claude-code-generator 0.4.3__tar.gz → 0.4.4__tar.gz

{claude_code_generator-0.4.3/src/claude_code_generator.egg-info → claude_code_generator-0.4.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: claude-code-generator
-Version: 0.4.3
+Version: 0.4.4
 Summary: Orchestrator CLI that drives Claude Code end-to-end to generate whole projects from a requirements.md file.
 Author: Silvio Baratto
 License: MIT
@@ -20,7 +20,7 @@ Classifier: Topic :: Software Development :: Code Generators
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: claude-agent-sdk<0.2.0,>=0.1.61
+Requires-Dist: claude-agent-sdk<0.4.0,>=0.3.0
 Requires-Dist: typer
 Requires-Dist: rich
 Provides-Extra: dev
@@ -134,6 +134,44 @@ Run a standalone Opus 4.7 review of the current codebase against the design prin
 
 Print a Rich table with the current mode, current cycle, current phase, open/closed issue counts, the rate-limit pause state (with minutes remaining if paused), per-cycle token consumption columns (`in | cache_read | cache_write | out`), wall-clock elapsed time, and any `last_error` highlighted in red.
 
+## Running against Ollama Pro
+
+An opt-in subcommand, `code-generator generate ollama`, runs the full 0→7 pipeline against **one** Ollama-hosted model instead of the Anthropic Max subscription. This is the only supported way to bypass the Max-subscription invariant and is gated by `provider == "ollama"` inside `env.py`.
+
+### One-time setup
+
+1. Install the Ollama daemon (≥ 0.14.0) and start it on the default endpoint `http://localhost:11434`.
+2. Sign the daemon into your Ollama Pro account — required for any `:cloud` model:
+
+   ```bash
+   ollama signin
+   ```
+
+3. Export your existing `OLLAMA_API_KEY` (the same secret you already use elsewhere — no new secret is introduced):
+
+   ```bash
+   export OLLAMA_API_KEY=...   # typically set once in ~/.zshrc
+   ```
+
+Preflight refuses to run if the daemon is unreachable, not signed in, or `OLLAMA_API_KEY` is empty — fix the message it prints and re-run.
+
+### Worked examples
+
+```bash
+# Plan + implement a whole repo on a cloud-hosted 480B coding model
+code-generator generate ollama --model "qwen3-coder:480b:cloud"
+
+# Same pipeline on a different cloud model
+code-generator generate ollama --model "gpt-oss:120b-cloud"
+```
+
+The `--model` tag you pass drives **every** phase (0 through 7). There is no per-phase override on this codepath: single-model is the whole point. The tag is persisted to `state.json` as `CycleState.ollama_model` so `code-generator generate ollama --continue` resumes with the same model without re-typing it.
+
+### What is overridden vs. preserved
+
+- **Overridden under `provider == "ollama"`:** non-negotiable #1 (Max-only env strip is narrowed to `ANTHROPIC_AUTH_TOKEN` / `ANTHROPIC_BASE_URL` passthrough), #4 (no Anthropic overage telemetry — replaced by turn-count + wall-clock budgets), #8 (fixed-model-per-phase — replaced by single-model routing).
+- **Preserved on every path:** #2 (never `--bare`), #3 (YOLO permissions), #5 (wait-and-resume on 429), #6 (fresh context per issue), #7 (atomic state writes), #9 (no default `max_turns`).
+
 ## Safety constraints
 
 The tool enforces nine non-negotiables (see `CLAUDE.md` for the full list):

{claude_code_generator-0.4.3 → claude_code_generator-0.4.4}/README.md

@@ -94,6 +94,44 @@ Run a standalone Opus 4.7 review of the current codebase against the design prin
 
 Print a Rich table with the current mode, current cycle, current phase, open/closed issue counts, the rate-limit pause state (with minutes remaining if paused), per-cycle token consumption columns (`in | cache_read | cache_write | out`), wall-clock elapsed time, and any `last_error` highlighted in red.
 
