
+
 ## 1.6.5
 
 ### Added
@@ -45,7 +94,6 @@
   text inside them stays. Code blocks are left alone. The system prompt also
   tells the model to write plain Markdown and to list choices as plain text
   (#122).
-
 - **Closing a thread that is waiting at a permission prompt no longer hangs.**
   `session/close` cancels the session's running turn and waits for it to end,
   but a turn stopped at a permission prompt only went on when the client

{sigit_code-1.6.5 → sigit_code-1.6.7}/CLAUDE.md

@@ -159,6 +159,12 @@ feeds results back. Neither the loop nor ACP/TUI surfaces depend on a concrete b
   never touched, and an opening tag only counts at the start of a line, since prose writes
   placeholders like `<repo_url>` the same way. It has to run after the inline-call scanner,
   because `<tool_call>` matches its underscore rule.
+  `src/repetition.rs` guards the same stream against a reply that degenerates into a loop over a
+  tiny vocabulary (issue #123): a window of 200 words with at most 40 distinct ones, fenced code
+  excepted, makes `consume_stream` stop reading, truncate the text to where the loop began (so
+  history never holds the junk), tell the user, and finish with `FinishReason::Repetition`
+  (`EndTurn` in ACP). `complete` then retries once with `REPETITION_RETRY`, like the malformed
+  tool call retry. Only the streaming path is guarded; `consume_json` and `LocalBackend` are not.
   Image attachments: ACP fixes `promptCapabilities.image` for the whole connection, while the
   model can change on any turn, so the capability is always advertised and the decision is made
   per prompt. `InferenceBackend::accepts_images` answers for the active model (on-device: no;
@@ -304,7 +310,11 @@ feeds results back. Neither the loop nor ACP/TUI surfaces depend on a concrete b
   conversation); lifecycle and config handlers hold it throughout, and `handle_prompt` holds it
   through a `WorkspaceHold` that it releases while waiting on an HTTP endpoint or a permission
   answer and retakes (reinstalling its session via `resume_workspace`) before any tool runs. An
-  on-device turn never releases it. Take the session lock first, never the other way round. Tool
+  on-device turn never releases it. Take the session lock first, never the other way round. A turn registers its `PromptCancellation` at
+  the top of `handle_prompt`, before it waits on either lock, and a `PromptRegistration`
+  guard clears it on every return, so a `session/cancel` that arrives while the turn
+  is still queued, switching threads, loading a model or running a slash command ends
+  it as `cancelled`. The checks sit after each of those waits. Tool
   execution, subagents included, still runs one session at a time.
 - **`src/instructions.rs`** — project instruction files, the always-on counterpart to skills.
   Reads `AGENTS.md` (the cross-tool [agents.md](https://agents.md) standard) and `CLAUDE.md`,

{sigit_code-1.6.5 → sigit_code-1.6.7}/Cargo.lock

@@ -185,7 +185,7 @@ version = "1.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "40c48f72fd53cd289104fc64099abca73db4166ad86ea0b4341abe65af83dadc"
 dependencies = [
- "windows-sys 0.60.2",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -196,7 +196,7 @@ checksum = "291e6a250ff86cd4a820112fb8898808a366d8f9f58ce16d1f538353ad55747d"
 dependencies = [
  "anstyle",
  "once_cell_polyfill",
- "windows-sys 0.60.2",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -514,6 +514,12 @@ version = "0.22.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
 
+[[package]]
+name = "base64"
+version = "0.23.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ac07cdecf99051d9a5238b80f35af32cdeba5b336e55d957b318b50137e18da5"
+
 [[package]]
 name = "basic-toml"
 version = "0.1.10"
@@ -1519,7 +1525,7 @@ dependencies = [
  "libc",
  "option-ext",
  "redox_users",
- "windows-sys 0.59.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -1608,6 +1614,22 @@ version = "0.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e1d926b4d407d372f141f93bb444696142c29d32962ccbd3531117cf3aa0bfa9"
 
