From 4a914a298ae2d761ff73c0cdad0102240329d54e Mon Sep 17 00:00:00 2001
From: Philipp Kohler <39829783+Snoup97@users.noreply.github.com>
Date: Sat, 17 Jun 2023 17:53:03 +0200
Subject: [PATCH 01/16] added .idea folder of jetbrains IDEs to gitignore
 (#111)

---
 .gitignore | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.gitignore b/.gitignore
index 2e6f48e..1c41f42 100644
--- a/.gitignore
+++ b/.gitignore
@@ -18,6 +18,7 @@ ENV/
 
 # IDE-specific files
 .vscode/
+.idea/
 
 # Compiled Python modules
 *.pyc

From c4c1203fc07b2e23c3e5a5e9277266a711ab9466 Mon Sep 17 00:00:00 2001
From: Vicente Reyes <vr.github@outlook.com>
Date: Sat, 17 Jun 2023 18:11:15 +0200
Subject: [PATCH 02/16] Minor formatting fixes in Readme; fix main python
 command (#97)

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index a7fea2e..40899bb 100644
--- a/README.md
+++ b/README.md
@@ -40,9 +40,9 @@ Contributors welcome! If you are unsure what to add, check out the ideas listed
 ## Features
 You can specify the "identity" of the AI agent by editing the files in the `identity` folder.
 
-Editing the identity, and evolving the main_prompt, is currently how you make the agent remember things between projects.
+Editing the identity, and evolving the `main_prompt`, is currently how you make the agent remember things between projects.
 
-Each step in steps.py will have its communication history with GPT4 stored in the logs folder, and can be rerun with scripts/rerun_edited_message_logs.py.
+Each step in `steps.py` will have its communication history with GPT4 stored in the logs folder, and can be rerun with `scripts/rerun_edited_message_logs.py`.
 
 ## Contributing
 If you want to contribute, please check out the [projects](https://github.com/AntonOsika/gpt-engineer/projects?query=is%3Aopen) or [issues tab](https://github.com/AntonOsika/gpt-engineer/issues) in the GitHub repo and please read the [contributing document](.github/CONTRIBUTING.md) on how to contribute.

From 31b00de247171a3c13ab46f8dba1d5bbaaec6d67 Mon Sep 17 00:00:00 2001
From: Anton Osika <anton.osika@gmail.com>
Date: Sat, 17 Jun 2023 19:52:22 +0200
Subject: [PATCH 03/16] Improve prompts

---
 gpt_engineer/steps.py        |  2 +-
 identity/{setup => generate} |  3 ++-
 identity/qa                  |  2 +-
 identity/respec              |  5 ++++-
 identity/spec                | 13 ++++++++-----
 identity/unit_tests          |  2 +-
 identity/use_qa              |  3 ++-
 7 files changed, 19 insertions(+), 11 deletions(-)
 rename identity/{setup => generate} (83%)

diff --git a/gpt_engineer/steps.py b/gpt_engineer/steps.py
index 60fea23..d6bf3fd 100644
--- a/gpt_engineer/steps.py
+++ b/gpt_engineer/steps.py
@@ -8,7 +8,7 @@ from gpt_engineer.chat_to_files import parse_chat
 
 
 def setup_sys_prompt(dbs):
-    return dbs.identity["setup"] + "\nUseful to know:\n" + dbs.identity["philosophy"]
+    return dbs.identity["generate"] + "\nUseful to know:\n" + dbs.identity["philosophy"]
 
 
 def run(ai: AI, dbs: DBs):
diff --git a/identity/setup b/identity/generate
similarity index 83%
rename from identity/setup
rename to identity/generate
index 4917945..8e5f427 100644
--- a/identity/setup
+++ b/identity/generate
@@ -1,7 +1,8 @@
 You will get instructions for code to write.
 You will write a very long answer. Make sure that every detail of the architecture is, in the end, implemented as code.
 
