xonecas.io
64875
Mc

mini-coder / commit dd9e160

chore(todo): update task list

xonecas2026-03-11 dd9e16081fc6c2a1e0c04083b1a3853f9733a0a4 parent 3a3ed36

1 file changed

TODO.md+29−92
@@ -1,64 +1,39 @@
11 # TODO
22
3-## Bug with chat completions models (kimi 2.5 for example)
3+## Gpt codex context window maxinng out
44
5-See bellow, there is the thinking spiner before each line, this doesn't happen with other models.
5+I've noticed several sessions with codex spark that error because the context got too big for the model:
66
77 ```
8-⠦ thinkingAdd reasoning indicator (e.g., "🤔" or "thinking") when `showReasoning` is true
9-
10-⠧ thinkingPhase 5: Update Command Context & CLI Commands
11-⠏ thinkingFiles: `src/cli/commands.ts`, `src/agent/session-runner.ts`, `src/index.ts`
12-
13-⠋ thinking1. Add `showReasoning` to `CommandContext`
14-⠹ thinking2. Add `/reasoning` command to toggle (on|off)
15-⠸ thinking3. Load/save preference from settings repo
16-⠼ thinking4. Pass setting through to `SessionRunner` and reporter
17-
18-⠦ thinkingPhase 6: Update Output Reporter & Headless Reporter
19-⠧ thinkingFiles: `src/cli/output-reporter.ts`, `src/cli/headless-reporter.ts`
20-
21-⠋ thinking1. Accept and forward `showReasoning` option
22-⠙ thinking2. Headless reporter: still consume reasoning events (for accumulation) but never render
23-
24-Phase 7: Agent Integration
25-Files: `src/agent/agent.ts`
26-
27-⠹ thinking1. Load `getShowReasoning()` preference
28-2. Pass to `CommandContext` and `SessionRunner`
29-⠸ thinking3. Update status bar calls to include reasoning flag
30-
31-⠼ thinkingPhase 8: Help & Documentation
32-Files: `src/cli/commands.ts`
33-
34-⠴ thinkingAdd `/reasoning` to help text
35-
36-────────────────────────────────────────
37-
38-⠦ thinkingFiles to Modify (in dependency order):
39-
40-⠧ thinking1. `src/session/db/settings-repo.ts` - Add new setting functions
41-⠇ thinking2. `src/llm-api/types.ts` - Add reasoning to TurnResult (if needed)
42-⠋ thinking3. `src/agent/reporter.ts` - Update StatusBarData
43-4. `src/cli/stream-render.ts` - Add showReasoning option
44-⠙ thinking5. `src/cli/status-bar.ts` - Add reasoning indicator
45-⠹ thinking6. `src/cli/output-reporter.ts` - Forward option
46-⠸ thinking7. `src/cli/headless-reporter.ts` - Handle reasoning events
47-⠼ thinking8. `src/cli/commands.ts` - Add /reasoning command
48-⠴ thinking9. `src/agent/session-runner.ts` - Accept and pass through setting
49-⠦ thinking10. `src/agent/agent.ts` - Load preference, wire up
50-⠧ thinking11. `src/index.ts` - Load preference on startup
51-⠇ thinking12. `src/session/db/index.ts` - Export new functions
52-
53-⠏ thinkingThis is a clean, incremental change that:
54-⠋ thinking· Maintains backward compatibility (defaults to showing reasoning)
55-⠙ thinking· Separates the "reasoning effort" setting from "reasoning display" setting
56-⠹ thinking· Properly accumulates reasoning text for message history
57-⠼ thinking· Works in both interactive and headless modes
58-kimi-k2.5 ✦ high mmm7tm8p ~/src/mini-coder ⎇ main ctx 37.9k/262.1k 14% ↑ 172.2k ↓ 2.3k
59-▶
8+ ← read node_modules/@ai-sdk/google/src/google-generative-ai-language-model.ts:680+120
9+ · node_modules/@ai-sdk/google/src/google-generative-ai-language-model.ts lines 680–799 of 1057 (truncated)
10+⠙ thinking{
11+ type: "error",
12+ sequence_number: 2,
13+ error: {
14+ type: "invalid_request_error",
15+ code: "context_length_exceeded",
16+ message: "Your input exceeds the context window of this model. Please adjust your input and try again.",
17+ param: "input",
18+ },
19+}
20+✖ [object Object]
21+✖ [object Object]
22+error: script "dev" exited with code 1
6023 ```
6124
25+The same task with GPT 5.4: `ctx 82.8k/1050.0k 8%` used on 82k in context. I know spark is a smaller context, but I'm suprised by how often we max out the 128k context.
26+
27+---
28+
29+## LSP Diagnostics (not very important, with tool-hooks and strong linting, this is not as necessary, but we should implement asap)
30+
31+We should have a closed loop feedback for LSP diagnostics on edits/reads.
32+
33+This could potentially be a very big slowdown, waiting for updated diagnostics every edit. This also has bias downsides, stale diagnostics confuse the LLM, and can cause negative distractions.
34+
35+We need to do research first, but maybe we can leverage the hooks feature to achieve a similar result without the performance penalties? Needs brainstorming
36+
6237 ---
6338
6439 ## Gpt 5.4, Gpt 5.3 codex both starts printing tool calls as the assistant message:
@@ -105,44 +80,6 @@ error: script "dev" exited with code 130
10580
10681 I was not able to reproduce the same behaviour with opencode using the same provider. Which points to an issue with our code.
10782
108-Let's investigate.
109-
110----
111-
112-## Gpt codex context window maxinng out
113-
114-I've noticed several sessions with codex spark that error because the context got too big for the model:
115-
116-```
117- ← read node_modules/@ai-sdk/google/src/google-generative-ai-language-model.ts:680+120
118- · node_modules/@ai-sdk/google/src/google-generative-ai-language-model.ts lines 680–799 of 1057 (truncated)
119-⠙ thinking{
120- type: "error",
121- sequence_number: 2,
122- error: {
123- type: "invalid_request_error",
124- code: "context_length_exceeded",
125- message: "Your input exceeds the context window of this model. Please adjust your input and try again.",
126- param: "input",
127- },
128-}
129-✖ [object Object]
130-✖ [object Object]
131-error: script "dev" exited with code 1
132-```
133-
134-The same task with GPT 5.4: `ctx 82.8k/1050.0k 8%` used on 82k in context. I know spark is a smaller context, but I'm suprised by how often we max out the 128k context.
135-
136----
137-
138-## LSP Diagnostics (not very important, with tool-hooks and strong linting, this is not as necessary, but we should implement asap)
139-
140-We should have a closed loop feedback for LSP diagnostics on edits/reads.
141-
142-This could potentially be a very big slowdown, waiting for updated diagnostics every edit. This also has bias downsides, stale diagnostics confuse the LLM, and can cause negative distractions.
143-
144-We need to do research first, but maybe we can leverage the hooks feature to achieve a similar result without the performance penalties? Needs brainstorming
145-
14683 ---
14784
14885 ## Deferred fixes