+## Running against Ollama Pro
+
+An opt-in subcommand, `code-generator generate ollama`, runs the full 0→7 pipeline against **one** Ollama-hosted model instead of the Anthropic Max subscription. This is the only supported way to bypass the Max-subscription invariant and is gated by `provider == "ollama"` inside `env.py`.
+
+### One-time setup
+
+1. Install the Ollama daemon (≥ 0.14.0) and start it on the default endpoint `http://localhost:11434`.
+2. Sign the daemon into your Ollama Pro account — required for any `:cloud` model:
+
+   ```bash
+   ollama signin
+   ```
+
+3. Export your existing `OLLAMA_API_KEY` (the same secret you already use elsewhere — no new secret is introduced):
+
+   ```bash
+   export OLLAMA_API_KEY=...   # typically set once in ~/.zshrc
+   ```
+
+Preflight refuses to run if the daemon is unreachable, not signed in, or `OLLAMA_API_KEY` is empty — fix the message it prints and re-run.
+
+### Worked examples
+
+```bash
+# Plan + implement a whole repo on a cloud-hosted 480B coding model
+code-generator generate ollama --model "qwen3-coder:480b:cloud"
+
+# Same pipeline on a different cloud model
+code-generator generate ollama --model "gpt-oss:120b-cloud"
+```
+
+The `--model` tag you pass drives **every** phase (0 through 7). There is no per-phase override on this codepath: single-model is the whole point. The tag is persisted to `state.json` as `CycleState.ollama_model` so `code-generator generate ollama --continue` resumes with the same model without re-typing it.
+
+### What is overridden vs. preserved
+
+- **Overridden under `provider == "ollama"`:** non-negotiable #1 (Max-only env strip is narrowed to `ANTHROPIC_AUTH_TOKEN` / `ANTHROPIC_BASE_URL` passthrough), #4 (no Anthropic overage telemetry — replaced by turn-count + wall-clock budgets), #8 (fixed-model-per-phase — replaced by single-model routing).
+- **Preserved on every path:** #2 (never `--bare`), #3 (YOLO permissions), #5 (wait-and-resume on 429), #6 (fresh context per issue), #7 (atomic state writes), #9 (no default `max_turns`).
+
 ## Safety constraints
 
 The tool enforces nine non-negotiables (see `CLAUDE.md` for the full list):

{claude_code_generator-0.4.3 → claude_code_generator-0.4.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "claude-code-generator"
-version = "0.4.3"
+version = "0.4.4"
 description = "Orchestrator CLI that drives Claude Code end-to-end to generate whole projects from a requirements.md file."
 readme = "README.md"
 license = { text = "MIT" }
@@ -23,7 +23,7 @@ classifiers = [
 ]
 requires-python = ">=3.11"
 dependencies = [
-    "claude-agent-sdk>=0.1.61,<0.2.0",
+    "claude-agent-sdk>=0.3.0,<0.4.0",
     "typer",
     "rich",
 ]

{claude_code_generator-0.4.3 → claude_code_generator-0.4.4/src/claude_code_generator.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: claude-code-generator
-Version: 0.4.3
+Version: 0.4.4
 Summary: Orchestrator CLI that drives Claude Code end-to-end to generate whole projects from a requirements.md file.
 Author: Silvio Baratto
 License: MIT
@@ -20,7 +20,7 @@ Classifier: Topic :: Software Development :: Code Generators
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: claude-agent-sdk<0.2.0,>=0.1.61
+Requires-Dist: claude-agent-sdk<0.4.0,>=0.3.0
 Requires-Dist: typer
 Requires-Dist: rich
 Provides-Extra: dev
@@ -134,6 +134,44 @@ Run a standalone Opus 4.7 review of the current codebase against the design prin
 
 Print a Rich table with the current mode, current cycle, current phase, open/closed issue counts, the rate-limit pause state (with minutes remaining if paused), per-cycle token consumption columns (`in | cache_read | cache_write | out`), wall-clock elapsed time, and any `last_error` highlighted in red.
 
+## Running against Ollama Pro
+
+An opt-in subcommand, `code-generator generate ollama`, runs the full 0→7 pipeline against **one** Ollama-hosted model instead of the Anthropic Max subscription. This is the only supported way to bypass the Max-subscription invariant and is gated by `provider == "ollama"` inside `env.py`.
+
+### One-time setup
+
+1. Install the Ollama daemon (≥ 0.14.0) and start it on the default endpoint `http://localhost:11434`.
+2. Sign the daemon into your Ollama Pro account — required for any `:cloud` model:
+
+   ```bash
+   ollama signin
+   ```
+
+3. Export your existing `OLLAMA_API_KEY` (the same secret you already use elsewhere — no new secret is introduced):
+
+   ```bash
+   export OLLAMA_API_KEY=...   # typically set once in ~/.zshrc
+   ```
+
+Preflight refuses to run if the daemon is unreachable, not signed in, or `OLLAMA_API_KEY` is empty — fix the message it prints and re-run.
+
+### Worked examples
+
+```bash
+# Plan + implement a whole repo on a cloud-hosted 480B coding model
+code-generator generate ollama --model "qwen3-coder:480b:cloud"
+
+# Same pipeline on a different cloud model
+code-generator generate ollama --model "gpt-oss:120b-cloud"
+```
+
+The `--model` tag you pass drives **every** phase (0 through 7). There is no per-phase override on this codepath: single-model is the whole point. The tag is persisted to `state.json` as `CycleState.ollama_model` so `code-generator generate ollama --continue` resumes with the same model without re-typing it.
+
+### What is overridden vs. preserved
+
+- **Overridden under `provider == "ollama"`:** non-negotiable #1 (Max-only env strip is narrowed to `ANTHROPIC_AUTH_TOKEN` / `ANTHROPIC_BASE_URL` passthrough), #4 (no Anthropic overage telemetry — replaced by turn-count + wall-clock budgets), #8 (fixed-model-per-phase — replaced by single-model routing).
+- **Preserved on every path:** #2 (never `--bare`), #3 (YOLO permissions), #5 (wait-and-resume on 429), #6 (fresh context per issue), #7 (atomic state writes), #9 (no default `max_turns`).
+
 ## Safety constraints
 
 The tool enforces nine non-negotiables (see `CLAUDE.md` for the full list):

{claude_code_generator-0.4.3 → claude_code_generator-0.4.4}/src/claude_code_generator.egg-info/SOURCES.txt

@@ -47,6 +47,7 @@ src/code_generator/orchestrator/_comments.py
 src/code_generator/orchestrator/_memory_writers.py
 src/code_generator/orchestrator/_phase5_precommit.py
 src/code_generator/orchestrator/cycle_loop.py
+src/code_generator/orchestrator/ollama_budget.py
 src/code_generator/orchestrator/phase0_complexity.py
 src/code_generator/orchestrator/phase1_plan.py
 src/code_generator/orchestrator/phase2_review.py
@@ -103,13 +104,18 @@ tests/test_commit_message.py
 tests/test_crash_recovery.py
 tests/test_cycle_loop.py
 tests/test_cycle_loop_multicycle.py
+tests/test_cycle_ollama_model.py
 tests/test_delta_planning.py
 tests/test_dependencies.py
 tests/test_detect.py
 tests/test_docs_no_default_max_turns.py
+tests/test_docs_ollama_model_guide.py
+tests/test_docs_ollama_pro.py
+tests/test_effective_model_routing.py
 tests/test_effort.py
 tests/test_env.py
 tests/test_generate.py
+tests/test_generate_ollama.py
 tests/test_generate_resume.py
 tests/test_gh.py
 tests/test_gh_labels.py
@@ -127,6 +133,8 @@ tests/test_message_parsing.py
 tests/test_no_max_turns_in_call_sites.py
 tests/test_no_max_turns_literal.py
 tests/test_non_goals_grep_guard.py
+tests/test_ollama_budget.py
+tests/test_ollama_rate_limit.py
 tests/test_optimize.py
 tests/test_options.py
 tests/test_phase0.py
@@ -141,6 +149,7 @@ tests/test_phase7.py
 tests/test_phase_mcp_regression.py
 tests/test_phase_token_logging.py
 tests/test_preflight.py
+tests/test_preflight_ollama.py
 tests/test_prompt_drift.py
 tests/test_prompt_prefix_snapshots.py
 tests/test_prompt_prefix_stability.py