-You will first lay out the names of the core classes, functions, methods that will be necessary, As well as a quick comment on their purpose.
+Think step by step and reason yourself to the right decisions to make sure we get it right.
+You will first lay out the names of the core classes, functions, methods that will be necessary, as well as a quick comment on their purpose.
 Then you will output the content of each file, with syntax below.
 (You will start with the "entrypoint" file, then go to the ones that are imported by that file, and so on.)
 Make sure that files contain all imports, types etc. Make sure that code in different files are compatible with each other.
diff --git a/identity/qa b/identity/qa
index f4f9934..58c3508 100644
--- a/identity/qa
+++ b/identity/qa
@@ -1,3 +1,3 @@
 You will read instructions and not carry them out, only seek to clarify them.
 Specifically you will first summarise a list of super short bullets of areas that need clarification.
-Then you will pick one clarifying question, and wait for an answer from the user.
+Then you will pick one clarifying question, and wait for an answer from the user.
\ No newline at end of file
diff --git a/identity/respec b/identity/respec
index 00b16b0..0ffc318 100644
--- a/identity/respec
+++ b/identity/respec
@@ -5,4 +5,7 @@ You have been asked to give feedback on the following:
 - Is there anything missing for the program to fully work?
 - Is there anything that can be simplified without decreasing quality?
 
-You are asked to make educated assumptions for each unclear item. For each of these, communicate which assumptions you'll make when implementing the feature.
+You are asked to make educated assumptions for each unclear item.
+For each of these, communicate which assumptions you'll make when implementing the feature.
+
+Think step by step to make sure we don't miss anything.
\ No newline at end of file
diff --git a/identity/spec b/identity/spec
index 90c1d0d..540d13b 100644
--- a/identity/spec
+++ b/identity/spec
@@ -1,8 +1,11 @@
-You are a super smart developer and an AI developed to write programs. You have been asked to make a specification for a program.
+You are a super smart developer. You have been asked to make a specification for a program.
 
-Please generate a specification based on the given input. First, be super explicit about what the program should do, which features it should have and give details about anything that might be unclear. **Don't leave anything unclear or undefined.**
+Think step by step to make sure we get a high quality specification and we don't miss anything.
+First, be super explicit about what the program should do, which features it should have
+and give details about anything that might be unclear. **Don't leave anything unclear or undefined.**
 
-Second, lay out the names of the core classes, functions, methods that will be necessary, As well as a quick comment on their purpose.
-Then write out which non-standard dependencies you'll have to use.
+Second, lay out the names of the core classes, functions, methods that will be necessary,
+as well as a quick comment on their purpose.
+Finally list all non-standard dependencies you'll have to use.
 
-This specification will be used later as the basis for your implementation.
+This specification will be used later as the basis for the implementation.
\ No newline at end of file
diff --git a/identity/unit_tests b/identity/unit_tests
index d21997e..4c9534b 100644
--- a/identity/unit_tests
+++ b/identity/unit_tests
@@ -1,3 +1,3 @@
-You are a super smart developer and an AI developed to use Test Driven Development to write tests according to a specification.
+You are a super smart developer using Test Driven Development to write tests according to a specification.
 
 Please generate tests based on the above specification. The tests should be as simple as possible, but still cover all the functionality.
diff --git a/identity/use_qa b/identity/use_qa
index 9aee050..a8b1f73 100644
--- a/identity/use_qa
+++ b/identity/use_qa
@@ -1,6 +1,7 @@
 Please now remember the steps:
 
-First lay out the names of the core classes, functions, methods that will be necessary, As well as a quick comment on their purpose.
+Think step by step and reason yourself to the right decisions to make sure we get it right.
+First lay out the names of the core classes, functions, methods that will be necessary, as well as a quick comment on their purpose.
 Then output the content of each file, with syntax below.
 (You will start with the "entrypoint" file, then go to the ones that are imported by that file, and so on.)
 Make sure that files contain all imports, types, variables etc. The code should be fully functional. If anything is unclear, just make assumptions. Make sure that code in different files are compatible with each other.