+[[package]]
+name = "ed-mcp"
+version = "1.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cf0c6ab7e27186954295ce7974b33d65860cd3b5073848e9d0a5b3eed90f68a2"
+dependencies = [
+ "anyhow",
+ "futures",
+ "http",
+ "rmcp",
+ "serde_json",
+ "tokio",
+ "tokio-util",
+ "tracing",
+]
+
 [[package]]
 name = "ego-tree"
 version = "0.10.0"
@@ -1718,7 +1740,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
 dependencies = [
  "libc",
- "windows-sys 0.52.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -3622,7 +3644,7 @@ version = "0.50.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7957b9740744892f114936ab4a57b3f487491bbeafaf8083688b16841a4240e5"
 dependencies = [
- "windows-sys 0.59.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -4573,6 +4595,20 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "process-wrap"
+version = "10.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1f21b97672d2dc848e7b25701ab4535618b92f4861c13cc3f7f7bed52ad3c8da"
+dependencies = [
+ "futures",
+ "indexmap 2.14.1",
+ "nix",
+ "tokio",
+ "tracing",
+ "windows 0.62.2",
+]
+
 [[package]]
 name = "profiling"
 version = "1.0.18"
@@ -4704,7 +4740,7 @@ dependencies = [
  "once_cell",
  "socket2",
  "tracing",
- "windows-sys 0.52.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -5217,6 +5253,31 @@ dependencies = [
  "windows-sys 0.52.0",
 ]
 
+[[package]]
+name = "rmcp"
+version = "3.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ab5023804cbe0304cbe06197ac16e645a0a0d0ffa2953bf735c15c2fa0213350"
+dependencies = [
+ "base64 0.23.1",
+ "bytes",
+ "chrono",
+ "futures",
+ "http",
+ "indexmap 2.14.1",
+ "pin-project-lite",
+ "process-wrap",
+ "reqwest 0.13.4",
+ "serde",
+ "serde_json",
+ "sse-stream",
+ "thiserror 2.0.20",
+ "tokio",
+ "tokio-stream",
+ "tokio-util",
+ "tracing",
+]
+
 [[package]]
 name = "rpassword"
 version = "7.5.4"
@@ -5315,7 +5376,7 @@ dependencies = [
  "errno",
  "libc",
  "linux-raw-sys",
- "windows-sys 0.52.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -5374,7 +5435,7 @@ dependencies = [
  "security-framework",
  "security-framework-sys",
  "webpki-root-certs",
- "windows-sys 0.52.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -5840,13 +5901,14 @@ checksum = "f8fadd59c855ef2080decdef8ff161eb6661b86933c9d82e5ba29dc602a55aba"
 
 [[package]]
 name = "sigit"
-version = "1.6.5"
+version = "1.6.7"
 dependencies = [
  "agent-client-protocol",
  "anyhow",
  "async-trait",
  "base64 0.22.1",
  "crossterm",
+ "ed-mcp",
  "futures",
  "libc",
  "log",
@@ -6028,7 +6090,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c3d1e2c7f27f8d4cb10542a02c49005dbd6e93095799d6f3be745fae9f8fedd4"
 dependencies = [
  "libc",
- "windows-sys 0.60.2",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -6076,6 +6138,19 @@ dependencies = [
  "unicode-segmentation",
 ]
 
+[[package]]
+name = "sse-stream"
+version = "0.2.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c25ac7aff0abd1dbc474536e40416e1102c7dd9bfba0b9861c6d357f835dcfb4"
+dependencies = [
+ "bytes",
+ "futures-util",
+ "http-body",
+ "http-body-util",
+ "pin-project-lite",
+]
+
 [[package]]
 name = "stable_deref_trait"
 version = "1.2.1"
@@ -6507,7 +6582,7 @@ dependencies = [
  "getrandom 0.4.3",
  "once_cell",
  "rustix",
- "windows-sys 0.52.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -6537,7 +6612,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "230a1b821ccbd75b185820a1f1ff7b14d21da1e442e22c0863ea5f08771a8874"
 dependencies = [
  "rustix",
- "windows-sys 0.59.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -6792,6 +6867,17 @@ dependencies = [
  "tokio",
 ]
 