{claude_code_generator-0.4.3 → claude_code_generator-0.4.4}/src/claude_code_generator.egg-info/requires.txt

@@ -1,4 +1,4 @@
-claude-agent-sdk<0.2.0,>=0.1.61
+claude-agent-sdk<0.4.0,>=0.3.0
 typer
 rich
 

{claude_code_generator-0.4.3 → claude_code_generator-0.4.4}/src/code_generator/__init__.py

@@ -1,3 +1,3 @@
 """code-generator: orchestrator CLI for end-to-end project generation."""
 
-__version__ = "0.4.3"
+__version__ = "0.4.4"

{claude_code_generator-0.4.3 → claude_code_generator-0.4.4}/src/code_generator/cli.py

@@ -10,7 +10,7 @@ import typer
 
 import code_generator
 from code_generator.commands.bench import bench_app
-from code_generator.commands.generate import generate_command
+from code_generator.commands.generate import generate_app
 from code_generator.commands.init import init_command
 from code_generator.commands.optimize import optimize_command
 from code_generator.commands.review import review_command
@@ -46,8 +46,8 @@ def root(
 
 
 app.add_typer(bench_app, name="bench")
+app.add_typer(generate_app, name="generate")
 app.command(name="init")(init_command)
 app.command(name="status")(status_command)
-app.command(name="generate")(generate_command)
 app.command(name="optimize")(optimize_command)
 app.command(name="review")(review_command)

{claude_code_generator-0.4.3 → claude_code_generator-0.4.4}/src/code_generator/commands/_dispatch.py

@@ -170,6 +170,7 @@ async def dispatch_async(
     state_path: Path | None = None,
     session_mode: Literal["shared", "fresh", "batch"] = "shared",
     max_turns: int | None = None,
+    ollama_model: str | None = None,
 ) -> None:
     """Async entry point for the orchestration pipeline.
 
@@ -221,14 +222,27 @@ async def dispatch_async(
         needs_phase0 = False
 
     if needs_phase0:
-        await phase0_complexity.run(st, project_dir, runner_module=runner_module, logger=logger)
+        await phase0_complexity.run(
+            st,
+            project_dir,
+            runner_module=runner_module,
+            logger=logger,
+            effective_model=ollama_model,
+        )
 
     # Dry-run: planning only (phase 0 + phase 1).
     if dry_run:
         from code_generator.orchestrator import phase1_plan
 
         logger.info("--dry-run: running phase 1 (planning only).")
-        await phase1_plan.run(st, None, project_dir, runner_module=runner_module, logger=logger)
+        await phase1_plan.run(
+            st,
+            None,
+            project_dir,
+            runner_module=runner_module,
+            logger=logger,
+            effective_model=ollama_model,
+        )
         return
 
     # Dispatch to cycle loop.
@@ -242,6 +256,7 @@ async def dispatch_async(
             start_phase=start_phase,
             session_mode=session_mode,
             max_turns=max_turns,
+            effective_model=ollama_model,
         )
     else:
         await cycle_loop.run_single_mode(
@@ -252,6 +267,7 @@ async def dispatch_async(
             start_phase=start_phase,
             session_mode=session_mode,
             max_turns=max_turns,
+            effective_model=ollama_model,
         )
 
 
@@ -309,6 +325,7 @@ def dispatch_orchestrator(
     session_mode: Literal["shared", "fresh", "batch"] = "shared",
     session_mode_explicit: bool = False,
     max_turns: int | None = None,
+    ollama_model: str | None = None,
 ) -> None:
     """Resolve resume parameters and dispatch the async orchestrator.
 
@@ -433,5 +450,6 @@ def dispatch_orchestrator(
             state_path=state_path,
             session_mode=effective_session_mode,
             max_turns=max_turns,
+            ollama_model=ollama_model,
         )
     )