From a3cb4964e9024e85841a520f9430d0841bc9b1c0 Mon Sep 17 00:00:00 2001
From: Anton Osika <anton.osika@gmail.com>
Date: Sat, 17 Jun 2023 19:52:48 +0200
Subject: [PATCH 04/16] Remove automatic execution for now

---
 gpt_engineer/steps.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/gpt_engineer/steps.py b/gpt_engineer/steps.py
index d6bf3fd..dcec0c2 100644
--- a/gpt_engineer/steps.py
+++ b/gpt_engineer/steps.py
@@ -125,7 +125,7 @@ def execute_workspace(ai: AI, dbs: DBs):
 
 # Different configs of what steps to run
 STEPS = {
-    'default': [gen_spec, pre_unit_tests, run_clarified, execute_workspace],
+    'default': [gen_spec, pre_unit_tests, run_clarified],
     'simple': [run, execute_workspace],
     'clarify': [clarify, run_clarified],
 }

From e8f47c1e702f901cd058d888cd0932b35323b8ab Mon Sep 17 00:00:00 2001
From: Anton Osika <anton.osika@gmail.com>
Date: Sat, 17 Jun 2023 20:36:51 +0200
Subject: [PATCH 05/16] improve execution step

---
 gpt_engineer/steps.py | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/gpt_engineer/steps.py b/gpt_engineer/steps.py
index dcec0c2..676159b 100644
--- a/gpt_engineer/steps.py
+++ b/gpt_engineer/steps.py
@@ -56,7 +56,7 @@ def gen_spec(ai: AI, dbs: DBs):
     '''
     Generate a spec from the main prompt + clarifications and save the results to the workspace
     '''
-    messages = [ai.fsystem(setup_sys_prompt(dbs)), ai.fsystem(f"Main prompt: {dbs.input['main_prompt']}")]
+    messages = [ai.fsystem(setup_sys_prompt(dbs)), ai.fsystem(f"Instructions: {dbs.input['main_prompt']}")]
 
     messages = ai.next(messages, dbs.identity['spec'])
     messages = ai.next(messages, dbs.identity['respec'])
@@ -97,10 +97,11 @@ def run_clarified(ai: AI, dbs: DBs):
 def execute_workspace(ai: AI, dbs: DBs):
     messages = ai.start(
         system=(
-            f"You will get infomation about a codebase that is currently on disk in the folder {dbs.workspace.path}.\n"
+            f"You will get information about a codebase that is currently on disk in the current folder.\n"
             "From this you will answer with one code block that includes all the necessary macos terminal commands to "
             "a) install dependencies "
-            "b) run the necessary parts of the codebase to try it.\n"
+            "b) run all necessary parts of the codebase (in parallell if necessary).\n"
+            "Do not install globally. Do not use sudo.\n"
             "Do not explain the code, just give the commands.\n"
         ),
         user="Information about the codebase:\n\n" + dbs.workspace["all_output.txt"],
@@ -109,6 +110,8 @@ def execute_workspace(ai: AI, dbs: DBs):
     [[lang, command]] = parse_chat(messages[-1]['content'])
     assert lang in ['', 'bash', 'sh']
 
+    dbs.workspace['run.sh'] = command
+
     print('Do you want to execute this code?')
     print(command)
     print()
@@ -119,7 +122,9 @@ def execute_workspace(ai: AI, dbs: DBs):
         return messages
     print('Executing the code...')
     print()
-    subprocess.run(command, shell=True)
+
+    # Run the subprocess in dbs.workspace.path
+    subprocess.run('bash run.sh', shell=True, cwd=dbs.workspace.path)
     return messages
 
 
@@ -128,6 +133,7 @@ STEPS = {
     'default': [gen_spec, pre_unit_tests, run_clarified],
     'simple': [run, execute_workspace],
     'clarify': [clarify, run_clarified],
+    'execute_only': [execute_workspace],
 }
 
 # Future steps that can be added:

From 4a9ab4647e6398d6901d68a1131352a6848ecd01 Mon Sep 17 00:00:00 2001
From: Anton Osika <anton.osika@gmail.com>
Date: Sat, 17 Jun 2023 20:39:18 +0200
Subject: [PATCH 06/16] Execute per default

---
 gpt_engineer/steps.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/gpt_engineer/steps.py b/gpt_engineer/steps.py
index 676159b..b3f9486 100644
--- a/gpt_engineer/steps.py
+++ b/gpt_engineer/steps.py
@@ -130,7 +130,7 @@ def execute_workspace(ai: AI, dbs: DBs):
 
 # Different configs of what steps to run
 STEPS = {
-    'default': [gen_spec, pre_unit_tests, run_clarified],
+    'default': [gen_spec, pre_unit_tests, run_clarified, execute_workspace],
     'simple': [run, execute_workspace],
     'clarify': [clarify, run_clarified],
     'execute_only': [execute_workspace],

From 903a8905cb449dce79b2d634f19c3e9f0e419c95 Mon Sep 17 00:00:00 2001
From: Philipp Kohler <39829783+Snoup97@users.noreply.github.com>
Date: Sat, 17 Jun 2023 20:53:04 +0200
Subject: [PATCH 07/16] fixed the DB import in the pytest file (#116)

---
 tests/test_db.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/test_db.py b/tests/test_db.py
index 5dea240..0843a21 100644
--- a/tests/test_db.py
+++ b/tests/test_db.py
@@ -1,4 +1,4 @@
-from ..db import DB
+from gpt_engineer.db import DB
 
 
 def test_db():

From 8ac2cd81b9e19ac90fd2204fcd546e1e84d48f51 Mon Sep 17 00:00:00 2001
From: Anton Osika <anton.osika@gmail.com>
Date: Sat, 17 Jun 2023 21:01:30 +0200
Subject: [PATCH 08/16] Always generate entrypoint

---
 .gitignore            |  1 +
 gpt_engineer/steps.py | 45 ++++++++++++++++++++++++++-----------------
 2 files changed, 28 insertions(+), 18 deletions(-)

diff --git a/.gitignore b/.gitignore
index 1c41f42..debee41 100644
--- a/.gitignore
+++ b/.gitignore
@@ -36,3 +36,4 @@ archive
 
 # any log file
 *log.txt
+todo
diff --git a/gpt_engineer/steps.py b/gpt_engineer/steps.py
index b3f9486..ef08214 100644
--- a/gpt_engineer/steps.py
+++ b/gpt_engineer/steps.py
@@ -95,6 +95,29 @@ def run_clarified(ai: AI, dbs: DBs):
 
 
 def execute_workspace(ai: AI, dbs: DBs):
+    messages = gen_entrypoint(ai, dbs)
+    execute_entrypoint(ai, dbs)
+    return messages
+
+
+def execute_entrypoint(ai, dbs):
+    command = dbs.workspace['run.sh']
+
+    print('Do you want to execute this code?')
+    print()
+    print(command)
+    print()
+    print('If yes, press enter. If no, type "no"')
+    print()
+    if input() == 'no':
+        print('Ok, not executing the code.')
+    print('Executing the code...')
+    print()
+    subprocess.run('bash run.sh', shell=True, cwd=dbs.workspace.path)
+    return []
+
+
+def gen_entrypoint(ai, dbs):
     messages = ai.start(
         system=(
             f"You will get information about a codebase that is currently on disk in the current folder.\n"
@@ -106,34 +129,20 @@ def execute_workspace(ai: AI, dbs: DBs):
         ),
         user="Information about the codebase:\n\n" + dbs.workspace["all_output.txt"],
     )
-
+    print()
     [[lang, command]] = parse_chat(messages[-1]['content'])
     assert lang in ['', 'bash', 'sh']
-
     dbs.workspace['run.sh'] = command
-
-    print('Do you want to execute this code?')
-    print(command)
-    print()
-    print('If yes, press enter. If no, type "no"')
-    print()
-    if input() == 'no':
-        print('Ok, not executing the code.')
-        return messages
-    print('Executing the code...')
-    print()
-
-    # Run the subprocess in dbs.workspace.path
-    subprocess.run('bash run.sh', shell=True, cwd=dbs.workspace.path)
     return messages
 