+[[package]]
+name = "tokio-stream"
+version = "0.1.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a3d06f0b082ba57c26b79407372e57cf2a1e28124f78e9479fe80322cf53420b"
+dependencies = [
+ "futures-core",
+ "pin-project-lite",
+ "tokio",
+]
+
 [[package]]
 name = "tokio-tungstenite"
 version = "0.28.0"
@@ -7724,7 +7810,7 @@ version = "0.1.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
 dependencies = [
- "windows-sys 0.52.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -7748,11 +7834,23 @@ version = "0.61.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9babd3a767a4c1aef6900409f85f5d53ce2544ccdfaa86dad48c91782c6d6893"
 dependencies = [
- "windows-collections",
+ "windows-collections 0.2.0",
  "windows-core 0.61.2",
- "windows-future",
+ "windows-future 0.2.1",
  "windows-link 0.1.3",
- "windows-numerics",
+ "windows-numerics 0.2.0",
+]
+
+[[package]]
+name = "windows"
+version = "0.62.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "527fadee13e0c05939a6a05d5bd6eec6cd2e3dbd648b9f8e447c6518133d8580"
+dependencies = [
+ "windows-collections 0.3.2",
+ "windows-core 0.62.2",
+ "windows-future 0.3.2",
+ "windows-numerics 0.3.1",
 ]
 
 [[package]]
@@ -7764,6 +7862,15 @@ dependencies = [
  "windows-core 0.61.2",
 ]
 
+[[package]]
+name = "windows-collections"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "23b2d95af1a8a14a3c7367e1ed4fc9c20e0a26e79551b1454d72583c97cc6610"
+dependencies = [
+ "windows-core 0.62.2",
+]
+
 [[package]]
 name = "windows-core"
 version = "0.61.2"
@@ -7798,7 +7905,18 @@ checksum = "fc6a41e98427b19fe4b73c550f060b59fa592d7d686537eebf9385621bfbad8e"
 dependencies = [
  "windows-core 0.61.2",
  "windows-link 0.1.3",
- "windows-threading",
+ "windows-threading 0.1.0",
+]
+
+[[package]]
+name = "windows-future"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e1d6f90251fe18a279739e78025bd6ddc52a7e22f921070ccdc67dde84c605cb"
+dependencies = [
+ "windows-core 0.62.2",
+ "windows-link 0.2.1",
+ "windows-threading 0.2.1",
 ]
 
 [[package]]
@@ -7845,6 +7963,16 @@ dependencies = [
  "windows-link 0.1.3",
 ]
 
+[[package]]
+name = "windows-numerics"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6e2e40844ac143cdb44aead537bbf727de9b044e107a0f1220392177d15b0f26"
+dependencies = [
+ "windows-core 0.62.2",
+ "windows-link 0.2.1",
+]
+
 [[package]]
 name = "windows-registry"
 version = "0.6.1"
@@ -7985,6 +8113,15 @@ dependencies = [
  "windows-link 0.1.3",
 ]
 
+[[package]]
+name = "windows-threading"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3949bd5b99cafdf1c7ca86b43ca564028dfe27d66958f2470940f73d86d75b37"
+dependencies = [
+ "windows-link 0.2.1",
+]
+
 [[package]]
 name = "windows_aarch64_gnullvm"
 version = "0.48.5"

{sigit_code-1.6.5 → sigit_code-1.6.7}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "sigit"
-version = "1.6.5"
+version = "1.6.7"
 edition = "2024"
 description = "siGit Code — ACP-compatible AI coding agent. Sí, git."
 documentation = "https://github.com/getsigit/sigit"
@@ -25,6 +25,9 @@ path = "src/main.rs"
 # ACP protocol SDK
 agent-client-protocol = { version = "2.2", features = ["unstable_session_fork"] }
 
+# MCP client (rmcp underneath), shared with the other Onde agents
+ed-mcp = "1.2.0"
+
 # Onde Inference engine (local LLM)
 # onde = { path = "../onde" }
 onde = "1.3.1"

{sigit_code-1.6.5 → sigit_code-1.6.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sigit-code
-Version: 1.6.5
+Version: 1.6.7
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers