mastracode 0.4.0-alpha.0 → 0.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -1,5 +1,71 @@
1
1
  # mastracode
2
2
 
3
+ ## 0.4.0
4
+
5
+ ### Minor Changes
6
+
7
+ - Added light theme support and automatic terminal theme detection. Mastra Code now detects your terminal's color scheme and applies a matching dark or light theme. Use the new `/theme` slash command to switch between `auto`, `dark`, and `light` modes. The choice is persisted across sessions. You can also set the `MASTRA_THEME` environment variable to override the detected theme. ([#13487](https://github.com/mastra-ai/mastra/pull/13487))
8
+
9
+ ```sh
10
+ # Switch theme at runtime via slash command
11
+ /theme auto # detect from terminal background
12
+ /theme dark # force dark theme
13
+ /theme light # force light theme
14
+
15
+ # Or override via environment variable
16
+ MASTRA_THEME=light mastracode
17
+ ```
18
+
19
+ - Added reasoning effort support for OpenAI Codex models. The `/think` command now controls the reasoning depth (off, low, medium, high, xhigh) sent to the Codex API via the `reasoningEffort` parameter. Without this, gpt-5.3-codex skips tool calls and narrates instead of acting. ([#13490](https://github.com/mastra-ai/mastra/pull/13490))
20
+
21
+ **Other improvements:**
22
+ - `/think` now shows an inline selector list when run without arguments, or accepts a level directly (e.g. `/think high`)
23
+ - Dropped `minimal` level (was redundantly mapping to same API value as `low`)
24
+ - Added `xhigh` level for GPT-5.2+ and Codex models
25
+ - Provider-specific values (e.g. `none`, `xhigh`) shown next to labels when an OpenAI model is selected
26
+ - Switching to an OpenAI model pack auto-enables reasoning at `low` if it was off
27
+ - Updated default Codex model from gpt-5.2 to gpt-5.3
28
+ - Shows a warning when the current model doesn't support reasoning
29
+
30
+ ### Patch Changes
31
+
32
+ - Added Claude Max OAuth warning for Anthropic authentication ([#13505](https://github.com/mastra-ai/mastra/pull/13505))
33
+
34
+ A warning now appears when authenticating with Anthropic via OAuth, alerting that using a Claude Max subscription through OAuth is a grey area that may violate Anthropic's Terms of Service.
35
+ - During `/login` or onboarding: **Continue** proceeds with OAuth, **Cancel** returns to the provider selection screen.
36
+ - At startup (when existing Anthropic OAuth credentials are detected and the warning has not been acknowledged): **Continue** keeps credentials, **Remove OAuth** logs out from Anthropic.
37
+ - The startup warning only appears once — acknowledging it persists the choice in settings.
38
+
39
+ - Fixed `/skills` so it lists skills even before the first message is sent. ([#13457](https://github.com/mastra-ai/mastra/pull/13457))
40
+
41
+ - Fixed `@` file autocomplete so fuzzy file search works when `fd` or `fdfind` is installed. ([#13460](https://github.com/mastra-ai/mastra/pull/13460))
42
+
43
+ - Fixed onboarding to allow API-key-only setup without requiring OAuth login. Previously, users with API keys configured as environment variables were blocked at the model pack selection step if they skipped OAuth login during onboarding. The auth step now clearly indicates that OAuth is optional when API keys are set. ([#13500](https://github.com/mastra-ai/mastra/pull/13500))
44
+
45
+ - Updated default observational memory settings: bufferTokens 1/5, bufferActivation 2000, blockAfter 2. ([#13476](https://github.com/mastra-ai/mastra/pull/13476))
46
+
47
+ - Fixed a fatal crash on startup that caused the TUI to fail immediately on launch. ([#13503](https://github.com/mastra-ai/mastra/pull/13503))
48
+
49
+ - Fixed stale git branch in system prompt and TUI status bar. The branch is now refreshed on every agent request and when switching threads, so both the system prompt and status bar reflect the current branch. Also improved the status line to show abbreviated branch names instead of hiding the branch entirely when the name is too long. ([#13456](https://github.com/mastra-ai/mastra/pull/13456))
50
+
51
+ - Fixed Mastra Code TUI hook triggering so `Stop` runs on every `agent_end` reason (`complete`, `aborted`, `error`) and `UserPromptSubmit` runs before sending non-command user prompts with block handling. ([#13442](https://github.com/mastra-ai/mastra/pull/13442))
52
+
53
+ - Updated thinking-level labels in Mastra Code UI to be provider-aware for OpenAI models. ([#13490](https://github.com/mastra-ai/mastra/pull/13490))
54
+ - `/think` and Settings now use shared label metadata
55
+ - OpenAI models show provider-specific labels (for example, `Very High (xhigh)`)
56
+ - Stored `thinkingLevel` values remain unchanged (`off`, `low`, `medium`, `high`, `xhigh`)
57
+
58
+ - Strengthened the Anthropic Claude Max OAuth warning language to explicitly call out account-ban risk and potential Terms of Service violations before users continue with OAuth. ([#13508](https://github.com/mastra-ai/mastra/pull/13508))
59
+
60
+ - Fixed slash command arguments being silently discarded when the command template doesn't use $ARGUMENTS or positional variables ($1, $2, etc.). Arguments are now appended to the output so the model can see what the user provided. ([#13493](https://github.com/mastra-ai/mastra/pull/13493))
61
+
62
+ - Updated dependencies [[`df170fd`](https://github.com/mastra-ai/mastra/commit/df170fd139b55f845bfd2de8488b16435bd3d0da), [`ae55343`](https://github.com/mastra-ai/mastra/commit/ae5534397fc006fd6eef3e4f80c235bcdc9289ef), [`b8621e2`](https://github.com/mastra-ai/mastra/commit/b8621e25e70cae69a9343353f878a9112493a2fe), [`c290cec`](https://github.com/mastra-ai/mastra/commit/c290cec5bf9107225de42942b56b487107aa9dce), [`c290cec`](https://github.com/mastra-ai/mastra/commit/c290cec5bf9107225de42942b56b487107aa9dce), [`f03e794`](https://github.com/mastra-ai/mastra/commit/f03e794630f812b56e95aad54f7b1993dc003add), [`aa4a5ae`](https://github.com/mastra-ai/mastra/commit/aa4a5aedb80d8d6837bab8cbb2e301215d1ba3e9), [`de3f584`](https://github.com/mastra-ai/mastra/commit/de3f58408752a8d80a295275c7f23fc306cf7f4f), [`74ae019`](https://github.com/mastra-ai/mastra/commit/74ae0197a6895f8897c369038c643d7e32dd84c2), [`d3fb010`](https://github.com/mastra-ai/mastra/commit/d3fb010c98f575f1c0614452667396e2653815f6), [`702ee1c`](https://github.com/mastra-ai/mastra/commit/702ee1c41be67cc532b4dbe89bcb62143508f6f0), [`f495051`](https://github.com/mastra-ai/mastra/commit/f495051eb6496a720f637fc85b6d69941c12554c), [`60b45e0`](https://github.com/mastra-ai/mastra/commit/60b45e0af29485c69f70f77b15d6643aaa5a9da7), [`e622f1d`](https://github.com/mastra-ai/mastra/commit/e622f1d3ab346a8e6aca6d1fe2eac99bd961e50b), [`861f111`](https://github.com/mastra-ai/mastra/commit/861f11189211b20ddb70d8df81a6b901fc78d11e), [`00f43e8`](https://github.com/mastra-ai/mastra/commit/00f43e8e97a80c82b27d5bd30494f10a715a1df9), [`1b6f651`](https://github.com/mastra-ai/mastra/commit/1b6f65127d4a0d6c38d0a1055cb84527db529d6b), [`96a1702`](https://github.com/mastra-ai/mastra/commit/96a1702ce362c50dda20c8b4a228b4ad1a36a17a), [`cb9f921`](https://github.com/mastra-ai/mastra/commit/cb9f921320913975657abb1404855d8c510f7ac5), [`114e7c1`](https://github.com/mastra-ai/mastra/commit/114e7c146ac682925f0fb37376c1be70e5d6e6e5), [`cb9f921`](https://github.com/mastra-ai/mastra/commit/cb9f921320913975657abb1404855d8c510f7ac5), [`1b6f651`](https://github.com/mastra-ai/mastra/commit/1b6f65127d4a0d6c38d0a1055cb84527db529d6b), [`c290cec`](https://github.com/mastra-ai/mastra/commit/c290cec5bf9107225de42942b56b487107aa9dce), [`72df4a8`](https://github.com/mastra-ai/mastra/commit/72df4a8f9bf1a20cfd3d9006a4fdb597ad56d10a)]:
63
+ - @mastra/core@1.8.0
64
+ - @mastra/mcp@1.0.2
65
+ - @mastra/pg@1.7.0
66
+ - @mastra/libsql@1.6.2
67
+ - @mastra/memory@1.5.2
68
+
3
69
  ## 0.4.0-alpha.0
4
70
 