 
 # Different configs of what steps to run
 STEPS = {
     'default': [gen_spec, pre_unit_tests, run_clarified, execute_workspace],
+    'benchmark': [gen_spec, pre_unit_tests, run_clarified, gen_entrypoint],
     'simple': [run, execute_workspace],
-    'clarify': [clarify, run_clarified],
-    'execute_only': [execute_workspace],
+    'clarify': [clarify, run_clarified, gen_entrypoint],
+    'execute_only': [execute_entrypoint],
 }
 
 # Future steps that can be added:

From a4019fb82fcd85edbc11ea7bba7c8df46d913e37 Mon Sep 17 00:00:00 2001
From: Anton Osika <anton.osika@gmail.com>
Date: Sat, 17 Jun 2023 21:32:46 +0200
Subject: [PATCH 09/16] Black

---
 gpt_engineer/steps.py | 64 ++++++++++++++++++++++++-------------------
 1 file changed, 36 insertions(+), 28 deletions(-)

diff --git a/gpt_engineer/steps.py b/gpt_engineer/steps.py
index ef08214..c414a5f 100644
--- a/gpt_engineer/steps.py
+++ b/gpt_engineer/steps.py
@@ -30,7 +30,7 @@ def clarify(ai: AI, dbs: DBs):
     while True:
         messages = ai.next(messages, user)
 
-        if messages[-1]['content'].strip().lower().startswith("no"):
+        if messages[-1]["content"].strip().lower().startswith("no"):
             break
 
         print()
@@ -53,29 +53,37 @@ def clarify(ai: AI, dbs: DBs):
 
 
 def gen_spec(ai: AI, dbs: DBs):
-    '''
+    """
     Generate a spec from the main prompt + clarifications and save the results to the workspace
-    '''
-    messages = [ai.fsystem(setup_sys_prompt(dbs)), ai.fsystem(f"Instructions: {dbs.input['main_prompt']}")]
+    """
+    messages = [
+        ai.fsystem(setup_sys_prompt(dbs)),
+        ai.fsystem(f"Instructions: {dbs.input['main_prompt']}"),
+    ]
 
-    messages = ai.next(messages, dbs.identity['spec'])
-    messages = ai.next(messages, dbs.identity['respec'])
-    messages = ai.next(messages, dbs.identity['spec'])
+    messages = ai.next(messages, dbs.identity["spec"])
+    messages = ai.next(messages, dbs.identity["respec"])
+    messages = ai.next(messages, dbs.identity["spec"])
 
-    dbs.memory['specification'] = messages[-1]['content']
+    dbs.memory["specification"] = messages[-1]["content"]
 
     return messages
 
+
 def pre_unit_tests(ai: AI, dbs: DBs):
-    '''
+    """
     Generate unit tests based on the specification, that should work.
-    '''
-    messages = [ai.fsystem(setup_sys_prompt(dbs)), ai.fuser(f"Instructions: {dbs.input['main_prompt']}"), ai.fuser(f"Specification:\n\n{dbs.memory['specification']}")]
+    """
+    messages = [
+        ai.fsystem(setup_sys_prompt(dbs)),
+        ai.fuser(f"Instructions: {dbs.input['main_prompt']}"),
+        ai.fuser(f"Specification:\n\n{dbs.memory['specification']}"),
+    ]
 
-    messages = ai.next(messages, dbs.identity['unit_tests'])
+    messages = ai.next(messages, dbs.identity["unit_tests"])
 
-    dbs.memory['unit_tests'] = messages[-1]['content']
-    to_files(dbs.memory['unit_tests'], dbs.workspace)
+    dbs.memory["unit_tests"] = messages[-1]["content"]
+    to_files(dbs.memory["unit_tests"], dbs.workspace)
 
     return messages
 
@@ -101,19 +109,19 @@ def execute_workspace(ai: AI, dbs: DBs):
 
 
 def execute_entrypoint(ai, dbs):
-    command = dbs.workspace['run.sh']
+    command = dbs.workspace["run.sh"]
 
-    print('Do you want to execute this code?')
+    print("Do you want to execute this code?")
     print()
     print(command)
     print()
     print('If yes, press enter. If no, type "no"')
     print()
-    if input() == 'no':
-        print('Ok, not executing the code.')
-    print('Executing the code...')
+    if input() == "no":
+        print("Ok, not executing the code.")
+    print("Executing the code...")
     print()
-    subprocess.run('bash run.sh', shell=True, cwd=dbs.workspace.path)
+    subprocess.run("bash run.sh", shell=True, cwd=dbs.workspace.path)
     return []
 
 
@@ -130,19 +138,19 @@ def gen_entrypoint(ai, dbs):
         user="Information about the codebase:\n\n" + dbs.workspace["all_output.txt"],
     )
     print()
-    [[lang, command]] = parse_chat(messages[-1]['content'])
-    assert lang in ['', 'bash', 'sh']
-    dbs.workspace['run.sh'] = command
+    [[lang, command]] = parse_chat(messages[-1]["content"])
+    assert lang in ["", "bash", "sh"]
+    dbs.workspace["run.sh"] = command
     return messages
 
 
 # Different configs of what steps to run
 STEPS = {
-    'default': [gen_spec, pre_unit_tests, run_clarified, execute_workspace],
-    'benchmark': [gen_spec, pre_unit_tests, run_clarified, gen_entrypoint],
-    'simple': [run, execute_workspace],
-    'clarify': [clarify, run_clarified, gen_entrypoint],
-    'execute_only': [execute_entrypoint],
+    "default": [gen_spec, pre_unit_tests, run_clarified, execute_workspace],
+    "benchmark": [gen_spec, pre_unit_tests, run_clarified, gen_entrypoint],
+    "simple": [run, execute_workspace],
+    "clarify": [clarify, run_clarified, gen_entrypoint],
+    "execute_only": [execute_entrypoint],
 }
 
 # Future steps that can be added:

From 0d186e22e6e3ff904f4295a0088a7bdf1b31aea9 Mon Sep 17 00:00:00 2001
From: Anton Osika <anton.osika@gmail.com>
Date: Sat, 17 Jun 2023 21:54:11 +0200
Subject: [PATCH 10/16] Skip the respec by default, fix that it changed
 application

---
 gpt_engineer/steps.py | 47 ++++++++++++++++++++++++++++++++++---------
 identity/respec       |  9 +++++----
 2 files changed, 43 insertions(+), 13 deletions(-)

diff --git a/gpt_engineer/steps.py b/gpt_engineer/steps.py
index c414a5f..b82af8a 100644
--- a/gpt_engineer/steps.py
+++ b/gpt_engineer/steps.py
@@ -11,7 +11,7 @@ def setup_sys_prompt(dbs):
     return dbs.identity["generate"] + "\nUseful to know:\n" + dbs.identity["philosophy"]
 
 
-def run(ai: AI, dbs: DBs):
+def simple_gen(ai: AI, dbs: DBs):
     """Run the AI on the main prompt and save the results"""
     messages = ai.start(
         setup_sys_prompt(dbs),
@@ -61,16 +61,31 @@ def gen_spec(ai: AI, dbs: DBs):
         ai.fsystem(f"Instructions: {dbs.input['main_prompt']}"),
     ]
 
-    messages = ai.next(messages, dbs.identity["spec"])
-    messages = ai.next(messages, dbs.identity["respec"])
     messages = ai.next(messages, dbs.identity["spec"])
 
     dbs.memory["specification"] = messages[-1]["content"]
 
     return messages
 
+def respec(ai: AI, dbs: DBs):
+    messages = dbs.logs[gen_spec.__name__]
+    messages += [ai.fsystem(dbs.identity["respec"])]
 