5
71
  ### Minor Changes
@@ -3,7 +3,7 @@ name: mastracode
3
3
  description: Documentation for mastracode. Use when working with mastracode APIs, configuration, or implementation.
4
4
  metadata:
5
5
  package: "mastracode"
6
- version: "0.4.0-alpha.0"
6
+ version: "0.4.0"
7
7
  ---
8
8
 
9
9
  ## When to use
@@ -1,5 +1,5 @@
1
1
  {
2
- "version": "0.4.0-alpha.0",
2
+ "version": "0.4.0",
3
3
  "package": "mastracode",
4
4
  "exports": {
5
5
  "createMastraCode": {
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "mastracode",
3
- "version": "0.4.0-alpha.0",
3
+ "version": "0.4.0",
4
4
  "description": "",
5
5
  "type": "module",
6
6
  "files": [
@@ -65,11 +65,11 @@
65
65
  "tree-kill": "latest",
66
66
  "vscode-jsonrpc": "latest",
67
67
  "vscode-languageserver-protocol": "latest",
68
- "@mastra/core": "1.8.0-alpha.0",
69
- "@mastra/mcp": "1.0.2-alpha.0",
70
- "@mastra/libsql": "1.6.2-alpha.0",
71
- "@mastra/pg": "1.7.0-alpha.0",
72
- "@mastra/memory": "1.5.2-alpha.0"
68
+ "@mastra/core": "1.8.0",
69
+ "@mastra/libsql": "1.6.2",
70
+ "@mastra/mcp": "1.0.2",
71
+ "@mastra/memory": "1.5.2",
72
+ "@mastra/pg": "1.7.0"
73
73
  },
74
74
  "peerDependencies": {
75
75
  "zod": "^3.25.0 || ^4.0.0"
@@ -86,8 +86,8 @@
86
86
  "typescript-eslint": "^8.51.0",
87
87
  "vitest": "4.0.18",
88
88
  "zod": "^4.3.6",
89
- "@internal/lint": "0.0.62",
90
- "@internal/types-builder": "0.0.37"
89
+ "@internal/lint": "0.0.63",
90
+ "@internal/types-builder": "0.0.38"
91
91
  },
92
92
  "engines": {
93
93
  "node": ">=22.13.0"