-def pre_unit_tests(ai: AI, dbs: DBs):
+    messages = ai.next(messages)
+    messages = ai.next(
+        messages,
+        (
+            'Based on the conversation so far, please reiterate the specification for the program. '
+            'If there are things that can be improved, please incorporate the improvements. '
+            "If you are satisfied with the specification, just write out the specification word by word again."
+        )
+    )
+
+    dbs.memory["specification"] = messages[-1]["content"]
+    return messages
+
+
+def gen_unit_tests(ai: AI, dbs: DBs):
     """
     Generate unit tests based on the specification, that should work.
     """
@@ -88,7 +103,20 @@ def pre_unit_tests(ai: AI, dbs: DBs):
     return messages
 
 
-def run_clarified(ai: AI, dbs: DBs):
+def gen_clarified_code(ai: AI, dbs: DBs):
+    # get the messages from previous step
+
+    messages = json.loads(dbs.logs[clarify.__name__])
+
+    messages = [
+        ai.fsystem(setup_sys_prompt(dbs)),
+    ] + messages[1:]
+    messages = ai.next(messages, dbs.identity["use_qa"])
+
+    to_files(messages[-1]["content"], dbs.workspace)
+    return messages
+
+def gen_code(ai: AI, dbs: DBs):
     # get the messages from previous step
 
     messages = [
@@ -146,10 +174,11 @@ def gen_entrypoint(ai, dbs):
 
 # Different configs of what steps to run
 STEPS = {
-    "default": [gen_spec, pre_unit_tests, run_clarified, execute_workspace],
-    "benchmark": [gen_spec, pre_unit_tests, run_clarified, gen_entrypoint],
-    "simple": [run, execute_workspace],
-    "clarify": [clarify, run_clarified, gen_entrypoint],
+    "default": [gen_spec, gen_unit_tests, gen_code, execute_workspace],
+    "benchmark": [gen_spec, gen_unit_tests, gen_code, gen_entrypoint],
+    "simple": [simple_gen, execute_workspace],
+    "clarify": [clarify, gen_clarified_code, execute_workspace],
+    "respec": [gen_spec, respec, gen_unit_tests, gen_code, execute_workspace],
     "execute_only": [execute_entrypoint],
 }
 
diff --git a/identity/respec b/identity/respec
index 0ffc318..ac907d7 100644
--- a/identity/respec
+++ b/identity/respec
@@ -1,9 +1,10 @@
-You are a pragmatic principal engineer at Google. You have been asked to review a specification for a new feature.
+You are a pragmatic principal engineer at Google.
+You have been asked to review a specification for a new feature by a previous version of yourself
 
 You have been asked to give feedback on the following:
-- Is there anything that might not work the way the user expects?
-- Is there anything missing for the program to fully work?
-- Is there anything that can be simplified without decreasing quality?
+- Is there anything that might not work the way intended by the instructions?
+- Is there anything in the specification missing for the program to work as expected?
+- Is there anything that can be simplified without significant drawback?
 
 You are asked to make educated assumptions for each unclear item.
 For each of these, communicate which assumptions you'll make when implementing the feature.

From 90cd00560768be171278200712cc1a74fdffde96 Mon Sep 17 00:00:00 2001
From: Anton Osika <anton.osika@gmail.com>
Date: Sat, 17 Jun 2023 22:21:10 +0200
Subject: [PATCH 11/16] Update README.md

---
 README.md | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/README.md b/README.md
index 40899bb..4bc6be0 100644
--- a/README.md
+++ b/README.md
@@ -13,10 +13,6 @@ GPT Engineer is made to be easy to adapt, extend, and make your agent learn how
 - Simplicity, all computation is "resumable" and persisted to the filesystem
 
 
-
-![output](https://github.com/AntonOsika/gpt-engineer/assets/4467025/a6938d43-2ac1-4cf1-98d1-93eea1bdfce4)
-
-
 ## Usage
 
 **Setup**:

From f44bd838f45d7fbd07675bc71404b8e816b55aae Mon Sep 17 00:00:00 2001
From: Anton Osika <anton.osika@gmail.com>
Date: Sat, 17 Jun 2023 22:22:59 +0200
Subject: [PATCH 12/16] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 4bc6be0..728568e 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
 # GPT Engineer
 **Specify what you want it to build, the AI asks for clarification, and then builds it.**
 
-GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt.
+GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt. [Demo](https://twitter.com/antonosika/status/1667641038104674306).
 
 ## Project philosophy
 - Simple to get value

From e0137261b1f7d1b992676310e3b1c9eeee17e7ee Mon Sep 17 00:00:00 2001
From: Anton Osika <anton.osika@gmail.com>
Date: Sat, 17 Jun 2023 22:23:55 +0200
Subject: [PATCH 13/16] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 728568e..2088d9a 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
 # GPT Engineer
 **Specify what you want it to build, the AI asks for clarification, and then builds it.**
 
-GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt. [Demo](https://twitter.com/antonosika/status/1667641038104674306).
+GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt: [demo](https://twitter.com/antonosika/status/1667641038104674306) 👶🤖
 
 ## Project philosophy
 - Simple to get value

From ed486aed74e2679b835f0c6e6df16900299ae0d6 Mon Sep 17 00:00:00 2001
From: Anton Osika <anton.osika@gmail.com>
Date: Sat, 17 Jun 2023 22:24:08 +0200
Subject: [PATCH 14/16] Update README.md

---
 README.md | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 2088d9a..4766c30 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,9 @@
 # GPT Engineer
 **Specify what you want it to build, the AI asks for clarification, and then builds it.**
 
-GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt: [demo](https://twitter.com/antonosika/status/1667641038104674306) 👶🤖
+GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt.
+
+[Demo](https://twitter.com/antonosika/status/1667641038104674306) 👶🤖
 
 ## Project philosophy
 - Simple to get value

From d20f086a9b4bb7e3c781619f40072ec4407f3116 Mon Sep 17 00:00:00 2001
From: Anton Osika <anton.osika@gmail.com>
Date: Sat, 17 Jun 2023 22:24:38 +0200
Subject: [PATCH 15/16] Update README.md

---
 README.md | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 4766c30..f16ddee 100644
--- a/README.md
+++ b/README.md
@@ -3,8 +3,6 @@
 
 GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt.
 
-[Demo](https://twitter.com/antonosika/status/1667641038104674306) 👶🤖
-
 ## Project philosophy
 - Simple to get value
 - Flexible and easy to add new own "AI steps". See `steps.py`.
@@ -14,6 +12,7 @@ GPT Engineer is made to be easy to adapt, extend, and make your agent learn how
 - Fast handovers back and forth between AI and human
 - Simplicity, all computation is "resumable" and persisted to the filesystem
 
+[Demo](https://twitter.com/antonosika/status/1667641038104674306) 👶🤖
 
 ## Usage
 

From fa7585f900d8ccecc4653005778369a7ba8da87a Mon Sep 17 00:00:00 2001
From: Anton Osika <anton.osika@gmail.com>
Date: Sat, 17 Jun 2023 22:50:52 +0200
Subject: [PATCH 16/16] Update README.md

---
 README.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index f16ddee..4766c30 100644
--- a/README.md
+++ b/README.md
@@ -3,6 +3,8 @@
 
 GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt.
 
+[Demo](https://twitter.com/antonosika/status/1667641038104674306) 👶🤖
+
 ## Project philosophy
 - Simple to get value
 - Flexible and easy to add new own "AI steps". See `steps.py`.
@@ -12,7 +14,6 @@ GPT Engineer is made to be easy to adapt, extend, and make your agent learn how
 - Fast handovers back and forth between AI and human
 - Simplicity, all computation is "resumable" and persisted to the filesystem
 
-[Demo](https://twitter.com/antonosika/status/1667641038104674306) 👶🤖
 
 ## Usage